Machine learning-based survival analysis approaches for predicting the risk of pneumonia post-stroke discharge.

BACKGROUND: Post-stroke pneumonia (PSP) is common among stroke patients. PSP occurring after hospital discharge continues to increase the risk of poor functional outcomes and death among stroke survivors. Currently, there is no prediction model specifically designed to predict the occurrence of PSP beyond the acute stage of stroke. This study aimed to explore the use of machine learning (ML) methods in predicting the risk of PSP after hospital discharge. METHODS: This study analyzed data from 5,754 hospitalized stroke patients. The dataset was randomly divided into a training set and a holdout test set, with a ratio of 80:20. Several clinical and laboratory variables were utilized as predictors and different ML algorithms were employed to model time-to-event data. The ML model's predictive performance was compared to existing risk-scoring systems. A model-agnostic method based on Shapley additive explanations was utilized to interpret the ML model. RESULTS: The study found that 5.7% of the study patients experienced pneumonia within one year after discharge. Based on repeated 5-fold cross-validation on the training set, the random survival forest (RSF) model had the highest C-index among the various ML algorithms and traditional Cox regression analysis. The final RSF model achieved a C-index of 0.787 (95% confidence interval: 0.737-0.840) on the holdout test set, outperforming five existing risk-scoring systems. The top three important predictors were the Glasgow Coma Scale score, age, and length of hospital stay. CONCLUSIONS: The RSF model demonstrated superior discriminative ability compared to other ML algorithms and traditional Cox regression analysis, suggesting a non-linear relationship between predictors and outcomes. The developed ML model can be integrated into the hospital information system to provide personalized risk assessments.

Promoter methylation and increased expression of PD-L1 in patients with active tuberculosis.

The PD-1/PD-L1 pathway plays a pivotal role in T cell activity and is involved in the pathophysiology of Mycobacterium tuberculosis (MTB) infection. DNA methylation is a mechanism that modulates PD-L1 expression in cancer cells. However, its effect on PD-L1 expression in macrophages after MTB infection remains unknown. We prospectively enrolled patients with active tuberculosis (TB) and non-TB subjects. The expression of PD-L1 and methylation-related genes in peripheral blood mononuclear cells (PBMCs) were investigated and their correlation with disease severity and treatment outcomes were examined. PD-L1 promoter methylation status was evaluated using bisulfite sequencing. Immunohistochemistry (IHC) and immunofluorescence (IF) staining were used to visualize PD-L1- and TET-1-expressing cells in lung tissues from patients with TB and in macrophage cell lines with MTB-related stimulation. In total, 80 patients with active TB and 40 non-TB subjects were enrolled in the analysis. Patients with active TB had significantly higher expression of PD-L1, DNMT3b, TET1, TET2, and lower expression of DNMT1, compared to that in the non-TB subjects. The expression of PD-L1 and TET-1 was significantly associated with 1-month smear and culture non-conversion. IHC and IF staining demonstrated the co-localization of PD-L1- and TET-1-expressing macrophages in patients with pulmonary TB and in human macrophage cell lines after MTB-related stimulation. DNMT inhibition and TET-1 knockdown in human macrophages increased and decreased PD-L1 expression, respectively. Overall, PD-L1 expression is increased in patients with active TB and is correlated with treatment outcomes. DNA methylation is involved in modulating PD-L1 expression in human macrophages.