Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms

ObjectiveEarly assessment and intervention of Acquired Immune Deficiency Syndrome (AIDS) patients at high risk of mortality is critical. This study aims to develop an optimally performing mortality risk prediction model for AIDS patients with comorbid AIDS-related diseases or symptoms to facilitate...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiwei Chen, Kejun Pan, Xiaobo Lu, Erxiding Maimaiti, Maimaitiaili Wubuli
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Public Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpubh.2025.1544351/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228629528641536
author Yiwei Chen
Kejun Pan
Xiaobo Lu
Erxiding Maimaiti
Maimaitiaili Wubuli
author_facet Yiwei Chen
Kejun Pan
Xiaobo Lu
Erxiding Maimaiti
Maimaitiaili Wubuli
author_sort Yiwei Chen
collection DOAJ
description ObjectiveEarly assessment and intervention of Acquired Immune Deficiency Syndrome (AIDS) patients at high risk of mortality is critical. This study aims to develop an optimally performing mortality risk prediction model for AIDS patients with comorbid AIDS-related diseases or symptoms to facilitate early intervention.MethodsThe study included 478 first-time hospital-admitted AIDS patients with related diseases or symptoms. Eight predictors were screened using lasso regression, followed by building eight models and using SHAP values (Shapley’s additive explanatory values) to identify key features in the best models. The accuracy and discriminatory power of model predictions were assessed using variable importance plots, receiver operating characteristic curves, calibration curves, and confusion matrices. Clinical benefits were evaluated through decision-curve analyses, and validation was performed with an external set of 48 patients.ResultsLasso regression identified eight predictors, including hemoglobin, infection pathway, Sulfamethoxazole-Trimethoprim, expectoration, headache, persistent diarrhea, Pneumocystis jirovecii pneumonia, and bacterial pneumonia. The optimal model, XGBoost, yielded an Area Under Curve (AUC) of 0.832, a sensitivity of 0.703, and a specificity of 0.799 in the training set. In the test set, the AUC was 0.729, the sensitivity was 0.717, and the specificity was 0.636. In the external validation set, the AUC was 0.873, the sensitivity was 0.852, and the specificity was 0.762. Furthermore, the calibration curves showed a high degree of fit, and the DCA curves demonstrated the overall high clinical utility of the model.ConclusionIn this study, an XGBoost-based mortality risk prediction model is proposed, which can effectively predict the mortality risk of patients with co-morbid AIDS-related diseases or symptomatic AIDS, providing a new reference for clinical decision-making.
format Article
id doaj-art-93f64bea4fa24e8495fd0fdba3d09a71
institution OA Journals
issn 2296-2565
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Public Health
spelling doaj-art-93f64bea4fa24e8495fd0fdba3d09a712025-08-20T02:04:28ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-03-011310.3389/fpubh.2025.15443511544351Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptomsYiwei Chen0Kejun Pan1Xiaobo Lu2Erxiding Maimaiti3Maimaitiaili Wubuli4Department of Epidemiology and Health Statistics, School of Public Health, Xinjiang Medical University, Urumqi, Xinjiang, ChinaDepartment of Infectious Diseases, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, ChinaDepartment of Infectious Diseases, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Xinjiang Medical University, Urumqi, Xinjiang, ChinaDepartment of Infectious Diseases, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, ChinaObjectiveEarly assessment and intervention of Acquired Immune Deficiency Syndrome (AIDS) patients at high risk of mortality is critical. This study aims to develop an optimally performing mortality risk prediction model for AIDS patients with comorbid AIDS-related diseases or symptoms to facilitate early intervention.MethodsThe study included 478 first-time hospital-admitted AIDS patients with related diseases or symptoms. Eight predictors were screened using lasso regression, followed by building eight models and using SHAP values (Shapley’s additive explanatory values) to identify key features in the best models. The accuracy and discriminatory power of model predictions were assessed using variable importance plots, receiver operating characteristic curves, calibration curves, and confusion matrices. Clinical benefits were evaluated through decision-curve analyses, and validation was performed with an external set of 48 patients.ResultsLasso regression identified eight predictors, including hemoglobin, infection pathway, Sulfamethoxazole-Trimethoprim, expectoration, headache, persistent diarrhea, Pneumocystis jirovecii pneumonia, and bacterial pneumonia. The optimal model, XGBoost, yielded an Area Under Curve (AUC) of 0.832, a sensitivity of 0.703, and a specificity of 0.799 in the training set. In the test set, the AUC was 0.729, the sensitivity was 0.717, and the specificity was 0.636. In the external validation set, the AUC was 0.873, the sensitivity was 0.852, and the specificity was 0.762. Furthermore, the calibration curves showed a high degree of fit, and the DCA curves demonstrated the overall high clinical utility of the model.ConclusionIn this study, an XGBoost-based mortality risk prediction model is proposed, which can effectively predict the mortality risk of patients with co-morbid AIDS-related diseases or symptomatic AIDS, providing a new reference for clinical decision-making.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1544351/fullmachine learningXGBoostAIDSHIVprediction model
spellingShingle Yiwei Chen
Kejun Pan
Xiaobo Lu
Erxiding Maimaiti
Maimaitiaili Wubuli
Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms
Frontiers in Public Health
machine learning
XGBoost
AIDS
HIV
prediction model
title Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms
title_full Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms
title_fullStr Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms
title_full_unstemmed Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms
title_short Machine learning-based prediction of mortality risk in AIDS patients with comorbid common AIDS-related diseases or symptoms
title_sort machine learning based prediction of mortality risk in aids patients with comorbid common aids related diseases or symptoms
topic machine learning
XGBoost
AIDS
HIV
prediction model
url https://www.frontiersin.org/articles/10.3389/fpubh.2025.1544351/full
work_keys_str_mv AT yiweichen machinelearningbasedpredictionofmortalityriskinaidspatientswithcomorbidcommonaidsrelateddiseasesorsymptoms
AT kejunpan machinelearningbasedpredictionofmortalityriskinaidspatientswithcomorbidcommonaidsrelateddiseasesorsymptoms
AT xiaobolu machinelearningbasedpredictionofmortalityriskinaidspatientswithcomorbidcommonaidsrelateddiseasesorsymptoms
AT erxidingmaimaiti machinelearningbasedpredictionofmortalityriskinaidspatientswithcomorbidcommonaidsrelateddiseasesorsymptoms
AT maimaitiailiwubuli machinelearningbasedpredictionofmortalityriskinaidspatientswithcomorbidcommonaidsrelateddiseasesorsymptoms