Comparison of machine learning and conventional statistical modeling for predicting readmission following acute heart failure hospitalization

INTRODUCTION

Developing accurate models for predicting the risk of 30-day readmission is a major healthcare interest. Evidence suggests that models developed using machine learning (ML) may have better discrimination than conventional statistical models (CSM), but the calibration of such models is unclear.

OBJECTIVES

To compare models developed using ML with those developed using CSM to predict 30-day readmission for cardiovascular and noncardiovascular causes in HF patients.

METHODS

We retrospectively enrolled 10,919 patients with HF (> 18 years) discharged alive from a hospital or emergency department (2004-2007) in Ontario, Canada. The study sample was randomly divided into training and validation sets in a 2:1 ratio. CSMs to predict 30-day readmission were developed using Fine-Gray subdistribution hazards regression (treating death as a competing risk), and the ML algorithm employed random survival forests for competing risks (RSF-CR). Models were evaluated in the validation set using both discrimination and calibration metrics.

RESULTS

In the validation sample of 3602 patients, RSF-CR (c-statistic=0.620) showed similar discrimination to the Fine-Gray competing risk model (c-statistic=0.621) for 30-day cardiovascular readmission. In contrast, for 30-day noncardiovascular readmission, the Fine-Gray model (c-statistic=0.641) slightly outperformed the RSF-CR model (c-statistic=0.632). For both outcomes, The Fine-Gray model displayed better calibration than RSF-CR using calibration plots of observed vs predicted risks across the deciles of predicted risk.

CONCLUSIONS

Fine-Gray models had similar discrimination but superior calibration to the RSF-CR model, highlighting the importance of reporting calibration metrics for ML-based prediction models. The discrimination was modest in all readmission prediction models regardless of the methods used.

Machine learning-based 30-day readmission prediction models for patients with heart failure: a systematic review

AIMS

Heart failure (HF) is one of the most frequent diagnoses for 30-day readmission after hospital discharge. Nurses have a role in reducing unplanned readmission and providing quality of care during HF trajectories. This systematic review assessed the quality and significant factors of machine learning (ML)-based 30-day HF readmission prediction models.

METHODS AND RESULTS

Eight academic and electronic databases were searched to identify all relevant articles published between 2013 and 2023. Thirteen studies met our inclusion criteria. The sample sizes of the selected studies ranged from 1778 to 272 778 patients, and the patients' average age ranged from 70 to 81 years. Quality appraisal was performed.

CONCLUSION

The most commonly used ML approaches were random forest and extreme gradient boosting. The 30-day HF readmission rates ranged from 1.2 to 39.4%. The area under the receiver operating characteristic curve for models predicting 30-day HF readmission was between 0.51 and 0.93. Significant predictors included 60 variables with 9 categories (socio-demographics, vital signs, medical history, therapy, echocardiographic findings, prescribed medications, laboratory results, comorbidities, and hospital performance index). Future studies using ML algorithms should evaluate the predictive quality of the factors associated with 30-day HF readmission presented in this review, considering different healthcare systems and types of HF. More prospective cohort studies by combining structured and unstructured data are required to improve the quality of ML-based prediction model, which may help nurses and other healthcare professionals assess early and accurate 30-day HF readmission predictions and plan individualized care after hospital discharge.

REGISTRATION

PROSPERO: CRD 42023455584.

Effect of health literacy on hospital readmission among patients with heart failure: A protocol for systematic review and meta-analysis

BACKGROUND

Patients with heart failure have a high rate of health literacy deficiency, and their hospital readmission is a great burden. Whether health literacy affects hospital readmission remains controversial.

OBJECTIVE

To investigate the impact of health literacy on hospital readmission among heart failure patients.

METHOD

Relevant keywords were used to search for Chinese and English literature from Web of Science, PubMed, Cochrane Library, China National Knowledge Infrastructure, VIP Database for Chinese Technical Periodicals, Digital Journal of Wanfang Data, and Chinese BioMedical Literature Database. Newcastle-Ottawa Scale was used to assess the quality of the studies. Statistical analysis was performed using Stata 15.0, the fixed effect model was used to calculate the pooled effect estimate, and Begg's and Egger's tests were applied to assess the presence of publication bias.

RESULTS

Nine studies, involving 4093 heart failure patients, were included in this study. The overall rate of inadequate health literacy was 40.3%. Among these articles, 6 were included in the meta-analysis to calculate the pooled effect. The results indicated that, when compared with patients with adequate health literacy, those with inadequate health literacy had a relative risk of hospital readmission of 1.01, which increased to 1.14 after adjusting for follow-up time, the result was not significant (P = .09).

CONCLUSIONS

About 2 out of 5 heart failure patients had inadequate health literacy, and there was no statistical association between health literacy and hospital readmission among these patients. This finding should be carefully considered and confirmed in further studies.

Deep learning for predicting rehospitalization in acute heart failure: Model foundation and external validation

AIMS

Assessing the risk for HF rehospitalization is important for managing and treating patients with HF. To address this need, various risk prediction models have been developed. However, none of them used deep learning methods with real-world data. This study aimed to develop a deep learning-based prediction model for HF rehospitalization within 30, 90, and 365 days after acute HF (AHF) discharge.

METHODS AND RESULTS

We analysed the data of patients admitted due to AHF between January 2014 and January 2019 in a tertiary hospital. In performing deep learning-based predictive algorithms for HF rehospitalization, we use hyperbolic tangent activation layers followed by recurrent layers with gated recurrent units. To assess the readmission prediction, we used the AUC, precision, recall, specificity, and F1 measure. We applied the Shapley value to identify which features contributed to HF readmission. Twenty-two prognostic features exhibiting statistically significant associations with HF rehospitalization were identified, consisting of 6 time-independent and 16 time-dependent features. The AUC value shows moderate discrimination for predicting readmission within 30, 90, and 365 days of follow-up (FU) (AUC:0.63, 0.74, and 0.76, respectively). The features during the FU have a relatively higher contribution to HF rehospitalization than features from other time points.

CONCLUSIONS

Our deep learning-based model using real-world data could provide valid predictions of HF rehospitalization in 1 year follow-up. It can be easily utilized to guide appropriate interventions or care strategies for patients with HF. The closed monitoring and blood test in daily clinics are important for assessing the risk of HF rehospitalization.

Prognostic models for patients suffering a heart failure with a preserved ejection fraction: a systematic review

The purpose of this study was to systematically review the development, performance, and applicability of prognostic models developed for predicting poor events in patients with heart failure with preserved ejection fraction (HFpEF). Databases including Embase, PubMed, Web of Science Core Collection, the Cochrane Library, China National Knowledge Infrastructure, Wan Fang, Wei Pu, and China Biological Medicine were queried from their respective dates of inception to 1 June 2023, to examine multivariate models for prognostic prediction in HFpEF. Both forward and backward citations of all studies were included in our analysis. Two researchers individually used the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) checklist to extract data and assess the quality of the models using the Predictive Mode Bias Risk Assessment Tool (PROBAST). Among the 6897 studies screened, 16 studies derived and/or validated a total of 39 prognostic models. The sample size ranges for model development, internal validation, and external validation are 119 to 5988, 152 to 1000, and 30 to 5957, respectively. The most frequently employed modelling technique was Cox proportional hazards regression. Six studies (37.50%) conducted internal validation of models; bootstrap and k-fold cross-validation were the commonly used methods for internal validation of models. Ten of these models (25.64%) were validated externally, with reported the c-statistic in the external validation set ranging from 0.70 to 0.96, while the remaining models await external validation. The MEDIA echo score and I-PRESERVE-sudden cardiac death prediction mode have been externally validated using multiple cohorts, and the results consistently show good predictive performance. The most frequently used predictors identified among the models were age, n-terminal pro-brain natriuretic peptide, ejection fraction, albumin, and hospital stay in the last 5 months owing to heart failure. All study predictor domains and outcome domains were at low risk of bias, high or unclear risk of bias of all prognostic models due to underreporting in the area of analysis. All studies did not evaluate the clinical utility of the prognostic models. Predictive models for predicting prognostic outcomes in patients with HFpEF showed good discriminatory ability but their utility and generalization remain uncertain due to the risk of bias, differences in predictors between models, and the lack of clinical application studies. Future studies should improve the methodological quality of model development and conduct external validation of models.

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.

Scoping Meta-Review of Methods Used to Assess Artificial Intelligence-Based Medical Devices for Heart Failure

Artificial intelligence and machine learning (AI/ML) are playing increasingly important roles, permeating the field of medical devices (MDs). This rapid progress has not yet been matched by the Health Technology Assessment (HTA) process, which still needs to define a common methodology for assessing AI/ML-based MDs. To collect existing evidence from the literature about the methods used to assess AI-based MDs, with a specific focus on those used for the management of heart failure (HF), the International Federation of Medical and Biological Engineering (IFMBE) conducted a scoping meta-review. This manuscript presents the results of this search, which covered the period from January 1974 to October 2022. After careful independent screening, 21 reviews, mainly conducted in North America and Europe, were retained and included. Among the findings were that deep learning is the most commonly utilised method and that electronic health records and registries are among the most prevalent sources of data for AI/ML algorithms. Out of the 21 included reviews, 19 focused on risk prediction and/or the early diagnosis of HF. Furthermore, 10 reviews provided evidence of the impact on the incidence/progression of HF, and 13 on the length of stay. From an HTA perspective, the main areas requiring improvement are the quality assessment of studies on AI/ML (included in 11 out of 21 reviews) and their data sources, as well as the definition of the criteria used to assess the selection of the most appropriate AI/ML algorithm.

Why do we evaluate 30-day readmissions in general medicine? A historical perspective and contemporary data

Reducing preventable readmissions is important to help manage current strains on healthcare systems. The metric of 30-day readmissions is commonly cited in discussions regarding this topic. While such thresholds have contemporary funding implications, the rationale for individual cut-off points is partially historical in nature. Through the examination of the basis for the analysis of 30-day readmissions, greater insight into the possible benefits and limitations of such a metric may be obtained.

Predicting Hospital Readmissions in a Commercially Insured Population over Varying Time Horizons

BACKGROUND

Reducing hospital readmissions is a federal policy priority, and predictive models of hospital readmissions have proliferated in recent years; however, most such models tend to focus on the 30-day readmission time horizon and do not consider readmission over shorter (or longer) windows.

OBJECTIVES

To evaluate the performance of a predictive model of hospital readmissions over three different readmission timeframes in a commercially insured population.

DESIGN

Retrospective multivariate logistic regression with an 80/20 train/test split.

PARTICIPANTS

A total of 2,213,832 commercially insured inpatient admissions from 2016 to 2017 comprising 782,768 unique patients from the Health Care Cost Institute.

MAIN MEASURES

Outcomes are readmission within 14 days, 15-30 days, and 31-60 days from discharge. Predictor variables span six different domains: index admission, condition history, demographic, utilization history, pharmacy, and environmental controls.

KEY RESULTS

Our model generates C-statistics for holdout samples ranging from 0.618 to 0.915. The model's discriminative power declines with readmission time horizon: discrimination for readmission predictions within 14 days following discharge is higher than for readmissions 15-30 days following discharge, which in turn is higher than predictions 31-60 days following discharge. Additionally, the model's predictive power increases nonlinearly with the inclusion of successive risk factor domains: patient-level measures of utilization and condition history add substantially to the discriminative power of the model, while demographic information, pharmacy utilization, and environmental risk factors add relatively little.

CONCLUSION

It is more difficult to predict distant readmissions than proximal readmissions, and the more information the model uses, the better the predictions. Inclusion of utilization-based risk factors add substantially to the discriminative ability of the model, much more than any other included risk factor domain. Our best-performing models perform well relative to other published readmission prediction models. It is possible that these predictions could have operational utility in targeting readmission prevention interventions among high-risk individuals.

Comparison of Machine Learning Algorithms for Predicting Hospital Readmissions and Worsening Heart Failure Events in Patients With Heart Failure With Reduced Ejection Fraction: Modeling Study

BACKGROUND

Heart failure (HF) is highly prevalent in the United States. Approximately one-third to one-half of HF cases are categorized as HF with reduced ejection fraction (HFrEF). Patients with HFrEF are at risk of worsening HF, have a high risk of adverse outcomes, and experience higher health care use and costs. Therefore, it is crucial to identify patients with HFrEF who are at high risk of subsequent events after HF hospitalization.

OBJECTIVE

Machine learning (ML) has been used to predict HF-related outcomes. The objective of this study was to compare different ML prediction models and feature construction methods to predict 30-, 90-, and 365-day hospital readmissions and worsening HF events (WHFEs).

METHODS

We used the Veradigm PINNACLE outpatient registry linked to Symphony Health's Integrated Dataverse data from July 1, 2013, to September 30, 2017. Adults with a confirmed diagnosis of HFrEF and HF-related hospitalization were included. WHFEs were defined as HF-related hospitalizations or outpatient intravenous diuretic use within 1 year of the first HF hospitalization. We used different approaches to construct ML features from clinical codes, including frequencies of clinical classification software (CCS) categories, Bidirectional Encoder Representations From Transformers (BERT) trained with CCS sequences (BERT + CCS), BERT trained on raw clinical codes (BERT + raw), and prespecified features based on clinical knowledge. A multilayer perceptron neural network, extreme gradient boosting (XGBoost), random forest, and logistic regression prediction models were applied and compared.

RESULTS

A total of 30,687 adult patients with HFrEF were included in the analysis; 11.41% (3184/27,917) of adults experienced a hospital readmission within 30 days of their first HF hospitalization, and nearly half (9231/21,562, 42.81%) of the patients experienced at least 1 WHFE within 1 year after HF hospitalization. The prediction models and feature combinations with the best area under the receiver operating characteristic curve (AUC) for each outcome were XGBoost with CCS frequency (AUC=0.595) for 30-day readmission, random forest with CCS frequency (AUC=0.630) for 90-day readmission, XGBoost with CCS frequency (AUC=0.649) for 365-day readmission, and XGBoost with CCS frequency (AUC=0.640) for WHFEs. Our ML models could discriminate between readmission and WHFE among patients with HFrEF. Our model performance was mediocre, especially for the 30-day readmission events, most likely owing to limitations of the data, including an imbalance between positive and negative cases and high missing rates of many clinical variables and outcome definitions.

CONCLUSIONS

We predicted readmissions and WHFEs after HF hospitalizations in patients with HFrEF. Features identified by data-driven approaches may be comparable with those identified by clinical domain knowledge. Future work may be warranted to validate and improve the models using more longitudinal electronic health records that are complete, are comprehensive, and have a longer follow-up time.

Artificial Intelligence Applications in Clinical Chemistry

Artificial intelligence (AI) applications are an area of active investigation in clinical chemistry. Numerous publications have demonstrated the promise of AI across all phases of testing including preanalytic, analytic, and postanalytic phases; this includes novel methods for detecting common specimen collection errors, predicting laboratory results and diagnoses, and enhancing autoverification workflows. Although AI applications pose several ethical and operational challenges, these technologies are expected to transform the practice of the clinical chemistry laboratory in the near future.

Driven by need, shaped by access: Heterogeneity in patient profiles and patterns of service utilization in patients with alcohol use disorders

BACKGROUND

Patients with alcohol-use disorders (AUDs) are highly heterogenous and account for an increasing proportion of general medical hospital visits. However, many patients with AUDs do not present with severe medical or psychiatric needs requiring immediate attention. There may be a mismatch between some patients' needs and the available services, potentially driving re-admissions and re-encounters. The current study aims to identify subgroups of AUD patients and predict differences in patterns of healthcare service use (HSU) over time.

METHODS

Latent class analysis (LCA) was conducted using hospital data incorporating sociodemographic, health behavior, clinical, and service use variables to identify subtypes of AUD patients, then class membership was used to predict patterns of HSU.

RESULTS

Four classes were identified with the following characteristics: (1) Patients with acute medical injuries (30 %); (2) Patients with socioeconomic and psychiatric risk factors, (11 %); (3) Patients with chronic AUD with primarily non-psychiatric medical needs (18 %); and (4) Patients with primary AUDs with low medical-treatment complexity (40 %). Negative binomial models showed that Class 4 patients accounted for the highest frequency of service use, including significantly higher rates of emergency department reencounters at 30 days and 12 months.

CONCLUSIONS

The profile and patterns of HSU exhibited by patients in class 4 suggest that these patients have needs which are not currently being addressed in the emergency department. These have implications for how resources are allocated to meet the needs of patients with AUDs, including those who make frequent visits to the emergency department without high acuity medical needs.

Predictors of early heart failure rehospitalization among older adults with preserved and reduced ejection fraction: A review and derivation of a conceptual model

BACKGROUND

Heart failure (HF) is prevalent among older adults who suffer with either heart failure preserved ejection fraction (HFpEF) or heart failure reduced ejection fraction (HFrEF) and have a high rate of early HF rehospitalization. Preventing early rehospitalization is complex because of major differences between the two subtypes of HF as well as inadequate predictive models to identify key contributing factors.

OBJECTIVE

To present research addressing relationships between selected clinical, hemodynamic, social factors, and early (≤ 60-day) HF rehospitalization in older adults with HFpEF and HFrEF, derive a conceptual model of predictors of rehospitalization, and understand to what extent the literature addresses these predictors among older women.

METHODS

Four computerized databases were searched for research addressing clinical, hemodynamic, and social factors relevant to early HF rehospitalization and older adults post index hospitalization for HF.

RESULTS

21 full-text articles were included in the final review and organized thematically. Most studies focused on early (≤ 30-day) HF rehospitalizations, with limited attention given to the 31 to 60-day period. Specific clinical, hemodynamic, and social factors which influenced early HF rehospitalization were identified. The existing literature confirms that risk predictors or their combinations which influence early (≤ 60-day) HF rehospitalization after an index HF hospitalization remains inconsistent. Further, the literature fails to capture the influence of these predictors solely among older women. A conceptual model of risk predictors is proposed for clinical intervention.

CONCLUSION

Further evaluation to understand risk predictors of early (31 to 60-day) HF rehospitalizations among older women is needed.

Integration of patient experience factors improves readmission prediction

Many readmission prediction models have marginal accuracy and are based on clinical and demographic data that exclude patient response data. The objective of this study was to evaluate the accuracy of a 30-day hospital readmission prediction model that incorporates patient response data capturing the patient experience. This was a prospective cohort study of 30-day hospital readmissions. A logistic regression model to predict readmission risk was created using patient responses obtained during interviewer-administered questionnaires as well as demographic and clinical data. Participants (N = 846) were admitted to 2 inpatient adult medicine units at Massachusetts General Hospital from 2012 to 2016. The primary outcome was the accuracy (measured by receiver operating characteristic) of a 30-day readmission risk prediction model. Secondary analyses included a readmission-focused factor analysis of individual versus collective patient experience questions. Of 1754 eligible participants, 846 (48%) were enrolled and 201 (23.8%) had a 30-day readmission. Demographic factors had an accuracy of 0.56 (confidence interval [CI], 0.50-0.62), clinical disease factors had an accuracy of 0.59 (CI, 0.54-0.65), and the patient experience factors had an accuracy of 0.60 (CI, 0.56-0.64). Taken together, their combined accuracy of receiver operating characteristic = 0.78 (CI, 0.74-0.82) was significantly more accurate than these factors were individually. The individual accuracy of patient experience, demographic, and clinical data was relatively poor and consistent with other risk prediction models. The combination of the 3 types of data significantly improved the ability to predict 30-day readmissions. This study suggests that more accurate 30-day readmission risk prediction models can be generated by including information about the patient experience.

