机器学习模型在全膝关节置换术后再入院和延长住院时间预测中于弱势群体表现不佳:公平性分析与缓解策略
本研究评估了四种已验证的机器学习模型预测全膝关节置换术后再入院和延长住院时间的公平性,发现随机森林模型预测性能最佳(再入院AUC=0.98;延长住院AUC=0.92),但在女性、非白人及西班牙裔/拉丁裔亚组中预测平等性较差。三种偏倚缓解策略虽改善了公平性指标,但存在权衡,无法完全消除偏倚,强调在临床算法发布或用作决策支持工具前需纠正亚组偏倚以确保公平。
要点
- 随机森林模型预测性能最佳,再入院AUC=0.98,延长住院AUC=0.92。
- 女性、非白人、西班牙裔/拉丁裔亚组再入院预测平等性较差。
- 偏倚缓解策略可改善公平性指标,但存在权衡且无法完全消除偏倚。
核心结论
- 当前已验证的机器学习模型在预测全膝关节置换术后再入院和延长住院时间时,对较小亚组(如女性、非白人、西班牙裔/拉丁裔)表现不公平或预测性能不佳。
- 偏倚缓解技术可改善公平性指标,但没有一种方法能完全消除偏倚,需仔细考虑每种策略的权衡。
- 在临床算法发布或用作临床决策支持工具前,应大力纠正亚组中的潜在偏倚以确保患者公平。
研究设计与样本
- 开发并验证了四种机器学习模型,用于预测全膝关节置换术后再入院和延长住院时间。
- 使用受保护属性(年龄、性别、种族和族裔)进行偏倚评估,并评估多种公平性指标。
- 针对每种算法试验了三种偏倚缓解策略,并将对给定受保护属性最有效的策略与原始模型整合后重新评估公平性指标。
主要发现
- 随机森林模型预测性能最佳:再入院AUC=0.98;延长住院AUC=0.92。
- 再入院预测平等性在女性(0.47 vs 男性)、非白人(0.75 vs 白人)和西班牙裔/拉丁裔(0.53 vs 非西班牙裔/拉丁裔)亚组中较差。
- 延长住院预测在除准确平等性外的所有公平性指标上,弱势队列间均存在显著差异。
- 偏倚缓解策略在两种机器学习模型中均有效,但公平性指标之间存在权衡。
临床怎么用
- 临床使用机器学习模型预测全膝关节置换术后结局前,应评估其在各亚组中的公平性。
- 针对识别出的偏倚,可尝试偏倚缓解策略,但需权衡公平性指标的变化。
- 不应将未经亚组偏倚校正的模型直接作为临床决策支持工具。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: While machine learning (ML) models demonstrate high predictive accuracy, recent studies reveal that ML models underperform for smaller subcohorts such as racial and ethnic minorities, suggesting inherent ML biases that may exacerbate health disparities. To assume a "one-size-fits-all" approach perpetuates inequities in decision-making for underrepresented groups. This study assessed validated ML model "fairness" for total knee arthroplasty (TKA) outcomes and explored bias mitigation strategies to enhance equitable prediction performance. METHODS: There were four ML models that were developed and validated to predict readmission and prolonged lengths of stay (pLOSs) following TKA. Bias assessment was performed using protected attributes (age, sex, race, and ethnicity), and various fairness metrics were evaluated. There were three bias mitigation strategies incorporated and trialed for each algorithm, and the most effective strategy for a given protected attribute was integrated with the original model and reassessed based on the fairness metrics. RESULTS: The random forest model had the best predictive performance (ReadmissionAUC = 0.98; pLOSAUC = 0.92). Inferior predictive equality for readmission was demonstrated in women (0.47 versus men), non-White (0.75 versus White), and Hispanic or LatinoX (0.53 versus not Hispanic/LatinoX) subcohorts. Significant differences in all, but accuracy equality metrics for pLOS were unveiled across underprivileged cohorts. Mitigation strategies were effective in both ML models; however, trade-offs were observed between the fairness metrics. CONCLUSIONS: Our study highlights the "unfairness" or underperformance of current validated ML models in predicting readmission and pLOS in smaller subcohorts after TKA. While mitigation techniques improved fairness metrics, no approach fully eliminated bias, underscoring the need to carefully consider the trade-offs of each strategy. Our findings suggest substantial efforts should be made to correct potential bias in subcohorts before clinical algorithms are published or utilized as clinical decision-support tools to ensure patient equity.
引用
- Shimizu MR, Raza MM, Xiao P, et al. Underperformance of Machine Learning Models Predicting Readmission and Prolonged Length of Stay Following Total Knee Arthroplasty Among Underrepresented Populations: Fairness Analysis and Mitigation Strategies. J Arthroplasty. 2026. PMID: 41935760. doi:10.1016/j.arth.2026.03.085
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。