Scalable classification of infant breast milk feeding status from clinical notes using weak supervision and rule-based natural language processing
JAMIA Open · 09.09.2026 · 9 (5)
DOI: 10.1093/jamiaopen/ooag211 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 30.10.2026. Verfasst von Connor Grannis und 9 weiteren Autor:innen. Beteiligte Einrichtung: Office of Data Sciences, Nationwide Children's Hospital, Columbus, OH 43205, United States. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NICHD NIH HHS, NCATS NIH HHS, The Ohio State University Clinical and Translational Science Institute.
Abstract (Originalsprache)
Objective
Extract infant breast milk feeding status from electronic health record clinical notes to support observational drug-safety studies. Materials and Methods Infant notes (19 489; 228 infants) were weakly labeled by large language model (LLM) and validated on 1045 manually reviewed notes. Using these labels, we built a rule-based medspaCy classifier from a curated feeding term set and compared it with ClinPhen and fine-tuned Bidirectional Encoder Representations from Transformers (BERT) document classifiers. Maternal postpartum notes (23 mothers; 616 partitions) were manually labeled to compare BERT with prompt-based language models.
Results
LLM labels achieved 99.62% accuracy (macro F1 99.32%). medspaCy achieved 94.36% accuracy and 90.40% balanced accuracy (macro F1 0.90) and was applied to 52 278 mother–infant dyads. On maternal notes, the prompt-based model improved Positive-class F1 vs BERT (0.96 vs 0.82).
Discussion
LLMs were most effective for scalable labeling; deterministic rules supported transparent large-scale inference.
Conclusion
Weak supervision plus lightweight rules can convert sparse breastfeeding documentation into structured variables at-scale.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Office of Data Sciences, Nationwide Children's Hospital, Columbus, OH 43205, United States.
- Department of Biomedical Informatics, The Ohio State University, Columbus, OH 43210, United States.
- Information Technology Research & Innovation, Nationwide Children's Hospital, Columbus, OH 43205, United States.
- The Steve and Cindy Rasmussen Institute for Genomic Medicine, Nationwide Children's Hospital, Columbus, OH 43205, United States.
- Department of Pediatrics, The Ohio State University, Columbus, OH 43210, United States.
- Center for Biobehavioral Health, The Abigal Wexner Research Institute, Nationwide Children's Hospital, Columbus, OH 43205, United States.
ORCID-Profile: Austin A Antoniou, Jianing Liu, Peter White, Lang Li
Förderung
- NICHD NIH HHS
- NCATS NIH HHS
- The Ohio State University Clinical and Translational Science Institute
- National Center for Advancing Translational Sciences
- National Institutes of Health
Zitieren
APA
Grannis, C., Wei, P., Antoniou, A. A., Gordon, D. M., Xu, J., Liu, J., White, P., Keim, S. A., Li, L., & Bartlett, C. W. (2026). Scalable classification of infant breast milk feeding status from clinical notes using weak supervision and rule-based natural language processing. JAMIA Open, 9(5). https://doi.org/10.1093/jamiaopen/ooag211
Vancouver
Grannis C, Wei P, Antoniou AA, Gordon DM, Xu J, Liu J, et al. Scalable classification of infant breast milk feeding status from clinical notes using weak supervision and rule-based natural language processing. JAMIA Open. 2026;9(5). doi:10.1093/jamiaopen/ooag211
BibTeX
@article{Grannis2026,
author = {Grannis, Connor and Wei, Ping and Antoniou, Austin A and Gordon, David M and Xu, Jinyu and Liu, Jianing and White, Peter and Keim, Sarah A and Li, Lang and Bartlett, Christopher W},
title = {Scalable classification of infant breast milk feeding status from clinical notes using weak supervision and rule-based natural language processing},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {5},
doi = {10.1093/jamiaopen/ooag211}
}
EUVIMED