Quality Improvement Program, University of Iowa Hospitals & Clinics, Iowa City, IA; Division of Medical Practice, Hospital Israelita Albert Einstein, São Paulo, Brazil.
Quality Improvement Program, University of Iowa Hospitals & Clinics, Iowa City, IA; Department of Infection Prevention and Control, King Abdulaziz Medical City, National Guard - Health Affairs, Riyadh, Saudi Arabia.
Diagn Microbiol Infect Dis. 2020 Oct;98(2):115104. doi: 10.1016/j.diagmicrobio.2020.115104. Epub 2020 Jun 8.
Previous studies have shown promising results of machine learning (ML) models for predicting health outcomes. We develop and test ML models for predicting Clostridioides difficile infection (CDI) in hospitalized patients. This is a retrospective cohort study conducted during 2015-2017. All inpatients tested for C. difficile were included. CDI was defined as having a positive glutamate dehydrogenase and toxin results. We restricted analyses to the first record of C. difficile testing per patient. Of 3514 patients tested, 136 (4%) had CDI. Age and antibiotic use within 90 days before C. difficile testing were associated with CDI (P < 0.01). We tested 10 ML methods with and without resampling. Logistic regression, random forest and naïve Bayes models yielded the highest AUC ROC performance: 0.6. Predicting CDI was difficult in our cohort of patients tested for CDI. Multiple ML models yielded only modest results in a real-world population of hospitalized patients tested for CDI.
先前的研究表明，机器学习 (ML) 模型在预测健康结果方面具有广阔的前景。我们开发并测试了用于预测住院患者艰难梭菌感染 (CDI) 的 ML 模型。这是一项回顾性队列研究，于 2015 年至 2017 年进行。所有接受艰难梭菌检测的住院患者均被纳入研究。CDI 的定义为谷氨酸脱氢酶和毒素检测结果阳性。我们将分析限制在每位患者首次艰难梭菌检测的记录上。在接受检测的 3514 名患者中，有 136 名（4%）患有 CDI。在艰难梭菌检测前 90 天内使用抗生素和年龄与 CDI 相关（P<0.01）。我们测试了 10 种带有和不带有重采样的 ML 方法。逻辑回归、随机森林和朴素贝叶斯模型的 AUC ROC 性能最高：0.6。在我们对 CDI 进行检测的患者队列中，预测 CDI 是困难的。在对 CDI 进行检测的实际住院患者人群中，多种 ML 模型的预测结果仅略有改善。
