Brazil
August 1, 2022
BrainRobotics Prosthetic Hand
August 1, 2022Article of the Month – August 2022
An interpretable mortality prediction model for COVID-19 patients.
Yan, Li; Zhang, Hai-Tao; Goncalves, Jorge; Xiao, Yang; Wang, Maolin; Guo, Yuqi; Sun, Chuan; Tang, Xiuchuan; Jing, Liang; Zhang, Mingyang; Huang, Xiang; Xiao, Ying; Cao, Haosen; Chen, Yanyan; Ren, Tongxin; Wang, Fang; Xiao, Yaru; Huang, Sufang; Tan, Xi; Huang, Niannian; Jiao, Bo; Cheng, Cheng; Zhang, Yong; Luo, Ailin; Mombaerts, Laurent; Jin, Junyang; Cao, Zhiguo; Li, Shusheng; Xu, Hui; Yuan, Ye.
Importance
The sudden increase in COVID-19 cases puts high pressure on healthcare services worldwide. At this stage, a fast, accurate and early clinical assessment of the disease severity is vital.
Objectives
This article suggests a simple and operable decision rule to quickly predict patients at the highest risk, allowing them to be prioritized and potentially reducing the mortality rate.
Design, Settings and Participants
To support decision-making and logistical planning in healthcare systems, this study leverages a database of blood samples from 485 infected patients in the region of Wuhan, China, to identify crucial predictive biomarkers of disease mortality. For this purpose, machine learning tools selected three biomarkers that predict the mortality of individual patients more than 10 days in advance with more than 90% accuracy: lactic dehydrogenase (LDH), lymphocyte, and high-sensitivity C-reactive protein (hs-CRP). Relatively high levels of LDH alone seem to play a crucial role in distinguishing most cases that require immediate medical attention.
Interventions
This study uses a supervised XGBoost classifier8 as the predictor model. XGBoost is a high-performance machine learning algorithm that benefits from great interpretability potential due to its recursive tree-based decision system. The importance of each individual feature in XGBoost is determined by its accumulated use in each decision step in trees. This computes a metric characterizing the relative importance of each feature, which is particularly valuable to estimate features that are the most discriminative of model outcomes, especially when they are related to meaningful clinical parameters.
Results and Conclusions
This study has identified three indicators (LDH, hs-CRP, and lymphocytes), together with a clinical route, for COVID-19 prognostic prediction. We have developed an XGBoost machine learning-based model that can predict the mortality rates of patients more than 10 days in advance with more than 90% accuracy, enabling detection, early intervention, and potentially a reduction of mortality in patients with COVID-19.
Relevance to Healthcare Field
Ever since it was identified in Wuhan, China, in December 2019, the COVID-19 pandemic has persisted as a serious global health threat. The XGBoost machine learning-based model offers some hope to a world left searching to understand this virus while at a deficit for healthcare resources. The three indicators identified in this study show great promise in helping determine a patient’s prognosis at a high accuracy, which will help for patient admittance and referral in a clinical setting. This is an ever-evolving study. While the original article was published on May 14, 2020, it remains current as of August 2021.