Literature DB >> 33863558

Understanding risk factors for postoperative mortality in neonates based on explainable machine learning technology.

Yaoqin Hu1, Xiaojue Gong1, Liqi Shu2, Xian Zeng3, Huilong Duan3, Qinyu Luo1, Baihui Zhang1, Yaru Ji1, Xiaofeng Wang1, Qiang Shu1, Haomin Li4.   

Abstract

PURPOSE: We aimed to introduce an explainable machine learning technology to help clinicians understand the risk factors for neonatal postoperative mortality at different levels.
METHODS: A total of 1481 neonatal surgeries performed between May 2016 and December 2019 at a children's hospital were included in this study. Perioperative variables, including vital signs during surgery, were collected and used to predict postoperative mortality. Several widely used machine learning methods were trained and evaluated on split datasets. The model with the best performance was explained by SHAP (SHapley Additive exPlanations) at different levels.
RESULTS: The random forest model achieved the best performance with an area under the receiver operating characteristic curve of 0.72 in the validation set. TreeExplainer of SHAP was used to identify the risk factors for neonatal postoperative mortality. The explainable machine learning model not only explains the risk factors identified by traditional statistical analysis but also identifies additional risk factors. The visualization of feature contributions at different levels by SHAP makes the "black-box" machine learning model easily understood by clinicians and families. Based on this explanation, vital signs during surgery play an important role in eventual survival.
CONCLUSIONS: The explainable machine learning model not only exhibited good performance in predicting neonatal surgical mortality but also helped clinicians understand each risk factor and each individual case.
Copyright © 2021. Published by Elsevier Inc.

Entities:  

Keywords:  Machine learning; Neonatal surgery; Postoperative mortality

Year:  2021        PMID: 33863558     DOI: 10.1016/j.jpedsurg.2021.03.057

Source DB:  PubMed          Journal:  J Pediatr Surg        ISSN: 0022-3468            Impact factor:   2.545


  2 in total

1.  A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest.

Authors:  Mehrdad Rostami; Mourad Oussalah
Journal:  Inform Med Unlocked       Date:  2022-04-06

2.  Understanding the risk factors for adverse events during exchange transfusion in neonatal hyperbilirubinemia using explainable artificial intelligence.

Authors:  Shuzhen Zhu; Lianjuan Zhou; Yuqing Feng; Jihua Zhu; Qiang Shu; Haomin Li
Journal:  BMC Pediatr       Date:  2022-09-30       Impact factor: 2.567

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.