Factors related to early readmissions after acute heart failure: a nested case-control study

AIMS

To describe the main characteristics of patients who were readmitted to hospital within 1 month after an index episode for acute decompensated heart failure (ADHF).

METHODS AND RESULTS

This is a nested case-control study in the ReIC cohort, cases being consecutive patients readmitted after hospitalization for an episode of ADHF and matched controls selected from those who were not readmitted. We collected clinical data and also patient-reported outcome measures, including dyspnea, Minnesota Living with Heart Failure Questionnaire (MLHFQ), Tilburg Frailty Indicator (TFI) and Hospital Anxiety and Depression Scale scores, as well as symptoms during a transition period of 1 month after discharge. We created a multivariable conditional logistic regression model. Despite cases consulted more than controls, there were no statistically significant differences in changes in treatment during this first month. Patients with chronic decompensated heart failure were 2.25 [1.25, 4.05] more likely to be readmitted than de novo patients. Previous diagnosis of arrhythmia and time since diagnosis ≥ 3 years, worsening in dyspnea, and changes in MLWHF and TFI scores were significant in the final model.

CONCLUSION

We present a model with explanatory variables for readmission in the short term for ADHF. Our study shows that in addition to variables classically related to readmission, there are others related to the presence of residual congestion, quality of life and frailty that are determining factors for readmission for heart failure in the first month after discharge.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT03300791. First registration: 03/10/2017.

Validation of the Meta-Analysis Global Group in Chronic Heart Failure risk score for the prediction of 1-year mortality in a Chinese cohort

BACKGROUND

The Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC) risk score was developed in 2013 to predict survival in heart failure (HF) patients. However, it has yet to be validated in a Chinese population. Our study aimed to investigate the ability of the score to predict 1-year mortality in a Chinese population.

METHODS

Consecutive patients with HF were retrospectively selected from the inpatient electronic medical records of the cardiology department in a regional hospital in China. A total integer score was calculated for each enrolled patient based on the value of each risk factor in the MAGGIC scoring system. Each enrolled patient was followed for at least 1 year. The observational endpoint of this study was all-cause mortality. The predictive ability of the MAGGIC score was assessed by comparing observed and predicted mortality within 1 year.

RESULTS

Between January 2018 and December 2020, a total of 635 patients were included in the study: 57 (9.0%) of whom died within 1 year after discharge. The average age of all patients was 74.6 ± 11.2 years, 264 of them (41.6%) were male, and the average left ventricular ejection fraction was 50.7% ± 13.2%. The area under the receiver operating characteristic curve was 0.840 (95% confidence interval: 0.779, 0.901), which indicated a fair discriminatory ability of the score. The Hosmer-Lemeshow test result ( χ2  = 12.902, degree of freedom = 8, P   =  0.115) indicated that the MAGGIC score had good calibration. The decision curve analysis showed that the MAGGIC score yielded a good clinical net benefit and net reduction in interventions.

CONCLUSIONS

This validation of the MAGGIC score showed that it has a good ability to predict 1-year mortality in Chinese patients with HF after discharge. Due to regional and inter-hospital differences, external validation studies need to be further confirmed in other centers.

Implementing predictive tools in surgery: A narrative review in the context of orthopaedic surgery

Clinical predictive tools are a topic gaining interest. Many tools are developed each year to predict various outcomes in medicine and surgery. However, the proportion of predictive tools that are implemented in clinical practice is small in comparison to the total number of tools developed. This narrative review presents key principles to guide the translation of predictive tools from academic bodies of work into useful tools that complement clinical practice. Our review identified the following principles: (1) identifying a clinical gap, (2) selecting a target user or population, (3) optimizing predictive tool performance, (4) externally validating predictive tools, (5) marketing and disseminating the tool, (6) navigating the challenges of integrating a tool into existing healthcare systems, and (7) developing an ongoing monitoring and evaluation strategy. Although the review focuses on examples in orthopaedic surgery, the principles can be applied to other disciplines in medicine and surgery.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

BACKGROUND

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

METHODS

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

RESULTS

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

CONCLUSION

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Systematic review and meta-analysis of prognostic models in Southeast Asian populations with acute myocardial infarction

Background

The cultural and genetic diversity of the Southeast Asian population has contributed to distinct cardiovascular disease risks, incidence, and prognosis compared to the Western population, thereby raising concerns about the accuracy of predicted risks of existing prognostic models.

Objectives

We aimed to evaluate the predictive performances of validated, recalibrated, and developed prognostic risk prediction tools used in the Southeast Asian population with acute myocardial infarction (AMI) events for secondary events

Methods

We searched MEDLINE and Cochrane Central databases until March 2022. We included prospective and retrospective cohort studies that exclusively evaluated populations in the Southeast Asian region with a confirmed diagnosis of an AMI event and evaluated for risk of secondary events such as mortality, recurrent AMI, and heart failure admission. The CHARMS and PRISMA checklists and PROBAST for risk of bias assessment were used in this review.

Results

We included 7 studies with 11 external validations, 3 recalibrations, and 3 new models from 4 countries. Both short- and long-term outcomes were assessed. Overall, we observed that the external validation studies provided a good predictive accuracy of the models in the respective populations. The pooled estimate of the C-statistic in the Southeast Asian population for GRACE risk score is 0.83 (95%CI 0.72–0.90, n = 6 validations) and for the TIMI risk score is 0.80 (95%CI: 0.772–0.83, n = 5 validations). Recalibrated and new models demonstrated marginal improvements in discriminative values. However, the method of predictive accuracy measurement in most studies was insufficient thereby contributing to the mixed accuracy effect. The evidence synthesis was limited due to the relatively low quality and heterogeneity of the available studies.

Conclusion

Both TIMI and GRACE risk scores demonstrated good predictive accuracies in the population. However, with the limited strength of evidence, these results should be interpreted with caution. Future higher-quality studies spanning various parts of the Asian region will help to understand the prognostic utility of these models better.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?%20RecordID=228486.

Prognostic value of patient-reported outcomes in predicting 30 day all-cause readmission among older patients with heart failure

AIMS

Previous prediction studies for 30 day readmission in patients with heart failure were built mainly based on electronic medical records and rarely involved patient-reported outcomes. This study aims to develop and validate a nomogram including patient-reported outcomes to predict the possibility of 30 day all-cause readmission in older patients with heart failure and to explore the value of patient-reported outcomes in prediction model.

METHODS AND RESULTS

This was a prospective cohort study. The nomogram was developed and internally validated by Logistic regression analysis based on 381 patients in training group from March to December 2019. The nomogram was externally validated based on 170 patients from July to October 2020. Receiver operating characteristic curves, calibration plots and decision-curve analysis were used to evaluate the performance of the nomogram. A total of 381 patients' complete data were analysed in the training group and 170 patients were enrolled in the external validation group. In the training group, 14.4% (n = 55) patients were readmitted to hospitals within 30 days of discharge and 15.9% (n = 27) patients were readmitted in the external validation group. The nomogram included six factors: history of surgery, changing the type of medicine by oneself, information acquisition ability, subjective support, depression level, quality of life, all of which were significantly associated with 30 day readmission in older patients with heart failure. The areas under the receiver operating characteristic curves of nomogram were 0.949 (95% CI: 0.925, 0.973, sensitivity: 0.873, specificity: 0.883) and 0.804 (95% CI: 0.691, 0.917, sensitivity: 0.778, specificity: 0.832) respectively in the training and external validation groups, which indicated that the nomogram had better discrimination ability. The calibration plots demonstrated favourable coordination between predictive probability of 30 day readmission and observed probability. Decision-curve analysis showed that the net benefit of the nomogram was better between threshold probabilities of 0-85%.

CONCLUSIONS

A novel and easy-to-use nomogram is constructed and demonstrated which emphasizes the important role of patient-reported outcomes in predicting studies. The performance of the nomogram drops in the external validation cohort and the nomogram must be validated in a wide prospective cohort of HF patients before its clinical relevance can be demonstrated. All these findings in this study can assist professionals in identifying the needs of HF patients so as to reduce 30 day readmission.

Predictive Model for Heart Failure Readmission Using Nationwide Readmissions Database

Objective

To generate a heart failure (HF) readmission prediction model using the Nationwide Readmissions Database to guide management and reduce HF readmissions.

Patients and Methods

A retrospective analysis was performed for patients listed for HF admissions in the Nationwide Readmissions Database from January 1, 2010, to December 31, 2014. A Cox proportional hazards model for sample survey data for the prediction of readmission for all patients with HF was implemented using a derivation cohort (2010-2012). We generated receiver operating characteristic (ROC) curves and estimated area under the ROC curve at each time point (30, 60, 90, and 180 days) to assess the accuracy of our predictive model using the derivation cohort (2010-2012) and compared it with the validation cohort (2013-2014). A risk score was computed for the validation cohort. On the basis of the total risk score, we calculated the probability of readmission at 30, 60, 90, and 180 days.

Results

Approximately 1,420,564 patients were admitted for HF, contributing to 1,817,735 total HF admissions. Of these, 665,867 patients had at least 1 readmission for HF. The 10 most common comorbidities for readmitted patients included hypertension, diabetes mellitus, renal failure, chronic pulmonary disease, deficiency anemia, fluid and electrolyte disorders, obesity, hypothyroidism, peripheral vascular disorders, and depression. The area under the ROC curve for the prediction model was 0.58 in the derivation cohort and 0.59 in the validation cohort.

Conclusion

The prediction model will find clinical utility at point of care in optimizing the management of patients with HF and reducing HF readmissions.

Predicting 31- to 60-Day Heart Failure Rehospitalization Among Older Women

The current study sought to identify social, hemodynamic, and comorbid risk factors associated with 31-to 60-day heart failure (HF) rehospitalization in African American and Caucasian older (aged >65 years) women. A non-equivalent, case-control, quantitative design study using secondary data analysis of medical records from a local community hospital in the Southeast region of the United States was performed over a 3-year period. Relationships between predictor variables and the outcome variable, 31- to 60-day HF rehospitalization, were explored. The full model containing all predictors was not able to distinguish between predictors (χ²[21, N = 188] = 35.77, p = 0.12). However, a condensed model showed that body mass index (BMI) level 1 (<25 kg/m²), BMI level 2 (>25 and <30 kg/m²), age 75 to 80 years, and those taking lipid-lowering agents were significant predictors. Subtype of HF (reduced or preserved) and race did not predict HF rehospitalization within the specified time period. Multiple comorbid risk factors failed to consistently predict rehospitalization, which may reflect dated HF-specific approaches and therapies. Future studies should evaluate contributions of current targeted post-discharge methods or therapies. [Research in Gerontological Nursing, xx(x), xx-xx.].

What can machines learn about heart failure? A systematic literature review

This paper presents a systematic literature review with respect to application of data science and machine learning (ML) to heart failure (HF) datasets with the intention of generating both a synthesis of relevant findings and a critical evaluation of approaches, applicability and accuracy in order to inform future work within this field. This paper has a particular intention to consider ways in which the low uptake of ML techniques within clinical practice could be resolved. Literature searches were performed on Scopus (2014-2021), ProQuest and Ovid MEDLINE databases (2014-2021). Search terms included ‘heart failure’ or ‘cardiomyopathy’ and ‘machine learning’, ‘data analytics’, ‘data mining’ or ‘data science’. 81 out of 1688 articles were included in the review. The majority of studies were retrospective cohort studies. The median size of the patient cohort across all studies was 1944 (min 46, max 93260). The largest patient samples were used in readmission prediction models with the median sample size of 5676 (min. 380, max. 93260). Machine learning methods focused on common HF problems: detection of HF from available dataset, prediction of hospital readmission following index hospitalization, mortality prediction, classification and clustering of HF cohorts into subgroups with distinctive features and response to HF treatment. The most common ML methods used were logistic regression, decision trees, random forest and support vector machines. Information on validation of models was scarce. Based on the authors’ affiliations, there was a median 3:1 ratio between IT specialists and clinicians. Over half of studies were co-authored by a collaboration of medical and IT specialists. Approximately 25% of papers were authored solely by IT specialists who did not seek clinical input in data interpretation. The application of ML to datasets, in particular clustering methods, enabled the development of classification models assisting in testing the outcomes of patients with HF. There is, however, a tendency to over-claim the potential usefulness of ML models for clinical practice. The next body of work that is required for this research discipline is the design of randomised controlled trials (RCTs) with the use of ML in an intervention arm in order to prospectively validate these algorithms for real-world clinical utility.

Abnormal Coagulation as a Risk Factor for Postoperative Complications After Primary and Revision Total Hip and Total Knee Arthroplasty

BACKGROUND

Patients undergoing total joint arthroplasty (TJA) have an increased likelihood of having an abnormal coagulation profile compared with the general population. Coagulation abnormalities are often screened for before surgery and considered during perioperative planning. This study assesses a preoperative abnormal coagulation profile as a risk factor for postoperative complications after total hip arthroplasty (THA), revision THA (rTHA), total knee arthroplasty (TKA), and revision TKA (rTKA) and then examines specific coagulopathies to determine their influence on complication rates.

METHODS

Patients who underwent THA, rTHA, TKA, or rTKA from 2011 to 2017 were identified in the American College of Surgeons National Surgical Quality Improvement Program database and then assessed for preoperative abnormal coagulation profiles. Various postoperative complications were analyzed for each cohort, and two separate multivariate regression analyses were used to assess the relationship between abnormal coagulation and postoperative complications.

RESULTS

403,566 THA, rTHA, TKA, or rTKA cases were identified, and 40,466 (10.0%) of patients were found to have an abnormal coagulation profile. Patients with preoperative coagulation abnormalities had higher likelihoods of postoperative complications after primary TJA than in revision TJA. An international normalized ratio>1.2 was associated with the most types of postoperative complications, followed by a bleeding disorder diagnosis. A partial thromboplastin time>35 seconds was associated with only one type of postoperative complication, while a platelet count <150,000 per μL was associated with postoperative complications only after TKA.

CONCLUSION

TJA in patients with abnormal coagulation profiles may result in adverse outcomes. These patients may benefit from preoperative intervention. Prophylactic care needs to be personalized to the specific coagulation abnormalities present.

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.

Current Trends in Readmission Prediction: An Overview of Approaches

Hospital readmission shortly after discharge threatens the quality of patient care and leads to increased medical care costs. In the United States, hospitals with high readmission rates are subject to federal financial penalties. This concern calls for incentives for healthcare facilities to reduce their readmission rates by predicting patients who are at high risk of readmission. Conventional practices involve the use of rule-based assessment scores and traditional statistical methods, such as logistic regression, in developing risk prediction models. The recent advancements in machine learning driven by improved computing power and sophisticated algorithms have the potential to produce highly accurate predictions. However, the value of such models could be overrated. Meanwhile, the use of other flexible models that leverage simple algorithms offer great transparency in terms of feature interpretation, which is beneficial in clinical settings. This work presents an overview of the current trends in risk prediction models developed in the field of readmission. The various techniques adopted by researchers in recent years are described, and the topic of whether complex models outperform simple ones in readmission risk stratification is investigated.

Using Deep Learning to Identify High-Risk Patients with Heart Failure with Reduced Ejection Fraction

Background: Deep Learning (DL) has not been well-established as a method to identify high-risk patients among patients with heart failure (HF). Objectives: This study aimed to use DL models to predict hospitalizations, worsening HF events, and 30-day and 90-day readmissions in patients with heart failure with reduced ejection fraction (HFrEF). Methods: We analyzed the data of adult HFrEF patients from the IBM® MarketScan® Commercial and Medicare Supplement databases between January 1, 2015 and December 31, 2017. A sequential model architecture based on bi-directional long short-term memory (Bi-LSTM) layers was utilized. For DL models to predict HF hospitalizations and worsening HF events, we utilized two study designs: with and without a buffer window. For comparison, we also tested multiple traditional machine learning models including logistic regression, random forest, and eXtreme Gradient Boosting (XGBoost). Model performance was assessed by area under the curve (AUC) values, precision, and recall on an independent testing dataset. Results: A total of 47 498 HFrEF patients were included; 9427 with at least one HF hospitalization. The best AUCs of DL models without a buffer window in predicting HF hospitalizations and worsening HF events in the total patient cohort were 0.977 and 0.972; with a 7-day buffer window the best AUCs were 0.573 and 0.608, respectively. The best AUCs in predicting 30- and 90-day readmissions in all adult patients were 0.597 and 0.614, respectively. An AUC of 0.861 was attained for prediction of 90-day readmission in patients aged 18-64. For all outcomes assessed, the DL approach outperformed traditional machine learning models. Discussion: The DL approach can automate feature engineering during the model learning, which can increase the clinical applicability and lead to comparable or better model performance. However, the lack of granular clinical data, and sample size and imbalance issues may have limited the model's performance. Conclusions: A DL approach using Bi-LSTM was shown to be a feasible and useful tool to predict HF-related outcomes. This study can help inform the future development and deployment of predictive tools to identify high-risk HFrEF patients and ultimately facilitate targeted interventions in clinical practice.

Development and validation of the Tool for Pharmacists to Predict 30-day hospital readmission in patients with Heart Failure (ToPP-HF)

PURPOSE

Pharmacists are well positioned to provide transitions of care (TOC) services to patients with heart failure (HF); however, hospitalizations for patients with HF likely exceed the capacity of a TOC pharmacist. We developed and validated a tool to help pharmacists efficiently identify high-risk patients with HF and maximize their potential impact by intervening on patients at the highest risk for 30-day all-cause readmission.

METHODS

We conducted a retrospective cohort study including adults with HF admitted to a health system between October 1, 2016, and October 31, 2019. We randomly divided the cohort into development (n = 2,114) and validation (n = 1,089) subcohorts. Nine models were applied to select the most important predictors of 30-day readmission. The final tool, called the Tool for Pharmacists to Predict 30-day hospital readmission in patients with Heart Failure (ToPP-HF) relied upon multivariable logistic regression. We assessed discriminative ability using the C statistic and calibration using the Hosmer-Lemeshow goodness-of-fit test.

RESULTS

The risk of 30-day all-cause readmission was 15.7% (n = 331) and 18.8% (n = 205) in the development and validation subcohorts, respectively. The ToPP-HF tool included 13 variables: number of hospital admissions in previous 6 months; admission diagnosis of HF; number of scheduled medications; chronic obstructive pulmonary disease diagnosis; number of comorbidities; estimated glomerular filtration rate; hospital length of stay; left ventricular ejection fraction; critical care requirement; renin-angiotensin-aldosterone system inhibitor use; antiarrhythmic use; hypokalemia; and serum sodium. Discriminatory performance (C statistic of 0.69; 95% confidence interval [CI], 0.65-0.73) and calibration (Hosmer-Lemeshow P = 0.28) were good.

CONCLUSIONS

The ToPP-HF performs well and can help pharmacists identify high-risk patients with HF most likely to benefit from TOC services.

Heart Failure Hospitalizations and Risk Factors among the Multi-Ethnic Population from a Middle Income Country: The Suriname Heart Failure Studies

INTRODUCTION

Heart failure (HF) is an emerging epidemic with poor disease outcomes and differences in its prevalence, etiology and management between and within world regions. Hypertension (HT) and ischemic heart disease (IHD) are the leading causes of HF. In Suriname, South-America, data on HF burden are lacking. The aim of this Suriname Heart Failure I (SUHF-I) study, is to assess baseline characteristics of HF admitted patients in order to set up the prospective interventional SUHF-II study to longitudinally determine the effectiveness of a comprehensive HF management program in HF patients.

METHODS

A cross-sectional analysis was conducted of Thorax Center Paramaribo (TCP) discharge data from January 2013-December 2015. The analysis included all admissions with primary or secondary discharge of HF ICD-10 codes I50-I50.9 and I11.0 and the following variables: patient demographics (age, sex, and ethnicity), # of readmissions, risk factors (RF) for HF: HT, diabetes mellitus (DM), smoking, and left ventricle (LV) function. T-tests were used to analyze continuous variables and Chi-square test for categorical variables. Differences were considered statistically significant when a p-value <0.05 is obtained.

RESULTS

895 patients (1:1 sex ratio) with either a primary (80%) or secondary HF diagnosis were admitted. Female patients were significantly older (66.2 ± 14.8 years, p < 0.01) at first admission compared to male patients (63.5 ± 13.7 years) and the majority of admissions were of Hindustani and Creole descent. HT, DM and smoking were highly prevalent respectively 62.6%, 38.9 and 17.3%. There were 379 readmissions (29.1%) and 7% of all admissions were readmissions within 30 days and 16% were readmissions for 31-365 day. IHD is more prevalent in patients from Asian descendant (52.2%) compared to African descendant (11.7%). Whereas, HT (39.3%) is more prevalent in African descendants compared to Asian descendants (12.7%). There were no statistically significant differences in age, sex, ethnicity, LV function and RFs between single admitted and readmitted patients.

CONCLUSION

RF prevalence, ethnic differences and readmission rates in Surinamese HF patients are in line with reports from other Caribbean and Latin American countries. These results are the basis for the SUHF-II study which will aid in identifying the country specific and clinical factors for the successful development of a multidisciplinary HF management program.

LACE Score-Based Risk Management Tool for Long-Term Home Care Patients: A Proof-of-Concept Study in Taiwan

Background: Effectively predicting and reducing readmission in long-term home care (LTHC) is challenging. We proposed, validated, and evaluated a risk management tool that stratifies LTHC patients by LACE predictive score for readmission risk, which can further help home care providers intervene with individualized preventive plans. Method: A before-and-after study was conducted by a LTHC unit in Taiwan. Patients with acute hospitalization within 30 days after discharge in the unit were enrolled as two cohorts (Pre-Implement cohort in 2017 and Post-Implement cohort in 2019). LACE score performance was evaluated by calibration and discrimination (AUC, area under receiver operator characteristic (ROC) curve). The clinical utility was evaluated by negative predictive value (NPV). Results: There were 48 patients with 87 acute hospitalizations in Pre-Implement cohort, and 132 patients with 179 hospitalizations in Post-Implement cohort. These LTHC patients were of older age, mostly intubated, and had more comorbidities. There was a significant reduction in readmission rate by 44.7% (readmission rate 25.3% vs. 14.0% in both cohorts). Although LACE score predictive model still has room for improvement (AUC = 0.598), it showed the potential as a useful screening tool (NPV, 87.9%; 95% C.I., 74.2–94.8). The reduction effect is more pronounced in infection-related readmission. Conclusion: As real-world evidence, LACE score-based risk management tool significantly reduced readmission by 44.7% in this LTHC unit. Larger scale studies involving multiple homecare units are needed to assess the generalizability of this study.

Gender differences in the impact of frailty on 90-day hospital readmission in heart failure patients: a retrospective cohort study

AIMS

Frequent hospital readmissions after heart failure (HF) are common, however, there is limited data on the association between frailty status and hospital readmission in HF patients. This study aimed to examine the 90-day hospital readmission rates and gender differences in the impact of frailty on 90-day hospital readmission in HF patients.

METHODS AND RESULTS

We retrospectively analysed hospital discharge records of 279 patients (men = 169, women = 110) who were diagnosed with HF between January 2017 and December 2018. Frailty was assessed using the Korean version of the FRAIL scale. A logistic regression analysis was conducted to explore the factors predicting 90-day hospital readmission by gender. The prevalence of frailty and 90-day hospital readmissions were ∼54.4% and 22.7% in women, compared with 45.6% and 27.8% in men, respectively. Frail patients with HF have an increased risk of 90-day hospital readmission in both males and females. Particularly, women with frailty had a higher risk of 90-day hospital readmission [adjusted odds ratio (OR) 6.72, 95% confidence interval (CI) 1.41-32.09] than men with frailty (adjusted OR 4.40, 95% CI 1.73-11.17).

CONCLUSION

Our findings highlight that readmission within 90 days of hospitalization for HF can be predicted by patients' frailty. More importantly, we found that women with frailty have a greater risk of readmission than men with frailty. Screening for frailty should therefore be integrated into the assessment of HF patients. Tailored interventions for preventing adverse outcomes should consider gender-associated factors in HF patients with frailty.

Predicting High-Risk Patients and High-Risk Outcomes in Heart Failure

Identifying patients with heart failure at high risk for poor outcomes is important for patient care, resource allocation, and process improvement. Although numerous risk models exist to predict mortality, hospitalization, and patient-reported health status, they are infrequently used for several reasons, including modest performance, lack of evidence to support routine clinical use, and barriers to implementation. Artificial intelligence has the potential to enhance the performance of risk prediction models, but has its own limitations and remains unproved.

Long-term Survival After Hospital Admission in Older Italians: Comparison Between Geriatrics and Internal Medicine Across Different Discharge Diagnoses and Risk Status

BACKGROUND

In randomized clinical trials, compared to Internal Medicine, admission to Geriatrics improved clinical outcomes of frail older patients accessing the Emergency Department (ED). Whether this advantage is maintained also in the "real world" is uncertain. We compared long-term survival of patients admitted to Geriatrics or Internal Medicine wards after stratification for background risk and across a variety of discharge diagnoses.

METHOD

Data were derived from the "Silver Code National Project," an observational study of 180,079 unselected 75+ years old persons, admitted via the ED to Internal Medicine (n = 169,717, 94.2%) or Geriatrics (n = 10,362) wards in Italy. The Dynamic Silver Code (DSC), based on administrative data, was applied to balance for background risk between participants admitted to Geriatrics or Internal Medicine.

RESULTS

One-year mortality was 33.7%, lower in participants discharged from Geriatrics (32.1%) than from Internal Medicine (33.8%; p < .001), and increased progressively across four DSC risk classes (p < .001). Admission to Geriatrics was associated with survival advantage in DSC class II to IV participants, with HR (95% CI) of 0.88 (0.83-0.94), 0.86 (0.80-0.92), and 0.92 (0.86-0.97), respectively. Cerebrovascular diseases, cognitive disorders, and heart failure were the discharge diagnoses with the widest survival benefit from admission to Geriatrics, which was mostly observed in DSC class III.

CONCLUSIONS

Admission to Geriatrics may provide long-term survival benefit in subjects who, based on the DSC, may be considered at an intermediate risk. Specific clinical conditions should be considered in the ED to improve selection of patients to be targeted for Geriatrics admission.

Real-time utilisation of administrative data in the ED to identify older patients at risk: development and validation of the Dynamic Silver Code

OBJECTIVE

Identification of older patients at risk, among those accessing the emergency department (ED), may support clinical decision-making. To this purpose, we developed and validated the Dynamic Silver Code (DSC), a score based on real-time linkage of administrative data.

DESIGN AND SETTING

The 'Silver Code National Project (SCNP)', a non-concurrent cohort study, was used for retrospective development and internal validation of the DSC. External validation was obtained in the 'Anziani in DEA (AIDEA)' concurrent cohort study, where the DSC was generated by the software routinely used in the ED.

PARTICIPANTS

The SCNP contained 281 321 records of 180 079 residents aged 75+ years from Tuscany and Lazio, Italy, admitted via the ED to Internal Medicine or Geriatrics units. The AIDEA study enrolled 4425 subjects aged 75+ years (5217 records) accessing two EDs in the area of Florence, Italy.

INTERVENTIONS

None.

OUTCOME MEASURES

Primary outcome: 1-year mortality.

SECONDARY OUTCOMES

7 and 30-day mortality and 1-year recurrent ED visits.

RESULTS

Advancing age, male gender, previous hospital admission, discharge diagnosis, time from discharge and polypharmacy predicted 1-year mortality and contributed to the DSC in the development subsample of the SCNP cohort. Based on score quartiles, participants were classified into low, medium, high and very high-risk classes. In the SCNP validation sample, mortality increased progressively from 144 to 367 per 1000 person-years, across DSC classes, with HR (95% CI) of 1.92 (1.85 to 1.99), 2.71 (2.61 to 2.81) and 5.40 (5.21 to 5.59) in class II, III and IV, respectively versus class I (p<0.001). Findings were similar in AIDEA, where the DSC predicted also recurrent ED visits in 1 year. In both databases, the DSC predicted 7 and 30-day mortality.

CONCLUSIONS

The DSC, based on administrative data available in real time, predicts prognosis of older patients and might improve their management in the ED.

Development of a predictive model of hospitalization in primary care patients with heart failure

BACKGROUND

Heart failure (HF) is the leading cause of hospitalization in people over age 65. Predictive hospital admission models have been developed to help reduce the number of these patients.

AIM

To develop and internally validate a model to predict hospital admission in one-year for any non-programmed cause in heart failure patients receiving primary care treatment.

DESIGN AND SETTING

Cohort study, prospective. Patients treated in family medicine clinics.

METHODS

Logistic regression analysis was used to estimate the association between the predictors and the outcome, i.e. unplanned hospitalization over a 12-month period. The predictive model was built in several steps. The initial examination included a set of 31 predictors. Bootstrapping was used for internal validation.

RESULTS

The study included 251 patients, 64 (25.5%) of whom were admitted to hospital for some unplanned cause over the 12 months following their date of inclusion in the study. Four predictive variables of hospitalization were identified: NYHA class III-IV, OR (95% CI) 2.46 (1.23-4.91); diabetes OR (95% CI) 1.94 (1.05-3.58); COPD OR (95% CI) 3.17 (1.45-6.94); MLHFQ Emotional OR (95% CI) 1.07 (1.02-1.12). AUC 0.723; R2N 0.17; Hosmer-Lemeshow 0.815. Internal validation AUC 0.706.; R2N 0.134.

CONCLUSION

This is a simple model to predict hospitalization over a 12-month period based on four variables: NYHA functional class, diabetes, COPD and the emotional dimension of the MLHFQ scale. It has an acceptable discriminative capacity enabling the identification of patients at risk of hospitalization.

Risk of hospitalization of elderly rural workers in the state of Rio Grande do Sul

Abstract Objective : To analyze the risk of hospitalization of elderly rural workers in the state of Rio Grande do Sul, Brazil. Method : A cross-sectional, population-based study was carried out of retired rural workers (N=604), over 60 years of age, of both genders, selected by clusters. In order to evaluate the risk of hospitalization, the Probability of Repeated Hospitalization (or PIR) instrument validated and evaluated for Brazil was used. Risk of hospitalization was calculated through logistic regression analysis, and was classified into the following strata: low (<0.300); medium (0.300-0.399); medium-high (0.400-0.499) and high (≥0.500). Results : The rural elderly persons surveyed had a low risk of hospitalization (n=553; 91.6%). There was a predominance of men among the medium to high risk categories (n=42; 82.3%), distributed mainly in the Santa Maria, Sul and Camaquã regions. Conclusion: The results of the present study suggest a low risk of hospitalization among this population, however, there is a need for improved, more profound and robust research into the identification of factors associated with the health specificities of this population.