Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records

Background Cytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, predictive model be developed to evaluate risk of cytopenia during hospitalization in HIV Such crucial designing more individualized evidence-based strategy Method The present study was conducted were admitted Guangxi Chest Hospital between June 2016 October 2021. We extracted total 66 clinical features from records employed them train five prediction models (artificial neural network [ANN], adaptive boosting [AdaBoost], k-nearest neighbour [KNN] support vector [SVM], decision tree [DT]). tested using 20% data. performance evaluated indicators such as area under receiver operating characteristic curve (AUC). best interpreted shapley additive explanation (SHAP). Result ANN better power. According SHAP interpretation model, hypoproteinemia cancer most important hospitalized Meanwhile, lower hemoglobin-to-RDW ratio (HGB/RDW), low-density lipoprotein cholesterol (LDL-C) levels, CD4 + T cell counts, creatinine clearance (Ccr) levels increase Conclusion constructed with record information. rational management personalized plan setting.