Risk prediction models for hospital readmission: a systematic review

Analysis of Clinical Criteria for Discharge Among Patients Hospitalized for COVID-19: Development and Validation of a Risk Prediction Model

BACKGROUND

Patients hospitalized with COVID-19 can clinically deteriorate after a period of initial stability, making optimal timing of discharge a clinical and operational challenge.

OBJECTIVE

To determine risks for post-discharge readmission and death among patients hospitalized with COVID-19.

DESIGN

Multicenter retrospective observational cohort study, 2020-2021, with 30-day follow-up.

PARTICIPANTS

Adults admitted for care of COVID-19 respiratory disease between March 2, 2020, and February 11, 2021, to one of 180 US hospitals affiliated with the HCA Healthcare system.

MAIN MEASURES

Readmission to or death at an HCA hospital within 30 days of discharge was assessed. The area under the receiver operating characteristic curve (AUC) was calculated using an internal validation set (33% of the HCA cohort), and external validation was performed using similar data from six academic centers associated with a hospital medicine research network (HOMERuN).

KEY RESULTS

The final HCA cohort included 62,195 patients (mean age 61.9 years, 51.9% male), of whom 4704 (7.6%) were readmitted or died within 30 days of discharge. Independent risk factors for death or readmission included fever within 72 h of discharge; tachypnea, tachycardia, or lack of improvement in oxygen requirement in the last 24 h; lymphopenia or thrombocytopenia at the time of discharge; being ≤ 7 days since first positive test for SARS-CoV-2; HOSPITAL readmission risk score ≥ 5; and several comorbidities. Inpatient treatment with remdesivir or anticoagulation were associated with lower odds. The model's AUC for the internal validation set was 0.73 (95% CI 0.71-0.74) and 0.66 (95% CI 0.64 to 0.67) for the external validation set.

CONCLUSIONS

This large retrospective study identified several factors associated with post-discharge readmission or death in models which performed with good discrimination. Patients 7 or fewer days since test positivity and who demonstrate potentially reversible risk factors may benefit from delaying discharge until those risk factors resolve.

Impact of wearable device data and multi-scale entropy analysis on improving hospital readmission prediction

OBJECTIVE

Unplanned readmissions following a hospitalization remain common despite significant efforts to curtail these. Wearable devices may offer help identify patients at high risk for an unplanned readmission.

MATERIALS AND METHODS

We conducted a multi-center retrospective cohort study using data from the All of Us data repository. We included subjects with wearable data and developed a baseline Feedforward Neural Network (FNN) model and a Long Short-Term Memory (LSTM) time-series deep learning model to predict daily, unplanned rehospitalizations up to 90 days from discharge. In addition to demographic and laboratory data from subjects, post-discharge data input features include wearable data and multiscale entropy features based on intraday wearable time series. The most significant features in the LSTM model were determined by permutation feature importance testing.

RESULTS

In sum, 612 patients met inclusion criteria. The complete LSTM model had a higher area under the receiver operating characteristic curve than the FNN model (0.83 vs 0.795). The 5 most important input features included variables from multiscale entropy (steps) and number of active steps per day.

DISCUSSION

Data available from wearable devices can improve ability to predict readmissions. Prior work has focused on predictors available up to discharge or on additional data abstracted from wearable devices. Our results from 35 institutions highlight how multiscale entropy can improve readmission prediction and may impact future work in this domain.

CONCLUSION

Wearable data and multiscale entropy can improve prediction of a deep-learning model to predict unplanned 90-day readmissions. Prospective studies are needed to validate these findings.

Enhancing readmission prediction models by integrating insights from home healthcare notes: Retrospective cohort study

BACKGROUND

Hospital readmission is an important indicator of inpatient care quality and a significant driver of increasing medical costs. Therefore, it is important to explore the effects of postdischarge information, particularly from home healthcare notes, on enhancing readmission prediction models. Despite the use of Natural Language Processing (NLP) and machine learning in prediction model development, current studies often overlook insights from home healthcare notes.

OBJECTIVE

This study aimed to develop prediction models for 30-day readmissions using home healthcare notes and structured data. In addition, it explored the development of 14- and 180-day prediction models using variables in the 30-day model.

DESIGN

A retrospective observational cohort study.

SETTING(S)

This study was conducted at Ajou University School of Medicine in South Korea.

PARTICIPANTS

Data from electronic health records, encompassing demographic characteristics of 1819 participants, along with information on conditions, drug, and home healthcare, were utilized.

METHODS

Two distinct models were developed for each prediction window (30-, 14-, 180-day): the traditional model, which utilized structured variables alone, and the common data model (CDM)-NLP model, which incorporated structured and topic variables extracted from home healthcare notes. BERTopic facilitated topic generation and risk probability, representing the likelihood of documents being assigned to specific topics. Feature selection involved experimenting with various algorithms. The best-performing algorithm, determined using the area under the receiver operating characteristic curve (AUROC), was used for model development. Model performance was assessed using various learning metrics including AUROC.

RESULTS

Among 1819 patients, 251 (13.80 %) experienced 30-day readmission. The least absolute shrinkage and selection operator was used for feature extraction and model development. The 15 structured features were used in the traditional model. Moreover, five additional topic variables from the home healthcare notes were applied in the CDM-NLP model. The AUROC of the traditional model was 0.739 (95 % CI: 0.672-0.807). The AUROC of the CDM-NLP model was high at 0.824 (95 % CI: 0.768-0.880), which indicated an outstanding performance. The topics in the CDM-NLP model included emotional distress, daily living functions, nutrition, postoperative status, and cardiorespiratory issues. In extended prediction model development for 14- and 180-day readmissions, the CDM-NLP consistently outperformed the traditional model.

CONCLUSIONS

This study developed effective prediction models using both structured and unstructured data, thereby emphasizing the significance of postdischarge information from home healthcare notes in readmission prediction.

Paramedic-Assisted Community Evaluation After Discharge: The PACED Intervention

OBJECTIVES

Early rehospitalization of frail older adults after hospital discharge is harmful to patients and challenging to hospitals. Mobile integrated health (MIH) programs may be an effective solution for delivering community-based transitional care. The objective of this study was to assess the feasibility and implementation of an MIH transitional care program.

DESIGN

Pilot clinical trial of a transitional home visit conducted by MIH paramedics within 72 hours of hospital discharge.

SETTING AND PARTICIPANTS

Patients aged ≥65 years discharged from an urban hospital with a system-adapted eFrailty index ≥0.24 were eligible to participate.

METHODS

Participants were enrolled after hospital discharge. Demographic and clinical information were recorded at enrollment and 30 days after discharge from the electronic health record. Data from a comparison group of patients excluded from enrollment due to geographical location was also abstracted. Primary outcomes were intervention feasibility and implementation, which were reported descriptively. Exploratory clinical outcomes included emergency department (ED) visits and rehospitalization within 30 days. Categorical and continuous group comparisons were conducted using χ2 tests and Kruskal-Wallis testing. Binomial regression was used for comparative outcomes.

RESULTS

One hundred of 134 eligible individuals (74.6%) were enrolled (median age 81, 64% female). Forty-seven participants were included in the control group (median age 80, 55.2% female). The complete protocol was performed in 92 (92.0%) visits. Paramedics identified acute clinical problems in 23 (23.0%) visits, requested additional services for participants during 34 (34.0%) encounters, and detected medication errors during 34 (34.0%). The risk of 30-day rehospitalization was lower in the Paramedic-Assisted Community Evaluation after Discharge (PACED) group compared with the control (RR, 0.40; CI, 0.19-0.84; P = .03); there was a trend toward decreased risk of 30-day ED visits (RR, 0.61; CI, 0.37-1.37; P = .23).

CONCLUSIONS AND IMPLICATIONS

This pilot study of an MIH transition care program was feasible with high protocol fidelity. It yields preliminary evidence demonstrating a decreased risk of rehospitalization in frail older adults.

Behavioral, Cognitive, and Functional Risk Factors for Repeat Hospital Episodes Among Medicare-Medicaid Dually Eligible Adults Receiving Long-Term Services and Supports

Repeat hospitalizations adversely impact the well-being of adults dually eligible for Medicare and Medicaid in the United States. This study aimed to identify behavioral, cognitive, and functional characteristics associated with the risk of a repeat hospital episode (HE) among the statewide population of dually eligible adults in Maryland receiving long-term services and supports prior to an HE between July 2018 and May 2020. The odds of experiencing a repeat HE within 30 days after an initial HE were positively associated with reporting difficulty with hearing (adjusted odds ratio, AOR: 1.10 [95% confidence interval: 1.02-1.19]), being easily distractible (AOR: 1.09 [1.00-1.18]), being self-injurious (AOR: 1.33 [1.09-1.63]), and exhibiting verbal abuse (AOR: 1.15 [1.02-1.30]). Conversely, displaying inappropriate public behavior (AOR: 0.62 [0.42-0.92]) and being dependent for eating (AOR: 0.91 [0.83-0.99]) or bathing (AOR: 0.79 [0.67-0.92]) were associated with reduced odds of a repeat HE. We also observed differences in the magnitude and direction of these associations among adults 65 years of age or older relative to younger counterparts.

Impact of time from discharge to readmission on outcomes: an observational study from the US National Readmission Database

BACKGROUND

The Hospital Readmission Reduction Programme (HRRP) was created to decrease the number of hospital readmissions for acute myocardial infarction (AMI), chronic obstructive pulmonary disease (COPD), heart failure (HF), pneumonia (PNA), coronary artery bypass graft (CABG), elective total hip arthroplasty (THA) and total knee arthroplasty.

OBJECTIVES

To analyse the impact of the HRRP on readmission rates from 2010 to 2019 and how time to readmission impacted outcomes.

DESIGN

Population-based retrospective study.

SETTING

All patients included in the US National Readmission database from 2010 to 2019.

PATIENTS

We recorded demographic and clinical variables.

MEASUREMENTS

Using linear regression models, we analysed the association between readmission status and timing with death and length of stay (LOS) outcomes. We transformed LOS and charges into log-LOS and log-charges to normalise the data.

RESULTS

There were 31 553 363 records included in the study. Of those, 4 593 228 (14.55%) were readmitted within 30 days. From 2010 to 2019, readmission rates for COPD (20.8%-19.8%), HF (24.9%-21.9%), PNA (16.4%-15.1%), AMI (15.6%-12.9%) and TKR (4.1%-3.4%) decreased whereas CABG (10.2%-10.6%) and THA (4.2%-5.8%) increased. Readmitted patients were at higher risk of mortality (6% vs 2.8%) and had higher LOS (3 (2-5) vs 4 (3-7)). Patients readmitted within 10 days had a mortality 6.4% higher than those readmitted in 11-20 days (5.4%) and 21-30 days (4.6%). Increased time from discharge to readmission was associated with a lower likelihood of mortality, like LOS.

CONCLUSION

Over the last 10 years, readmission rates decreased for most conditions included in the HRRP except CABG and THA. Patients readmitted shortly after discharge were at higher risk of death.

Using machine learning methods to predict all-cause somatic hospitalizations in adults: A systematic review

AIM

In this review, we investigated how Machine Learning (ML) was utilized to predict all-cause somatic hospital admissions and readmissions in adults.

METHODS

We searched eight databases (PubMed, Embase, Web of Science, CINAHL, ProQuest, OpenGrey, WorldCat, and MedNar) from their inception date to October 2023, and included records that predicted all-cause somatic hospital admissions and readmissions of adults using ML methodology. We used the CHARMS checklist for data extraction, PROBAST for bias and applicability assessment, and TRIPOD for reporting quality.

RESULTS

We screened 7,543 studies of which 163 full-text records were read and 116 met the review inclusion criteria. Among these, 45 predicted admission, 70 predicted readmission, and one study predicted both. There was a substantial variety in the types of datasets, algorithms, features, data preprocessing steps, evaluation, and validation methods. The most used types of features were demographics, diagnoses, vital signs, and laboratory tests. Area Under the ROC curve (AUC) was the most used evaluation metric. Models trained using boosting tree-based algorithms often performed better compared to others. ML algorithms commonly outperformed traditional regression techniques. Sixteen studies used Natural language processing (NLP) of clinical notes for prediction, all studies yielded good results. The overall adherence to reporting quality was poor in the review studies. Only five percent of models were implemented in clinical practice. The most frequently inadequately addressed methodological aspects were: providing model interpretations on the individual patient level, full code availability, performing external validation, calibrating models, and handling class imbalance.

CONCLUSION

This review has identified considerable concerns regarding methodological issues and reporting quality in studies investigating ML to predict hospitalizations. To ensure the acceptability of these models in clinical settings, it is crucial to improve the quality of future studies.

Nursing Variables Predicting Readmissions in Patients With a High Risk: A Scoping Review

Unplanned readmission endangers patient safety and increases unnecessary healthcare expenditure. Identifying nursing variables that predict patient readmissions can aid nurses in providing timely nursing interventions that help patients avoid readmission after discharge. We aimed to provide an overview of the nursing variables predicting readmission of patients with a high risk. The authors searched five databases-PubMed, CINAHL, EMBASE, Cochrane Library, and Scopus-for publications from inception to April 2023. Search terms included "readmission" and "nursing records." Eight studies were included for review. Nursing variables were classified into three categories-specifically, nursing assessment, nursing diagnosis, and nursing intervention. The nursing assessment category comprised 75% of the nursing variables; the proportions of the nursing diagnosis (25%) and nursing intervention categories (12.5%) were relatively low. Although most variables of the nursing assessment category focused on the patients' physical aspect, emotional and social aspects were also considered. This study demonstrated how nursing care contributes to patients' adverse outcomes. The findings can assist nurses in identifying the essential nursing assessment, diagnosis, and interventions, which should be provided from the time of patients' admission. This can mitigate preventable readmissions of patients with a high risk and facilitate their safe transition from an acute care setting to the community.

The Clinical Impact of Hospital-Acquired Adverse Drug Reactions in Older Adults: An Australian Cohort Study

INTRODUCTION

Hospital-acquired adverse drug reactions (HA-ADRs) are common in older adults. However, there is limited knowledge regarding the association between HA-ADRs and adverse clinical outcomes.

OBJECTIVE

To investigate the incidence and characteristics of HA-ADRs in older adults, and any association with mortality, length of stay, and readmissions.

DESIGN

Prospective cohort study.

SETTING AND PARTICIPANTS

Flinders Medical Centre, a large tertiary referral hospital in Adelaide, South Australia. Older adults admitted under the General Medicine and Acute Care of the Elderly units with no previous diagnosis of dementia.

METHODS

All patients had a Multidimensional Prognostic Index (MPI) assessment performed within 3 days of the admission. Data collected included age, gender, estimated glomerular filtration rate (eGFR), length of stay, readmissions, and mortality. HA-ADRs were identified by review of individual discharge summaries. Univariate and multivariate analyses were performed to investigate associations with clinical outcomes including mortality, length of stay, and readmissions. Exploratory analyses were performed for HA-ADR groups based on Medical Dictionary for Regulatory Activities System Organ Class and World Health Organization Anatomical Therapeutic Chemical classifications that accounted for ≥10% of all HA-ADRs.

RESULTS

There were 737 patients in the cohort with 72 having experienced a HA-ADRs (incidence = 9.8%). Patients with an HA-ADR had increased length of stay and 30-day readmissions compared with those without an HA-ADR. In multivariate analysis, the number of HA-ADRs was associated with in-hospital mortality and length of stay but not post-discharge mortality or readmissions within 30 days. In exploratory analyses, patients with an HA-ADR to antibacterial drugs had significantly higher rates of in-hospital mortality compared with those without these reactions.

CONCLUSIONS AND IMPLICATIONS

The number of HA-ADRs are associated with in-hospital mortality and length of stay in older Australian inpatients. The occurrence of HA-ADRs may be a trigger to offer advice to prescribers to prevent future ADRs to similar agents and proactively manage disease to improve health outcomes.

Comparison of machine-learning and logistic regression models for prediction of 30-day unplanned readmission in electronic health records: A development and validation study

It is expected but unknown whether machine-learning models can outperform regression models, such as a logistic regression (LR) model, especially when the number and types of predictor variables increase in electronic health records (EHRs). We aimed to compare the predictive performance of gradient-boosted decision tree (GBDT), random forest (RF), deep neural network (DNN), and LR with the least absolute shrinkage and selection operator (LR-LASSO) for unplanned readmission. We used EHRs of patients discharged alive from 38 hospitals in 2015-2017 for derivation and in 2018 for validation, including basic characteristics, diagnosis, surgery, procedure, and drug codes, and blood-test results. The outcome was 30-day unplanned readmission. We created six patterns of data tables having different numbers of binary variables (that ≥5% or ≥1% of patients or ≥10 patients had) with and without blood-test results. For each pattern of data tables, we used the derivation data to establish the machine-learning and LR models, and used the validation data to evaluate the performance of each model. The incidence of outcome was 6.8% (23,108/339,513 discharges) and 6.4% (7,507/118,074 discharges) in the derivation and validation datasets, respectively. For the first data table with the smallest number of variables (102 variables that ≥5% of patients had, without blood-test results), the c-statistic was highest for GBDT (0.740), followed by RF (0.734), LR-LASSO (0.720), and DNN (0.664). For the last data table with the largest number of variables (1543 variables that ≥10 patients had, including blood-test results), the c-statistic was highest for GBDT (0.764), followed by LR-LASSO (0.755), RF (0.751), and DNN (0.720), suggesting that the difference between GBDT and LR-LASSO was small and their 95% confidence intervals overlapped. In conclusion, GBDT generally outperformed LR-LASSO to predict unplanned readmission, but the difference of c-statistic became smaller as the number of variables was increased and blood-test results were used.

A Systematic Review of Recent Studies on Hospital Readmissions of Patients With Diabetes

Hospital readmissions are a major area of concern across the healthcare ecosystem. Diabetes mellitus (DM) and associated complications significantly contributed to hospital readmissions in 2018, placing it among the leading causes alongside septicemia and heart failure. Diabetes is an urgent public health concern that has reached epidemic proportions globally. Compared to the early 2000s, the prevalence of diabetes among individuals aged 20-79 years in the US has significantly increased. This research provides an in-depth examination of diabetes-related hospital readmissions and reviews recent studies (2015-2023) to understand the characteristics, risk factors, and potential outcomes for re-admitted diabetes patients. The study identified 21 articles that met the inclusion criteria to provide valuable insights and analyze risk factors associated with these readmissions. The findings indicated that risk factors such as age, demographics, income, insurance type, severity of illness, and comorbidities among diabetic patients were critical and warranted further investigation. Diabetes awareness, quality of hospital care, involvement of healthcare providers, timely screening, and lifestyle changes were noted as important factors to improve the effectiveness of healthcare delivery, reduce diabetes-related complications, and eventually lower preventable hospital readmissions.

A case vignette study to refine the target group of an intermediate care model: the Acute Geriatric Community Hospital

PURPOSE

To refine the admission criteria of the Acute Geriatric Community Hospital (AGCH) by defining its target group boundaries with (geriatric) hospital care and other bed-based intermediate care models in the Netherlands.

METHODS

A qualitative study consisting of a three-phase refinement procedure with case vignettes. Physicians, medical specialists, nurse practitioners, and physician assistants in hospitals (n = 10) or intermediate care facilities (n = 10) in the Netherlands participated. They collected case vignettes from clinical practice (phase one). The referral considerations and decisions for each case were then documented through surveys (phase two) and two focus groups (phase 3). For thematic data analysis, inductive and deductive approaches were used.

RESULTS

The combination of medical specialist care (MSC) and medical generalist care (MGC), is unique for the AGCH compared to other intermediate care models in the Netherlands. Compared to (geriatric) hospital care, the AGCH offers a more limited scope of MSC. Based on these findings, 13 refined admission criteria were developed such as 'The required diagnostic tests to monitor the effectiveness of treatment are available at the AGCH'. Besides admission criteria, additional clinical and organizational considerations played a role in referral decision-making; 10 themes were identified.

CONCLUSION

This case vignette study defined the target group boundaries between the AGCH and other care models, allowing us to refine the AGCH admission criteria. Our findings may help to determine the required competencies of the interdisciplinary AGCH team and to develop triage instruments. The identified consideration themes can be used as conceptual framework in further research. The findings may also be of interests for healthcare systems outside the Netherlands who aspire to design integrated care for older people closer to home.

Medications for alcohol-use disorder and follow-up after hospitalization for alcohol withdrawal: A multicenter study

BACKGROUND

Alcohol withdrawal is a common reason for admission to acute care hospitals. Prescription of medications for alcohol-use disorder (AUD) and close outpatient follow-up are commonly recommended, but few studies report their effects on postdischarge outcomes.

OBJECTIVES

The objective of this study is to evaluate the effects of medications for AUD and follow-up appointments on readmission and abstinence.

METHODS

This retrospective cohort study evaluated veterans admitted for alcohol withdrawal to medical services at 19 Veteran Health Administration hospitals between October 1, 2018 and September 30, 2019. Factors associated with all-cause 30-day readmission and 6-month abstinence were examined using logistic regression.

