Privacy-preserving, low-annotation pregnancy status classification from obstetric ultrasound reports using on-premises small language models

Ultrasound reports in obstetric care provide information about the status of the pregnancy which is essential for clinical informatics purposes. This information, however, is buried in free text. We evaluated seven frozen small language models with 3–4 billion parameters, run on-premises, on 628 MIMIC-IV reports and 340 reports processed with OCR from one Indian clinical site. The models were used to classify the reports as early active pregnancy, late active pregnancy, or no active pregnancy with a 14-week operational boundary and a labeling scheme based on management status. With 12 in-context exemplars, a seven-model committee achieved a macro F1 of 0.9622 on MIMIC-IV and 0.9814 on the Indian OCR cohort. When MIMIC-IV exemplars were transferred to the Indian OCR cohort, performance did not differ detectably from that obtained with Indian OCR cohort exemplars in a paired bootstrap test. We also investigated how to reduce labeling burden and introduced a probability-guided exemplar selection procedure. The procedure converted 95–98% of annotation effort into usable balanced prompt exemplars, compared with 52–66% under random sampling. These retrospective results support pregnancy-status extraction with human review in low-annotation settings where data remain on-premises, without fine-tuning or offsite data transfer.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-17
DOI
https://doi.org/10.1038/s41598-026-79573-0
Primary Topic
Machine Learning in Healthcare
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Privacy-preserving, low-annotation pregnancy status classification from obstetric ultrasound reports using on-premises small language models

Vijay Mago, Pawan J. Lingras, Nikita Neveditsin, Swarup Patil et al.
2 links
Scientific Reports
Machine Learning in Healthcare
article

Privacy-preserving, low-annotation pregnancy status classification from obstetric ultrasound reports using on-premises small language models

Vijay Mago, Pawan J. Lingras, Nikita Neveditsin, Swarup Patil, Salil Patil
article en

Abstract

Ultrasound reports in obstetric care provide information about the status of the pregnancy which is essential for clinical informatics purposes. This information, however, is buried in free text. We evaluated seven frozen small language models with 3–4 billion parameters, run on-premises, on 628 MIMIC-IV reports and 340 reports processed with OCR from one Indian clinical site. The models were used to classify the reports as early active pregnancy, late active pregnancy, or no active pregnancy with a 14-week operational boundary and a labeling scheme based on management status. With 12 in-context exemplars, a seven-model committee achieved a macro F1 of 0.9622 on MIMIC-IV and 0.9814 on the Indian OCR cohort. When MIMIC-IV exemplars were transferred to the Indian OCR cohort, performance did not differ detectably from that obtained with Indian OCR cohort exemplars in a paired bootstrap test. We also investigated how to reduce labeling burden and introduced a probability-guided exemplar selection procedure. The procedure converted 95–98% of annotation effort into usable balanced prompt exemplars, compared with 52–66% under random sampling. These retrospective results support pregnancy-status extraction with human review in low-annotation settings where data remain on-premises, without fine-tuning or offsite data transfer.

Scientific Reports
York University (CA), Saint Mary's University (CA)
Natural Sciences and Engineering Research Council of Canada
Good health and well-being
Machine Learning in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon