An Absolute Risk Prediction Model to Determine Unplanned Cardiovascular Readmissions for Adults with Chronic Heart Failure

Impact of mental disorders on unplanned readmissions for congestive heart failure patients: a population-level study

AIMS

Reducing preventable hospitalization for congestive heart failure (CHF) patients is a challenge for health systems worldwide. CHF patients who also have a recent or ongoing mental disorder may have worse health outcomes compared with CHF patients with no mental disorders. This study examined the impact of mental disorders on 28 day unplanned readmissions of CHF patients.

METHODS AND RESULTS

This retrospective cohort study used population-level linked public and private hospitalization and death data of adults aged ≥18 years who had a CHF admission in New South Wales, Australia, between 1 January 2014 and 31 December 2020. Individuals' mental disorder diagnosis and Charlson comorbidity and hospital frailty index scores were derived from admission records. Competing risk and cause-specific risk analyses were conducted to examine the impact of having a mental disorder diagnosis on all-cause hospital readmission. Of the 65 861 adults with index CHF admission discharged alive (mean age: 78.6 ± 12.1; 48% female), 19.2% (12 675) had at least one unplanned readmission within 28 days following discharge. Adults with CHF with a mental disorder diagnosis within 12 months had a higher risk of 28 day all-cause unplanned readmission [hazard ratio (HR): 1.21, 95% confidence interval (CI): 1.15-1.27, P-value < 0.001], particularly those with anxiety disorder (HR: 1.49, 95% CI: 1.35-1.65, P-value < 0.001). CHF patients aged ≥85 years (HR: 1.19, 95% CI: 1.11-1.28), having ≥3 other comorbidities (HR: 1.35, 95% CI: 1.25-1.46), and having an intermediate (HR: 1.34, 95% CI: 1.28-1.40) or high (HR: 1.37, 95% CI: 1.27-1.47) frailty score on admission had a higher risk of unplanned readmission. CHF patients with a mental disorder who have ≥3 other comorbidities and an intermediate frailty score had the highest probability of unplanned readmission (29.84%, 95% CI: 24.68-35.73%) after considering other patient-level factors and competing events.

CONCLUSIONS

CHF patients who had a mental disorder diagnosis in the past 12 months are more likely to be readmitted compared with those without a mental disorder diagnosis. CHF patients with frailty and a mental disorder have the highest probability of readmission. Addressing mental health care services in CHF patient's discharge plan could potentially assist reduce unplanned readmissions.

Leveraging deep survival models to predict quality of care risk in diverse hospital readmissions

Hospital readmissions rate is reportedly high and has caused huge financial burden on health care systems in many countries. It is viewed as an important indicator of health care providers' quality of care. We examine the use of machine learning-based survival analysis to assess quality of care risk in hospital readmissions. This study applies various survival models to explore the risk of hospital readmissions given patient demographics and their respective hospital discharges extracted from a health care claims dataset. We explore advanced feature representation techniques such as BioBERT and Node2Vec to encode high-dimensional diagnosis code features. To our knowledge, this study is the first to apply deep-learning based survival-analysis models for predicting hospital readmission risk agnostic of specific medical conditions and a fixed window for readmission. We found that modeling the time from discharge date to readmission date as a Weibull distribution as in the SparseDeepWeiSurv model yields the best discriminative power and calibration. In addition, embedding representations of the diagnosis codes do not contribute to improvement in model performance. We find dependency of each model's performance on the time point at which it is evaluated. This time dependency of the models' performance on the health care claims data may necessitate a different choice of model in quality of care issue detection at different points in time. We show the effectiveness of deep-learning based survival-analysis models in estimating the quality of care risk in hospital readmissions.

Comparison of linear and non-linear machine learning models for time-dependent readmission or mortality prediction among hospitalized heart failure patients

Although many models are available to predict prognosis of heart failure patients, most tools combining survival analysis are based on proportional hazard model. Non-linear machine learning algorithms would overcome the limitation of the time-independent hazard ratio assumption and provide more information in readmission or mortality prediction among heart failure patients. The present study collected the clinical information of 1796 hospitalized heart failure patients surviving during hospitalization in a Chinese clinical center from December 2016 to June 2019. A traditional multivariate Cox regression model and three machine learning survival models were developed in derivation cohort. Uno's concordance index and integrated Brier score in validation cohort were calculated to evaluate the discrimination and calibration of different models. Time-dependent AUC and Brier score curves were plotted to assess the performance of models at different time phases.

