EUVIMEDEUVIMED entdecken
Systematische Übersicht

Harnessing Large Language Models in Neonatal Intraventricular Hemorrhage: Exploring Retrieval Augmented Generation Methodology for Prognostic Variable Discovery

Tanima Arora iD, Kristyn Beam iD

American Journal of Perinatology · 2026-10 · 43 (14) · 1904-1912

DOI: 10.1055/a-2838-5446 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift American Journal of Perinatology, online erschienen am 31.03.2026. Verfasst von Tanima Arora und 1 weiteren Autor:innen. Beteiligte Einrichtung: Division of Newborn Medicine, Boston Children's Hospital, Boston, Massachusetts, United States. Hauptthemen laut MEDLINE: Large Language Models, Cerebral Intraventricular Hemorrhage. Die Arbeit nennt 67 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The objective of this study is to evaluate whether large language models (LLMs) can autonomously synthesize existing literature and accurately extract prognostic variables for neonatal intraventricular hemorrhage (IVH) and its outcomes while assessing their capability for clinical feature ranking and risk stratification. This pilot study employed a systematic literature review combined with retrieval-augmented generation (RAG) methodology. GPT 4 (OpenAI) and Claude Sonnet (4.0, Anthropic) were prompted to identify peer-reviewed studies utilizing machine learning and deep learning to predict IVH outcomes in preterm neonates. Data extraction was prompted to follow TRIPOD artificial intelligence (AI) guidelines, capturing study design, population characteristics, predictor variables, and outcome measures. Semi-automated RAG extraction was performed with manual validation to mitigate hallucination risk. LLMs initially identified 39 studies, with 28 meeting some or all the validation criteria after excluding references that were hallucinated. From these, 14 distinct prognostic predictors were extracted across four outcome domains: mortality, progression, complications, and resolution. Universal high-impact predictors included gestational age (13 mentions; 41%), birth weight (8 mentions, 25%), and Apgar scores (11 mentions, 34%). Variables were categorized into three clinical tiers based on frequency, outcome breadth, and modifiability. A preliminary risk stratification model demonstrated high-risk neonates (32 weeks, >1,500 g, Apgar > 5) showed favorable trajectories. This study demonstrates that LLMs can synthesize medical literature and extract clinically relevant prognostic variables for neonatal IVH outcomes. However, LLM outputs were susceptible to hallucinations and incomplete data synthesis, underscoring the need for rigorous clinical oversight and human validation to ensure reliability. The identified universal predictors provide a foundation for developing AI-assisted clinical decision support tools. Notable research gaps include the complete absence of resolution prediction studies and limited investigation of complication predictors, highlighting opportunities for future investigation in precision neonatology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsCerebral Intraventricular HemorrhageHumansInfant, NewbornPrognosisPilot ProjectsGestational AgeInfant, PrematureRisk AssessmentBirth WeightGenerative Artificial Intelligence

Autor:innen und Institutionen

  • Division of Newborn Medicine, Boston Children's Hospital, Boston, Massachusetts, United States.
  • Division of Neonatology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, United States.

ORCID-Profile: Tanima Arora, Kristyn Beam

Zitieren

APA

Arora, T., & Beam, K. (2026). Harnessing Large Language Models in Neonatal Intraventricular Hemorrhage: Exploring Retrieval Augmented Generation Methodology for Prognostic Variable Discovery. American Journal of Perinatology, 43(14), 1904-1912. https://doi.org/10.1055/a-2838-5446

Vancouver

Arora T, Beam K. Harnessing Large Language Models in Neonatal Intraventricular Hemorrhage: Exploring Retrieval Augmented Generation Methodology for Prognostic Variable Discovery. American Journal of Perinatology. 2026;43(14):1904-1912. doi:10.1055/a-2838-5446

BibTeX
@article{Arora2026,
  author = {Arora, Tanima and Beam, Kristyn},
  title = {Harnessing Large Language Models in Neonatal Intraventricular Hemorrhage: Exploring Retrieval Augmented Generation Methodology for Prognostic Variable Discovery},
  journal = {American Journal of Perinatology},
  year = {2026},
  volume = {43},
  number = {14},
  pages = {1904--1912},
  doi = {10.1055/a-2838-5446}
}
Kostenlos starten →