Machine learning-based in-hospital mortality prediction of HIV/AIDS patients with Talaromyces marneffei infection in Guangxi, China

Abstract

Objective Talaromycosis is a serious regional disease endemic in Southeast Asia. In China, Talaromyces marneffei (T. marneffei) infections is mainly concentrated in the southern region, especially in Guangxi, and cause considerable in-hospital mortality in HIV-infected individuals. Currently, the factors that influence in-hospital death of HIV/AIDS patients with T. marneffei infection are not completely clear. Existing machine learning techniques can be used to develop a predictive model to identify relevant prognostic factors to predict death and appears to be essential to reducing in-hospital mortality. Methods We prospectively enrolled HIV/AIDS patients with talaromycosis in the Fourth People’s Hospital of Nanning, Guangxi, from January 2012 to June 2019. Clinical features were selected and used to train four different machine learning models (logistic regression, XGBoost, KNN, and SVM) to predict the treatment outcome of hospitalized patients, and 30% internal validation was used to evaluate the performance of models. Machine learning model performance was assessed according to a range of learning metrics, including area under the receiver operating characteristic curve (AUC). The SHapley Additive exPlanations (SHAP) tool was used to explain the model. Results A total of 1927 HIV/AIDS patients with T. marneffei infection were included. The average in-hospital mortality rate was 13.3% (256/1927) from 2012 to 2019. The most common complications/coinfections were pneumonia (68.9%), followed by oral candida (47.5%), and tuberculosis (40.6%). Deceased patients showed higher CD4/CD8 ratios, aspartate aminotransferase (AST) levels, creatinine levels, urea levels, uric acid (UA) levels, lactate dehydrogenase (LDH) levels, total bilirubin levels, creatine kinase levels, white blood-cell counts (WBC) counts, neutrophil counts, procaicltonin levels and C-reactive protein (CRP) levels and lower CD3+ T-cell count, CD8+ T-cell count, and lymphocyte counts, platelet (PLT), high-density lipoprotein cholesterol (HDL), hemoglobin (Hb) levels than those of surviving patients. The predictive XGBoost model exhibited 0.71 sensitivity, 0.99 specificity, and 0.97 AUC in the training dataset, and our outcome prediction model provided robust discrimination in the testing dataset, showing an AUC of 0.90 with 0.69 sensitivity and 0.96 specificity. The other three models were ruled out due to poor performance. Septic shock and respiratory failure were the most important predictive features, followed by uric acid, urea, platelets, and the AST/ALT ratios. Conclusion The XGBoost machine learning model is a good predictor in the hospitalization outcome of HIV/AIDS patients with T. marneffei infection. The model may have potential application in mortality prediction and high-risk factor identification in the talaromycosis population.

Characteristics of Talaromyces marneffei infection associated with inborn errors of immunity

“…Multiple studies had demonstrated that respiratory failure, shock, high urea levels, and signi cantly lower PLT are predictive of poor outcomes and prognosis in HIV patients with talaromycosis. In deceased patients, AST/ALT rate was 3.07, which is signi cantly higher than that in survivors (1.96) [21]. Similar ndings were present in Histoplasma, with signi cantly higher AST/ALT than in other localized lung diseases.…”

“…Six deceased patients (6/7) had signi cantly elevated CD4 + /CD8 + T cell ratios, 11 survivors (11/32) exhibited elevated CD4 + /CD8 + T cell ratios, and the rest (21/32)were reduced or normal. Therefore, immunological pro ling of talaromycosis patients should not be limited to CD4 + T cell counts but rather should comprehensively measure CD4 + T cells, CD8 + T cells, and the CD4 + /CD8 + ratio [16,21]. Follow up data for of AST, ALT, and other tests were lacking in IEI patients, and the relationship between IEI and hepatic injury in the context of talaromycosis needs to be further studied.…”

Population pharmacokinetics of voriconazole and initial dosage optimization in patients with talaromycosis

“…C-reactive protein is an acute protein mainly produced by hepatocytes that increase dramatically in response to injury, infection, and inflammation, which plasma level can reflect the severity of inflammation ( Sproston and Ashworth, 2018 ). Invasive T. marneffei infection can cause multiple organ damage and CRP is significantly increased in patients with poor prognosis ( Sun et al, 2021 ; Shi et al, 2022 ). Studies have shown that drug-metabolizing enzymes, including cytochrome P450 (CYP) isoenzymes, are decreased at the transcriptional levels during infection or inflammation, which leading to reduce the metabolism of VRC ( Renton, 2004 ; Aitken and Morgan, 2007 ; van Wanrooy et al, 2014 ; Encalada Ventura et al, 2015 ; Veringa et al, 2017 ).…”

Disseminated Talaromyces marneffei infection after renal transplantation: A case report and literature review

“…This pathogen grows in the filamentous form at 25°C and in the yeast form at 37°C. It is mainly prevalent in Southeast Asia and South China ( Ying et al., 2020 ; Sun et al., 2021 ; Li et al., 2022 ; Shi et al., 2022 ), with a mortality rate of up to one-third ( Narayanasamy et al., 2021 ). In recent years, along with an increase in the frequency of organ transplantation, T. marneffei infections have been increasingly reported, and the affected area has a tendency to expand ( He et al., 2021 ; Shen et al., 2022 ).…”