One-year rehospitalisation and mortality after acute heart failure hospitalisation: a competing risk analysis

OBJECTIVE

To identify factors that independently predict the risk of rehospitalisation and death after acute heart failure (AHF) hospital discharge in a real-world setting, considering death without rehospitalisation as a competing event.

METHODS

Single-centre, retrospective, observational study enrolling 394 patients discharged from an index AHF hospitalisation. Overall survival was evaluated using Kaplan-Meier and Cox regression models. For the risk of rehospitalisation, survival analysis considering competing risks was performed: rehospitalisation was the event of interest, and death without rehospitalisation was the competing event.

RESULTS

During the first year after discharge, 131 (33.3%) patients were rehospitalised for AHF and 67 (17.0%) died without being readmitted; the remaining 196 patients (49.7%) lived without further hospitalisations. The 1-year overall survival estimate was 0.71 (SE=0.02). After adjusting for gender, age and left ventricle ejection fraction, the results showed that the risk of death was higher in patients with dementia, higher levels of plasma creatinine (PCr), lower levels of platelet distribution width (PDW) and at Q4 of red cell distribution width (RDW). Multivariable models showed that the risk of rehospitalisation was increased in patients with atrial fibrillation, higher PCr or taking beta-blockers at discharge. Furthermore, the risk of death without AHF rehospitalisation was higher in males, those aged ≥80 years, patients with dementia or RDW at Q4 on admission (compared with Q1). Taking beta-blockers at discharge and having a higher PDW on admission reduced the risk of death without rehospitalisation.

CONCLUSION

When assessing rehospitalisation as a study endpoint, death without rehospitalisation should be considered a competing event in the analyses. Data from this study reveal that patients with atrial fibrillation, renal dysfunction or taking beta-blockers are more likely to be rehospitalised for AHF, while older men with dementia or high RDW are more prone to die without hospital readmission.

Predictive Modeling of Hospital Readmission: Challenges and Solutions

Hospital readmission prediction is a study to learn models from historical medical data to predict probability of a patient returning to hospital in a certain period, e.g. 30 or 90 days, after the discharge. The motivation is to help health providers deliver better treatment and post-discharge strategies, lower the hospital readmission rate, and eventually reduce the medical costs. Due to inherent complexity of diseases and healthcare ecosystems, modeling hospital readmission is facing many challenges. By now, a variety of methods have been developed, but existing literature fails to deliver a complete picture to answer some fundamental questions, such as what are the main challenges and solutions in modeling hospital readmission; what are typical features/models used for readmission prediction; how to achieve meaningful and transparent predictions for decision making; and what are possible conflicts when deploying predictive approaches for real-world usages. In this paper, we systematically review computational models for hospital readmission prediction, and propose a taxonomy of challenges featuring four main categories: (1) data variety and complexity; (2) data imbalance, locality and privacy; (3) model interpretability; and (4) model implementation. The review summarizes methods in each category, and highlights technical solutions proposed to address the challenges. In addition, a review of datasets and resources available for hospital readmission modeling also provides firsthand materials to support researchers and practitioners to design new approaches for effective and efficient hospital readmission prediction.

Medicare Claim-Based National Institutes of Health Stroke Scale to Predict 30-Day Mortality and Hospital Readmission

BACKGROUND

The Centers for Medicare and Medicaid Services (CMS) penalizes hospitals for higher than expected 30-day mortality rates using methods without accounting for condition severity risk adjustment. For patients with stroke, CMS claims did not quantify stroke severity until recently, when the National Institutes of Health Stroke Scale (NIHSS) reporting began.

OBJECTIVE

Examine the predictive ability of claim-based NIHSS to predict 30-day mortality and 30-day hospital readmission in patients with ischemic stroke.

DESIGN

Retrospective cohort study of Medicare claims data.

PATIENTS

Medicare beneficiaries with ischemic stroke (N=43,241) acute hospitalization between October 2016 and November 2017.

MEASUREMENTS

All-cause 30-day mortality and 30-day hospital readmission. NIHSS score was derived from ICD-10 codes and stratified into the following: minor to moderate, moderate, moderate to severe, and severe categories.

RESULTS

Among 43,241 patients with ischemic stroke with NIHSS from 2,659 US hospitals, 64.6% had minor to moderate stroke, 14.3% had moderate, 12.7% had moderate to severe, and 8.5% had a severe stroke,10.1% died within 30 days, 12.1% were readmitted within 30 days. The NIHSS exhibited stronger discriminant property (C-statistic 0.83, 95% CI: 0.82-0.84) for 30-day mortality compared to Elixhauser (0.74, 95% CI: 0.73-0.75). A monotonic increase in the adjusted 30-day mortality risk occurred relative to minor to moderate stroke category: hazard ratio [HR]=2.92 (95% CI=2.59-3.29) for moderate stroke, HR=5.49 (95% CI=4.90-6.15) for moderate to severe stroke, and HR=7.82 (95% CI=6.95-8.80) for severe stroke. After accounting for competing risk of mortality, there was a significantly higher readmission risk in the moderate stroke (HR=1.11, 95% CI=1.03-1.20), but significantly lower readmission risk in the severe stroke (HR=0.84, 95% CI=0.74-0.95) categories.

LIMITATION

Timing of NIHSS reporting during hospitalization is unknown.

CONCLUSIONS

Medicare claim-based NIHSS is significantly associated with 30-day mortality in Medicare patients with ischemic stroke and significantly improves discriminant property relative to the Elixhauser comorbidity index.

Exploring risk factors of short-term readmission in heart failure patients: A cohort study

BACKGROUND

The risk of all-cause mortality in patients with heart failure (HF) has been studied previously. Readmission risk of HF patients was rarely explored. Thus, we aimed to explore early warning factors that may influence short-term readmission of HF patients.

METHODS

The data of this study came from an HF database in China. It was a retrospective single-center observational study that collected characteristic data on Chinese HF patients by integrating electronic medical records and follow-up outcome data. Eventually, 1,727 patients with HF were finally included in our study.

RESULTS

In our study, the proportion of HF patients with New York Heart Association (NYHA) class II, III, and IV HF were 17.20%, 52.69%, and 30.11%, respectively. The proportion of patients with readmission within 6 months and readmission within 3 months was 38.33% and 24.20%, respectively. Multivariate logistic regression showed that NYHA class (p _III = 0.028, p _IV < 0.001), diabetes (p = 0.002), Cr (p = 0.003), and RDW-SD (p = 0.039) were risk factors for readmission within 6 months of HF patients. NYHA class (p _III = 0.038, p _IV < 0.001), CCI (p = 0.033), Cr (p = 0.012), UA (p = 0.042), and Na (p = 0.026) were risk factors for readmission within 3 months of HF patients.

CONCLUSIONS

Our study implied risk factors of short-term readmission risk in patients with HF, which may provide policy guidance for the prognosis of patients with HF.

Association between the frequency of toothbrushing and lifestyle in people with type 2 diabetes mellitus: at the baseline date of the Kamogawa-DM cohort study

It has been reported that oral health is associated with some co-morbid conditions, including cardiovascular disease, in people with type 2 diabetes mellitus. The present study investigated the association between the frequency of toothbrushing and lifestyle in people with type 2 diabetes mellitus. This cross-sectional study included 624 outpatients at the Kyoto Prefectural University of Medicine in Kyoto, Japan from January 2014 to January 2016. Lifestyle was evaluated using a self-administered questionnaire. The average age and hemoglobin A1c level were 67.6 ± 10.9 years and 7.2 ± 1.1%, respectively. The number of patients who brushed their teeth twice or more a day was 189 (50.3%) in men and 198 (79.8%) in women. Among men, the proportion of patients living alone was lower in those who brushed their teeth twice or more a day than those who brushed their teeth never/rarely or once a day. The logistic regression analysis, after adjusting for confounding factors, revealed that living alone (odds ratio 2.88; 95% confidence interval 1.53–5.66) was associated with the increased odds of the low frequency of toothbrushing (never/rarely or once a day) in men, but not in women. In conclusion, the results of our study suggest that living alone was associated with the low frequency of toothbrushing in people with type 2 diabetes mellitus, particularly in men.

Prediction models for hospital readmissions in patients with heart disease: a systematic review and meta-analysis

OBJECTIVE

To describe the discrimination and calibration of clinical prediction models, identify characteristics that contribute to better predictions and investigate predictors that are associated with unplanned hospital readmissions.

DESIGN

Systematic review and meta-analysis.

DATA SOURCE

Medline, EMBASE, ICTPR (for study protocols) and Web of Science (for conference proceedings) were searched up to 25 August 2020.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES

Studies were eligible if they reported on (1) hospitalised adult patients with acute heart disease; (2) a clinical presentation of prediction models with c-statistic; (3) unplanned hospital readmission within 6 months.

PRIMARY AND SECONDARY OUTCOME MEASURES

Model discrimination for unplanned hospital readmission within 6 months measured using concordance (c) statistics and model calibration. Meta-regression and subgroup analyses were performed to investigate predefined sources of heterogeneity. Outcome measures from models reported in multiple independent cohorts and similarly defined risk predictors were pooled.

RESULTS

Sixty studies describing 81 models were included: 43 models were newly developed, and 38 were externally validated. Included populations were mainly patients with heart failure (HF) (n=29). The average age ranged between 56.5 and 84 years. The incidence of readmission ranged from 3% to 43%. Risk of bias (RoB) was high in almost all studies. The c-statistic was <0.7 in 72 models, between 0.7 and 0.8 in 16 models and >0.8 in 5 models. The study population, data source and number of predictors were significant moderators for the discrimination. Calibration was reported for 27 models. Only the GRACE (Global Registration of Acute Coronary Events) score had adequate discrimination in independent cohorts (0.78, 95% CI 0.63 to 0.86). Eighteen predictors were pooled.

CONCLUSION

Some promising models require updating and validation before use in clinical practice. The lack of independent validation studies, high RoB and low consistency in measured predictors limit their applicability.

PROSPERO REGISTRATION NUMBER

CRD42020159839.

Published models that predict hospital readmission: a critical appraisal

INTRODUCTION

The number of readmission risk prediction models available has increased rapidly, and these models are used extensively for health decision-making. Unfortunately, readmission models can be subject to flaws in their development and validation, as well as limitations in their clinical usefulness.

OBJECTIVE

To critically appraise readmission models in the published literature using Delphi-based recommendations for their development and validation.

METHODS

We used the modified Delphi process to create Critical Appraisal of Models that Predict Readmission (CAMPR), which lists expert recommendations focused on development and validation of readmission models. Guided by CAMPR, two researchers independently appraised published readmission models in two recent systematic reviews and concurrently extracted data to generate reference lists of eligibility criteria and risk factors.

RESULTS

We found that published models (n=81) followed 6.8 recommendations (45%) on average. Many models had weaknesses in their development, including failure to internally validate (12%), failure to account for readmission at other institutions (93%), failure to account for missing data (68%), failure to discuss data preprocessing (67%) and failure to state the model's eligibility criteria (33%).

CONCLUSIONS

The high prevalence of weaknesses in model development identified in the published literature is concerning, as these weaknesses are known to compromise predictive validity. CAMPR may support researchers, clinicians and administrators to identify and prevent future weaknesses in model development.

Predictors of Heart Failure Readmission in a High-Risk Primarily Hispanic Population in a Rural Setting

BACKGROUND

High risk for readmission in patients with heart failure (HF) is associated with Hispanic ethnicity, multimorbidity, smaller hospitals, and hospitals serving low-socioeconomic or heavily Hispanic regions and those with limited cardiac services. Information for hospitals caring primarily for such high-risk patients is lacking.

OBJECTIVE

The aim of this study was to identify factors associated with 30-day HF readmission after HF hospitalization in a rural, primarily Hispanic, low-socioeconomic, and underserved region.

METHODS

Electronic medical records for all HF admissions within a 2-year period to a 107-bed hospital near the California-Mexico border were reviewed. Logistic regression was used to identify independent predictors of readmission.

RESULTS

A total of 189 unique patients had 30-day follow-up data. Patients were primarily Hispanic (71%), male (58%), and overweight or obese (82.5%) with 4 or more chronic conditions (83%) and a mean age of 68 years. The 30-day HF readmission rate was 5.3%. Early readmission was associated with history of HF, more previous emergency department (ED) and hospital visits, higher diastolic blood pressure and hypokalemia at presentation, shorter length of stay, and higher heart rate, diastolic blood pressure, and atrial fibrillation (AF) at discharge. Using logistic regression, previous 6-month ED visits (odds ratio, 1.5; P = .009) and AF at discharge (odds ratio, 5.7; P = .039) were identified as independent predictors of 30-day HF readmission.

CONCLUSIONS

Previous ED use and AF at discharge predicted early HF readmission in a high-risk, primarily Hispanic, rural population in a low-socioeconomic region.

Nurses as educators in the comprehensive heart failure care programme-Are we ready for it?

Aim

To assess education frequency and nurses' comfort when educating patients hospitalized in different hospital units to prepare them for self-care.

Design

A cross-sectional survey. The study included nurses working in units where HF patients were hospitalized.

Results

The average score for comfort of education was 5.43 (between "slightly comfortable" and "very comfortable"). The most comfortable topics were "Daily weight monitoring" (5.81 ± 1.25), "Signs/symptoms of worsening condition" (5.77 ± 1.19) and "Fluid restriction" (5.76 ± 1.23). The respondents felt least comfortable when teaching about "Medications" (5.06 ± 1.35) and "Low-sodium diet" (5.31 ± 1.42). The mean score obtained for education frequency was 5.21 (SD 2.51). The nurses most frequently educated their patients on such topics as "Daily weight monitoring" (5.82), "Signs/symptoms of worsening condition" (5.9) and "Fluid restriction" (5.92).

