Data Mining of Electronic Health Records to Identify Undiagnosed Patients with Rare Genetic Diseases

Abstract

Rare genetic diseases affect 5-8% of the population but are often undiagnosed or misdiagnosed. Electronic health records (EHR) contain large amounts of data, which provide opportunities for analysing and mining. Data mining was performed on a database containing deidentified health records of 1.28 million patients across 3 major hospitals in Singapore, in a bid to improve the diagnostic process for patients who are living with an undiagnosed rare disease, specifically focusing on Fabry Disease and Familial Hypercholesterolaemia (FH). On a baseline of 4 patients, we identified 2 additional patients with potential diagnosis of Fabry disease, suggesting a 50% increase in diagnosis. Similarly, we identified >12,000 individuals who fulfil the clinical and laboratory criteria for FH, suggesting that data mining of EHR may allow for increased diagnosis of patients with rare disorders. This proof-of-concept study showed that it is indeed possible to perform data mining on EHR albeit with some challenges and limitations.