Guangxi-ASEAN Collaborative Innovation Center for Major Disease Prevention and Treatment, Life Sciences Institute, Guangxi Medical University, Nanning, 530021, China.
Joint Laboratory for Emerging Infectious Diseases in China (Guangxi)-ASEAN, Life Sciences Institute, Guangxi Medical University, Nanning, Guangxi, 530021, China.
BMC Infect Dis. 2024 Oct 8;24(1):1121. doi: 10.1186/s12879-024-10013-y.
To develop and validate a machine learning model for predicting mortality-associated prognostic factors in order to reduce in-hospital mortality rates among HIV/AIDS patients with Cryptococcus infection in Guangxi, China.
This retrospective prognostic study included HIV/AIDS patients with cryptococcosis in the Fourth People's Hospital of Nanning from October 2011 to June 2019. Clinical features were extracted and used to train ten machine learning models, including Logistic Regression, KNN, DT, RF, Adaboost, Xgboost, LightGBM, Catboost, SVM, and NBM, to predict the outcome of HIV patients with cryptococcosis infection. The sensitivity, specificity, AUC, and F1 value were applied to assess model performance in both the testing and training sets. The optimal model was selected and interpreted.
A total of 396 patients were included in the study. The average in-hospital mortality of HIV/AIDS patients with cryptococcosis was 12.9% from 2012 to 2019. After feature screening, 20 clinical features were selected for model construction, accounting for 93.8%, including ART, Electrolyte disorder, Anemia, and 17 laboratory tests. The RF model (AUC 0.9787, Sensitivity 0.9535, Specificity 0.8889, F1 0.7455) and the SVM model (AUC 0.9286, Sensitivity 0.7907, Specificity 0.9786, F1 0.8293) had excellent performance. The SHAP analysis showed that the primary risk factors for prognosis prediction were identified as BUN/CREA, Electrolyte disorder, NEUT%, Urea, and IBIL.
RF and SVM machine learning models have shown promising predictive abilities for the prognosis of hospitalized HIV/AIDS patients with cryptococcosis, which can aid clinical assessment and treatment decisions for patient prognosis.
开发和验证一种机器学习模型，用于预测与死亡率相关的预后因素，以降低中国广西 HIV/AIDS 合并隐球菌感染患者的住院死亡率。
本回顾性预后研究纳入了 2011 年 10 月至 2019 年 6 月在南宁市第四人民医院住院的 HIV 合并隐球菌感染患者。提取临床特征并用于训练 10 种机器学习模型，包括 Logistic 回归、KNN、DT、RF、Adaboost、Xgboost、LightGBM、Catboost、SVM 和 NBM，以预测 HIV 合并隐球菌感染患者的结局。在测试集和训练集中应用灵敏度、特异度、AUC 和 F1 值评估模型性能。选择并解释最佳模型。
本研究共纳入 396 例患者。2012 年至 2019 年，HIV/AIDS 合并隐球菌感染患者的住院死亡率平均为 12.9%。经过特征筛选，选择了 20 个临床特征用于模型构建，占 93.8%，包括 ART、电解质紊乱、贫血和 17 项实验室检查。RF 模型（AUC 0.9787、灵敏度 0.9535、特异度 0.8889、F1 0.7455）和 SVM 模型（AUC 0.9286、灵敏度 0.7907、特异度 0.9786、F1 0.8293）具有优异的性能。SHAP 分析表明，预测预后的主要危险因素是 BUN/CREA、电解质紊乱、NEUT%、尿素和 IBIL。
RF 和 SVM 机器学习模型对住院 HIV/AIDS 合并隐球菌感染患者的预后具有良好的预测能力，可以辅助临床评估和治疗决策。
