An evaluation of machine-learning methods for predicting pneumonia mortality
An evaluation of machine-learning methods for predicting pneumonia mortality
复制标题
DOI：
10.1016/s0933-3657(96)00367-3
复制
发表时间：
1997-02-01
影响因子：
7.5
通讯作者：
Spirtes, P
中科院分区：
文献类型：
--
作者：
Cooper, GF;Aliferis, CF;Spirtes, P
本文描述了八种统计和机器学习方法的应用，以获得计算机模型，用于从最初的研究结果中预测医院肺炎患者的死亡率。这8个模型分别基于9847例患者病例构建，并分别在另外4352例病例上进行评价。主要评估指标是预测生存率的误差，作为预测生存的患者比例的函数。该度量在评估模型的潜力以帮助临床医生决定是否在医院或家中治疗给定患者时是有用的。我们检查了模型在预测给定比例的患者将存活时的错误率。我们检查了0.1和0.6之间的存活分数。在这个范围内，每个模型的预测误差率都在其他模型误差率的1%以内。当预测约30%的患者将存活时，所有模型的误差率均小于1.5%。这些模型的区别更多的是它们所包含的变量和参数的数量，而不是它们的错误率;这些差异表明，哪些模型可能最适合作为纸质指南在未来实施。版权所有（C）1997 Elsevier Science B. V.
This paper describes the application of eight statistical and machine-learning methods to derive computer models for predicting mortality of hospital patients with pneumonia from their findings at initial presentation. The eight models were each constructed based on 9847 patient cases and they were each evaluated on 4352 additional cases. The primary evaluation metric was the error in predicted survival as a function of the fraction of patients predicted to survive. This metric is useful in assessing a model's potential to assist a clinician in deciding whether to treat. a given patient in the hospital or at home. We examined the error rates of the models when predicting that a given fraction of patients will survive. We examined survival fractions between 0.1 and 0.6. Over this range, each model's predictive error rate was within 1% of the error rate of every other model. When predicting that approximately 30% of the patients will survive, all the models have an error rate of less than 1.5%. The models are distinguished more by the number of variables and parameters that they contain than by their error rates; these differences suggest which models may be the most amenable to future implementation as paper-based guidelines. Copyright (C) 1997 Elsevier Science B.V.