Validation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda
| dc.contributor.author | Tumwesigye, Habert | |
| dc.contributor.author | Atwine, Daniel | |
| dc.contributor.author | Atwine, Raymond | |
| dc.contributor.author | Birungi, Abraham | |
| dc.contributor.author | Birungi, Caroline | |
| dc.contributor.author | Munguciada, Esther | |
| dc.contributor.author | Nabimanya, Phionah | |
| dc.contributor.author | Akandwanaho, Joseph | |
| dc.contributor.author | Ochama, Benard | |
| dc.contributor.author | Mitala, Yekosani | |
| dc.date.accessioned | 2026-11-18T08:21:34Z | |
| dc.date.issued | 2026-10-15 | |
| dc.description.abstract | Background: 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.sponsorship | Mbarara University of Science and Technology Faculty of Health Sciences Seed Grant. | |
| dc.identifier.citation | Tumwesigye, 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.uri | https://ir.must.ac.ug/handle/123456789/4761 | |
| dc.language.iso | en_US | |
| dc.publisher | Medical Devices: Evidence and Research | |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | en |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject | tuberculosis | |
| dc.subject | acid-fast bacilli | |
| dc.subject | Ziehl–Neelsen microscopy | |
| dc.subject | artificial intelligence | |
| dc.subject | deep learning | |
| dc.subject | swin transformer | |
| dc.subject | DenseNet-121 | |
| dc.subject | ResNet-50 V2 | |
| dc.subject | sputum microscopy | |
| dc.subject | Uganda | |
| dc.title | Validation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda | |
| dc.type | Article |
Files
Original bundle
1 - 1 of 1
Loading...
- 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
1 - 1 of 1
Loading...
- Name:
- license.txt
- Size:
- 1.64 KB
- Format:
- Item-specific license agreed upon to submission
- Description: