What does this research mean for the field?

An AI-triaged, pooled molecular testing workflow embedded in routine health check-ups effectively identifies a substantial burden of asymptomatic tuberculosis in older adults that is missed by conventional symptom-based screening. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To evaluate the feasibility, diagnostic yield, and epidemiological value of combining AI-assisted chest X-ray triage with pooled molecular testing during routine health check-ups for community-dwelling older adults.

August 14, 2026BMC GeriatricsOpen Access

Active tuberculosis screening incorporated with AI-assisted chest X-ray among the elderly in community settings, a cross-sectional study in China

View Full Paper

Ask AI

Bookmark

Authors

CCChi Chen CCChi Chen QYQuanji Yu

Discussion

Member takes

Overview

Cross-sectional study finds AI-assisted chest X-ray screening detects high rates of asymptomatic tuberculosis in older adults, highlighting the value of routine symptom-agnostic active screening.

Key Points

To evaluate the feasibility, diagnostic yield, and epidemiological value of combining AI-assisted chest X-ray triage with pooled molecular testing during routine health check-ups for community-dwelling older adults.
Screened 14,312 community-dwelling older adults (aged ≥65 years) across 14 communities in Jiangsu Province, China, using symptom assessments and digital chest X-rays triaged by a convolutional neural network AI system.
Collected sputum specimens from 2,436 presumptive patients (2,309 AI-suspected and 127 symptomatic with normal X-rays) for molecular testing using an 8:1 pooling workflow via the Xpert MTB/RIF Ultra assay.
Identified 20 active pulmonary tuberculosis cases (16 microbiologically positive and 4 clinically diagnosed), all originating from the AI-suspected group and none from the symptomatic group with normal X-rays.
Observed an age- and sex-standardized tuberculosis prevalence of 154.5 per 100,000, significantly higher than the regional passive surveillance rate of 48.9 per 100,000 (P < 0.001).
Found that 70.0% (14/20) of confirmed cases were asymptomatic, with a median AI suspicion score of 0.89 (IQR: 0.83–0.95).

Cite This Study

Chen et al. (2026) studied this question.

synapsesocial.com/papers/6a7ec79cb70b84ec8b914255 https://doi.org/10.1186/s12877-026-08113-2

View Full Paper

Ask AI

Bookmark

August 14, 2026BMC GeriatricsOpen Access

Active tuberculosis screening incorporated with AI-assisted chest X-ray among the elderly in community settings, a cross-sectional study in China

View Full Paper

Ask AI

Bookmark

Authors

CCChi Chen CCChi Chen QYQuanji Yu

Discussion

Member takes

Overview

Cross-sectional study finds AI-assisted chest X-ray screening detects high rates of asymptomatic tuberculosis in older adults, highlighting the value of routine symptom-agnostic active screening.

Key Points

To evaluate the feasibility, diagnostic yield, and epidemiological value of combining AI-assisted chest X-ray triage with pooled molecular testing during routine health check-ups for community-dwelling older adults.
Screened 14,312 community-dwelling older adults (aged ≥65 years) across 14 communities in Jiangsu Province, China, using symptom assessments and digital chest X-rays triaged by a convolutional neural network AI system.
Collected sputum specimens from 2,436 presumptive patients (2,309 AI-suspected and 127 symptomatic with normal X-rays) for molecular testing using an 8:1 pooling workflow via the Xpert MTB/RIF Ultra assay.
Identified 20 active pulmonary tuberculosis cases (16 microbiologically positive and 4 clinically diagnosed), all originating from the AI-suspected group and none from the symptomatic group with normal X-rays.
Observed an age- and sex-standardized tuberculosis prevalence of 154.5 per 100,000, significantly higher than the regional passive surveillance rate of 48.9 per 100,000 (P < 0.001).
Found that 70.0% (14/20) of confirmed cases were asymptomatic, with a median AI suspicion score of 0.89 (IQR: 0.83–0.95).

Cite This Study

Chen et al. (2026) studied this question.

synapsesocial.com/papers/6a7ec79cb70b84ec8b914255 https://doi.org/10.1186/s12877-026-08113-2

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark