{
  "abstract": "To develop an open-source multimodal model for bacterial-versus-fungal microbial keratitis classification and assess shortcuts from geographic pooling. Participants: 1,645 US and Indian patients contributed 17,158 slit-lamp images under blue-light, sclerotic-scatter, and white-light illumination. Methods: The model combined cross-modality contrastive learning, modality-specific fine-tuning, and fusion with 7 clinical variables. Diagnoses used smear, culture, and polymerase chain reaction results, with expert review of culture-negative cases. The model and 5 comparators used 5 patient-disjoint outer folds stratified by country and organism, with inner validation. Secondary analyses examined within-country performance, a country-only reference, ablations, and imbalance mitigation. Code: https://github.com/yqwang01/TPMKA. Main Outcome Measures: Patient-level macro-F1, class-specific F1, accuracy, and area under the receiver operating characteristic curve (AUROC), overall and by country. Results: The model had the highest overall macro-F1 (83.06%; 95% CI, 81.58-84.56) and accuracy (84.50%; 95% CI, 83.16-85.84) among matched comparators, with 89.9% AUROC (95% CI, 88.7-91.1). Paired differences were not consistently significant. AUROC was 83.9% in India and 67.0% in the US; bacterial F1 in India was 47.78%, and fungal F1 in the US was 40.97%. A country-only reference achieved 81.88% accuracy and 78.2% AUROC overall despite 50.0% AUROC within each country. Resampling and group distributionally robust optimization improved some underrepresented groups without removing the geographic pattern. Conclusions: The model compared favorably with matched methods, but geographic prevalence differences made pooled performance more reassuring than within-country discrimination. Independent geographic validation is needed.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.03740",
  "author_total": 14,
  "authors": [
    {
      "name": "Yiqing Wang"
    },
    {
      "name": "Maria A. Woodward"
    },
    {
      "name": "Ziyun Yang"
    },
    {
      "name": "N. Venkatesh Prajna"
    },
    {
      "name": "Chunming He"
    },
    {
      "name": "Leslie M. Niziol"
    },
    {
      "name": "Mercy Pawar"
    },
    {
      "name": "Ming-Chen Lu"
    },
    {
      "name": "Guillermo Amescua"
    },
    {
      "name": "Rachel A. F. Wozniak"
    },
    {
      "name": "Sejal Amin"
    },
    {
      "name": "Abinaya Krishnan"
    },
    {
      "name": "Prabhleen Kochar"
    },
    {
      "name": "Sina Farsiu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fhggbv6vj1ax1.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.03740",
  "fulltext_url": null,
  "id": "fhggbv6vj1ax1",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.03740",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "2731|Ocular Infections and Treatments"
    ]
  ],
  "openalex": "W7167607949",
  "pdf_url": "https://arxiv.org/pdf/2607.03740",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fhggbv6vj1ax1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:56Z",
      "native_id": "2607.03740",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.03740"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Multimodal Knowledge Aggregation for Microbial Keratitis: Geographic Confounding and Shortcut Risk in Pooled Multicountry Data",
  "title_text": "Multimodal Knowledge Aggregation for Microbial Keratitis: Geographic Confounding and Shortcut Risk in Pooled Multicountry Data",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:56Z",
  "url": "https://research.draconitic.com/paper/fhggbv6vj1ax1",
  "venue": "arXiv",
  "versions": []
}