Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA.
Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA.
AMIA Annu Symp Proc. 2021 Jan 25;2020:602-611. eCollection 2020.
Predictive models can be useful in predicting patient outcomes under uncertainty. Many algorithms employ "population" methods, which optimize a single model to perform well on average over an entire population, but the model may perform poorly on some patients. Personalized methods optimize predictive performance for each patient by tailoring the model to the individual. We present a new personalized method based on decision trees: the Personalized Decision Path using a Bayesian score (PDP-Bay). Performance on eight synthetic, genomic, and clinical datasets was compared to that of decision trees and a previously described personalized decision path method in terms of area under the ROC curve (AUC) and expected calibration error (ECE). Model complexity was measured by average path length. The PDP-Bay model outperformed the decision tree in terms of both AUC and ECE. The results support the conclusion that personalization may achieve better predictive performance and produce simpler models than population approaches.
预测模型在预测不确定情况下的患者结局时可能很有用。许多算法采用“群体”方法，该方法优化单个模型以使其在整个群体中的平均表现良好，但该模型在某些患者身上的表现可能不佳。个性化方法通过根据个体定制模型来为每个患者优化预测性能。我们提出了一种基于决策树的新的个性化方法：基于贝叶斯评分的个性化决策路径 (PDP-Bay)。在八个合成的、基因组学的和临床数据集上，与决策树和之前描述的个性化决策路径方法相比，根据 ROC 曲线下面积 (AUC) 和预期校准误差 (ECE) 来比较性能。通过平均路径长度来衡量模型的复杂性。PDP-Bay 模型在 AUC 和 ECE 方面都优于决策树。结果支持这样的结论，即个性化可能比群体方法实现更好的预测性能并产生更简单的模型。
