Comparison of Machine Learning Algorithms for the Prediction of Preventable Hospital Readmissions

Abstract

A diverse universe of statistical models in the literature aim to help hospitals understand the risk factors of their preventable readmissions. However, these models are usually not necessarily applicable in other contexts, fail to achieve good discriminatory power, or cannot be compared with other models. We built and compared predictive models based on machine learning algorithms for 30-day preventable hospital readmissions of Medicare patients. This work used the same inclusion/exclusion criteria for diseases used by the Centers for Medicare and Medicaid Services. In addition, risk stratification techniques were implemented to study covariate behavior on each risk strata. The new models resulted in improved performance measured by the area under the receiver operating characteristic curve. Finally, factors such as higher length of stay, disease severity index, being discharged to a hospital, and primary language other than English were associated with increased risk to be readmitted within 30 days. In the future, better predictive models for 30-day preventable hospital readmissions can point to the development of systems that identify patients at high risk and lead to the implementation of interventions (e.g., discharge planning and follow-up) to those patients, providing consistent improvement in the quality and efficiency of the healthcare system.

Machine Learning-Augmented Propensity Score-Adjusted Multilevel Mixed Effects Panel Analysis of Hands-On Cooking and Nutrition Education versus Traditional Curriculum for Medical Students as Preventive Cardiology: Multisite Cohort Study of 3,248 Trainees over 5 Years

“…The first phase of the analysis was conducted with ML within a supervised learning framework to test 43 algorithms with 10-fold cross-validation, selected based upon the data type. Algorithm performance was assessed favorably based on higher accuracy, lower root relative squared error (RRSE) with model acceptability set at 100% (for comparison among ML algorithms), and lower root mean squared error (RMSE, for comparison to traditional statistical models) [ 38 ]. Performance could be improved further if the relevant ML algorithms would be additionally permitted to select which variables should be included in the models.…”

Leveraging Electronic Health Records and Machine Learning to Tailor Nursing Care for Patients at High Risk for Readmissions

“…3 More recently, EHRs are employed as a means to identify patterns of high utilization within health care systems, including unplanned readmissions. 4,5 A study by Shadmi and colleagues, for example, employed the EHR to develop a readmission risk prediction model for all cause readmissions to an integrated delivery system, 6 while other studies have leveraged the EHR to identify psychosocial risk factors that may heighten risk for 30-day readmission. 7 Readmissions are of particular interest to health care systems due to the Hospital Readmissions Reduction Program (HRRP), which penalizes hospitals for higher-thanexpected readmission rates for selected conditions.…”

Anastomotic Leak is Increased With Clostridium difficile Infection After Colectomy: Machine Learning-Augmented Propensity Score Modified Analysis of 46 735 Patients

“…Performance among algorithms were assessed based on higher accuracy, lower root relative squared error (RRSE) with model acceptability set at 100% (for comparison among machine learning (ML) algorithms), and lower RMSE (for comparison to traditional statistical models). 25 The following algorithms by type were tested: Bayesian (Bayes Net, Naive Bayes, Naive Bayes Multinomial Text, and Naive Bayes Updateable), Functions ( An academic physician data scientist and biostatistician confirmed that the final regression models were sufficiently supported by the existing literature and clinical and statistical theory. Fully adjusted regression results were reported with 95% confidence intervals (CIs) with statistical significance set with a two-tailed P-value of <.05.…”