Temporal trend of drug-resistant tuberculosis among Thai children during 2006-2021

Treatment outcomes among children and adolescents with extensively drug-resistant (XDR) and pre-XDR tuberculosis: Systematic review and meta-analysis

Extensively drug-resistant (XDR) and pre-XDR- tuberculosis (TB) account for approximately a third of pediatric MDR-TB cases globally. Clinical management is challenging; recommendations are based on limited evidence. We assessed the clinical outcomes for children and adolescents treated for XDR-and pre-XDR-TB. We performed a systematic review and meta-analysis of published studies reporting treatment outcomes for children and adolescents with XDR-and pre-XDR-TB. MEDLINE, EMBASE, Scopus, Web of Science, Google Scholar, and trial registries up to 31 December 2023 were searched. Eligible studies included children and adolescents aged <18 years with XDR-or pre-XDR-TB. The primary outcome was treatment success, defined as a composite of cure and treatment completion. Secondary outcomes were death, failure/ lost to follow-up and adverse events. We identified 34 population-based studies and 14 case studies, which reported treatment outcomes for a total of 656 patients. Treatment durations ranged from 6 to 27 months; follow-up after treatment completion ranged from 2 months to 4 years. The pooled estimate for treatment success in XDR-and pre-XDR-TB was 88·9% (95%CI: 59·7-100%) and 65·4% (95%CI: 27·7-100%), respectively. Drug adverse effects were reported in 56.4% (95%CI: 9.9-100%) and 68.2% (95%CI: 0-100%) of children respectively. Few childhood XDR- and pre-XDR-TB cases are reported. The relatively good treatment outcomes in children compared to adults may be partly due to publishing bias. Drug adverse effects are common.

Global prevalence and burden of multidrug-resistant tuberculosis from 1990 to 2019

BACKGROUND

Tuberculosis(TB) remains a pressing public health challenge, with multidrug-resistant tuberculosis (MDR-TB) emerging as a major threat. And healthcare authorities require reliable epidemiological evidence as a crucial reference to address this issue effectively. The aim was to offer a comprehensive epidemiological assessment of the global prevalence and burden of MDR-TB from 1990 to 2019.

METHODS

Estimates and 95% uncertainty intervals (UIs) for the age-standardized prevalence rate (ASPR), age-standardized incidence rate (ASIR), age-standardized disability-adjusted life years rate (ASR of DALYs), and age-standardized death rate (ASDR) of MDR-TB were obtained from the Global Burden of Disease (GBD) 2019 database. The prevalence and burden of MDR-TB in 2019 were illustrated in the population and regional distribution. Temporal trends were analyzed by using Joinpoint regression analysis to calculate the annual percentage change (APC), average annual percentage change (AAPC) and its 95% confidence interval(CI).

RESULTS

The estimates of the number of cases were 687,839(95% UIs: 365,512 to 1223,262), the ASPR were 8.26 per 100,000 (95%UIs: 4.61 to 15.20), the ASR of DALYs were 52.38 per 100,000 (95%UIs: 22.64 to 97.60) and the ASDR were 1.36 per 100,000 (95%UIs: 0.54 to 2.59) of MDR-TB at global in 2019. Substantial burden was observed in Africa and Southeast Asia. Males exhibited higher ASPR, ASR of DALYs, and ASDR than females across most age groups, with the burden of MDR-TB increasing with age. Additionally, significant increases were observed globally in the ASIR (AAPC = 5.8; 95%CI: 5.4 to 6.1; P < 0.001), ASPR (AAPC = 5.9; 95%CI: 5.4 to 6.4; P < 0.001), ASR of DALYs (AAPC = 4.6; 95%CI: 4.2 to 5.0; P < 0.001) and ASDR (AAPC = 4.4; 95%CI: 4.0 to 4.8; P < 0.001) of MDR-TB from 1990 to 2019.

CONCLUSIONS

This study underscored the persistent threat of drug-resistant tuberculosis to public health. It is imperative that countries and organizations worldwide take immediate and concerted action to implement measures aimed at significantly reducing the burden of TB.

Computer-aided diagnosis using embedded ensemble deep learning for multiclass drug-resistant tuberculosis classification

Introduction

This study aims to develop a web application, TB-DRD-CXR, for the categorization of tuberculosis (TB) patients into subgroups based on their level of drug resistance. The application utilizes an ensemble deep learning model that classifies TB strains into five subtypes: drug sensitive tuberculosis (DS-TB), drug resistant TB (DR-TB), multidrug-resistant TB (MDR-TB), pre-extensively drug-resistant TB (pre-XDR-TB), and extensively drug-resistant TB (XDR-TB).

Methods

The ensemble deep learning model employed in the TB-DRD-CXR web application incorporates novel fusion techniques, image segmentation, data augmentation, and various learning rate strategies. The performance of the proposed model is compared with state-of-the-art techniques and standard homogeneous CNN architectures documented in the literature.

Results

Computational results indicate that the suggested method outperforms existing methods reported in the literature, providing a 4.0%-33.9% increase in accuracy. Moreover, the proposed model demonstrates superior performance compared to standard CNN models, including DenseNet201, NASNetMobile, EfficientNetB7, EfficientNetV2B3, EfficientNetV2M, and ConvNeXtSmall, with accuracy improvements of 28.8%, 93.4%, 2.99%, 48.0%, 4.4%, and 7.6% respectively.

Conclusion

The TB-DRD-CXR web application was developed and tested with 33 medical staff. The computational results showed a high accuracy rate of 96.7%, time-based efficiency (ET) of 4.16 goals/minutes, and an overall relative efficiency (ORE) of 100%. The system usability scale (SUS) score of the proposed application is 96.7%, indicating user satisfaction and a likelihood of recommending the TB-DRD-CXR application to others based on previous literature.