Rare-Disease Diagnosis on the ZebraMap Multimodal Case Report Dataset: A Hybrid Pipeline with Grounded Explainability
Sensors · 04.06.2026 · 26 (11) · 3582
DOI: 10.3390/s26113582 ↗Kurz gefasst
Fallbericht in der Zeitschrift Sensors, online erschienen am 04.06.2026. Verfasst von Md Sanzidul Islam und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia. Hauptthemen laut MEDLINE: Case Reports as Topic, Classification Algorithms, Large Language Models, Rare Diseases. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Abdulaziz University.
Abstract (Originalsprache)
Rare-disease diagnosis is difficult because clinicians must identify plausible conditions from a large, severely imbalanced disease space using evidence distributed across clinical narratives, structured findings, and image-linked descriptions. This paper presents a hybrid pipeline with caption-mediated multimodal fusion for ranked rare-disease diagnosis and grounded explanation, developed and evaluated on the ZebraMap multimodal case-report dataset (69,146 structured cases; 1727 diseases). Grouped train–validation–test splitting by source article was applied to prevent leakage, and a sequential pipeline was constructed combining BM25 lexical retrieval, a class-balanced TF–IDF classifier, MedCPT dense retrieval and cross-encoder reranking, caption-based image-aware late fusion, and post hoc grounded explanation generation. The final pipeline achieved test MRR 0.3905 and Recall@10 0.5507 (nDCG@10 0.4273), while the strongest individual component, the class-balanced TF–IDF classifier, reached MRR 0.4200 and Recall@10 0.6279; the hybrid pipeline therefore integrates ranking with grounded explanation rather than maximizing single-metric diagnostic accuracy. On 256 explained cases, the explanation module achieved citation coverage 0.7334 and usefulness 3.8734, exposing a tradeoff between diagnostic accuracy and explanation richness. These results indicate that a hybrid retrieval-and-classification approach can support ranked rare-disease differential diagnosis and that grounded explanation quality can be evaluated quantitatively, extending computational support for the prolonged rare-disease diagnostic process.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia.
- Department of Computer Science, Faculty of Science and Information Technology, Daffodil International University, Birulia 1216, Bangladesh.
- Center of Research Excellence in Artificial Intelligence and Data Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia.
ORCID-Profile: Md Sanzidul Islam, Amani Jamal, Ali Alkhathlan
Förderung
- King Abdulaziz University
Zitieren
APA
Islam, M. S., Jamal, A., & Alkhathlan, A. (2026). Rare-Disease Diagnosis on the ZebraMap Multimodal Case Report Dataset: A Hybrid Pipeline with Grounded Explainability. Sensors, 26(11), 3582. https://doi.org/10.3390/s26113582
Vancouver
Islam MS, Jamal A, Alkhathlan A. Rare-Disease Diagnosis on the ZebraMap Multimodal Case Report Dataset: A Hybrid Pipeline with Grounded Explainability. Sensors. 2026;26(11):3582. doi:10.3390/s26113582
BibTeX
@article{Islam2026,
author = {Islam, Md Sanzidul and Jamal, Amani and Alkhathlan, Ali},
title = {Rare-Disease Diagnosis on the ZebraMap Multimodal Case Report Dataset: A Hybrid Pipeline with Grounded Explainability},
journal = {Sensors},
year = {2026},
volume = {26},
number = {11},
pages = {3582},
doi = {10.3390/s26113582}
}
EUVIMED