RESULTS

Of the 594 patients included in this study, 296 (50.7%) were prescribed medications for AUD at discharge and 459 (78.5%) were discharged with follow-up appointments, including 251 (42.8%) with a substance-use clinic appointment, 191 (32.9%) with a substance-use program appointment, and 73 (12.5%) discharged to a residential program. All-cause 30-day readmission occurred for 150 patients (25.5%) and 103 (17.8%) remained abstinent at 6 months. Medications for AUD and outpatient discharge appointments were not associated with readmission or abstinence. Discharge to residential treatment program was associated with reduced 30-day readmission (adjusted odds ratio [AOR]: 0.39, 95% confidence interval [95% CI]: 0.18-0.82) and improved abstinence (AOR: 2.50, 95% CI: 1.33-4.73).

CONCLUSIONS

Readmission and return to heavy drinking are common for patients discharged for alcohol withdrawal. Medications for AUD were not associated with improved outcomes. The only intervention at the time of discharge that improved outcomes was discharge to residential treatment program, which was associated with decreased readmission and improved abstinence.

Predicting Outcomes in Frail Older Community-Dwellers in Western Australia: Results from the Community Assessment of Risk Screening and Treatment Strategies (CARTS) Programme

Understanding risk factors for frailty, functional decline and incidence of adverse healthcare outcomes amongst community-dwelling older adults is important to plan population-level health and social care services. We examined variables associated with one-year risk of institutionalisation, hospitalisation and death among patients assessed in their own home by a community-based Aged Care Assessment Team (ACAT) in Western Australia. Frailty and risk were measured using the Clinical Frailty Scale (CFS) and Risk Instrument for Screening in the Community (RISC), respectively. Predictive accuracy was measured from the area under the curve (AUC). Data from 417 patients, median 82 ± 10 years, were included. At 12-month follow-up, 22.5% (n = 94) were institutionalised, 44.6% (n = 186) were hospitalised at least once and 9.8% (n = 41) had died. Frailty was common, median CFS score 6/9 ± 1, and significantly associated with institutionalisation (p = 0.001), hospitalisation (p = 0.007) and death (p < 0.001). Impaired activities of daily living (ADL) measured on the RISC had moderate correlation with admission to long-term care (r = 0.51) and significantly predicted institutionalisation (p < 0.001) and death (p = 0.01). The RISC had the highest accuracy for institutionalisation (AUC 0.76). The CFS and RISC had fair to good accuracy for mortality (AUC of 0.69 and 0.74, respectively), but neither accurately predicted hospitalisation. Home assessment of community-dwelling older patients by an ACAT in Western Australia revealed high levels of frailty, ADL impairment and incident adverse outcomes, suggesting that anticipatory care planning is imperative for these patients.

Multimodal Machine Learning for Prediction of 30-Day Readmission Risk in Elderly Population

BACKGROUND

Readmission within 30 days is a prevalent issue among elderly patients, linked to unfavorable health outcomes. Our objective was to develop and validate multimodal machine learning models for predicting 30-day readmission risk in elderly patients discharged from internal medicine departments.

METHODS

This was a retrospective cohort study which included elderly patients aged 75 or older, who were hospitalized at the Hadassah Medical Center internal medicine departments between 2014 and 2020. Three machine learning algorithms were developed and employed to predict 30-day readmission risk. The primary measures were predictive model performance scores, specifically area under the receiver operator curve (AUROC), and average precision.

RESULTS

This study included 19,569 admissions. Of them, 3258 (16.65%) resulted in 30-day readmission. Our 3 proposed models demonstrated high accuracy and precision on an unseen test set, with AUROC values of 0.87, 0.89, and 0.93, respectively, and average precision values of 0.76, 0.78, and 0.81. Feature importance analysis revealed that the number of admissions in the past year, history of 30-day readmission, Charlson score, and admission length were the most influential variables. Notably, the natural language processing score, representing the probability of readmission according to a textual-based model trained on social workers' assessment letters during hospitalization, ranked among the top 10 contributing factors.

CONCLUSIONS

Leveraging multimodal machine learning offers a promising strategy for identifying elderly patients who are at high risk for 30-day readmission. By identifying these patients, machine learning models may facilitate the effective execution of preventive actions to reduce avoidable readmission incidents.

How artificial intelligence could transform emergency care

Artificial intelligence (AI) in healthcare is the ability of a computer to perform tasks typically associated with clinical care (e.g. medical decision-making and documentation). AI will soon be integrated into an increasing number of healthcare applications, including elements of emergency department (ED) care. Here, we describe the basics of AI, various categories of its functions (including machine learning and natural language processing) and review emerging and potential future use-cases for emergency care. For example, AI-assisted symptom checkers could help direct patients to the appropriate setting, models could assist in assigning triage levels, and ambient AI systems could document clinical encounters. AI could also help provide focused summaries of charts, summarize encounters for hand-offs, and create discharge instructions with an appropriate language and reading level. Additional use cases include medical decision making for decision rules, real-time models that predict clinical deterioration or sepsis, and efficient extraction of unstructured data for coding, billing, research, and quality initiatives. We discuss the potential transformative benefits of AI, as well as the concerns regarding its use (e.g. privacy, data accuracy, and the potential for changing the doctor-patient relationship).

Impact of a patient risk-scoring tool pilot on prioritization of pharmacy-conducted medication histories

BACKGROUND

Approximately 50% to 70% of patients have at least 1 medication discrepancy in their initial medication history. These discrepancies can lead to errors on admission and discharge orders and have the potential to cause patient harm and incur added costs associated with increased length of stay and readmission rates. Several studies have demonstrated improved medication history accuracy with pharmacy-conducted services, but variations in practice exist due to challenges with workflow and resources.

OBJECTIVE

This study aims to assess the impact of implementing a patient risk-scoring tool for the prioritization of medication history review by pharmacy staff.

METHODS

This quasi-experimental, single-center study was conducted at a 948-bed academic medical center as a pilot study with the medication history team which consists of pharmacists and certified pharmacy technicians in the emergency department. The endpoints assessed included pharmacy completion rate of patients in the high-risk category, overall pharmacy conducted medication history rate, and the proportion of medication discrepancies identified after reconciliation.

RESULTS

The number of medication histories completed by pharmacy (n=849) decreased by 5.7% in the postintervention period (P = 0.002). Between the preintervention and postintervention period, there were fewer low-risk patients being captured by pharmacy (89.7% to 59.9%, respectively). There was also an increase in the number of medium-risk (Δ=25.4%) and high-risk patients (Δ=4.4%) being captured by pharmacy staff (P < 0.017, α = 0.017).

CONCLUSION

Use of a risk-scoring tool allowed pharmacy staff to prioritize workflow and capture more high-risk patients for medication history.

Targeted care coordination towards patients with a history of multiple readmissions effectively reduces readmissions

BACKGROUND

To decrease hospital readmission rates, clinical practices create a transition of care (TOC) process to assess patients and coordinate care postdischarge. As current evidence suggests lack of universal benefit, this study's objectives are to determine what patient and process factors associate with hospital readmissions, as well as construct a model to decrease 30-day readmissions.

METHODS

Three months of retrospective discharged patient data (n = 123) were analysed for readmission influences including: patient-specific comorbidities, admission-specific diagnoses, and TOC components. A structured intervention of weekly contact, the Care Coordination Cocoon (CCC), was created for multiply readmitted patients (MRPs), defined as ≥2 readmissions. Three months of postintervention data (n = 141) were analysed. Overall readmission rates and patient- and process-specific characteristics were analysed for associations with hospital readmission.

RESULTS

Standard TOC lacked significance. Patient-specific comorbidities of cancer (odds ratio [OR] 6.27; 95% confidence interval [CI] 1.73-22.75) and coronary artery disease (OR 6.71; 95% CI 1.84-24.46), and admission-specific diagnoses within pulmonary system admissions (OR 7.20; 95% CI 1.96-26.41) were associated with readmissions. Post-CCC data demonstrated a 48-h call (OR 0.21; 95% CI 0.09-0.50), answered calls (OR 0.16; CI 0.07-0.38), 14-day scheduled visit (OR 0.20; 95% CI 0.07-0.54), and visit arrival (OR 0.39; 95% CI 0.17-0.91) independently associated with decreased readmission rate. Patient-specific (hypertension-OR 3.65; CI 1.03-12.87) and admission-specific (nephrologic system-OR 3.22; CI 1.02-10.14) factors associated with readmissions which differed from the initial analysis.

CONCLUSIONS

Targeting a practice's MRPs with CCC resources improves the association of TOC components with readmissions and rates decreased. This is a more efficient use of TOC resources.

Development of a prediction model of postpartum hospital use using an equity-focused approach

BACKGROUND

Racial inequities in maternal morbidity and mortality persist into the postpartum period, leading to a higher rate of postpartum hospital use among Black and Hispanic people. Delivery hospitalizations provide an opportunity to screen and identify people at high risk to prevent adverse postpartum outcomes. Current models do not adequately incorporate social and structural determinants of health, and some include race, which may result in biased risk stratification.

OBJECTIVE

This study aimed to develop a risk prediction model of postpartum hospital use while incorporating social and structural determinants of health and using an equity approach.

STUDY DESIGN

We conducted a retrospective cohort study using 2016-2018 linked birth certificate and hospital discharge data for live-born infants in New York City. We included deliveries from 2016 to 2017 in model development, randomly assigning 70%/30% of deliveries as training/test data. We used deliveries in 2018 for temporal model validation. We defined "Composite postpartum hospital use" as at least 1 readmission or emergency department visit within 30 days of the delivery discharge. We categorized diagnosis at first hospital use into 14 categories based on International Classification of Diseases-Tenth Revision diagnosis codes. We tested 72 candidate variables, including social determinants of health, demographics, comorbidities, obstetrical complications, and severe maternal morbidity. Structural determinants of health were the Index of Concentration at the Extremes, which is an indicator of racial-economic segregation at the zip code level, and publicly available indices of the neighborhood built/natural and social/economic environment of the Child Opportunity Index. We used 4 statistical and machine learning algorithms to predict "Composite postpartum hospital use", and an ensemble approach to predict "Cause-specific postpartum hospital use". We simulated the impact of each risk stratification method paired with an effective intervention on race-ethnic equity in postpartum hospital use.

RESULTS

The overall incidence of postpartum hospital use was 5.7%; the incidences among Black, Hispanic, and White people were 8.8%, 7.4%, and 3.3%, respectively. The most common diagnoses for hospital use were general perinatal complications (17.5%), hypertension/eclampsia (12.0%), nongynecologic infections (10.7%), and wound infections (8.4%). Logistic regression with least absolute shrinkage and selection operator selection retained 22 predictor variables and achieved an area under the receiver operating curve of 0.69 in the training, 0.69 in test, and 0.69 in validation data. Other machine learning algorithms performed similarly. Selected social and structural determinants of health features included the Index of Concentration at the Extremes, insurance payor, depressive symptoms, and trimester entering prenatal care. The "Cause-specific postpartum hospital use" model selected 6 of the 14 outcome diagnoses (acute cardiovascular disease, gastrointestinal disease, hypertension/eclampsia, psychiatric disease, sepsis, and wound infection), achieving an area under the receiver operating curve of 0.75 in training, 0.77 in test, and 0.75 in validation data using a cross-validation approach. Models had slightly lower performance in Black and Hispanic subgroups. When simulating use of the risk stratification models with a postpartum intervention, identifying high-risk individuals with the "Composite postpartum hospital use" model resulted in the greatest reduction in racial-ethnic disparities in postpartum hospital use, compared with the "Cause-specific postpartum hospital use" model or a standard approach to identifying high-risk individuals with common pregnancy complications.

CONCLUSION

The "Composite postpartum hospital use" prediction model incorporating social and structural determinants of health can be used at delivery discharge to identify persons at risk for postpartum hospital use.

al-BERT: a semi-supervised denoising technique for disease prediction

BACKGROUND

Medical records are a valuable source for understanding patient health conditions. Doctors often use these records to assess health without solely depending on time-consuming and complex examinations. However, these records may not always be directly relevant to a patient's current health issue. For instance, information about common colds may not be relevant to a more specific health condition. While experienced doctors can effectively navigate through unnecessary details in medical records, this excess information presents a challenge for machine learning models in predicting diseases electronically. To address this, we have developed 'al-BERT', a new disease prediction model that leverages the BERT framework. This model is designed to identify crucial information from medical records and use it to predict diseases. 'al-BERT' operates on the principle that the structure of sentences in diagnostic records is similar to regular linguistic patterns. However, just as stuttering in speech can introduce 'noise' or irrelevant information, similar issues can arise in written records, complicating model training. To overcome this, 'al-BERT' incorporates a semi-supervised layer that filters out irrelevant data from patient visitation records. This process aims to refine the data, resulting in more reliable indicators for disease correlations and enhancing the model's predictive accuracy and utility in medical diagnostics.

METHOD

To discern noise diseases within patient records, especially those resembling influenza-like illnesses, our approach employs a customized semi-supervised learning algorithm equipped with a focused attention mechanism. This mechanism is specifically calibrated to enhance the model's sensitivity to chronic conditions while concurrently distilling salient features from patient records, thereby augmenting the predictive accuracy and utility of the model in clinical settings. We evaluate the performance of al-BERT using real-world health insurance data provided by Taiwan's National Health Insurance.

RESULT

In our study, we evaluated our model against two others: one based on BERT that uses complete disease records, and another variant that includes extra filtering techniques. Our findings show that models incorporating filtering mechanisms typically perform better than those using the entire, unfiltered dataset. Our approach resulted in improved outcomes across several key measures: AUC-ROC (an indicator of a model's ability to distinguish between classes), precision (the accuracy of positive predictions), recall (the model's ability to find all relevant cases), and overall accuracy. Most notably, our model showed a 15% improvement in recall compared to the current best-performing method in the field of disease prediction.

CONCLUSION

The conducted ablation study affirms the advantages of our attention mechanism and underscores the crucial role of the selection module within al-BERT.

Nursing diagnoses and hospital readmission of patients with respiratory diseases: Findings from a case-control study

AIM

The rate of readmission after hospitalisation for respiratory diseases has become a common and challenging clinical problem. Social and functional patient variables could help identify cases at high risk of readmission. The aim was to identify the nursing diagnoses that were associated with readmission after hospitalisation for respiratory disease in Spain.

DESIGN

Case-control study within the cohort of patients admitted for respiratory disease during 2016-19 in a tertiary public hospital in Spain (n = 3781).

METHODS

Cases were patients who were readmitted within the first 30 days of discharge, and their controls were the remaining patients. All nursing diagnoses (n = 130) were collected from the electronic health record. They were then grouped into 29 informative diagnostic categories. Clinical confounder-adjusted odds ratios (ORs) and 95% confidence intervals (95% CIs) were calculated using logistic regression models.

RESULTS

The readmission rate was 13.1%. The nursing diagnoses categories 'knowledge deficit' (OR: 1.61; 95%CI: 1.13-2.31), 'impaired skin integrity and risk of ulcer infection' (OR: 1.45; 95%CI: 1.06-1.97) and 'activity intolerance associated with fatigue' (OR: 1.56; 95%CI: 1.21-2.01) were associated with an increased risk of suffering an episode of hospital readmission rate at 30% after hospital discharge, and this was independent of sociodemographic background, care variables and comorbidity.

PATIENT OR PUBLIC CONTRIBUTION

The nursing diagnoses assigned as part of the care plan of patients during hospital admission may be useful for predicting readmissions.

Predictive Models to Assess Risk of Persistent Opioid Use, Opioid Use Disorder, and Overdose

BACKGROUND

This systematic review summarizes the development, accuracy, quality, and clinical utility of predictive models to assess the risk of opioid use disorder (OUD), persistent opioid use, and opioid overdose.

METHODS

In accordance with Preferred Reporting Items for a Systematic Review and Meta-analysis guidelines, 8 electronic databases were searched for studies on predictive models and OUD, overdose, or persistent use in adults until June 25, 2023. Study selection and data extraction were completed independently by 2 reviewers. Risk of bias of included studies was assessed independently by 2 reviewers using the Prediction model Risk of Bias ASsessment Tool (PROBAST).

RESULTS

The literature search yielded 3130 reports; after removing 199 duplicates, excluding 2685 studies after abstract review, and excluding 204 studies after full-text review, the final sample consisted of 41 studies that developed more than 160 predictive models. Primary outcomes included opioid overdose (31.6% of studies), OUD (41.4%), and persistent opioid use (17%). The most common modeling approach was regression modeling, and the most common predictors included age, sex, mental health diagnosis history, and substance use disorder history. Most studies reported model performance via the c statistic, ranging from 0.507 to 0.959; gradient boosting tree models and neural network models performed well in the context of their own study. One study deployed a model in real time. Risk of bias was predominantly high; concerns regarding applicability were predominantly low.

CONCLUSIONS

Models to predict opioid-related risks are developed using diverse data sources and predictors, with a wide and heterogenous range of accuracy metrics. There is a need for further research to improve their accuracy and implementation.

Evaluating Algorithmic Bias in 30-Day Hospital Readmission Models: Retrospective Analysis

BACKGROUND

The adoption of predictive algorithms in health care comes with the potential for algorithmic bias, which could exacerbate existing disparities. Fairness metrics have been proposed to measure algorithmic bias, but their application to real-world tasks is limited.

OBJECTIVE

This study aims to evaluate the algorithmic bias associated with the application of common 30-day hospital readmission models and assess the usefulness and interpretability of selected fairness metrics.

METHODS

We used 10.6 million adult inpatient discharges from Maryland and Florida from 2016 to 2019 in this retrospective study. Models predicting 30-day hospital readmissions were evaluated: LACE Index, modified HOSPITAL score, and modified Centers for Medicare & Medicaid Services (CMS) readmission measure, which were applied as-is (using existing coefficients) and retrained (recalibrated with 50% of the data). Predictive performances and bias measures were evaluated for all, between Black and White populations, and between low- and other-income groups. Bias measures included the parity of false negative rate (FNR), false positive rate (FPR), 0-1 loss, and generalized entropy index. Racial bias represented by FNR and FPR differences was stratified to explore shifts in algorithmic bias in different populations.

RESULTS

The retrained CMS model demonstrated the best predictive performance (area under the curve: 0.74 in Maryland and 0.68-0.70 in Florida), and the modified HOSPITAL score demonstrated the best calibration (Brier score: 0.16-0.19 in Maryland and 0.19-0.21 in Florida). Calibration was better in White (compared to Black) populations and other-income (compared to low-income) groups, and the area under the curve was higher or similar in the Black (compared to White) populations. The retrained CMS and modified HOSPITAL score had the lowest racial and income bias in Maryland. In Florida, both of these models overall had the lowest income bias and the modified HOSPITAL score showed the lowest racial bias. In both states, the White and higher-income populations showed a higher FNR, while the Black and low-income populations resulted in a higher FPR and a higher 0-1 loss. When stratified by hospital and population composition, these models demonstrated heterogeneous algorithmic bias in different contexts and populations.

CONCLUSIONS

Caution must be taken when interpreting fairness measures' face value. A higher FNR or FPR could potentially reflect missed opportunities or wasted resources, but these measures could also reflect health care use patterns and gaps in care. Simply relying on the statistical notions of bias could obscure or underplay the causes of health disparity. The imperfect health data, analytic frameworks, and the underlying health systems must be carefully considered. Fairness measures can serve as a useful routine assessment to detect disparate model performances but are insufficient to inform mechanisms or policy changes. However, such an assessment is an important first step toward data-driven improvement to address existing health disparities.

The Early HOSPITAL Score to Predict 30-Day Readmission Soon After Hospitalization: a Prospective Multicenter Study

BACKGROUND

The simplified HOSPITAL score is an easy-to-use prediction model to identify patients at high risk of 30-day readmission before hospital discharge. An earlier stratification of this risk would allow more preparation time for transitional care interventions.

OBJECTIVE

To assess whether the simplified HOSPITAL score would perform similarly by using hemoglobin and sodium level at the time of admission instead of discharge.

DESIGN

Prospective national multicentric cohort study.

PARTICIPANTS

In total, 934 consecutively discharged medical inpatients from internal general services.

MAIN MEASURES

We measured the composite of the first unplanned readmission or death within 30 days after discharge of index admission and compared the performance of the simplified score with lab at discharge (simplified HOSPITAL score) and lab at admission (early HOSPITAL score) according to their discriminatory power (Area Under the Receiver Operating characteristic Curve (AUROC)) and the Net Reclassification Improvement (NRI).

KEY RESULTS

During the study period, a total of 3239 patients were screened and 934 included. In total, 122 (13.2%) of them had a 30-day unplanned readmission or death. The simplified and the early versions of the HOSPITAL score both showed very good accuracy (Brier score 0.11, 95%CI 0.10-0.13). Their AUROC were 0.66 (95%CI 0.60-0.71), and 0.66 (95%CI 0.61-0.71), respectively, without a statistical difference (p value 0.79). Compared with the model at discharge, the model with lab at admission showed improvement in classification based on the continuous NRI (0.28; 95%CI 0.08 to 0.48; p value 0.004).

CONCLUSION

The early HOSPITAL score performs, at least similarly, in identifying patients at high risk for 30-day unplanned readmission and allows a readmission risk stratification early during the hospital stay. Therefore, this new version offers a timely preparation of transition care interventions to the patients who may benefit the most.

Hospital Readmissions for Fluid Overload among Individuals with Diabetes and Diabetic Kidney Disease: Risk Factors and Multivariable Prediction Models

AIMS

Hospital readmissions due to recurrent fluid overload in diabetes and diabetic kidney disease can be avoided with evidence-based interventions. We aimed to identify at-risk patients who can benefit from these interventions by developing risk prediction models for readmissions for fluid overload in people living with diabetes and diabetic kidney disease.

METHODS

This was a single-center retrospective cohort study of 1,531 adults with diabetes and diabetic kidney disease hospitalized for fluid overload, congestive heart failure, pulmonary edema, and generalized edema between 2015 and 2017. The multivariable regression models for 30-day and 90-day readmission for fluid overload were compared with the LACE score for discrimination, calibration, sensitivity, specificity, and net reclassification index (NRI).

RESULTS

Readmissions for fluid overload within 30 days and 90 days occurred in 8.6% and 17.2% of patients with diabetes, and 8.2% and 18.3% of patients with diabetic kidney disease, respectively. After adjusting for demographics, comorbidities, clinical parameters, and medications, a history of alcoholism (HR 3.85, 95% CI: 1.41-10.55) and prior hospitalization for fluid overload (HR 2.50, 95% CI: 1.26-4.96) were independently associated with 30-day readmission in patients with diabetic kidney disease, as well as in individuals with diabetes. Additionally, current smoking, absence of hypertension, and high-dose intravenous furosemide were also associated with 30-day readmission in individuals with diabetes. Prior hospitalization for fluid overload (HR 2.43, 95% CI: 1.50-3.94), cardiovascular disease (HR 1.44, 95% CI: 1.03-2.02), eGFR ≤45 mL/min/1.73 m2 (HR 1.39, 95% CI: 1.003-1.93) was independently associated with 90-day readmissions in individuals with diabetic kidney disease. Additionally, thiazide prescription at discharge reduced 90-day readmission in diabetic kidney disease, while the need for high-dose intravenous furosemide predicted 90-day readmission in diabetes. The clinical and clinico-psychological models for 90-day readmission in individuals with diabetes and diabetic kidney disease had better discrimination and calibration than the LACE score. The NRI for the clinico-psychosocial models to predict 30- and 90-day readmissions in diabetes was 22.4% and 28.9%, respectively. The NRI for the clinico-psychosocial models to predict 30- and 90-day readmissions in diabetic kidney disease was 5.6% and 38.9%, respectively.

CONCLUSION

The risk models can potentially be used to identify patients at risk of readmission for fluid overload for evidence-based interventions, such as patient education or transitional care programs to reduce preventable hospitalizations.

Development and Validation of Inpatient Hypoglycemia Models Centered Around the Insulin Ordering Process

BACKGROUND

The insulin ordering process is an opportunity to provide clinicians with hypoglycemia risk predictions, but few hypoglycemia models centered around the insulin ordering process exist.

METHODS

We used data on adult patients, admitted in 2019 to non-ICU floors of a large teaching hospital, who had orders for subcutaneous insulin. Our outcome was hypoglycemia, defined as a blood glucose (BG) <70 mg/dL within 24 hours after ordering insulin. We trained and evaluated models to predict hypoglycemia at the time of placing an insulin order, using logistic regression, random forest, and extreme gradient boosting (XGBoost). We compared performance using area under the receiver operating characteristic curve (AUCs) and precision-recall curves. We determined recall at our goal precision of 0.30.

RESULTS

Of 21 052 included insulin orders, 1839 (9%) were followed by a hypoglycemic event within 24 hours. Logistic regression, random forest, and XGBoost models had AUCs of 0.81, 0.80, and 0.79, and recall of 0.44, 0.49, and 0.32, respectively. The most significant predictor was the lowest BG value in the 24 hours preceding the order. Predictors related to the insulin order being placed at the time of the prediction were useful to the model but less important than the patient's history of BG values over time.

CONCLUSIONS

Hypoglycemia within the next 24 hours can be predicted at the time an insulin order is placed, providing an opportunity to integrate decision support into the medication ordering process to make insulin therapy safer.

An overview of reviews and synthesis across 440 studies examines the importance of hospital readmission predictors across various patient populations

OBJECTIVES

The scientific literature contains an abundance of prediction models for hospital readmissions. However, no review has yet synthesized their predictors across various patient populations. Therefore, our aim was to examine predictors of hospital readmissions across 13 patient populations.

STUDY DESIGN AND SETTING

An overview of systematic reviews was combined with a meta-analytical approach. Two thousand five hundred four different predictors were categorized using common ontologies to pool and examine their odds ratios and frequencies of use in prediction models across and within different patient populations.

RESULTS

Twenty-eight systematic reviews with 440 primary studies were included. Numerous predictors related to prior use of healthcare services (odds ratio; 95% confidence interval: 1.64; 1.42-1.89), diagnoses (1.41; 1.31-1.51), health status (1.35; 1.20-1.52), medications (1.28; 1.13-1.44), administrative information about the index hospitalization (1.23; 1.14-1.33), clinical procedures (1.20; 1.07-1.35), laboratory results (1.18; 1.11-1.25), demographic information (1.10; 1.06-1.14), and socioeconomic status (1.07; 1.02-1.11) were analyzed. Diagnoses were frequently used (in 37.38%) and displayed large effect sizes across all populations. Prior use of healthcare services showed the largest effect sizes but were seldomly used (in 2.57%), whereas demographic information (in 13.18%) was frequently used but displayed small effect sizes.

CONCLUSION

Diagnoses and patients' prior use of healthcare services showed large effects both across and within different populations. These results can serve as a foundation for future prediction modeling.

Consensus methodology to investigate the crucial referral criteria to pharmacist-led counseling clinics in Makkah City

Aim

Identifying and prioritizing criteria for referring patients to a counseling clinic managed by hospital pharmacists in the tertiary care setting in Saudi Arabia (SA).

Method

A two-phase consensus Delphi methodological approach was adopted in this study. Data was collected from physicians and pharmacists from different specialties working in different hospitals in Makkah City. In Phase 1, semi-structured interviews were conducted with physicians and pharmacists to discuss and develop the initial list of potential referral criteria for post-discharge counseling. Phase 2 consisted of two rounds of online surveys where participants were asked to independently rank the referral criteria using a 5-point Likert Scale.

Results

In Phase 1, four participants undertook the interviews (two physicians and two pharmacists). Overall, no major comments were given on the suggested criteria. In Phase 2, most suggested referral criteria to the counseling clinic reached participants' consensus agreement of >70 % in both rounds for all three domains. Among all criteria that achieved consensus agreement, two demographic criteria were top-ranked by the participants; the elderly patients (100 %) and those who needed help with their devices (96 %). These were followed by five medication-related criteria, which are medication-related problems, polypharmacy, medication that needs monitoring, high-risk medication, and medication with special formulations. All had a consensus agreement of 96 %.

Conclusion

This study suggests that a counseling clinic led by pharmacists is particularly advisable for the elderly, individuals requiring assistance with their devices, and those encountering medication issues. It is essential to prioritize specific patient demographics when contemplating the extensive establishment and integration of such clinics across various hospitals in SA.

Early repeat hospitalization for fluid overload in individuals with cardiovascular disease and risks: a retrospective cohort study

AIMS

Fluid overload is a common manifestation of cardiovascular and kidney disease and a leading cause of hospitalizations. To identify patients at risk of recurrent severe fluid overload, we evaluated the incidence and risk factors associated with early repeat hospitalization for fluid overload among individuals with cardiovascular disease and risks.

METHODS

Single-center retrospective cohort study of 3423 consecutive adults with an index hospitalization for fluid overload between January 2015 and December 2017 and had cardiovascular risks (older age, diabetes mellitus, hypertension, dyslipidemia, kidney disease, known cardiovascular disease), but excluded if lost to follow-up or eGFR < 15 ml/min/1.73 m2. The outcome was early repeat hospitalization for fluid overload within 30 days of discharge.

RESULTS

The mean age was 73.9 ± 11.6 years and eGFR was 54.1 ± 24.6 ml/min/1.73 m2 at index hospitalization. Early repeat hospitalization for fluid overload occurred in 291 patients (8.5%). After adjusting for demographics, comorbidities, clinical parameters during index hospitalization and medications at discharge, cardiovascular disease (adjusted odds ratio, OR 1.66, 95% CI 1.27-2.17), prior hospitalization for fluid overload within 3 months (OR 2.52, 95% CI 1.17-5.44), prior hospitalization for any cause in within 6 months (OR 1.33, 95% CI 1.02-1.73) and intravenous furosemide use (OR 1.58, 95% CI 1.10-2.28) were associated with early repeat hospitalization for fluid overload. Higher systolic BP on admission (OR 0.992, 95% 0.986-0.998) and diuretic at discharge (OR 0.50, 95% CI 0.26-0.98) reduced early hospitalization for fluid overload.

CONCLUSION

Patients at-risk of early repeat hospitalization for fluid overload may be identified using these risk factors for targeted interventions.

Patients with repeated acute admissions to somatic departments: sociodemographic characteristics, disease burden, and contact with primary healthcare sector - a retrospective register-based case-control study

BACKGROUND

Healthcare systems face escalating capacity challenges and patients with repeated acute admissions strain hospital resources disproportionately. However, studies investigating the characteristics of such patients across all public healthcare providers in a universal healthcare system are lacking.

OBJECTIVE

To investigate characteristics of patients with repeated acute admissions (three or more acute admissions within a calendar year) in regard to sociodemographic characteristics, disease burden, and contact with the primary healthcare sector.

METHODS

This matched register-based case-control study investigated repeated acute admissions from 1 January 2014 to 31 December 2018, among individuals, who resided in four Danish municipalities. The study included 6169 individuals with repeated acute admissions, matched 1:4 to individuals with no acute admissions and one to two acute admissions, respectively. Group comparisons were conducted using conditional logistic regression.

RESULTS

Receiving social benefits increased the odds of repeated acute admissions 9.5-fold compared with no acute admissions (odds ratio (OR) 9.5; 95% confidence interval (CI) 8.5; 10.6) and 3.4-fold compared with one to two acute admissions (OR 3.4; 95% CI 3.1; 3.7). The odds of repeated acute admissions increased with the number of used medications and chronic diseases. Having a mental illness increased the odds of repeated acute admissions 5.8-fold when compared with no acute admissions (OR 5.7; 95% CI 5.2; 6.4) and 2.3-fold compared with one to two acute admissions (OR 2.3; 95% CI 2.1; 2.5). Also, high use of primary sector services (e.g. nursing care) increased the odds of repeated acute admissions when compared with no acute admissions and one to two acute admissions.

CONCLUSIONS

This study pinpointed key factors encompassing social status, disease burden, and healthcare utilisation as pivotal markers of risk for repeated acute admissions, thus identifying high-risk patients and facilitating targeted intervention.

A study protocol for a predictive model to assess population-based avoidable hospitalization risk: Avoidable Hospitalization Population Risk Prediction Tool (AvHPoRT)

INTRODUCTION

Avoidable hospitalizations are considered preventable given effective and timely primary care management and are an important indicator of health system performance. The ability to predict avoidable hospitalizations at the population level represents a significant advantage for health system decision-makers that could facilitate proactive intervention for ambulatory care-sensitive conditions (ACSCs). The aim of this study is to develop and validate the Avoidable Hospitalization Population Risk Tool (AvHPoRT) that will predict the 5-year risk of first avoidable hospitalization for seven ACSCs using self-reported, routinely collected population health survey data.

METHODS AND ANALYSIS

The derivation cohort will consist of respondents to the first 3 cycles (2000/01, 2003/04, 2005/06) of the Canadian Community Health Survey (CCHS) who are 18-74 years of age at survey administration and a hold-out data set will be used for external validation. Outcome information on avoidable hospitalizations for 5 years following the CCHS interview will be assessed through data linkage to the Discharge Abstract Database (1999/2000-2017/2018) for an estimated sample size of 394,600. Candidate predictor variables will include demographic characteristics, socioeconomic status, self-perceived health measures, health behaviors, chronic conditions, and area-based measures. Sex-specific algorithms will be developed using Weibull accelerated failure time survival models. The model will be validated both using split set cross-validation and external temporal validation split using cycles 2000-2006 compared to 2007-2012. We will assess measures of overall predictive performance (Nagelkerke R2), calibration (calibration plots), and discrimination (Harrell's concordance statistic). Development of the model will be informed by the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement.

ETHICS AND DISSEMINATION

This study was approved by the University of Toronto Research Ethics Board. The predictive algorithm and findings from this work will be disseminated at scientific meetings and in peer-reviewed publications.

Characteristics and Outcome of ICU Unplanned Readmission in Trauma Patients During the Same Hospitalization

Objective

This study aimed to determine the rate of readmission for trauma patients in ICUs, as well as the factors that predict this outcome.

Methods

This retrospective cohort study was conducted at Emtiaz Hospital, a level I referral trauma center (Shiraz, Iran). It analyzed the ICU readmission rates among trauma patients over three years. The required data were extracted from the Iranian Intensive Care Registry (IICUR), which included patient demographics, injury severity, physiological parameters, and clinical outcomes. Statistical analysis was performed using SPSS version 25.0. Descriptive statistics and different statistical tests, such as T-tests, Mann-Whitney tests, Chi-square tests, and logistic binary regression test were utilized.

Results

Among the 5273 patients discharged from the ICU during the study period, 195 (3.7%) were readmitted during the same hospitalization. Patients readmitted to the ICU had a significantly higher mean age (54.83±22.73 years) than those who were not readmitted (47.08 years, p<0.001). Lower Glasgow Coma Scale (GCS) scores at admission and discharge were associated with ICU readmission, implying that neurological status and readmission risk were correlated with each other. Furthermore, respiratory challenges were identified as the leading cause of unexpected readmission, including respiratory failure, hypoxic respiratory failure, respiratory distress, and respiratory infections such as pneumonia. Injury patterns analysis revealed a higher frequency of poly-trauma and head and neck injuries among patients readmitted to the ICU.

Conclusion

This study underscored the importance of ICU readmission among trauma patients, with a high readmission rate during the same hospitalization. By developing comprehensive guidelines and optimizing discharge processes, healthcare providers could potentially mitigate ICU readmissions and associated complications, ultimately enhancing patient outcomes and resource utilization in trauma ICU settings. This research provided valuable insights to inform evidence-based practices and improve the quality of care delivery for trauma patients in intensive care settings.

Prediction of patient admission and readmission in adults from a Colombian cohort with bipolar disorder using artificial intelligence

Introduction

Bipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology.

Aim

To develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques.

Methods

The study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index.

Results

The admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70.

Conclusion

ML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.

Development of a risk prediction model to predict the risk of hospitalization due to exacerbated asthma among adult asthma patients in a lower middle-income country

BACKGROUND

Asthma patients experience higher rates of hospitalizations due to exacerbations leaving a considerable clinical and economic burden on the healthcare system. The use of a simple, risk prediction tool offers a low-cost mechanism to identify these high-risk asthma patients for specialized care. The study aimed to develop and validate a risk prediction model to identify high-risk asthma patients for hospitalization due to exacerbations.

METHODS

Hospital-based, case-control study was carried out among 466 asthma patients aged ≥ 20 years recruited from four tertiary care hospitals in a district of Sri Lanka to identify risk factors for asthma-related hospitalizations. Patients (n = 116) hospitalized due to an exacerbation with respiratory rate > 30/min, pulse rate > 120 bpm, O2 saturation (on air) < 90% on admission, selected consecutively from medical wards; controls (n = 350;1:3 ratio) randomly selected from asthma/medical clinics. Data was collected via a pre-tested Interviewer-Administered Questionnaire (IAQ). Logistic Regression (LR) analyses were performed to develop the model with consensus from an expert panel. A second case-control study was carried out to assess the criterion validity of the new model recruiting 158 cases and 101 controls from the same hospitals. Data was collected using an IAQ based on the newly developed risk prediction model.

RESULTS

The developed model consisted of ten predictors with an Area Under the Curve (AUC) of 0.83 (95% CI: 0.78 to 0.88, P < 0.001), sensitivity 69.0%, specificity 86.1%, positive predictive value (PPV) 88.6%, negative predictive value (NPV) 63.9%. Positive and negative likelihood ratios were 4.9 and 0.3, respectively.

CONCLUSIONS

The newly developed model was proven valid to identify adult asthma patients who are at risk of hospitalization due to exacerbations. It is recommended as a simple, low-cost tool for identifying and prioritizing high-risk asthma patients for specialized care.

Factors associated with readmission in chronic kidney disease: Systematic review and meta-analysis

BACKGROUND

Risk factors associated with all-cause hospital readmission are poorly characterised in patients with chronic kidney disease.

OBJECTIVE

A systematic review and meta-analysis were conducted to identify risk factors and protectors of hospital readmission in chronic kidney disease.

DESIGN, PARTICIPANTS & MEASUREMENTS

Studies involving adult patients were identified from four databases from inception to 31/03/2020. Random-effects meta-analyses were conducted to determine factors associated with all-cause 30-day hospital readmission in general chronic kidney disease, in dialysis and in kidney transplant recipient groups.

RESULTS

Eighty relevant studies (chronic kidney disease, n = 14 studies; dialysis, n = 34 studies; and transplant, n = 32 studies) were identified. Meta-analysis revealed that in both chronic kidney disease and transplant groups, increasing age in years and days spent at the hospital during the initial stay were associated with a higher risk of 30-day readmission. Other risk factors identified included increasing body mass index (kg/m2 ) in the transplant group, and functional impairment and discharge destination in the dialysis group. Within the chronic kidney disease ​​​​group, having an outpatient follow-up appointment with a nephrologist within 14 days of discharge was protective against readmission but this was not protective if provided by a primary care provider or a cardiologist.

CONCLUSION

Risk-reduction interventions that can be implemented include a nephrologist appointment within 14 days of hospital discharge, rehabilitation programme for functional improvement in the dialysis group and meal plans in the transplant group. Future risk analysis should focus on modifiable factors to ensure that strategies can be tested and implemented in those who are more at risk.

Incidence and risk factors for unplanned readmission after colorectal surgery: A meta-analysis

BACKGROUND

Unplanned readmissions (URs) after colorectal surgery (CRS) are common, expensive, and result from failure to progress in postoperative recovery. These are considered preventable, although the true extent is yet to be defined. In addition, their successful prediction remains elusive due to significant heterogeneity in this field of research. This systematic review and meta-analysis of observational studies aimed to identify the clinically relevant predictors of UR after colorectal surgery.

METHODS

A systematic review was conducted using indexed sources (The Cochrane Database of Systematic Reviews, MEDLINE, and Embase) to search for published studies in English between 1996 and 2022. The search strategy returned 625 studies for screening of which, 150 were duplicates, and 305 were excluded for irrelevance. An additional 150 studies were excluded based on methodology and definition criteria. Twenty studies met the inclusion criteria and for the meta-analysis. Independent meta-extraction was conducted by multiple reviewers (JD & SR) in accordance with PRISMA guidelines. The primary outcome was defined as UR within 30 days of index discharge after colorectal surgery. Data were pooled using a random-effects model. Risk of bias was assessed using the Quality in Prognosis Studies tool.

RESULTS

The reported 30-day UR rate ranged from 6% to 22.8%. Increased comorbidity was the strongest preoperative risk factor for UR (OR 1.39, 95% CI 1.28-1.51). Stoma formation was the strongest operative risk factor (OR 1.54, 95% CI 1.38-1.72). The occurrence of postoperative complications was the strongest postoperative and overall risk factor for UR (OR 3.03, 95% CI 1.21-7.61).

CONCLUSIONS

Increased comorbidity, stoma formation, and postoperative complications are clinically relevant predictors of UR after CRS. These risk factors are readily identifiable before discharge and serve as clinically relevant targets for readmission risk-reducing strategies. Successful readmission prediction may facilitate the efficient allocation of healthcare resources.

Which frailty tool best predicts morbidity and mortality in ambulatory patients with heart failure? A prospective study

BACKGROUND

Frailty is common in patients with heart failure (HF) and is associated with adverse outcome, but it is uncertain how frailty should best be measured.

OBJECTIVES

To compare the prognostic value of commonly-used frailty tools in ambulatory patients with HF.

METHODS AND RESULTS

We assessed, simultaneously, three screening tools [clinical frailty scale (CFS); Derby frailty index (DFI); acute frailty network (AFN) frailty criteria), three assessment tools (Fried criteria; Edmonton frailty score (EFS); deficit index (DI)) and three physical tests (handgrip strength, timed get-up-and-go test (TUGT), 5-metre walk test (5MWT)] in consecutive patients with HF attending a routine follow-up visit. 467 patients (67% male, median age = 76 years, median NT-proBNP = 1156 ng/L) were enrolled. During a median follow-up of 554 days, 82 (18%) patients died and 201 (43%) patients were either hospitalised or died. In models corrected for age, Charlson score, haemoglobin, renal function, sodium, NYHA, atrial fibrillation (AF), and body mass index, only log[NT-proBNP] and frailty were independently associated with all-cause death. A base model for predicting mortality at 1 year including NYHA, log[NT-proBNP], sodium and AF, had a C-statistic = 0.75. Amongst screening tools: CFS (C-statistic = 0.84); amongst assessment tools: DI (C-statistic = 0.83) and amongst physical test: 5MWT (C-statistic = 0.80), increased model performance most compared with base model (P <0.05 for all).

CONCLUSION

Frailty is strongly associated with adverse outcomes in ambulatory patients with HF. When added to a base model for predicting mortality at 1 year including NYHA, NT-proBNP, sodium, and AF, CFS provides comparable prognostic information with assessment tools taking longer to perform.

Multimorbidity and prior falls correlate with risk of 30-day hospital readmission in aged 80+: A prospective cohort study

BACKGROUND/PURPOSE

Thirty-day hospital readmission rate significantly raised with advanced age. The performance of existing predictive models for readmission risk remained uncertain in the oldest population. We aimed to examine the effect of geriatric conditions and multimorbidity on readmission risk among older adults aged 80 and over.

METHODS

This prospective cohort study enrolled patients aged 80 and older discharged from a geriatric ward at a tertiary hospital, with phone follow-up for 12 months. Demographics, multimorbidity, and geriatric conditions were assessed before hospital discharge. Logistic regression models were conducted to analyse risk factors for 30-day readmission.

RESULTS

Patients readmitted had higher Charlson comorbidity index scores, and were more likely to have falls, frailty, and longer hospital stay, compared to those without 30-day readmission. Multivariate analysis revealed that higher Charlson comorbidity index score was associated with readmission risk. Older patients with a fall history within 12 months had a near 4-fold increase in readmission risk. Severe frailty status before index admission was associated with a higher 30-day readmission risk. Functional status at discharge was not associated with readmission risk.

CONCLUSION

In addition to multimorbidity, history of falls and frailty were associated with higher hospital readmission risk in the oldest.

Using the Elixhauser risk adjustment model to predict outcomes among patients hospitalized in internal medicine at a large, tertiary-care hospital in Israel

BACKGROUND

In Israel, internal medicine admissions are currently reimbursed without accounting for patient complexity. This is at odds with most other developed countries and has the potential to lead to market distortions such as avoiding sicker patients. Our objective was to apply a well-known, freely available risk adjustment model, the Elixhauser model, to predict relevant outcomes among patients hospitalized on the internal medicine service of a large, Israeli tertiary-care hospital.

METHODS

We used data from the Shaare Zedek Medical Center, a large tertiary referral hospital in Jerusalem. The study included 55,946 hospitalizations between 01.01.2016 and 31.12.2019. We modeled four patient outcomes: in-hospital mortality, escalation of care (intensive care unit (ICU) transfer, mechanical ventilation, daytime bi-level positive pressure ventilation, or vasopressors), 30-day readmission, and length of stay (LOS). We log-transformed LOS to address right skew. As is usual with the Elixhauser model, we identified 29 comorbid conditions using international classification of diseases codes, clinical modification, version 9. We derived and validated the coefficients for these 29 variables using split-sample derivation and validation. We checked model fit using c-statistics and R2, and model calibration using a Hosmer-Lemeshow test.

RESULTS

The Elixhauser model achieved acceptable prediction of the three binary outcomes, with c-statistics of 0.712, 0.681, and 0.605 to predict in-hospital mortality, escalation of care, and 30-day readmission respectively. The c-statistic did not decrease in the validation set (0.707, 0.687, and 0.603, respectively), suggesting that the models are not overfitted. The model to predict log length of stay achieved an R2 of 0.102 in the derivation set and 0.101 in the validation set. The Hosmer-Lemeshow test did not suggest issues with model calibration.

CONCLUSION

We demonstrated that a freely-available risk adjustment model can achieve acceptable prediction of important clinical outcomes in a dataset of patients admitted to a large, Israeli tertiary-care hospital. This model could potentially be used as a basis for differential payment by patient complexity.

Machine Learning on Medicare Claims Poorly Predicts the Individual Risk of 30-Day Unplanned Readmission After Total Joint Arthroplasty, Yet Uncovers Interesting Population-level Associations With Annual Procedure Volumes

BACKGROUND

Unplanned hospital readmissions after total joint arthroplasty (TJA) represent potentially serious adverse events and remain a critical measure of hospital quality. Predicting the risk of readmission after TJA may provide patients and clinicians with valuable information for preoperative decision-making.

QUESTIONS/PURPOSES

(1) Can nonlinear machine-learning models integrating preoperatively available patient, surgeon, hospital, and county-level information predict 30-day unplanned hospital readmissions in a large cohort of nationwide Medicare beneficiaries undergoing TJA? (2) Which predictors are the most important in predicting 30-day unplanned hospital readmissions? (3) What specific information regarding population-level associations can we obtain from interpreting partial dependency plots (plots describing, given our modeling choice, the potentially nonlinear shape of associations between predictors and readmissions) of the most important predictors of 30-day readmission?

METHODS

National Medicare claims data (chosen because this database represents a large proportion of patients undergoing TJA annually) were analyzed for patients undergoing inpatient TJA between October 2016 and September 2018. A total of 679,041 TJAs (239,391 THAs [61.3% women, 91.9% White, 52.6% between 70 and 79 years old] and 439,650 TKAs [63.3% women, 90% White, 55.2% between 70 and 79 years old]) were included. Model features included demographics, county-level social determinants of health, prior-year (365-day) hospital and surgeon TJA procedure volumes, and clinical classification software-refined diagnosis and procedure categories summarizing each patient's Medicare claims 365 days before TJA. Machine-learning models, namely generalized additive models with pairwise interactions (prediction models consisting of both univariate predictions and pairwise interaction terms that allow for nonlinear effects), were trained and evaluated for predictive performance using area under the receiver operating characteristic (AUROC; 1.0 = perfect discrimination, 0.5 = no better than random chance) and precision-recall curves (AUPRC; equivalent to the average positive predictive value, which does not give credit for guessing "no readmission" when this is true most of the time, interpretable relative to the base rate of readmissions) on two holdout samples. All admissions (except the last 2 months' worth) were collected and split randomly 80%/20%. The training cohort was formed with the random 80% sample, which was downsampled (so it included all readmissions and a random, equal number of nonreadmissions). The random 20% sample served as the first test cohort ("random holdout"). The last 2 months of admissions (originally held aside) served as the second test cohort ("2-month holdout"). Finally, feature importances (the degree to which each variable contributed to the predictions) and partial dependency plots were investigated to answer the second and third research questions.

RESULTS

For the random holdout sample, model performance values in terms of AUROC and AUPRC were 0.65 and 0.087, respectively, for THA and 0.66 and 0.077, respectively, for TKA. For the 2-month holdout sample, these numbers were 0.66 and 0.087 and 0.65 and 0.075. Thus, our nonlinear models incorporating a wide variety of preoperative features from Medicare claims data could not well-predict the individual likelihood of readmissions (that is, the models performed poorly and are not appropriate for clinical use). The most predictive features (in terms of mean absolute scores) and their partial dependency graphs still confer information about population-level associations with increased risk of readmission, namely with older patient age, low prior 365-day surgeon and hospital TJA procedure volumes, being a man, patient history of cardiac diagnoses and lack of oncologic diagnoses, and higher county-level rates of hospitalizations for ambulatory-care sensitive conditions. Further inspection of partial dependency plots revealed nonlinear population-level associations specifically for surgeon and hospital procedure volumes. The readmission risk for THA and TKA decreased as surgeons performed more procedures in the prior 365 days, up to approximately 75 TJAs (odds ratio [OR] = 1.2 for TKA and 1.3 for THA), but no further risk reduction was observed for higher annual surgeon procedure volumes. For THA, the readmission risk decreased as hospitals performed more procedures, up to approximately 600 TJAs (OR = 1.2), but no further risk reduction was observed for higher annual hospital procedure volumes.

CONCLUSION

A large dataset of Medicare claims and machine learning were inadequate to provide a clinically useful individual prediction model for 30-day unplanned readmissions after TKA or THA, suggesting that other factors that are not routinely collected in claims databases are needed for predicting readmissions. Nonlinear population-level associations between low surgeon and hospital procedure volumes and increased readmission risk were identified, including specific volume thresholds above which the readmission risk no longer decreases, which may still be indirectly clinically useful in guiding policy as well as patient decision-making when selecting a hospital or surgeon for treatment.

LEVEL OF EVIDENCE

Level III, therapeutic study.

Performance of advanced machine learning algorithms overlogistic regression in predicting hospital readmissions: A meta-analysis

Objectives

Machine learning algorithms are being increasingly used for predicting hospital readmissions. This meta-analysis evaluated the performance of logistic regression (LR) and machine learning (ML) models for the prediction of 30-day hospital readmission among patients in the US.

Methods

Electronic databases (i.e., Medline, PubMed, and Embase) were searched from January 2015 to December 2019. Only studies in the English language were included. Two reviewers performed studies screening, quality appraisal, and data collection. The quality of the studies was assessed using the Quality in Prognosis Studies (QUIPS) tool. Model performance was evaluated using the Area Under the Curve (AUC). A random-effects meta-analysis was performed using STATA 16.

Results

Nine studies were included based on the selection criteria. The most common ML techniques were tree-based methods such as boosting and random forest. Most of the studies had a low risk of bias (8/9). The AUC was greater with ML to predict 30-day all-cause hospital readmission compared with LR [Mean Difference (MD): 0.03; 95% Confidence Interval (CI) 0.01-0.05]. Subgroup analyses found that deep-learning methods had a better performance compared with LR (MD 0.06; 95% CI, 0.04-0.09), followed by neural networks (MD: 0.03; 95% CI, 0.03-0.03), while the AUCs of the tree-based (MD: 0.02; 95% CI -0.00-0.04) and kernel-based (MD: 0.02; 95% CI 0.02 (-0.13-0.16) methods were no different compared to LR. More than half of the studies evaluated heart failure-related rehospitalization (N = 5). For the readmission prediction among heart failure patients, ML performed better compared with LR, with a mean difference in AUC of 0.04 (95% CI, 0.01-0.07). The leave-one-out sensitivity analysis confirmed the robustness of the findings.

Conclusion

Multiple ML methods were used to predict 30-day all-cause hospital readmission. Performance varied across the ML methods, with deep-learning methods showing the best performance over the LR.

Inferior vena cava diameter and risk of acute decompensated heart failure rehospitalisations

OBJECTIVES

Inferior vena cava (IVC) diameter may be a surrogate for volume status in acute decompensated heart failure (ADHF). The utility of IVC diameter measurement is under studied. The aim of this study was to assess the relationship between IVC diameter, clinical variables and ADHF rehospitalisations.

METHODS

Retrospective chart review of 200 patients admitted for ADHF from 2018 to 2019 with transthoracic echocardiogram during index hospitalisation. Charts were assessed for ADHF rehospitalisation within 1 year.

