JMIR Publications

ABSTRACT

Background:

Falls among hospitalized patients are a critical issue that often leads to prolonged hospital stays and increased health care costs. Traditional fall risk assessments typically rely on standardized scoring systems; however, these may fail to capture the complex and multifactorial nature of fall risk factors.

Objective:

This retrospective observational multicenter study aimed to develop and validate a machine learning-based model to predict in-hospital falls and to evaluate its performance in terms of discrimination and calibration.

Methods:

We analyzed the data of 83,917 inpatients aged ≥ 65 years with a hospital stay of at least 3 days. Using Diagnosis Procedure Combination data and laboratory results, we extracted demographic, clinical, functional, and pharmacological variables. Following the selection of 30 key features, 4 predictive models were constructed: logistic regression, extreme gradient boosting, light gradient boosting machine (LGBM), and categorical boosting (CatBoost). The synthetic minority over-sampling technique and isotonic regression calibration were applied to improve the prediction quality and address class imbalance.

Results:

Falls occurred in 2,173 patients (2.6%). CatBoost achieved the highest F1 score (0.189, 95% confidence interval [CI]: 0.162–0.215) and precision-recall curve (PRAUC) (0.112, 95% CI: 0.091–0.136), whereas LGBM had the best calibration slope (0.964, 95% CI 0.858–1.070) with good discrimination (F1 0.182, 95% CI 0.156–0.209; PRAUC 0.094, 95% CI: 0.078–0.113). LR had the lowest discrimination (F1 0.120, 95% CI: 0.100–0.143). SHapley Additive exPlanations analysis consistently identified low albumin, impaired transfer ability, and use of sedative-hypnotics or diabetes medications as major contributors to fall risk. In incident report analysis (n=435), 49.2% of falls were toileting-related, peaking between 4 and 6 AM, with bedside falls predominating in high/very high risk groups.

Conclusions:

CatBoost and LGBM offer clinically valuable prediction performance, with CatBoost favored for high-risk patient identification and LGBM for probability-based intervention thresholds. Integrating such models into electronic health records could enable real-time risk scoring and trigger targeted interventions (e.g., toileting assistance and mobility support). Future work should incorporate dynamic, time-varying patient data to improve real-time risk prediction. Clinical Trial: This study was not registered, as it was an observational study without any intervention