Deep learning of point-of-care lung ultrasound and clinical data for pulmonary tuberculosis triage in Uganda

Rationale: Point of care lung ultrasound is portable and radiation free and could extend tuberculosis screening to settings without chest radiography, but no standardized criteria exist for interpreting it for tuberculosis. Objectives: To develop and internally evaluate deep learning models that classify pulmonary tuberculosis from lung ultrasound images, alone and combined with routine clinical variables, and to derive an abbreviated scanning protocol. Methods: In a prospective study in Kampala, Uganda (2023 to 2025), we enrolled people aged 13 years or older with microbiologically confirmed pulmonary tuberculosis, their household contacts, and symptomatic people with other respiratory conditions. One still frame from each of 12 lung ultrasound zones was analyzed with an attention-based multiple-instance learning network. We compared clinical-only (random forest), ultrasound only, and combined models and derived a 6 zone protocol from training set attention weights. Participants were allocated to training (n = 223), validation (n = 20), and held-out test (n = 73) sets. Results: Of 318 enrolled participants, 316 were analyzed (118 with and 198 without tuberculosis). In the test set, areas under the receiver operating characteristic curve were 0.88 (95% confidence interval, 0.80 to 0.95) for the clinical-only model; 0.93 (0.86 to 0.97) and 0.95 (0.89 to 0.99) for the 12 zone ultrasound-only and combined models; and 0.91 (0.83 to 0.97) and 0.93 (0.86 to 0.99) for the corresponding 6-zone models. At 90% sensitivity, specificity was 82.2% (34.9 to 97.8) for the 12-zone combined model and 91.1% (25.0 to 98.0) for the 6-zone combined model. Point estimates for all 12-zone models and the 6-zone combined model met the 2025 World Health Organization minimum accuracy targets for a high-sensitivity screening test (≥90% sensitivity, ≥60% specificity). Conclusion: Lung ultrasound analyzed with attention-based deep learning and combined with clinical variables showed high internal discrimination for pulmonary tuberculosis, and a simplified 6-zone protocol retained most of this performance. External validation in intended-use screening populations is needed

Authors

Institutions

Publication Details

Journal
medRxiv
Published
2026-11-17
DOI
https://doi.org/10.64898/2026.11.14.26368125
Primary Topic
Ultrasound in Clinical Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Deep learning of point-of-care lung ultrasound and clinical data for pulmonary tuberculosis triage in Uganda

Keith P. Guevarra, Yingda Linda Xie, Eva Nabawanuka, Anant Madabhushi et al.
4 links
medRxiv
Ultrasound in Clinical Applications
preprint

Deep learning of point-of-care lung ultrasound and clinical data for pulmonary tuberculosis triage in Uganda

Keith P. Guevarra, Yingda Linda Xie, Eva Nabawanuka, Anant Madabhushi, Rohan Dhamdhere, Elena Jovanovska Janeva, Moses Lutaakome Joloba, Jerrold J. Ellner, Lydia Nakiyingi, Raphael Shankman, Wycliff Nate, Guadalupe Astorga, Akanksha Sharma
preprint en

Abstract

Rationale: Point of care lung ultrasound is portable and radiation free and could extend tuberculosis screening to settings without chest radiography, but no standardized criteria exist for interpreting it for tuberculosis. Objectives: To develop and internally evaluate deep learning models that classify pulmonary tuberculosis from lung ultrasound images, alone and combined with routine clinical variables, and to derive an abbreviated scanning protocol. Methods: In a prospective study in Kampala, Uganda (2023 to 2025), we enrolled people aged 13 years or older with microbiologically confirmed pulmonary tuberculosis, their household contacts, and symptomatic people with other respiratory conditions. One still frame from each of 12 lung ultrasound zones was analyzed with an attention-based multiple-instance learning network. We compared clinical-only (random forest), ultrasound only, and combined models and derived a 6 zone protocol from training set attention weights. Participants were allocated to training (n = 223), validation (n = 20), and held-out test (n = 73) sets. Results: Of 318 enrolled participants, 316 were analyzed (118 with and 198 without tuberculosis). In the test set, areas under the receiver operating characteristic curve were 0.88 (95% confidence interval, 0.80 to 0.95) for the clinical-only model; 0.93 (0.86 to 0.97) and 0.95 (0.89 to 0.99) for the 12 zone ultrasound-only and combined models; and 0.91 (0.83 to 0.97) and 0.93 (0.86 to 0.99) for the corresponding 6-zone models. At 90% sensitivity, specificity was 82.2% (34.9 to 97.8) for the 12-zone combined model and 91.1% (25.0 to 98.0) for the 6-zone combined model. Point estimates for all 12-zone models and the 6-zone combined model met the 2025 World Health Organization minimum accuracy targets for a high-sensitivity screening test (≥90% sensitivity, ≥60% specificity). Conclusion: Lung ultrasound analyzed with attention-based deep learning and combined with clinical variables showed high internal discrimination for pulmonary tuberculosis, and a simplified 6-zone protocol retained most of this performance. External validation in intended-use screening populations is needed

medRxiv
Rutgers, The State University of New Jersey (US), Georgia Institute of Technology (US), Emory University (US), Mulago Hospital (UG), Infectious Diseases Institute (UG), Rutgers New Jersey Medical School (US), Makerere University (UG)
Good health and well-being
Ultrasound in Clinical Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon