TY  - JOUR
AU  - Yang, Doris
AU  - Zhou, Doudou
AU  - Cai, Steven
AU  - Gan, Ziming
AU  - Pencina, Michael
AU  - Avillach, Paul
AU  - Cai, Tianxi
AU  - Hong, Chuan
PY  - 2025
DA  - 2025/1/22
TI  - Robust Automated Harmonization of Heterogeneous Data Through Ensemble Machine Learning: Algorithm Development and Validation Study
JO  - JMIR Med Inform
SP  - e54133
VL  - 13
KW  - ensemble learning
KW  - semantic learning
KW  - distribution learning
KW  - variable harmonization
KW  - machine learning
KW  - cardiovascular health study
KW  - intracohort comparison
KW  - intercohort comparison
KW  - gold standard labels
AB  - Background: Cohort studies contain rich clinical data across large and diverse patient populations and are a common source of observational data for clinical research. Because large scale cohort studies are both time and resource intensive, one alternative is to harmonize data from existing cohorts through multicohort studies. However, given differences in variable encoding, accurate variable harmonization is difficult. Objective: We propose SONAR (Semantic and Distribution-Based Harmonization) as a method for harmonizing variables across cohort studies to facilitate multicohort studies. Methods: SONAR used semantic learning from variable descriptions and distribution learning from study participant data. Our method learned an embedding vector for each variable and used pairwise cosine similarity to score the similarity between variables. This approach was built off 3 National Institutes of Health cohorts, including the Cardiovascular Health Study, the Multi-Ethnic Study of Atherosclerosis, and the Women’s Health Initiative. We also used gold standard labels to further refine the embeddings in a supervised manner. Results: The method was evaluated using manually curated gold standard labels from the 3 National Institutes of Health cohorts. We evaluated both the intracohort and intercohort variable harmonization performance. The supervised SONAR method outperformed existing benchmark methods for almost all intracohort and intercohort comparisons using area under the curve and top-k accuracy metrics. Notably, SONAR was able to significantly improve harmonization of concepts that were difficult for existing semantic methods to harmonize. Conclusions: SONAR achieves accurate variable harmonization within and between cohort studies by harnessing the complementary strengths of semantic learning and variable distribution learning. 
SN  - 2291-9694
UR  - https://medinform.jmir.org/2025/1/e54133
UR  - https://doi.org/10.2196/54133
DO  - 10.2196/54133
ID  - info:doi/10.2196/54133
ER  -