Conclusions

Polish nurses are not ready to perform comprehensive HF care tasks without preparation.

Hospitalization for acute heart failure: the in-hospital care pathway predicts one-year readmission

In patients with heart failure, some organizational and modifiable factors could be prognostic factors. We aimed to assess the association between the in-hospital care pathways during hospitalization for acute heart failure and the risk of readmission. This retrospective study included all elderly patients who were hospitalized for acute heart failure at the Universitary Hospital Lariboisière (Paris) during 2013. We collected the wards attended, length of stay, admission and discharge types, diagnostic procedures, and heart failure discharge treatment. The clinical factors were the specific medical conditions, left ventricular ejection fraction, type of heart failure syndrome, sex, smoking status, and age. Consistent groups of in-hospital care pathways were built using an ascending hierarchical clustering method based on a primary components analysis. The association between the groups and the risk of readmission at 1 month and 1 year (for heart failure or for any cause) were measured via a count data model that was adjusted for clinical factors. This study included 223 patients. Associations between the in-hospital care pathway and the 1 year-readmission status were studied in 207 patients. Five consistent groups were defined: 3 described expected in-hospital care pathways in intensive care units, cardiology and gerontology wards, 1 described deceased patients, and 1 described chaotic pathways. The chaotic pathway strongly increased the risk (p = 0.0054) of 1 year readmission for acute heart failure. The chaotic in-hospital care pathway, occurring in specialized wards, was associated with the risk of readmission. This could promote specific quality improvement actions in these wards. Follow-up research projects should aim to describe the processes causing the generation of chaotic pathways and their consequences.

Evaluating risk prediction models for adults with heart failure: A systematic literature review

Background

The ability to predict risk allows healthcare providers to propose which patients might benefit most from certain therapies, and is relevant to payers’ demands to justify clinical and economic value. To understand the robustness of risk prediction models for heart failure (HF), we conducted a systematic literature review to (1) identify HF risk-prediction models, (2) assess statistical approach and extent of validation, (3) identify common variables, and (4) assess risk of bias (ROB).

Methods

Literature databases were searched from March 2013 to May 2018 to identify risk prediction models conducted in an out-of-hospital setting in adults with HF. Distinct risk prediction variables were ranked according to outcomes assessed and incorporation into the studies. ROB was assessed using Prediction model Risk Of Bias ASsessment Tool (PROBAST).

Results

Of 4720 non-duplicated citations, 40 risk-prediction publications were deemed relevant. Within the 40 publications, 58 models assessed 55 (co)primary outcomes, including all-cause mortality (n = 17), cardiovascular death (n = 9), HF hospitalizations (n = 15), and composite endpoints (n = 14). Few publications reported detail on handling missing data (n = 11; 28%). The discriminatory ability for predicting all-cause mortality, cardiovascular death, and composite endpoints was generally better than for HF hospitalization. 105 distinct predictor variables were identified. Predictors included in >5 publications were: N-terminal prohormone brain-natriuretic peptide, creatinine, blood urea nitrogen, systolic blood pressure, sodium, NYHA class, left ventricular ejection fraction, heart rate, and characteristics including male sex, diabetes, age, and BMI. Only 11/58 (19%) models had overall low ROB, based on our application of PROBAST. In total, 26/58 (45%) models discussed internal validation, and 14/58 (24%) external validation.

Conclusions

The majority of the 58 identified risk-prediction models for HF present particular concerns according to ROB assessment, mainly due to lack of validation and calibration. The potential utility of novel approaches such as machine learning tools is yet to be determined.

Registration number

The SLR was registered in Prospero (ID: CRD42018100709).

Clinical and Socioeconomic Predictors of Heart Failure Readmissions: A Review of Contemporary Literature

Heart failure represents a clinical syndrome that results from a constellation of disease processes affecting myocardial function. Although recent studies have suggested a declining or stable incidence of heart failure, patients with heart failure continue to have high hospitalization and readmission rates, resulting in a substantial economic and public health burden. We searched PubMed and Google Scholar to identify published literature from 1998 through 2018 using the following keywords: heart failure, readmissions, predictors, prediction models, and interventions. Cited references were also used to identify relevant literature. Developments in the diagnosis and management of patients with heart failure have improved hospitalization and readmission rates in the past few decades. However, heart failure remains the most common cause of hospitalization in persons older than 65 years. As a result, given the enormous clinical and financial burden associated with heart failure readmissions on health care, there has been growing interest in the investigation of mechanisms aimed at improving outcomes and curtailing associated costs of care. Herein, we review the current literature on clinical and socioeconomic predictors of heart failure readmissions, briefly discussing limitations of existing strategies and providing an overview of current technology aimed at reducing hospitalizations.

