Predictive modeling for 14-day unplanned hospital readmission risk by using machine learning algorithms

Abstract

Background Early unplanned hospital readmissions are associated with increased harm to patients, increased medical costs, and negative hospital reputation. With the identification of at-risk patients, a crucial step toward improving care, appropriate interventions can be adopted to prevent readmission. This study aimed to build machine learning models to predict 14-day unplanned readmissions. Methods We conducted a retrospective cohort study on 37,091 consecutive hospitalized adult patients with 55,933 discharges between September 1, 2018, and August 31, 2019, in an 1193-bed university hospital. Patients who were aged < 20 years, were admitted for cancer-related treatment, participated in clinical trial, were discharged against medical advice, died during admission, or lived abroad were excluded. Predictors for analysis included 7 categories of variables extracted from hospital’s medical record dataset. In total, four machine learning algorithms, namely logistic regression, random forest, extreme gradient boosting, and categorical boosting, were used to build classifiers for prediction. The performance of prediction models for 14-day unplanned readmission risk was evaluated using precision, recall, F1-score, area under the receiver operating characteristic curve (AUROC), and area under the precision–recall curve (AUPRC). Results In total, 24,722 patients were included for the analysis. The mean age of the cohort was 57.34 ± 18.13 years. The 14-day unplanned readmission rate was 1.22%. Among the 4 machine learning algorithms selected, Catboost had the best average performance in fivefold cross-validation (precision: 0.9377, recall: 0.5333, F1-score: 0.6780, AUROC: 0.9903, and AUPRC: 0.7515). After incorporating 21 most influential features in the Catboost model, its performance improved (precision: 0.9470, recall: 0.5600, F1-score: 0.7010, AUROC: 0.9909, and AUPRC: 0.7711). Conclusions Our models reliably predicted 14-day unplanned readmissions and were explainable. They can be used to identify patients with a high risk of unplanned readmission based on influential features, particularly features related to diagnoses. The operation of the models with physiological indicators also corresponded to clinical experience and literature. Identifying patients at high risk with these models can enable early discharge planning and transitional care to prevent readmissions. Further studies should include additional features that may enable further sensitivity in identifying patients at a risk of early unplanned readmissions.

Comparison of machine learning models for predicting the risk of breast cancer-related lymphedema in Chinese women

“…In order to address the study objectives, we used standard evaluation indices to evaluate our ML models, as suggested by previous research, [25] including the accuracy, precision score (positive predict rate), recall score (sensitivity), AUC (area under the receiver operating characteristic curve), F1 score (the harmonic mean of precision and recall scores), and the precision-recall curve for the training dataset. We used the calibration J o u r n a l P r e -p r o o f plot (i.e., a plot showing whether the risk prediction of BCRL was accurate) to examine the performance of the validation dataset.…”

Explainable machine learning models for predicting 30-day readmission in pediatric pulmonary hypertension: A multicenter, retrospective study

“…Zhao QY et al developed a model for predicting extubation failure in intensive care units with 11 ML algorithms and the CatBoost algorithm showed the best performance in the internal and prospective validation set ( 37 ). Lo YT et al built a risk stratification tool for predicting 14-day unplanned readmission, in which the CatBoost algorithm showed the best performance in the 5-fold cross-validation (AUROC:0.9903) of four selected ML algorithms ( 38 ).…”

Correction to: Predictive modeling for 14-day unplanned hospital readmission risk by using machine learning algorithms

“…Following publication of the original article [ 1 ], the following errors were reported: Jah Chiehen Liao’s name was misspelled as ‘Jay Chie-hen Liao’ A note marking Yu-Tai Lo and Jay Chiehen Liao as co-first authors was missing A grant number was missing in the Acknowledgement declaration …”