提高预测模型判别准确性的视觉传达：概率阈值图。
Improving visual communication of discriminative accuracy for predictive models: the probability threshold plot.
作者信息
Johnston Stephen S, Fortin Stephen, Kalsekar Iftekhar, Reps Jenna, Coplan Paul
机构信息
Epidemiology, Medical Devices, Johnson & Johnson, New Brunswick, New Jersey, USA.
Epidemiology; Janssen Research and Development, Titusville, New Jersey, USA.
出版信息
JAMIA Open. 2021 Mar 12;4(1):ooab017. doi: 10.1093/jamiaopen/ooab017. eCollection 2021 Jan.
OBJECTIVES
To propose a visual display-the probability threshold plot (PTP)-that transparently communicates a predictive models' measures of discriminative accuracy along the range of model-based predicted probabilities ().
MATERIALS AND METHODS
We illustrate the PTP by replicating a previously-published and validated machine learning-based model to predict antihyperglycemic medication cessation within 1-2 years following metabolic surgery. The visual characteristics of the PTPs for each model were compared to receiver operating characteristic (ROC) curves.
RESULTS
A total of 18 887 patients were included for analysis. Whereas during testing each predictive model had nearly identical ROC curves and corresponding area under the curve values (0.672 and 0.673), the visual characteristics of the PTPs revealed substantive between-model differences in sensitivity, specificity, PPV, and NPV across the range of .
DISCUSSION AND CONCLUSIONS
The PTP provides improved visual display of a predictive model's discriminative accuracy, which can enhance the practical application of predictive models for medical decision making.
目的
提出一种可视化展示——概率阈值图（PTP），该图能直观地传达预测模型在基于模型预测概率范围内的判别准确性度量。
材料与方法
我们通过复制一个先前发表并经验证的基于机器学习的模型来说明PTP，该模型用于预测代谢手术后1 - 2年内抗高血糖药物停用情况。将每个模型的PTP的视觉特征与受试者工作特征（ROC）曲线进行比较。
结果
共纳入18887例患者进行分析。虽然在测试期间每个预测模型具有几乎相同的ROC曲线和相应的曲线下面积值（0.672和0.673），但PTP的视觉特征显示在整个范围内模型间在敏感性、特异性、阳性预测值和阴性预测值方面存在实质性差异。
讨论与结论
PTP能更好地直观展示预测模型的判别准确性，这可增强预测模型在医疗决策中的实际应用。
Zotero 插件