Background Older adults (≥ 65 years) account for a disproportionately high proportion of hospitalization and in-hospital mortality, some of which may be avoidable. Although machine learning (ML) models have already been built and validated for predicting hospitalization and mortality, there remains a significant need to optimise ML models further. Accurately predicting hospitalization may tremendously impact the clinical care of older adults as preventative measures can be implemented to improve clinical outcomes for the patient. Methods In this retrospective cohort study, a dataset of 14,198 community-dwelling older adults (≥ 65 years) with complex care needs from the Inter-Resident Assessment Instrument database was used to develop and optimise three ML models to predict 30-day-hospitalization. The models developed and optimized were Random Forest (RF), XGBoost (XGB), and Logistic Regression (LR). Variable importance plots were generated for all three models to identify key predictors of 30-day-hospitalization. Results The area under the receiver operating characteristics curve for the RF, XGB and LR models were 0.97, 0.90 and 0.72, respectively. Variable importance plots identified the Drug Burden Index and alcohol consumption as important, immediately potentially modifiable variables in predicting 30-day-hospitalization. Conclusions Identifying immediately potentially modifiable risk factors such as the Drug Burden Index and alcohol consumption is of high clinical relevance. If clinicians can influence these variables, they could proactively lower the risk of 30-day-hospitalization. ML holds promise to improve the clinical care of older adults. It is crucial that these models undergo extensive validation through large-scale clinical studies before being utilized in the clinical setting.

中文翻译：

---

药物负担指数是具有复杂护理需求的社区老年人 30 天住院的可修改预测因子：InterRAI 数据的机器学习分析

背景 老年人（≥ 65 岁）在住院治疗和院内死亡中所占比例过高，其中一些死亡是可以避免的。尽管机器学习 (ML) 模型已经建立并验证用于预测住院和死亡率，但仍然非常需要进一步优化 ML 模型。准确预测住院治疗可能会对老年人的临床护理产生巨大影响，因为可以采取预防措施来改善患者的临床结果。方法 在这项回顾性队列研究中，使用居民间评估工具数据库中 14,198 名具有复杂护理需求的社区居住老年人（≥ 65 岁）的数据集来开发和优化三个 ML 模型，以预测 30 天住院情况。开发和优化的模型包括随机森林 (RF)、XGBoost (XGB) 和逻辑回归 (LR)。为所有三个模型生成了变量重要性图，以确定 30 天住院的关键预测因素。结果 RF、XGB 和 LR 模型的受试者工作特征曲线下面积分别为 0.97、0.90 和 0.72。变量重要性图将药物负担指数和饮酒量确定为预测 30 天住院率的重要且可立即修改的变量。结论 立即识别潜在可改变的危险因素（例如药物负担指数和饮酒）具有很高的临床相关性。如果临床医生能够影响这些变量，他们就可以主动降低 30 天住院的风险。机器学习有望改善老年人的临床护理。至关重要的是，这些模型在应用于临床之前必须通过大规模临床研究进行广泛验证。