Data-driven cluster analysis identifies three clinical phenotypes in hemodialysis patients

Clinical heterogeneity among hemodialysis patients necessitates precision medicine approaches transcending conventional single-parameter management. Through machine learning analysis of 1,207 maintenance hemodialysis patients, we developed a novel two-tier phenotyping framework integrating unsupervised K-means clustering across 22 clinical indicators with supervised classification using six universally available biomarkers. Five mechanistically informed composite indicators were constructed, including the Middle-Small Molecule Clearance Index (β₂-microglobulin reduction ratio × <i>Kt</i>/<i>V</i>) and ferritin–hemoglobin ratio, achieving superior discriminatory capacity over traditional approaches. Three distinct metabolic phenotypes emerged with exceptional stability (Adjusted Rand Index = 0.9181): high retention-inflammatory (19.5%) characterized by dialysis inadequacy and functional iron deficiency, optimal clearance (24.3%) demonstrating superior toxin removal, and intermediate-stable (56.0%) maintaining balanced parameters. The simplified six-parameter model achieved clinically acceptable performance (AUC: 0.893–0.919, accuracy &gt;88%) enabling automated EMR integration. This cross-sectional phenotype discovery represents the foundational step toward precision nephrology, establishing classification frameworks essential for subsequent longitudinal validation studies. The methodology facilitates phenotype-guided interventions: intensified dialysis for high retention-inflammatory patients, clearance optimization for optimal clearance patients, and proactive monitoring for intermediate-stable patients, advancing hemodialysis toward algorithm-driven individualized care with potential to optimize clinical outcomes and resource utilization, pending prospective validation of phenotype-outcome associations.

血液透析患者间存在的临床异质性，亟需超越传统单参数管理模式的精准医学（precision medicine）干预方案。本研究通过对1207例维持性血液透析（maintenance hemodialysis）患者开展机器学习分析，构建了一种全新的双层表型分型框架：该框架整合了基于22项临床指标的无监督K-means聚类（unsupervised K-means clustering），以及基于6种通用生物标志物（biomarkers）的监督分类流程。研究构建了5项基于机制的复合指标，包括中小分子清除指数（Middle-Small Molecule Clearance Index，即β₂微球蛋白（β₂-microglobulin）清除率比值 × Kt/V）与铁蛋白-血红蛋白比值，其判别性能优于传统方法。最终得到3种具有极高稳定性的代谢表型，调整兰德指数（Adjusted Rand Index）为0.9181：分别为高潴留-炎症型（占比19.5%），以透析不充分与功能性铁缺乏为特征；最佳清除型（占比24.3%），表现为优异的毒素清除效果；以及中间稳定型（占比56.0%），各项参数维持平衡状态。简化后的6参数模型达到了临床可接受的性能表现：曲线下面积（Area Under Curve，AUC）为0.893~0.919，准确率＞88%，可实现与电子病历（Electronic Medical Record，EMR）系统的自动化集成。本次横断面表型发掘研究是迈向精准肾脏病学（precision nephrology）的基础性步骤，所建立的分型框架可为后续纵向验证研究提供核心支撑。该分型方法可支持表型导向的干预策略：针对高潴留-炎症型患者实施强化透析，针对最佳清除型患者优化毒素清除方案，针对中间稳定型患者开展主动监测，从而推动血液透析向算法驱动的个体化诊疗模式迈进，有望改善临床结局与资源利用效率，相关结论仍需等待表型-结局关联的前瞻性验证。