Validation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda

dc.contributor.authorTumwesigye, Habert
dc.contributor.authorAtwine, Daniel
dc.contributor.authorAtwine, Raymond
dc.contributor.authorBirungi, Abraham
dc.contributor.authorBirungi, Caroline
dc.contributor.authorMunguciada, Esther
dc.contributor.authorNabimanya, Phionah
dc.contributor.authorAkandwanaho, Joseph
dc.contributor.authorOchama, Benard
dc.contributor.authorMitala, Yekosani
dc.date.accessioned2026-11-18T08:21:34Z
dc.date.issued2026-10-15
dc.description.abstractBackground: Ziehl–Neelsen (ZN) sputum smear microscopy remains an accessible method for detecting acid-fast bacilli (AFB), but its interpretation is dependent on specimen quality and trained microscopy personnel. Artificial intelligence (AI) may provide a microscopy reading aid that supports consistent identification of AFB-positive and AFB-negative smear images. Objective: To evaluate transfer-learning deep learning models for classification of AFB-positive and AFB-negative digitized ZN- stained sputum smear images generated in a Ugandan regional referral laboratory. Methods: A retrospective laboratory-based cross-sectional study used 512 archived digitized ZN-stained sputum smear images from Mbarara Regional Referral Hospital. The dataset contained 256 AFB-positive and 256 AFB-negative images and was partitioned by stratified sampling into training (n=358), validation (n=77), and an internal hold-out test set (n=77). ResNet-50 V2, DenseNet-121, and Swin Transformer-Tiny models were trained using ImageNet-pretrained weights in PyTorch. Performance was assessed using sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), F1-score, and ROC-AUC. Results: On the internal test set, Swin Transformer-Tiny achieved 97.40% accuracy, 97.37% sensitivity, 97.44% specificity, 97.37% PPV, 97.44% NPV, 97.37% F1-score, and ROC-AUC 0.9939. DenseNet-121 achieved 88.31% accuracy, 84.21% sensitivity, 92.31% specificity, and ROC-AUC 0.9730. ResNet-50 V2 achieved 85.71% accuracy, 81.58% sensitivity, 89.74% specificity, and ROC-AUC 0.9555. Wilson 95% confidence intervals were calculated for the threshold-based metrics. Conclusion: The models demonstrated promising internal performance for classification of microscopy-defined AFB status. Swin Transformer-Tiny had the highest observed performance, but the small, balanced, single-centre internal test set and use of routine microscopy labels rather than an independent microbiological reference standard limit clinical interpretation. The platform should therefore be considered an AI-assisted microscopy reading aid rather than an autonomous tuberculosis diagnostic system. Prospective, multicentre evaluation using patient/specimen-level separation, independent microbiological reference standards, and multiple blinded readers is required before clinical deployment.
dc.description.sponsorshipMbarara University of Science and Technology Faculty of Health Sciences Seed Grant.
dc.identifier.citationTumwesigye, H., Atwine, D., Atwine, R., Birungi, A., Birungi, C., Munguciada, E., ... & Mitala, Y. (2026). Validation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda. Medical Devices: Evidence and Research, 639007.
dc.identifier.urihttps://ir.must.ac.ug/handle/123456789/4761
dc.language.isoen_US
dc.publisherMedical Devices: Evidence and Research
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internationalen
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjecttuberculosis
dc.subjectacid-fast bacilli
dc.subjectZiehl–Neelsen microscopy
dc.subjectartificial intelligence
dc.subjectdeep learning
dc.subjectswin transformer
dc.subjectDenseNet-121
dc.subjectResNet-50 V2
dc.subjectsputum microscopy
dc.subjectUganda
dc.titleValidation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Validation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda.pdf
Size:
7.41 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.64 KB
Format:
Item-specific license agreed upon to submission
Description: