Comparison of machine-learning and logistic regression models to predict 30-day unplanned readmission: a development and validation study
Authors:
- Masao IwagamiMIMasao Iwagami
- Ryota InokuchiRIRyota Inokuchi
- Eiryo KawakamiEKEiryo Kawakami
- Tomohide YamadaTYTomohide Yamada
- Atsushi GotoAGAtsushi Goto
- Toshiki KunoTKToshiki Kuno
- Yohei HashimotoYHYohei Hashimoto
- Nobuaki MichihataNMNobuaki Michihata
- Tadahiro GotoTGTadahiro Goto
- Tomohiro ShinozakiTSTomohiro Shinozaki
- Yu SunYSYu Sun
- Yuta TaniguchiYTYuta Taniguchi
Preprint
Abstract
We compared the predictive performance of gradient-boosted decision tree (GBDT), random forest (RF), deep neural network (DNN), and logistic regression (LR) with the least absolute shrinkage and selection operator (LASSO) for 30-day unplanned readmission, according to the number of predictor variables and presence/absence of blood-test results. We used electronic health records of patients discharged alive from 38 hospitals in 2015–2017 for derivation (n=339,513) and in 2018 for validation (n=118,074), including basic characteristics (age, sex, admission diagnosis category, number of hospitalizations in the past year, discharge location), diagnosis, surgery, procedure, and drug codes, and blood-test results. We created six patterns of datasets having different numbers of binary variables (that ≥5% or ≥1% of patients or ≥10 patients had) with and without blood-test results. For the dataset with the smallest number of variables (102), the c-statistic was highest for GBDT (0.740), followed by RF (0.734), LR-LASSO (0.720), and DNN (0.664). For the dataset with the largest number of variables (1543), the c-statistic was highest for GBDT (0.764), followed by LR-LASSO (0.755), RF (0.751), and DNN (0.720). We found that GBDT generally outperformed LR-LASSO, but the difference became smaller when the number of variables was increased and blood-test results were used.Keywords
This publication has 22 references indexed in Scilit:
- A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records dataBMC Medical Informatics and Decision Making, 2018
- Predicting Hospital Readmission via Cost-Sensitive Deep LearningIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2018
- Predicting all-cause risk of 30-day hospital readmission using artificial neural networksPLOS ONE, 2017
- Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary ViewJournal of Medical Internet Research, 2016
- Utility of models to predict 28-day or 30-day unplanned hospital readmissions: an updated systematic reviewBMJ Open, 2016
- Comparison of predictive modeling approaches for 30-day all-cause non-elective readmission riskBMC Medical Research Methodology, 2016
- How to develop a more accurate risk prediction model when there are few eventsBMJ, 2015
- Preventing 30-Day Hospital ReadmissionsJAMA Internal Medicine, 2014
- Risk Prediction Models for Hospital ReadmissionJAMA, 2011
- Rehospitalizations among Patients in the Medicare Fee-for-Service ProgramNew England Journal of Medicine, 2009