Purpose <p>Fabry disease (FD) is an X-linked lysosomal storage disorder caused by pathogenic variants in the α-galactosidase A (<i>GLA</i>) gene, leading to reduced α-galactosidase A enzyme activity and progressive glycosphingolipid accumulation. FD remains underdiagnosed due to its heterogeneous presentation and overlapping symptoms with other conditions. The prevalence of FD is particularly underexplored in regions such as the United Arab Emirates (UAE). This study aimed to identify high-risk FD cases in a UAE hospital setting using a predictive algorithm applied to electronic medical records (EMR).</p> Methods <p>This is an observational, single-arm, single-center study with interventional diagnostic procedures (biochemical and molecular testing on dried blood spot) for each patient meeting inclusion criteria, conducted at Cleveland Clinic Abu Dhabi (CCAD), UAE. The study retrospectively screened the CCAD EMR over a 6-year period (May 2016–May 2022) using a predictive algorithm to identify patients at high risk for FD. In the prospective phase (October 2022–March 2023), identified high-risk patients underwent targeted diagnostic testing to confirm FD diagnoses.</p> Results <p>The algorithm screened 1787 patients, identifying 259 (14.5%) as high-risk for FD, with a target enrollment of 230 for diagnostic testing. However, only 15 patients completed evaluations, precluding computation of disease prevalence. None of these 15 subjects were ultimately diagnosed with FD. All enrolled patients exhibited comorbidities commonly associated with FD, such as chronic kidney disease and proteinuria.</p> Conclusion <p>This study underscores the potential of predictive algorithms for identifying high-risk FD patients but highlights significant recruitment challenges that limited diagnostic outcomes. Despite identifying a substantial high-risk cohort, low participation hindered FD case confirmation. Addressing these challenges requires robust collaboration among healthcare providers, public health authorities, and community leaders to build awareness, reduce social stigma, and emphasize the importance of research participation in rare diseases. Such interdisciplinary efforts are critical to improving early FD detection, refining algorithmic specificity, and supporting broader application across diverse populations.</p> <p>Trial registration number (TRN): NCT05671770</p> <p>Date of registration: 20 Dec 2022</p>