Adaptive Systems and Medical Data Science, Department of Mathematics and Computer Science, University of Basel, Basel, Switzerland.
Division of Neonatology, University of Basel Children's Hospital (UKBB), Basel, Switzerland.
Pediatr Res. 2019 Jul;86(1):122-127. doi: 10.1038/s41390-019-0384-x. Epub 2019 Mar 31.
Machine learning models may enhance the early detection of clinically relevant hyperbilirubinemia based on patient information available in every hospital.
We conducted a longitudinal study on preterm and term born neonates with serial measurements of total serum bilirubin in the first two weeks of life. An ensemble, that combines a logistic regression with a random forest classifier, was trained to discriminate between the two classes phototherapy treatment vs. no treatment.
Of 362 neonates included in this study, 98 had a phototherapy treatment, which our model was able to predict up to 48 h in advance with an area under the ROC-curve of 95.20%. From a set of 44 variables, including potential laboratory and clinical confounders, a subset of just four (bilirubin, weight, gestational age, hours since birth) suffices for a strong predictive performance. The resulting early phototherapy prediction tool (EPPT) is provided as an open web application.
Early detection of clinically relevant hyperbilirubinemia can be enhanced by the application of machine learning. Existing guidelines can be further improved to optimize timing of bilirubin measurements to avoid toxic hyperbilirubinemia in high-risk patients while minimizing unneeded measurements in neonates who are at low risk.
机器学习模型可以基于每个医院都可用的患者信息，提高对临床相关高胆红素血症的早期检测能力。
我们对早产儿和足月儿进行了一项纵向研究，在生命的头两周内对总血清胆红素进行了多次测量。我们训练了一个集成模型，该模型将逻辑回归与随机森林分类器相结合，以区分光疗治疗和非治疗两种情况。
在这项研究中，有 362 名新生儿被纳入研究，其中 98 名接受了光疗治疗，我们的模型能够提前 48 小时预测，ROC 曲线下面积为 95.20%。从包括潜在实验室和临床混杂因素在内的 44 个变量中，只需要四个变量（胆红素、体重、胎龄、出生后小时数）就能获得很强的预测性能。由此产生的早期光疗预测工具（EPPT）作为一个开放的网络应用程序提供。
通过应用机器学习可以提高对临床相关高胆红素血症的早期检测能力。现有的指南可以进一步改进，以优化胆红素测量的时间，以避免高危患者出现毒性高胆红素血症，同时最大限度地减少低危新生儿不必要的测量。
