Researchers in Taiwan have successfully developed a hierarchical algorithm that identifies pregnancies and estimates gestational age directly from nationwide health insurance records, bypassing the need for manual chart review or ultrasound data access. The computational method integrates diagnostic codes, procedure records, and laboratory measurements from Taiwan’s National Health Insurance Research Database, which covers over 23 million insured patients.
This breakthrough enables epidemiologists and pharmacovigilance specialists to assemble large pregnancy cohorts efficiently for drug safety research. By systematically classifying pregnancies and determining their duration through linked administrative data, the algorithm provides a scalable approach to pregnancy-related pharmacoepidemiology that could be adapted globally. The findings, published in Pharmacoepidemiology and Drug Safety, demonstrate how modern health information systems can be leveraged to strengthen maternal medication safety surveillance without compromising data privacy or requiring direct clinical access.
Read the full article on GMJ Newsroom.
Was this article helpful?
