Predictive model and risk analysis for coronary heart disease in people living with HIV using machine learning.

OBJECTIVE: This study aimed to construct a coronary heart disease (CHD) risk-prediction model in people living with human immunodeficiency virus (PLHIV) with the help of machine learning (ML) per electronic medical records (EMRs). METHODS: Sixty-one medical characteristics (including demography information, laboratory measurements, and complicating disease) readily available from EMRs were retained for clinical analysis. These characteristics further aided the development of prediction models by using seven ML algorithms [light gradient-boosting machine (LightGBM), support vector machine (SVM), eXtreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), decision tree, multilayer perceptron (MLP), and logistic regression]. The performance of this model was assessed using the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) was further applied to interpret the findings of the best-performing model. RESULTS: The LightGBM model exhibited the highest AUC (0.849; 95% CI, 0.814-0.883). Additionally, the SHAP plot per the LightGBM depicted that age, heart failure, hypertension, glucose, serum creatinine, indirect bilirubin, serum uric acid, and amylase can help identify PLHIV who were at a high or low risk of developing CHD. CONCLUSION: This study developed a CHD risk prediction model for PLHIV utilizing ML techniques and EMR data. The LightGBM model exhibited improved comprehensive performance and thus had higher reliability in assessing the risk predictors of CHD. Hence, it can potentially facilitate the development of clinical management techniques for PLHIV care in the era of EMRs.

Anemia and opportunistic infections in hospitalized people living with HIV: a retrospective study.

BACKGROUND: There is a high prevalence of anemia among people living with HIV in Guangxi, China. Therefore, we investigated anemia and opportunistic infections in hospitalized people living with HIV and explored the risk factors related to anemia in people living with HIV to actively prevent anemia in people living with HIV. METHODS: We retrospectively studied people living with HIV admitted to Guangxi Chest Hospital from June 2016 to October 2021. Detailed information on the sociodemographic and clinical features of the participants was collected. The X2 test was used to compare the prevalence between the anemic and non-anemic groups. The logistic regression analysis was applied to exclude confounding factors and identify factors related to anemia. RESULTS: Among 5645 patients with HIV, 1525 (27.02%) had anemia. The overall prevalence of mild, moderate, and severe anemia was 4.66%, 14.08%, and 8.27%, respectively. The factors significantly related to increased risk of anemia were CD4 count < 50 cells/µl (aOR = 2.221, 95% CI = [1.775, 2.779]), CD4 count 50-199 cells/µl (aOR = 1.659, 95% CI = [1.327, 2. 073]), female (aOR = 1.644, 95% CI = [1.436, 1.881]) co-infected with HCV (aOR = 1.465, 95% CI = [1.071, 2.002]), PM (aOR = 2.356, 95% CI = [1.950, 2.849]), or TB (aOR = 1.198, 95% CI = [1.053, 1.365]). CONCLUSIONS: Within Guangxi of China, 27.02% of hospitalized people living with HIV presented with anemia. Most patients with anemia were in the mild to moderate stage. The low CD4 count, female gender, and concomitant infection with Penicillium marneffei, Hepatitis C virus, or Tuberculosis were independent correlates of anemia. Thus, these findings would be helpful to clinicians in preventing and intervening in anemia in people living with HIV.

Mycobacterium tuberculosis co-infection is associated with increased surrogate marker of the HIV reservoir.

BACKGROUND: Tuberculosis (Tb) is the most frequent opportunistic infection among people living with HIV infection. The impact of Tb co-infection in the establishment and maintenance of the HIV reservoir is unclear. METHOD: We enrolled 13 HIV-infected patients with microbiologically confirmed Tb and 10 matched mono-HIV infected controls. Total HIV DNA in peripheral blood mononuclear cells (PBMCs), plasma interleukin-7 (IL-7) concentrations and the activities of indoleamine 2,3-dioxygenase (IDO) were measured for all the participants prior to therapy and after antiretroviral therapy (ART). RESULTS: After a duration of 16 (12, 22) months' ART, patients co-infected with Tb who were cured of Tb maintained higher levels of HIV DNA compared with mono-HIV infected patients [2.89 (2.65- 3.05) log10 copies/106 cells vs. 2.30 (2.11-2.84) log10 copies/106 cells, P = 0.008]. The levels of on-ART HIV DNA were positively correlated with the baseline viral load (r = 0.64, P = 0.02) in Tb co-infected group. However, neither plasma IL-7 concentration nor plasma IDO activity was correlated with the level of on-ART HIV DNA. CONCLUSIONS: Tb co-infection was associated with the increased surrogate marker of the HIV reservoir, while its mechanism warrants further examination.