Explainable machine learning for early predicting treatment failure risk among patients with TB-diabetes comorbidity.

The present study aims to assess the treatment outcome of patients with diabetes and tuberculosis (TB-DM) at an early stage using machine learning (ML) based on electronic medical records (EMRs). A total of 429 patients were included at Chongqing Public Health Medical Center. The random-forest-based Boruta algorithm was employed to select the essential variables, and four models with a fivefold cross-validation scheme were used for modeling and model evaluation. Furthermore, we adopted SHapley additive explanations to interpret results from the tree-based model. 9 features out of 69 candidate features were chosen as predictors. Among these predictors, the type of resistance was the most important feature, followed by activated partial throm-boplastic time (APTT), thrombin time (TT), platelet distribution width (PDW), and prothrombin time (PT). All the models we established performed above an AUC 0.7 with good predictive performance. XGBoost, the optimal performing model, predicts the risk of treatment failure in the test set with an AUC 0.9281. This study suggests that machine learning approach (XGBoost) presented in this study identifies patients with TB-DM at higher risk of treatment failure at an early stage based on EMRs. The application of a convenient and economy EMRs based on machine learning provides new insight into TB-DM treatment strategies in low and middle-income countries.

Global, regional, and national burden of diet high in processed meat from 1990 to 2019: a systematic analysis from the global burden of disease study 2019.

Objective: The objective of this study is to explore the prevalence and attributable burden of diet high in processed meat (DHIPM) in global, regional, and national level due to the burden caused by unhealthy dietary pattern worldwide. Design: Cross-sectional study. Materials and design: All the data involved in this research were obtained from Global Burden of Diseases Study 2019. DisMod-MR 2.1, a Bayesian meta-regression tool, was used to estimate the prevalence, which was measured by summary exposure value (SEV) and attributable burden of DHIPM. The Spearman rank order correlation method was performed to measure the correlation between sociodemographic index (SDI) and the prevalence as well as attributable burden. The estimated annual percentage change (EAPC) was calculated to demonstrate the temporal trends. Results: Globally, there were 304.28 thousand deaths and 8556.88 disability-adjusted life years (DALYs) caused by DHIPM in 2019 and increased by 34.63 and 68.69%, respectively. The prevalence had decreased slightly from 1990 to 2019, however increased in most regions and countries, especially in middle SDI regions, despite the implicitly high prevalence in high SDI regions. Countries with higher SDI values were facing higher prevalence and attributable burden of DHIPM while developing countries were observed with severer temporal trends. Compared with women, men had suffered from lower exposure level however graver attributable burden of DHIPM in the past three decades. Conclusion: The progress of continuous urbanization allowed increasingly severe prevalence and attributable burden of DHIPM, thus the challenge to alleviate this trend was acute. Effective measures such as education on beneficial dietary pattern and supplement on healthy food were urgently required, especially in developing regions and countries.