Can We Do More With Less While Building Predictive Models? A Study in Parsimony of Risk Models for Predicting Heart Failure Readmissions

Hospital readmission due to heart failure is a topic of concern for patients and hospitals alike: it is both the most frequent and expensive diagnosis for hospitalization. Therefore, accurate prediction of readmission risk while patients are still in the hospital helps to guide appropriate postdischarge interventions. As our understanding of the disease and the volume of electronic health record data both increase, the number of predictors and model-building time for predicting risk grow rapidly. This suggests a need to use methods for reducing the number of predictors without losing predictive performance. We explored and described three such methods and demonstrated their use by applying them to a real-world dataset consisting of 57 variables from health data of 1210 patients from one hospital system. We compared all models generated from predictor reduction methods against the full, 57-predictor model for predicting risk of 30-day readmissions for patients with heart failure. Our predictive performance, measured by the C-statistic, ranged from 0.630 to 0.840, while model-building time ranged from 10 minutes to 10 hours. Our final model achieved a C-statistic (0.832) comparable to the full model (0.840) in the validation cohort while using only 16 predictors and providing a 66-fold improvement in model-building time.

Readmissions following hospitalisations for cardiovascular disease: a scoping review of the Australian literature

Objective International studies suggest high rates of readmissions after cardiovascular hospitalisations, but the burden in Australia is uncertain. We summarised the characteristics, frequency, risk factors of readmissions and interventions to reduce readmissions following cardiovascular hospitalisation in Australia. Methods A scoping review of the published literature from 2000-2016 was performed using Medline, EMBASE and Cumulative Index to Nursing and Allied Health Literature (CINAHL) databases and relevant grey literature. Results We identified 35 studies (25 observational, 10 reporting outcomes of interventions). Observational studies were typically single-centre (11/25) and reported readmissions following hospitalisations for heart failure (HF; 10/25), acute coronary syndrome (7/25) and stroke (6/25), with other conditions infrequently reported. The definition of a readmission was heterogeneous and was assessed using diverse methods. Readmission rate, most commonly reported at 1 month (14/25), varied from 6.3% to 27%, with readmission rates of 10.1-27% for HF, 6.5-11% for stroke and 12.7-17% for acute myocardial infarction, with a high degree of heterogeneity among studies. Of the 10 studies of interventions to reduce readmissions, most (n=8) evaluated HF management programs and three reported a significant reduction in readmissions. We identified a lack of national studies of readmissions and those assessing the cost and resource impact of readmissions on the healthcare system as well as a paucity of successful interventions to lower readmissions. Conclusions High rates of readmissions are reported for cardiovascular conditions, although substantial methodological heterogeneity exists among studies. Nationally standardised definitions are required to accurately measure readmissions and further studies are needed to address knowledge gaps and test interventions to lower readmissions in Australia. What is known about the topic? International studies suggest readmissions are common following cardiovascular hospitalisations and are costly to the health system, yet little is known about the burden of readmission in the Australian setting or the effectiveness of intervention to reduce readmissions. What does this paper add? We found relatively high rates of readmissions following common cardiovascular conditions although studies differed in their methodology making it difficult to accurately gauge the readmission rate. We also found several knowledge gaps including lack of national studies, studies assessing the impact on the health system and few interventions proven to reduce readmissions in the Australian setting. What are the implications for practitioners? Practitioners should be cautious when interpreting studies of readmissions due the heterogeneity in definitions and methods used in Australian literature. Further studies are needed to test interventions to reduce readmissions in the Australians setting.

Predictive models for hospital readmission risk: A systematic review of methods

OBJECTIVES

Hospital readmission risk prediction facilitates the identification of patients potentially at high risk so that resources can be used more efficiently in terms of cost-benefit. In this context, several models for readmission risk prediction have been proposed in recent years. The goal of this review is to give an overview of prediction models for hospital readmission, describe the data analysis methods and algorithms used for building the models, and synthesize their results.

METHODS

Studies that reported the predictive performance of a model for hospital readmission risk were included. We defined the scope of the review and accordingly built a search query to select the candidate papers. This query string was used as input for the chosen search engines, namely PubMed and Google Scholar. For each study, we recorded the population, feature selection method, classification algorithm, sample size, readmission threshold, readmission rate and predictive performance of the model.

RESULTS

We identified 77 studies that met the inclusion criteria, out of 265 citations. In 68% of the studies (n = 52) logistic regression or other regression techniques were utilized as the main method. Ten (13%) studies used survival analysis for model construction, while 14 (18%) used machine learning techniques for classification, of which decision tree-based methods and SVM were the most utilized algorithms. Among these, only four studies reported the use of any class imbalance addressing technique, of which resampling is the most frequent (75%). The performance of the models varied significantly among studies, with Area Under the ROC Curve (AUC) values in the ranges between 0.54 and 0.92.

CONCLUSION

Logistic regression and survival analysis have been traditionally the most widely used techniques for model building. Nevertheless, machine learning techniques are becoming increasingly popular in recent years. Recent comparative studies suggest that machine learning techniques can improve prediction ability over traditional statistical approaches. Regardless, the lack of an appropriate benchmark dataset of hospital readmissions makes a comparison of models' performance across different studies difficult.

Predictive models for identifying risk of readmission after index hospitalization for heart failure: A systematic review

Aims:

Readmission rates for patients with heart failure have consistently remained high over the past two decades. As more electronic data, computing power, and newer statistical techniques become available, data-driven care could be achieved by creating predictive models for adverse outcomes such as readmissions. We therefore aimed to review models for predicting risk of readmission for patients admitted for heart failure. We also aimed to analyze and possibly group the predictors used across the models.

Methods:

Major electronic databases were searched to identify studies that examined correlation between readmission for heart failure and risk factors using multivariate models. We rigorously followed the review process using PRISMA methodology and other established criteria for quality assessment of the studies.

Results:

We did a detailed review of 334 papers and found 25 multivariate predictive models built using data from either health system or trials. A majority of models was built using multiple logistic regression followed by Cox proportional hazards regression. Some newer studies ventured into non-parametric and machine learning methods. Overall predictive accuracy with C-statistics ranged from 0.59 to 0.84. We examined significant predictors across the studies using clinical, administrative, and psychosocial groups.

Conclusions:

Complex disease management and correspondingly increasing costs for heart failure are driving innovations in building risk prediction models for readmission. Large volumes of diverse electronic data and new statistical methods have improved the predictive power of the models over the past two decades. More work is needed for calibration, external validation, and deployment of such models for clinical use.

A comparative study of social capital and hospital readmission in older adults

Numerous factors contribute to hospital readmissions of older adults. The role social capital may play in preventing hospital readmissions is unknown. The aim of this descriptive, cross-sectional study was to determine if levels of personal social capital differ in two groups of patients aged 65 and older, those readmitted to the hospital within 30 days of discharge and those not readmitted. Participants in this study (N = 106) were community-dwelling older adults discharged from 11 hospitals in the Midwestern United States. The Personal Social Capital Scale and a demographic questionnaire were mailed to eligible participants for completion. Multivariate Analysis of Variance (MANOVA) was computed to examine the differences in the dependent variables of bonding and bridging social capital between those patients readmitted within 30 days and those not readmitted within 30 days. No significant differences between the two groups' mean levels of bonding or bridging social capital were identified.

Scalable and accurate deep learning with electronic health records

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient's record. We propose a representation of patients' entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two US academic medical centers with 216,221 adult patients hospitalized for at least 24 h. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting: in-hospital mortality (area under the receiver operator curve [AUROC] across sites 0.93-0.94), 30-day unplanned readmission (AUROC 0.75-0.76), prolonged length of stay (AUROC 0.85-0.86), and all of a patient's final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed traditional, clinically-used predictive models in all cases. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios. In a case study of a particular prediction, we demonstrate that neural networks can be used to identify relevant information from the patient's chart.

Predictors of Frequent Readmissions in Patients With Heart Failure

BACKGROUND

Patients with heart failure (HF) have a high incidence of hospital readmissions. However risk models that explore predictors of a single readmission may be less useful at identifying the patients with frequent readmissions who contribute to a disproportionately large proportion of morbidity and health care costs.

METHODS

A total of 6252 patients enrolled in the Management of Cardiac Failure Program (MACARF) in Northern Sydney Area Hospitals between 1998 and 2015 were randomly divided into derivation and validation cohorts to create and test a risk model for predictors of ≥2 readmissions or death within 1year of initial hospitalisation for HF.

RESULTS

Multivariate predictors of frequent (≥2) readmissions or death were a history of ischaemic heart disease and chronic kidney disease, being unmarried, having anaemia, low serum albumin, elevated creatinine, prolonged hospital stay (>7 days), and not receiving beta blockers on discharge. Event rates increased with a higher risk score (p<0.001) and the prediction was similar in the validation and derivation cohorts (p=0.588). The C-statistic was 0.65.

CONCLUSIONS

Our risk score may assist in focussing health care resources and interventions by identifying the subset of HF patients at increased risk for a disproportionately high burden of disease.

Risk factors for 30-day readmission in patients with congestive heart failure

BACKGROUND

Risk of readmission is elevated in patients congestive heart failure (CHF), and clinical decision makers need to better understand risk factors for 30-day readmissions.

OBJECTIVE

To identify risk factors for readmission in patients with CHF.

METHODS

We studied all admissions for patients with CHF during 2011 using a statewide discharge data set from Pennsylvania. The primary outcome was readmission to any Pennsylvania hospital within 30 days of discharge.

RESULTS

Of 155,146 CHF patients admitted, 35,294 (22.8%) were readmitted within 30 days. Male sex, black race, coverage by Medicare, comorbidities, discharge to a skilled nursing facility or with a home nurse, a longer length of stay (LOS), admission from another facility, and emergent admission (all p < 0.001) were significant risk factors.

CONCLUSIONS

Comorbidities, sociodemographic factors including male sex, age, black race and Medicare coverage, and prolonged length of stay are associated with increased risk of readmission in patients with CHF.

Association between opioid use and readmission following liver transplantation

The aim of this study was to assess the independent association between pre-transplant prescription opioid use and readmission following liver transplantation. We reviewed the medical records of all patients at a single medical center undergoing primary, single-organ, liver transplantation from 2004 to 2014. We assessed factors associated with hospital readmission 30 days and 1 year after hospital discharge using multivariable competing risk regression models. Among 1056 transplant recipients, 49 (4.6%) were prescribed pre-transplant prescription opioids. Readmission occurred in 421 (40%) patients within 30 days and 689 (65%) within 1 year. Patients with pre-transplant opioid use had a significantly higher risk of readmission at 30 days (HR 1.7; 95% CI 1.1-2.5) and a non-significantly elevated risk at 1 year (HR 1.4; 95% CI 1.0-1.9) when controlling for other potential confounders. Although pain was the major reason for readmission in only 12 (3%) patients at 30 days and 33 (6%) patients at 1 year, pre-transplant opioid use was significantly associated with pain-related readmission at both time points. In conclusion, prescription opioid use pre-transplantation was significantly associated with all-cause 30-day readmissions and pain-related readmissions at 30 days and 1 year.

Utility of models to predict 28-day or 30-day unplanned hospital readmissions: an updated systematic review

OBJECTIVE

To update previous systematic review of predictive models for 28-day or 30-day unplanned hospital readmissions.

DESIGN

Systematic review.

SETTING/DATA SOURCE

CINAHL, Embase, MEDLINE from 2011 to 2015.

PARTICIPANTS

All studies of 28-day and 30-day readmission predictive model.

OUTCOME MEASURES

Characteristics of the included studies, performance of the identified predictive models and key predictive variables included in the models.

RESULTS

Of 7310 records, a total of 60 studies with 73 unique predictive models met the inclusion criteria. The utilisation outcome of the models included all-cause readmissions, cardiovascular disease including pneumonia, medical conditions, surgical conditions and mental health condition-related readmissions. Overall, a wide-range C-statistic was reported in 56/60 studies (0.21-0.88). 11 of 13 predictive models for medical condition-related readmissions were found to have consistent moderate discrimination ability (C-statistic ≥0.7). Only two models were designed for the potentially preventable/avoidable readmissions and had C-statistic >0.8. The variables 'comorbidities', 'length of stay' and 'previous admissions' were frequently cited across 73 models. The variables 'laboratory tests' and 'medication' had more weight in the models for cardiovascular disease and medical condition-related readmissions.

CONCLUSIONS

The predictive models which focused on general medical condition-related unplanned hospital readmissions reported moderate discriminative ability. Two models for potentially preventable/avoidable readmissions showed high discriminative ability. This updated systematic review, however, found inconsistent performance across the included unique 73 risk predictive models. It is critical to define clearly the utilisation outcomes and the type of accessible data source before the selection of the predictive model. Rigorous validation of the predictive models with moderate-to-high discriminative ability is essential, especially for the two models for the potentially preventable/avoidable readmissions. Given the limited available evidence, the development of a predictive model specifically for paediatric 28-day all-cause, unplanned hospital readmissions is a high priority.