{
  "abstract": "Background\n\nZiehl-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\n\nTo 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\n\nA 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\n\nOn 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\n\nThe 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.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Pathology, Mbarara University of Science and Technology (MUST), Mbarara, Uganda.",
    "SRF Research and Training Centers, Mbarara, Uganda.",
    "Department of Laboratory Services, Mbarara Regional Referral Hospital (MRRH), Mbarara, Uganda."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Habert Tumwesigye",
      "orcid": "0009-0000-7113-2922"
    },
    {
      "affs": [
        1
      ],
      "name": "Daniel Atwine"
    },
    {
      "affs": [
        0
      ],
      "name": "Raymond Atwine",
      "orcid": "0000-0001-7888-7818"
    },
    {
      "affs": [
        0
      ],
      "name": "Abraham Birungi"
    },
    {
      "affs": [
        1
      ],
      "name": "Caroline Birungi"
    },
    {
      "affs": [
        1
      ],
      "name": "Esther Munguciada"
    },
    {
      "affs": [
        0
      ],
      "name": "Phionah Nabimanya"
    },
    {
      "affs": [
        0
      ],
      "name": "Joseph Akandwanaho"
    },
    {
      "affs": [
        2
      ],
      "name": "Benard Ochama"
    },
    {
      "affs": [
        0
      ],
      "name": "Yekosani Mitala",
      "orcid": "0000-0001-8344-8967"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8m1emk6m5f8a3.bib",
  "cited_by": 0,
  "doi": "10.2147/mder.s639007",
  "fulltext_url": "https://europepmc.org/articles/PMC13679598",
  "id": "8m1emk6m5f8a3",
  "issns": [
    "1179-1470"
  ],
  "landing_url": "https://europepmc.org/article/MED/42899212",
  "language": "eng",
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7222174751",
  "pdf_url": "https://europepmc.org/articles/PMC13679598?pdf=render",
  "pmcid": "PMC13679598",
  "pmid": "42899212",
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8m1emk6m5f8a3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:33Z",
      "native_id": "MED:42899212",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42899212"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "journal-openalex:F27",
      "subfield": "general"
    }
  ],
  "title": "Validation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda.",
  "title_text": "Validation of an AI-Driven Sputum Analysis Platform for Accurate and Reliable Tuberculosis Detection in South-Western Uganda.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:33Z",
  "url": "https://research.draconitic.com/paper/8m1emk6m5f8a3",
  "venue": "Medical devices (Auckland, N.Z.)",
  "versions": []
}