Identifying Family Relationships from Electronic Health Records: A Machine Learning Approach
- 1University of Colorado Anschutz
Abstract
ObjectiveTo develop and evaluate machine learning methods for automated identification of family relationships from electronic health records (EHRs). We employed Random Forest classifiers to identify five relationship types: Mother-Child, Father-Child, Sibling-Sibling, Twin-Twin, and Partner-Partner, using a four-stage iterative refinement process to improve precision for patient-centered outcomes research (PCOR) and healthcare applications.
Materials and MethodsWe used two large-scale Indiana datasets: the Indiana Network for Patient Care (INPC), comprising approximately 15 million unique individuals across approximately 45 million medical records, and the Indiana Natality dataset (birth certificates, 1970-2024), which served as the gold standard. Positive cases were derived by linking verified relationships from Natality records to INPC using a shared Global Identifier. Negative cases were drawn from a three-tier blocking strategy combined with sliding window restriction and similarity scoring, which together reduced the comparison space from over 10{superscript 1} potential pairs to approximately 121 million candidates. Five Random Forest classifiers underwent four-stage iterative refinement: initial training, feature removal for multicollinearity, feature engineering to address systematic errors, and training-data refinement restricted to relationship pairs with at least one shared contact feature.
ResultsThe models achieved precision of 0.92 to 1.00, recall of 0.97 to 1.00, and F1 scores of 0.94 to 1.00 across all relationship types (Mother-Child 0.97, Father-Child 0.98, Sibling-Sibling 0.98, Twin-Twin 1.00, Partner-Partner 0.94). Between 15% and 78% of Natality-verified relationships lacked any shared contact information in INPC and were structurally undetectable by record linkage; restricting training and evaluation to linkable pairs improved precision for four of the five models, and training-data refinement improved F1-scores by a further 0.02-0.04 for the Mother-Child, Father-Child, and Sibling models. High-confidence predictions (probability [≥] 0.9) captured 77-99% of true positives. Age difference was the primary predictor for parent-child and twin relationships, while phone number similarity was most important for siblings.
DiscussionThe framework identifies family relationships from standard demographic fields available in most EHR systems. The iterative refinement approach shows how systematic error analysis can guide methodological improvements. Training-data refinement addresses a constraint in EHR-based family linkage: not all verified biological relationships have overlapping demographic footprints in healthcare data. Unlike rule-based approaches, the framework provides probability scores that enable configurable deployment thresholds.
ConclusionThe Random Forest models demonstrate high performance suitable for large-scale research deployment and are ready for testing in clinical applications rather than immediate widespread clinical use. The methodology can be adapted to other EHR systems, supporting family-centered study design in patient-centered outcomes research.
Related
- Scalable Causal-Interpretable Machine Learning for Cancer Prescreening Using Electronic Health Records
- Screening for patients at risk for cardiac amyloidosis via electronic health records: A multicenter machine learning development and validation study
- Prediction of incident inflammatory bowel disease from routine electronic health records: development and external validation of a longitudinal machine learning model
- An uncertainty-aware multimodal deep learning framework for Alzheimer’s disease classification using MRI and electronic health records
- Machine learning models for identifying prediabetes: a systematic review of performance, validation, and implications for primary care
BibTeX
@misc{pundir2026identifying,
title = {{Identifying Family Relationships from Electronic Health Records: A Machine Learning Approach}},
author = {A. Pundir and A. Hill and M. G. Kahn and B. M. Kwan and D. M. Lindberg and S. J. Grannis and T. K. Schleyer and L. M. Schilling and S. V. Kautz and T. C. Ong},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.18.26363428},
url = {https://www.medrxiv.org/content/10.64898/2026.09.18.26363428v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Identifying Family Relationships from Electronic Health Records: A Machine Learning Approach
AU - A. Pundir
AU - A. Hill
AU - M. G. Kahn
AU - B. M. Kwan
AU - D. M. Lindberg
AU - S. J. Grannis
AU - T. K. Schleyer
AU - L. M. Schilling
AU - S. V. Kautz
AU - T. C. Ong
PY - 2026
DA - 2026/09/18
PB - medRxiv
DO - 10.64898/2026.09.18.26363428
UR - https://www.medrxiv.org/content/10.64898/2026.09.18.26363428v1
AB - ObjectiveTo develop and evaluate machine learning methods for automated identification of family relationships from electronic health records (EHRs). We employed Random Forest classifiers to identify five relationship types: Mother-Child, Father-Child, Sibling-Sibling, Twin-Twin, and Partner-Partner, using a four-stage iterative refinement process to improve precision for patient-centered outcomes research (PCOR) and healthcare applications. Materials and MethodsWe used two large-scale Indiana datasets: the Indiana Network for Patient Care (INPC), comprising approximately 15 million unique individuals across approximately 45 million medical records, and the Indiana Natality dataset (birth certificates, 1970-2024), which served as the gold standard. Positive cases were derived by linking verified relationships from Natality records to INPC using a shared Global Identifier. Negative cases were drawn from a three-tier blocking strategy combined with sliding window restriction and similarity scoring, which together reduced the comparison space from over 10{superscript 1} potential pairs to approximately 121 million candidates. Five Random Forest classifiers underwent four-stage iterative refinement: initial training, feature removal for multicollinearity, feature engineering to address systematic errors, and training-data refinement restricted to relationship pairs with at least one shared contact feature. ResultsThe models achieved precision of 0.92 to 1.00, recall of 0.97 to 1.00, and F1 scores of 0.94 to 1.00 across all relationship types (Mother-Child 0.97, Father-Child 0.98, Sibling-Sibling 0.98, Twin-Twin 1.00, Partner-Partner 0.94). Between 15% and 78% of Natality-verified relationships lacked any shared contact information in INPC and were structurally undetectable by record linkage; restricting training and evaluation to linkable pairs improved precision for four of the five models, and training-data refinement improved F1-scores by a further 0.02-0.04 for the Mother-Child, Father-Child, and Sibling models. High-confidence predictions (probability [≥] 0.9) captured 77-99% of true positives. Age difference was the primary predictor for parent-child and twin relationships, while phone number similarity was most important for siblings. DiscussionThe framework identifies family relationships from standard demographic fields available in most EHR systems. The iterative refinement approach shows how systematic error analysis can guide methodological improvements. Training-data refinement addresses a constraint in EHR-based family linkage: not all verified biological relationships have overlapping demographic footprints in healthcare data. Unlike rule-based approaches, the framework provides probability scores that enable configurable deployment thresholds. ConclusionThe Random Forest models demonstrate high performance suitable for large-scale research deployment and are ready for testing in clinical applications rather than immediate widespread clinical use. The methodology can be adapted to other EHR systems, supporting family-centered study design in patient-centered outcomes research.
ER -