No abstract

BACKGROUND Tuberculosis (TB) is a pandemic, being one of the top 10 causes of death and the main cause of death from a single source of infection. Drug-induced liver injury (DILI) is the most common and serious side effect during the treatment of TB. OBJECTIVE We aim to predict the status of liver injury in patients with TB at the clinical treatment stage. METHODS We designed an interpretable prediction model based on the XGBoost algorithm and identified the most robust and meaningful predictors of the risk of TB-DILI on the basis of clinical data extracted from the Hospital Information System of Shenzhen Nanshan Center for Chronic Disease Control from 2014 to 2019. RESULTS In total, 757 patients were included, and 287 (38%) had developed TB-DILI. Based on values of relative importance and area under the receiver operating characteristic curve, machine learning tools selected patients’ most recent alanine transaminase levels, average rate of change of patients’ last 2 measures of alanine transaminase levels, cumulative dose of pyrazinamide, and cumulative dose of ethambutol as the best predictors for assessing the risk of TB-DILI. In the validation data set, the model had a precision of 90%, recall of 74%, classification accuracy of 76%, and balanced error rate of 77% in predicting cases of TB-DILI. The area under the receiver operating characteristic curve score upon 10-fold cross-validation was 0.912 (95% CI 0.890-0.935). In addition, the model provided warnings of high risk for patients in advance of DILI onset for a median of 15 (IQR 7.3-27.5) days. CONCLUSIONS Our model shows high accuracy and interpretability in predicting cases of TB-DILI, which can provide useful information to clinicians to adjust the medication regimen and avoid more serious liver injury in patients.

Background: Autophagy can inhibit the survival of intracellular microorganisms including Mycobacterium tuberculosis ( Mtb ) , and the PI3K/AKT/mTOR pathway plays a crucial role. This study investigated the association between PI3K/AKT/mTOR pathway autophagy-related gene polymorphisms and pulmonary tuberculosis (PTB) susceptibility. Methods: KEGG pathway and gene ontology (GO) databases were searched for genes belonging to the PI3K/AKT/mTOR and autophagy pathways. Thirty SNPs in nine genes were identified and tested for their associations with tuberculosis in 130 patients with PTB and 271 controls. We constructed genetic risk scores (GRSs) and divided the participants into 3 subgroups based on their GRSs:0-5, 6-10, and 11-16. Results: This analysis revealed that the AKT1 (rs12432802), RPTOR (rs11654508, rs12602885, rs2090204, rs2589144, and rs2672897), and TSC2 (rs2074969) polymorphisms were significantly associated with PTB risk. A decreasing trend was observed ( P trend 0.020), in which a lower GRS was associated with a higher risk of PTB ([6-10] vs. [0-5]: OR (95%CI) 0.590 (0.374-0.931); [11-16] vs. [0-5]: OR (95%CI) 0.381 (0.160-0.906)). Conclusions: Polymorphisms in AKT1, RPTOR, and TSC2 may influence susceptibility to PTB.

BACKGROUND Treatment of pulmonary tuberculosis (TB) requires at least six months and is compromised by poor adherence. In the directly observed therapy (DOT) scheme recommended by the World Health Organization, the patient is directly observed taking their medications at a health post. An alternative to DOT is video-observed therapy (VOT), in which the patients take videos of themselves taking the medication and the video is uploaded into the app and reviewed by a health care worker. We developed a comprehensive TB management system by using VOT that is installed as an app on the smartphones of both patients and health care workers. It was implemented into the routine TB control program of the Nanshan District of Shenzhen, China. OBJECTIVE The aim of this study was to compare the effectiveness of VOT with that of DOT in managing the treatment of patients with pulmonary TB and to evaluate the acceptance of VOT for TB management by patients and health care workers. METHODS Patients beginning treatment between September 2017 and August 2018 were enrolled into the VOT group and their data were compared with the retrospective data of patients who began TB treatment and were managed with routine DOT between January 2016 and August 2017. Sociodemographic characteristics, clinical features, treatment adherence, positive findings of sputum smears, reporting of side effects, time and costs of transportation, and satisfaction were compared between the 2 treatment groups. The attitudes of the health care workers toward the VOT-based system were also analyzed. RESULTS This study included 158 patients in the retrospective DOT group and 235 patients in the VOT group. The VOT group showed a significantly higher fraction of doses observed (<i>P</i>&lt;.001), less missed observed doses (<i>P</i>&lt;.001), and fewer treatment discontinuations (<i>P</i>&lt;.05) than the DOT group. Over 79.1% (186/235) of the VOT patients had &gt;85% of their doses observed, while only 16.4% (26/158) of the DOT patients had &gt;85% of their doses observed. All patients were cured without recurrences. The VOT management required significantly (<i>P</i>&lt;.001) less median patient time (300 minutes vs 1240 minutes, respectively) and transportation costs (¥53 [US $7.57] vs ¥276 [US $39.43], respectively; <i>P</i>&lt;.001) than DOT. Significantly more patients (191/235, 81.3%) in the VOT group preferred their treatment method compared to those on DOT (37/131, 28.2%) (<i>P</i>&lt;.001), and 92% (61/66) of the health care workers thought that the VOT method was more convenient than DOT for managing patients with TB. CONCLUSIONS Implementation of the VOT-based system into the routine program of TB management was simple and it significantly increased patient adherence to their drug regimens. Our study shows that a comprehensive VOT-based TB management represents a viable and improved evolution of DOT.

UNSTRUCTURED Description: The corresponding author should be Shenyuan Liu. The 2 and 7 authors’ affiliation missing China. The 3-5 authors’ affiliation should be Department of Applied Biology and Chemical Technology, Hong Kong Polytechnic University, Hong Kong, China.