Ma Yuxuan, Tu Xi, Luo Xiaodong, Hu Linlin, Wang Chen
School of Health Policy and Management, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
The Second Hospital of Jinhua, Zhejiang, China.
BMC Psychiatry. 2025 Jan 9;25(1):33. doi: 10.1186/s12888-024-06358-y.
Mental disorders are increasingly prevalent, leading to increased medical expenditures. To refine the reimbursement of medical costs for inpatients with mental disorders by health insurance, an accurate prediction model is essential. Per-diem payment is a common internationally implemented payment method for medical insurance of inpatients with mental disorders, necessitating the exploration of advanced machine learning methods for predicting the average daily hospitalization costs (ADHC) based on the characteristics of inpatients with mental disorders.
We used data including demographic information, clinical/functional characteristics, institutional features, and cost information of 5070 hospitalized patients with mental disorders in Jinhua, China, and employed six algorithms to predict ADHC. Performance of these six algorithms was evaluated through 5- old cross-validation combined with bootstrap method to select the most suitable algorithm and identify key factors influencing ADHC.
The random forest (RF) model demonstrated better performance (R-squared (R) = 0.6417 (95% CI, 0.6236-0.6611), root-mean-square error (RMSE) = 0.2398 (95% CI, 0.2252-0.2553), mean-absolute error (MAE) = 0.1677 (95% CI, 0.1626-0.1735), mean-absolute-percentage error (MAPE) = 0.0295 (95% CI, 0.0287-0.0304)). According to feature importance ranking, models incorporating top 11 factors (> 0.01) demonstrated comparable performance to those encompassing all variables. Top four factors (> 0.05) were level of medical institution, age, functional classification, and cognitive classification. Notably, level of medical institutions was the most significant factor across all primary models. Higher medical institutions level, patients below 20 and above 75 years old, lower functional classification, and lower cognitive classification are associated with increased ADHC.
Machine learning algorithms, particularly RF algorithm, enhance accuracy of predicting ADHC for mental health patients. The findings of this study provide evidence for setting up more reasonable insurance payment standards for inpatients with mental disorders and support resource allocation in clinical practice.
精神障碍日益普遍，导致医疗支出增加。为完善医疗保险对精神障碍住院患者医疗费用的报销，准确的预测模型至关重要。按日付费是国际上对精神障碍住院患者医疗保险普遍采用的支付方式，因此有必要探索基于精神障碍住院患者特征预测平均每日住院费用（ADHC）的先进机器学习方法。
我们使用了包括中国金华5070例精神障碍住院患者的人口统计学信息、临床/功能特征、机构特征和费用信息的数据，并采用六种算法预测ADHC。通过5折交叉验证结合自助法评估这六种算法的性能，以选择最合适的算法并确定影响ADHC的关键因素。
随机森林（RF）模型表现更佳（决定系数（R）=0.6417（95%置信区间，0.6236 - 0.6611），均方根误差（RMSE）=0.2398（95%置信区间，0.2252 - 0.2553），平均绝对误差（MAE）=0.1677（95%置信区间，0.1626 - 0.1735），平均绝对百分比误差（MAPE）=0.0295（95%置信区间，0.0287 - 0.0304））。根据特征重要性排名，纳入前11个因素（>0.01）的模型与包含所有变量的模型表现相当。前四个因素（>0.05）为医疗机构级别、年龄、功能分类和认知分类。值得注意的是，医疗机构级别是所有主要模型中最重要的因素。医疗机构级别越高、年龄在20岁以下和75岁以上、功能分类越低以及认知分类越低与ADHC增加相关。
机器学习算法，尤其是RF算法，提高了预测精神健康患者ADHC的准确性。本研究结果为制定更合理的精神障碍住院患者保险支付标准提供了依据，并支持临床实践中的资源分配。