RESULTS

The median age was 64, 30.5% were female, and average left ventricular ejection fraction was 41%±20%. IVC diameter correlated to pulmonary arterial (PA) pressure (R=0.347, p<0.001) and body surface area (BSA) (R=0.424 p<0.001). IVC diameter corrected for BSA correlated to PA pressure (R=0.287, p<0.001) and log N-terminal B-type natriuretic peptide (NT-proBNP) (R=0.247, p≤0.01). Patients rehospitalised within 1 year had significantly greater mean IVC diameter compared with those not rehospitalised (p<0.001) while there was no difference in mean net weight lost during index hospitalisation or mean log NT-proBNP. Patients with IVC diameter greater than 2.07 cm had significantly increased ADHF rehospitalisation (85.6% vs 49.3%, log rank p<0.001) with HR 2.44 (95% CI 1.85 to 3.23, p<0.001). In multivariable Cox regression only IVC diameter (p<0.001), presence of tricuspid regurgitation (p=0.02) and NYHA class III/IV (p<0.001) independently predicted ADHF rehospitalisation within 1 year.

CONCLUSIONS

IVC diameter is predictive of rehospitalisation in patients with ADHF and may identify patients in need of greater monitoring and diuresis.

A Data-Driven Approach to Identify the Predictors of Perceived Health Status Among Chinese and Korean Americans

Asian Americans are the country's fastest-growing racial group, and several studies have focused on the health outcomes of Asian Americans, including perceived health status. Perceived health status provides a summarized view of the health of populations for diverse domains, such as the psychological, social, and behavioral aspects. Given its multifaceted nature, perceived health status should be carefully approached when examining any variables' influence because it results from interactions among many variables. A data-driven approach using machine learning provides an effective way to discover new insights when there are complex interactions among multiple variables. To date, there are not many studies available that use machine learning to examine the effects of diverse variables on the perceived health status of Chinese and Korean Americans. This study aims to develop and evaluate three prediction models using logistic regression, random forest, and support vector machines to find the predictors of perceived health status among Chinese and Korean Americans from survey data. The prediction models identified specific predictors of perceived health status. These predictors can be utilized when planning for effective interventions for the better health outcomes of Chinese and Korean Americans.

Development and validation of predictive models for unplanned hospitalization in the Basque Country: analyzing the variability of non-deterministic algorithms

BACKGROUND

The progressive ageing in developed countries entails an increase in multimorbidity. Population-wide predictive models for adverse health outcomes are crucial to address these growing healthcare needs. The main objective of this study is to develop and validate a population-based prognostic model to predict the probability of unplanned hospitalization in the Basque Country, through comparing the performance of a logistic regression model and three families of machine learning models.

METHODS

Using age, sex, diagnoses and drug prescriptions previously transformed by the Johns Hopkins Adjusted Clinical Groups (ACG) System, we predict the probability of unplanned hospitalization in the Basque Country (2.2 million inhabitants) using several techniques. When dealing with non-deterministic algorithms, comparing a single model per technique is not enough to choose the best approach. Thus, we conduct 40 experiments per family of models - Random Forest, Gradient Boosting Decision Trees and Multilayer Perceptrons - and compare them to Logistic Regression. Models' performance are compared both population-wide and for the 20,000 patients with the highest predicted probabilities, as a hypothetical high-risk group to intervene on.

RESULTS

The best-performing technique is Multilayer Perceptron, followed by Gradient Boosting Decision Trees, Logistic Regression and Random Forest. Multilayer Perceptrons also have the lowest variability, around an order of magnitude less than Random Forests. Median area under the ROC curve, average precision and positive predictive value range from 0.789 to 0.802, 0.237 to 0.257 and 0.485 to 0.511, respectively. For Brier Score the median values are 0.048 for all techniques. There is some overlap between the algorithms. For instance, Gradient Boosting Decision Trees perform better than Logistic Regression more than 75% of the time, but not always.

CONCLUSIONS

All models have good global performance. The only family that is consistently superior to Logistic Regression is Multilayer Perceptron, showing a very reliable performance with the lowest variability.

Predicting Acute Care Events Among Patients Initiating Chemotherapy: A Practice-Based Validation and Adaptation of the PROACCT Model

PURPOSE

Acute care events (ACEs), comprising emergency department visits and hospitalizations, are a priority area for reduction in oncology. Prognostic models are a compelling strategy to identify high-risk patients and target preventive services, but have yet to be broadly implemented, partly because of challenges with electronic health record (EHR) integration. To facilitate EHR integration, we adapted and validated the previously published PRediction Of Acute Care use during Cancer Treatment (PROACCT) model to identify patients at highest risk for ACEs after systemic anticancer treatment.

METHODS

A retrospective cohort of adults with a cancer diagnosis starting systemic therapy at a single center between July and November 2021 was divided into development (70%) and validation (30%) sets. Clinical and demographic variables were extracted, limited to those in structured format in the EHR, including cancer diagnosis, age, drug category, and ACE in prior year. Three logistic regression models of increasing complexity were developed to predict risk of ACEs.

RESULTS

Five thousand one hundred fifty-three patients were evaluated (3,603 development and 1,550 validation). Several factors were predictive of ACEs: age (in decades), receipt of cytotoxic chemotherapy or immunotherapy, thoracic, GI or hematologic malignancy, and ACE in the prior year. We defined high-risk as the top 10% of risk scores; this population had 33.6% ACE rate compared with 8.3% for the remaining 90% in the low-risk group. The simplest Adapted PROACCT model had a C-statistic of 0.79, sensitivity of 0.28, and specificity of 0.93.

CONCLUSION

We present three models designed for EHR integration that effectively identify oncology patients at highest risk for ACE after initiation of systemic anticancer treatment. By limiting predictors to structured data fields and including all cancer types, these models offer broad applicability for cancer care organizations and may offer a safety net to identify and target resources to this high risk.

A risk scoring model of COVID-19 at hospital admission

BACKGROUND

The COVID-19 pandemic has been the most serious public health crisis in recent times, a pandemic whose impact was felt across the globe in various groups and populations. Confronted with an urgent problem, people and governments were forced to make decisions without fully understanding the disease. The present work aims to reinforce our ever-growing knowledge of the illness, particularly in modelling the risk of death of a patient admitted to a hospital with a positive COVID-19 test.

METHODS

Given the simplicity of using and programming logistic regression in any national healthcare unit and the ease of interpreting the results, we chose to use this technique over several other. Using scoring techniques, it is possible to associate the various diagnoses with a numerical value (score), making it possible therefore to integrate the patient's multiple medical conditions as a single continuous variable in the model.

RESULTS

It is possible to establish with good discriminatory capacity (ROC AUC Test = 0.8) which COVID patients are at higher risk when admitted to the healthcare unit-people of advanced age with pre-existing conditions, such as diabetes and high blood pressure, or newly acquired conditions, such as pneumonia. Moreover, males and clinical episodes occurring in healthcare units with few available beds (high healthcare unit occupancy) are also at higher risk. The importance of each variable in predicting the target is: age (47%), sum of comorbidity scores (28%), healthcare unit score (12.0%), gender score (7%) and healthcare unit occupancy (6%).

CONCLUSIONS

Using a dataset with more than 52000 people, it was possible to successfully differentiate likelihood of death by COVID using age, comorbidity information, healthcare unit, healthcare unit occupancy and gender. The age and the comorbidities associated with each patient had a joint contribution of about 75% in explaining the COVID related mortality in Portuguese public hospitals in the period between March 2020 and May 2021.

Predictors of unplanned hospital readmission after non-cardiac surgery in Singapore: a 2-year retrospective review

INTRODUCTION

Unplanned hospital readmissions after surgery contribute significantly to healthcare costs and potential complications. Identifying predictors of readmission is inherently complex and involves an intricate interplay between medical factors, healthcare system factors and sociocultural factors. Therefore, the aim of this study was to elucidate the predictors of readmissions in an Asian surgical patient population.

METHODS

A two-year single-institution retrospective cohort study of 2744 patients was performed in a university-affiliated tertiary hospital in Singapore, including patients aged 45 and above undergoing intermediate or high-risk non-cardiac surgery. Unadjusted analysis was first performed, followed by multivariable logistic regression.

RESULTS

Two hundred forty-nine patients (9.1%) had unplanned 30-day readmissions. Significant predictors identified from multivariable analysis include: American Society of Anaesthesiologists (ASA) Classification grades 3 to 5 (adjusted OR 1.51, 95% CI 1.10-2.08, p = 0.01), obesity (adjusted OR 1.66, 95% CI 1.18-2.34, p = 0.04), asthma (OR 1.70, 95% CI 1.03-2.81, p = 0.04), renal disease (OR 2.03, 95% CI 1.41-2.92, p < 0.001), malignancy (OR 1.68, 95% CI 1.29-2.37, p < 0.001), chronic obstructive pulmonary disease (OR 2.46, 95% CI 1.19-5.11, p = 0.02), cerebrovascular disease (OR 1.73, 95% CI 1.17-2.58, p < 0.001) and anaemia (OR 1.45, 95% CI 1.07-1.96, p = 0.02).

CONCLUSION

Several significant predictors of unplanned readmissions identified in this Asian surgical population corroborate well with findings from Western studies. Further research will require future prospective studies and development of predictive risk modelling to further address and mitigate this phenomenon.

Understanding the characteristics of high users of hospital services in Singapore and their associations with healthcare utilisation and mortality: A cluster analysis

INTRODUCTION

High users of hospital services require targeted healthcare services planning for effective resource allocation due to their high costs. This study aims to segmentize the population in the "Ageing In Place-Community Care Team" (AIP-CCT), a programme for complex patients with high inpatient service use, and examine the association of segment membership and healthcare utilisation and mortality.

METHODS

We analysed 1,012 patients enrolled between June 2016 and February 2017. To identify patient segments, a cluster analysis was performed based on medical complexity and psychosocial needs. Next, multivariable negative binomial regression was performed using patient segments as the predictor, with healthcare and programme utilisation over the 180-day follow-up as outcomes. Multivariate cox proportional hazard regression was applied to assess the time to first hospital admission and mortality between segments within the 180-day follow-up. All models were adjusted for age, gender, ethnicity, ward class, and baseline healthcare utilisation.

RESULTS

Three distinct segments were identified (Segment 1 (n = 236), Segment 2 (n = 331), and Segment 3 (n = 445)). Medical, functional, and psychosocial needs of individuals were significantly different between segments (p-value<0.001). The rates of hospitalisation in Segments 1 (IRR = 1.63, 95%CI:1.3-2.1) and 2 (IRR = 2.11, 95%CI:1.7-2.6) were significantly higher than in Segment 3 on follow-up. Similarly, both Segments 1 (IRR = 1.76, 95%CI:1.6-2.0) and 2 (IRR = 1.25, 95%CI:1.1-1.4) had higher rates of programme utilisation compared to Segment 3. Patients in Segments 1 (HR = 2.48, 95%CI:1.5-4.1) and 2 (HR = 2.25, 95%CI:1.3-3.6) also had higher mortality on follow-up.

CONCLUSIONS

This study provided a data-based approach to understanding healthcare needs among complex patients with high inpatient services utilisation. Resources and interventions can be tailored according to the differences in needs among segments, to facilitate better allocation.