EUVIMEDEUVIMED entdecken
Scoping ReviewOpen Access

Machine Learning, Large Language Models, and Multimodal AI for Diagnosing Pediatric Rare Diseases: Scoping Review

Machine Learning, Large Language Models und multimodale KI zur Diagnose seltener pädiatrischer Erkrankungen: Scoping Review

Jungang Zhao, Jiawei Luo, Qiu Li, Yaolong Chen

Journal of Medical Internet Research · 28.08.2026 · 28 · e96169-e96169

DOI: 10.2196/96169 ↗

Auf einen Blick

Die Scoping Review kartierte diagnostische KI-Anwendungen bei seltenen pädiatrischen Erkrankungen. Die Evidenz war überwiegend retrospektiv und intern validiert; LLMs und multimodale KI waren selten.

Fragestellung

Welche diagnostischen Anwendungen, Datenmodalitäten, Validierungsstrategien und welcher Evidenzreifegrad von KI bei seltenen pädiatrischen Erkrankungen sind beschrieben?

Methode

Scoping Review nach Joanna Briggs Institute und PRISMA-ScR; Suche am 26. Juni 2026 in PubMed, Scopus, Web of Science Core Collection, Embase, CNKI, Wanfang Data und Cochrane Library sowie in medRxiv und arXiv.

Ergebnisse

81 Studien eingeschlossen. 38 (46,9 %) zu klassischem Machine Learning, 18 (22,2 %) zu Facial AI, 15 (18,5 %) zu Deep Learning, 6 (7,4 %) zu LLMs und 4 (4,9 %) zu multimodaler KI. 76 (93,8 %) mit interner Validierung, 21 (25,9 %) mit externer Validierung.

Einschränkungen

Überwiegend retrospektive Studien; die Evidenzreife hielt mit der schnellen Entwicklung nicht Schritt.

Schlussfolgerung der Autor:innen

Die Forschung zur KI-gestützten Diagnose seltener pädiatrischer Erkrankungen hat schnell zugenommen, aber die Evidenzreife nicht. Die meisten Studien zeigten technische Machbarkeit statt generalisierbaren klinischen Nutzen.

Kernaussagen

  • 81 Studien von 2016 bis 2026
  • Meist retrospektiv und intern validiert
  • LLMs und multimodale KI bisher selten

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Scoping Review in der Zeitschrift Journal of Medical Internet Research, online erschienen am 28.08.2026. Verfasst von Jungang Zhao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Chevidence Lab Child & Adolescent Health, Department of Pediatric Research Institute, Children's Hospital of Chongqing Medical University, National C…. Hauptthemen laut MEDLINE: Rare Diseases, Machine Learning, Artificial Intelligence. Die Arbeit nennt 92 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Pediatric rare diseases often cause a prolonged diagnostic odyssey. AI, including machine learning, deep learning, large language models (LLMs), and multimodal systems, may support diagnosis, but these applications in children have not been systematically mapped.

Objective

The aim of the study is to map diagnostic applications, data modalities, validation strategies, and evidence maturity of AI methods for pediatric rare diseases.

Methods

We conducted a scoping review following Joanna Briggs Institute methodology and reported it according to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). On June 26, 2026, we searched PubMed, Scopus, Web of Science Core Collection, Embase, China National Knowledge Infrastructure (CNKI), Wanfang Data, and the Cochrane Library for records published from January 1, 2015, through June 1, 2026. We additionally searched medRxiv and arXiv and hand-searched the reference lists of included studies and relevant reviews. Eligibility was defined using the population-concept-context framework: pediatric rare diseases, diagnostic AI, and any clinical or research setting. JZ and JL independently screened titles and abstracts and assessed potentially eligible full-text reports. JZ charted the data, and JL verified every field. Findings were synthesized descriptively according to disease focus, AI technology, input modality, diagnostic task, validation strategy, and evidence maturity.

Results

Database searches identified 2557 records; 2063 remained after deduplication. Of 106 full-text reports assessed, 77 database studies and 4 studies from hand searching and preprint servers were included, yielding 81 studies. Studies were published from 2016 through 2026, with 55 of 81 (67.9%) published from 2024 through 2026. Using a mutually exclusive primary technology classification, classical machine learning accounted for 38 (46.9%) studies, facial AI for 18 (22.2%), deep learning for 15 (18.5%), LLMs for 6 (7.4%), and multimodal AI for 4 (4.9%). Electronic health records, claims, clinical text, or structured clinical vignettes were used in 25 (30.9%) studies, facial images in 17 (21%), and other medical imaging in 13 (16%). Evidence remained mainly retrospective and internally validated: 62 (76.5%) studies included a retrospective component and 76 (93.8%) reported internal validation, whereas 21 (25.9%) included external validation and 12 (14.8%) included a prospective component.

Conclusions

Research on AI-assisted diagnosis of pediatric rare diseases has expanded rapidly, but evidence maturity has not kept pace. Most studies established technical feasibility rather than generalizable clinical benefit, and performance should be interpreted by task, inputs, reference standard, and validation design rather than used to rank technologies. Evidence for LLMs and multimodal AI remains limited. Future research should prioritize multicenter validation, reproducible task-specific benchmarks, prospective evaluation, and assessment of incremental clinical value.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Rare DiseasesMachine LearningArtificial IntelligenceHumansLarge Language ModelsChild

Stichwörter der Autor:innen

AIdeep learningdiagnostic decision supportlarge language modelsmachine learningmultimodal AIpediatricsrare diseasesscoping review

Autor:innen und Institutionen

  • Chevidence Lab Child & Adolescent Health, Department of Pediatric Research Institute, Children's Hospital of Chongqing Medical University, National Clinical Research Center for Children and Adolescents' Health and Disea…
  • Chongqing Municipal Health Commission Key Laboratory of Children's Vital Organ Development and Diseases, Chongqing, China.
  • Department of Nephrology, Children's Hospital of Chongqing Medical University, Chongqing, China.
  • Research Unit of Evidence-Based Evaluation and Guidelines, Chinese Academy of Medical Sciences (2021RU017), School of Basic Medical Sciences, Lanzhou University, Lanzhou, China.
  • WHO Collaborating Center for Guideline Implementation and Knowledge Translation, Lanzhou University, Lanzhou, China.

Zitieren

APA

Zhao, J., Luo, J., Li, Q., & Chen, Y. (2026). Machine Learning, Large Language Models, and Multimodal AI for Diagnosing Pediatric Rare Diseases: Scoping Review. Journal of Medical Internet Research, 28, e96169-e96169. https://doi.org/10.2196/96169

Vancouver

Zhao J, Luo J, Li Q, Chen Y. Machine Learning, Large Language Models, and Multimodal AI for Diagnosing Pediatric Rare Diseases: Scoping Review. Journal of Medical Internet Research. 2026;28:e96169-e96169. doi:10.2196/96169

BibTeX
@article{Zhao2026,
  author = {Zhao, Jungang and Luo, Jiawei and Li, Qiu and Chen, Yaolong},
  title = {Machine Learning, Large Language Models, and Multimodal AI for Diagnosing Pediatric Rare Diseases: Scoping Review},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e96169--e96169},
  doi = {10.2196/96169}
}
Kostenlos starten →