+ HEALTH Interstitial lung disease (IRD-ILD) is a significant cause of morbidity and mortality in patients with inflam…± HEALTH Artificial intelligence (AI) is increasingly being integrated into oncology for applications including cancer…± HEALTH Prostate magnetic resonance imaging (MRI) reporting is a high-impact communication task because small differe…+ HEALTH To investigate the clinical performance of a novel deep-learning based image reconstruction algorithm, namely…+ HEALTH Spinal cord injury (SCI) is a serious medical condition. Spinal Cord Injury limits the movement of the body,…+ HEALTH PURPOSE: To develop a deep learning model for the preoperative, non-invasive identification of germinomas in…+ HEALTH Diabetic Retinopathy (DR) is a vision-threatening complication in diabetic patients. It harms retinal vessels…+ CLIMATE This study evaluates an innovative field-scale targeted sampling strategy within a regional hybrid spatial pr…
TruaceTracing the truth around AITuesday, August 18, 2026
Subscribe
Health·The Trace·Dual reading·Published 2026-08-18

AI/ML models predicting tuberculosis treatment failure

Source article: Artificial Intelligence and Machine Learning-based prediction of tuberculosis treatment failure: A systematic review and meta-analysis

Abstract: Tuberculosis (TB) remains a leading cause of infectious disease mortality worldwide, and treatment failure contributes to ongoing transmission, drug resistance, and poor clinical outcomes. Artificial intelligence (AI) and machine learning (ML) approaches have attracted growing interest in predicting TB treatment outcomes, but the literature is heterogeneous and lacks a comprehensive synthesis. We systematically searched PubMed/MEDLINE and Embase (January 2000-October 2025) for studies developing or validating AI…

TRV-2026-0817Peer-reviewedPermanent record — cite & verify
Trace impact reading

Contested: both sides are scored from claims and sources, not community votes.

P 75The P score combines the specificity and measured human impact of the grounded problem claim with the strength of this Trace’s cited sources.G 74The G score combines the specificity and measured human impact of the grounded gain claim with the strength of this Trace’s cited sources.
Artificial Intelligence and Machine Learning-based prediction of tuberculosis treatment failure: A systematic review and meta-analysis

Granada - Hospital Doctor Olóriz 2 by Zarateman. CC0 · http://creativecommons.org/publicdomain/zero/1.0/deed.en

The quick read

By August 2026, a systematic review and meta-analysis of 34 studies evaluated AI and machine learning models to predict tuberculosis treatment failure. Nineteen studies with 100,790 participants were pooled, yielding an AUC of 0.836 with high heterogeneity, with tree-based and multimodal approaches common and most publications appearing after 2019.

The findings matter because treatment failure drives transmission and drug resistance, yet the review found only 23.5% of studies had external validation and 2.9% were low risk of bias, with lower performance in HIV-positive groups and evidence of publication bias. This leaves uncertainty about calibration, generalizability to high-burden and pediatric populations, and readiness for clinical deployment.

Main points
  • Systematic review included 34 studies from 2000-2025, with 91% published from 2019 onwards.
  • Tree-based methods predominated at 52.9% and multimodal models using >=3 data types were used in 41.2% of studies.
  • Subgroup analysis found lower discrimination when HIV-positive participants were included, AUC 0.748 versus 0.924 when excluded.
Gain

Meta-analysis of 19 studies with 100,790 participants found AI/ML models achieved pooled discrimination of 0.836 for predicting tuberculosis treatment failure.

Problem

Most models lacked external validation, only one was low risk of bias, publication bias was detected, and performance dropped in HIV-positive populations, leaving models not ready for routine clinical implementation.

The rundown

The review searched PubMed/MEDLINE and Embase from January 2000 to October 2025 and registered as PROSPERO CRD420251101443. Two reviewers extracted AUC, sensitivity, specificity and confidence intervals, estimating missing standard errors from sample sizes and event rates, and assessed bias with PROBAST.

Nineteen studies contributed to random-effects meta-analysis. Authors reported funnel plots, Egger's test, trim-and-fill, subgroup analyses and meta-regression to explore heterogeneity, and identified gaps including high-burden countries, social determinants, pediatric TB and extrapulmonary disease.

Sources

Reader signal

How should this claim be treated?

The debate