将黑盒临床预测模型转化为独立透明列线图：心脏移植中的时间外部验证
Translation of Black-Box Clinical Prediction Models into Standalone Transparent Nomograms: Temporal External Validation in Heart Transplantation
- Lund University（隆德大学）
- Liverpool John Moores University（利物浦约翰摩尔斯大学）
- Skåne University Hospital（斯科讷大学医院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出PRiSM方法，将黑盒临床预测模型转化为可审计的独立列线图，并在心脏移植数据中验证其非劣效性、校准性和临床净收益，且已开源。
AI中文摘要：
我们将用于表格数据的黑盒临床预测模型转化为可逐项审计的独立列线图。PRiSM（结构化模型中的部分响应）从源模型中提取每个效应和交互作用的形状，而不仅仅是哪些变量重要，并让结果选择并加权它们。我们在50,356名心脏移植受者中进行了测试，并在比训练更晚的时代进行了验证。来自所有5个源模型（一个公开的临床风险评分、逻辑回归、神经网络、随机森林和极端梯度提升）的列线图在进一步简化之前均达到了预定义的非劣效性判别标准，并通常保持了校准和临床净收益。来自3个机器学习模型的列线图与从头生成的广义加性模型和可解释提升模型在判别力上没有可检测的差异，超过了神经加性模型，并且比可解释提升模型携带更少的项。PRiSM作为开源Python包发布。
英文摘要：
We convert black-box clinical prediction models for tabular data into standalone nomograms that can be audited term by term. PRiSM (Partial Responses in Structured Models) takes the shape of each effect and interaction from the source model, not merely which variables mattered, and lets the outcome select and weight them. We tested this in 50,356 heart transplant recipients, with validation in a later era than training. Nomograms from all 5 source models - a public clinical risk score, logistic regression, neural networks, random forests and extreme gradient boosting - met a prespecified noninferiority criterion for discrimination before any further simplification, and generally preserved calibration and clinical net benefit. Those from the 3 machine-learning models showed no detectable difference in discrimination from de novo generalized additive and explainable boosting models, exceeded neural additive models, and carried fewer terms than the explainable boosting model. PRiSM is released as an open-source Python package.
