EUVIMEDEUVIMED entdecken
Crossref

Beyond the artificial intelligence translational gap: can foundation models finally bridge research and practice in pediatrics?—a narrative review

Michael Kim, Denys Herasymuk, Dmytro Lopushanskyy, Mjaye Mazwi, Danny Eytan

Translational Pediatrics · 2026-11 · 15 (11) · 471-471

DOI: 10.21037/tp-2026-0796 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Pediatrics, 2026-11. Verfasst von Michael Kim und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Objective: Artificial intelligence (AI) is rapidly advancing, yet a persistent gap separates strong retrospective model performance from measurable clinical benefit—the “AI chasm”. This gap is wider in Pediatrics where physiology varies with maturational stage, datasets are small and fragmented, and the field is underfunded relative to adult medicine. Foundation models (FMs), pretrained and then adapted, have been proposed as a solution to this problem. We examine whether that promise holds for children.

Methods

This narrative review is organized around research questions that span FM capabilities, pediatric evidence by data modality, AI safety, and the conditions for clinical adoption. We combined agentic and semantic literature search across PubMed, arXiv, medRxiv, and Semantic Scholar with manual search of high-impact venues and screening of reference lists. Searches covered English-language literature, with emphasis on 2023 to 2026, and were last updated on July 22, 2026. Pediatric patients were defined as 0 to under 18 years. Every included study was verified against its primary source, and each claim was rechecked against the original text.Key Content and Findings: FM capabilities are real, but the convincing demonstrations come from adult medicine—medical question answering, multimodal generalists, and subspecialty specific FMs including adult cardiology and oncology. To the best of our knowledge, no pediatric FM system that directly informs diagnosis or treatment has undergone clinical validation and reached clinical deployment. Pediatrics continues to be characterized by task-specific deep learning. Diagnostic models remain at the retrospective-benchmark stage, and pediatric-native FMs are typically unpublished preprints confined to one or two centers. Major factors hindering clinical deployment include model overconfidence and miscalibration, limited explainability, absence of validation frameworks, regulatory uncertainty, safety risks, and ethical concerns specific to pediatrics.

Conclusions

FMs hold genuine promise for closing the translational gap in pediatrics. Including children in this translation requires models trained on data that span children and adults, safety benchmarks run in pediatric age groups, and pediatric-specific pathways for adaptation, deployment, and governance, combined with prospective validation, interpretability, and safety oversight.

Zitieren

APA

Kim, M., Herasymuk, D., Lopushanskyy, D., Mazwi, M., & Eytan, D. (2026). Beyond the artificial intelligence translational gap: can foundation models finally bridge research and practice in pediatrics?—a narrative review. Translational Pediatrics, 15(11), 471-471. https://doi.org/10.21037/tp-2026-0796

Vancouver

Kim M, Herasymuk D, Lopushanskyy D, Mazwi M, Eytan D. Beyond the artificial intelligence translational gap: can foundation models finally bridge research and practice in pediatrics?—a narrative review. Translational Pediatrics. 2026;15(11):471-471. doi:10.21037/tp-2026-0796

BibTeX
@article{Kim2026,
  author = {Kim, Michael and Herasymuk, Denys and Lopushanskyy, Dmytro and Mazwi, Mjaye and Eytan, Danny},
  title = {Beyond the artificial intelligence translational gap: can foundation models finally bridge research and practice in pediatrics?—a narrative review},
  journal = {Translational Pediatrics},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {471--471},
  doi = {10.21037/tp-2026-0796}
}
Kostenlos starten →