Machine learning-driven in-hospital mortality prediction in HIV/AIDS patients with Cytomegalovirus infection: a single-centred retrospective study
Journal of Medical Microbiology · 2024
DOI: 10.1099/jmm.0.001935 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medical Microbiology, 2024. Verfasst von Shiyi Lai und 14 weiteren Autor:innen. Beteiligte Einrichtung: Guangxi Key Laboratory of AIDS Prevention and Treatment, School of Public Health, Guangxi Medical University, Nanning, Guangxi, PR China. Hauptthemen laut MEDLINE: Cytomegalovirus Infections, Machine Learning, Hospital Mortality, HIV Infections. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Guangxi Medical University Training Program for Young Leading Talents(to Junjun Jiang).
Abstract (Originalsprache)
Introduction
Cytomegalovirus ( CMV ) is a widely disseminated betaherpesvirus that typically induces latant infections. In immunocompromised populations, especially transplant and HIV-infected patients, CMV infection increases in-hospital mortality. Gap statement. Although machine learning models have been widely used in clinical diagnosis and prognosis prediction, reports on machine learning model predictions for the in-hospital mortality of HIV/AIDS patients with CMV infection have not been reported.
Aim
Analyze the general gemographic and clinical characteristics of HIV/AIDS patients with CMV infection and identify the factors affecting the prognosis of this population, which will help to reduce their in-hospital mortality.
Methods
Hospitalized HIV/AIDS patients with CMV infection were recruited from the Fourth People’s Hospital of Nanning, Guangxi, from 2012 to 2019. After dividing them into survival and death groups based on their in-hospital survival status, their general and clinical profiles were described. Following 1 : 3 propensity score matching to equalize baseline characteristics, three machine-learning models (Random Forest, Support Vector Machine and eXtreme Gradient Boosting) were deployed to forecast factors influencing prognosis. The SHapley Additive exPlanations tool explained the models.
Results
A total of 1102 HIV/AIDS patients with CMV infection were analysed. There was no statistical difference in the general condition of the study subjects ( P >0.05). Prevalent complications/coinfections included pneumonia (63.6%), tuberculosis (47.2%) and oral fungal infections (44.6%). There were significant differences between the groups in pneumonia, cryptococcosis and hypoproteinaemia ( P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Guangxi Key Laboratory of AIDS Prevention and Treatment, School of Public Health, Guangxi Medical University, Nanning, Guangxi, PR China.
- Joint Laboratory for Emerging Infectious Diseases in China (Guangxi)-ASEAN, Life Sciences Institute, Guangxi Medical University, Nanning, Guangxi, PR China.
- The Fourth People's Hospital of Nanning, Nanning, Guangxi, PR China.
Förderung
- Guangxi Medical University Training Program for Young Leading Talents(to Junjun Jiang)
Zitieren
APA
Lai, S., Wei, W., Yang, S., Wu, Y., Shi, M., Meng, S., Tao, X., Chen, S., Chen, R., Su, J., Yuan, Z., Ye, L., Liang, H., Xie, Z., & Jiang, J. (2024). Machine learning-driven in-hospital mortality prediction in HIV/AIDS patients with Cytomegalovirus infection: a single-centred retrospective study. Journal of Medical Microbiology. https://doi.org/10.1099/jmm.0.001935
Vancouver
Lai S, Wei W, Yang S, Wu Y, Shi M, Meng S, et al. Machine learning-driven in-hospital mortality prediction in HIV/AIDS patients with Cytomegalovirus infection: a single-centred retrospective study. Journal of Medical Microbiology. 2024. doi:10.1099/jmm.0.001935
BibTeX
@article{Lai2024,
author = {Lai, Shiyi and Wei, Wudi and Yang, Shixiong and Wu, Yuting and Shi, Minjuan and Meng, Sirun and Tao, Xing and Chen, Shanshan and Chen, Rongfeng and Su, Jinming and Yuan, Zongxiang and Ye, Li and Liang, Hao and Xie, Zhiman and Jiang, Junjun},
title = {Machine learning-driven in-hospital mortality prediction in HIV/AIDS patients with Cytomegalovirus infection: a single-centred retrospective study},
journal = {Journal of Medical Microbiology},
year = {2024},
doi = {10.1099/jmm.0.001935}
}
EUVIMED