Qualitative description of clusters.

BackgroundMachine learning (ML) algorithms are increasingly used in healthcare to support clinical decision-making. While models with similar overall performance are often considered interchangeable for deployment, they may produce divergent predictions, a phenomenon known as algorithmic multiplicity. In such cases, the choice of algorithm may introduce bias. This study investigates the impacts of algorithmic multiplicity in mortality prediction and assesses the influence of patient characteristics on model decisions.MethodsA cohort of 4,337 adult patients (≥18 years) with RT-PCR–confirmed covid-19 from five tertiary care hospitals in Brazil was followed from March to August 2020. Five popular ML models for structured data were trained on demographic and laboratory data collected at early hospital admission to predict in-hospital mortality. Model performance, feature importance, and algorithmic prediction similarity were evaluated. Feature distributions were compared between patients correctly or incorrectly classified by all models using paired t-tests or Mann–Whitney U tests, as applicable, at the 5% significance level. Subgroup performance differences were assessed using 10-fold cross-validation applied to five k-means–delineated clusters, compared by one-way ANOVA. Within-cluster predictive divergence was assessed within a 95% confidence interval.ResultsAll models achieved high overall predictive performance (µ = 0.855, σ² = 0.0072). However, the comparison of individual-level predictions revealed substantial heterogeneity, with pairwise prediction correlations ranging from R² = 0.56 to 0.80. Unsupervised k-means clustering identified five clinically distinct patient subgroups with mortality rates ranging from 22% to 80%, within which model performance varied significantly (F = 73.18, p ConclusionsThis study demonstrates that ML models with similar overall performance can yield substantially divergent predictions at both the individual and subgroup levels, and that no single algorithm consistently outperforms others across all patient subgroups. These findings highlight the limitations of relying solely on global performance metrics and underscore the need for context-aware evaluation of ML models in heterogeneous clinical populations.

**背景** 机器学习（ML）算法在医疗领域的应用日益广泛，用于辅助临床决策。尽管整体性能相近的模型通常被认为可互换部署，但它们可能生成截然不同的预测结果，这一现象被称为算法多样性（algorithmic multiplicity）。在此类场景下，算法的选择可能引入偏倚。本研究探讨了算法多样性在死亡率预测中的影响，并评估了患者特征对模型决策的作用。
**方法** 本研究队列纳入2020年3月至8月期间，来自巴西5家三级医院的4337名经逆转录聚合酶链式反应（RT-PCR）确认感染新型冠状病毒肺炎（COVID-19）的成年患者（年龄≥18岁），并对其开展随访。研究采用5种常用于结构化数据分析的主流机器学习模型，以患者入院早期收集的人口统计学与实验室检查数据作为训练特征，预测其住院死亡率。本研究对模型性能、特征重要性及算法预测相似度进行了评估。针对所有模型均正确分类或均错误分类的患者，根据数据适用类型分别采用配对t检验或曼-惠特尼U检验比较其特征分布，检验显著性水平设定为5%。对于通过K均值聚类划分出的5个患者亚组，采用10折交叉验证评估亚组间的性能差异，并通过单因素方差分析进行组间比较。同时在95%置信区间内评估各聚类组内的预测分歧程度。
**结果** 所有模型均实现了较高的整体预测性能（均值μ=0.855，方差σ²=0.0072）。然而，对个体水平预测结果的对比显示出显著的异质性，两两预测的决定系数R²范围为0.56至0.80。无监督K均值聚类划分出5个具有明确临床差异的患者亚组，其死亡率介于22%至80%之间，各亚组内的模型性能存在显著差异（F=73.18，p）。
**结论** 本研究表明，整体性能相近的机器学习模型在个体与亚组层面均可生成差异显著的预测结果，且不存在某一种算法可在所有患者亚组中始终优于其他算法。本研究结果凸显了仅依赖全局性能指标的局限性，同时强调了在异质性临床人群中开展场景感知式机器学习模型评估的必要性。