A new approach to identifying patients with elevated risk for Fabry disease using a machine learning algorithm.

BACKGROUND: Fabry disease (FD) is a rare genetic disorder characterized by glycosphingolipid accumulation and progressive damage across multiple organ systems. Due to its heterogeneous presentation, the condition is likely significantly underdiagnosed. Several approaches, including provider education efforts and newborn screening, have attempted to address underdiagnosis of FD across the age spectrum, with limited success. Artificial intelligence (AI) methods present another option for improving diagnosis. These methods isolate common health history patterns among patients using longitudinal real-world data, and can be particularly useful when patients experience nonspecific, heterogeneous symptoms over time. In this study, the performance of an AI tool in identifying patients with FD was analyzed. The tool was calibrated using de-identified health record data from a large cohort of nearly 5000 FD patients, and extracted phenotypic patterns from these records. The tool then used this FD pattern information to make individual-level estimates of FD in a testing dataset. Patterns were reviewed and confirmed with medical experts. RESULTS: The AI tool demonstrated strong analytic performance in identifying FD patients. In out-of-sample testing, it achieved an area under the receiver operating characteristic curve (AUROC) of 0.82. Strong performance was maintained when testing on male-only and female-only cohorts, with AUROCs of 0.83 and 0.82 respectively. The tool identified small segments of the population with greatly increased prevalence of FD: in the 1% of the population identified by the tool as at highest risk, FD was 23.9 times more prevalent than in the population overall. The AI algorithm used hundreds of phenotypic signals to make predictions and included both familiar symptoms associated with FD (e.g. renal manifestations) as well as less well-studied characteristics. CONCLUSIONS: The AI tool analyzed in this study performed very well in identifying Fabry disease patients using structured medical history data. Performance was maintained in all-male and all-female cohorts, and the phenotypic manifestations of FD highlighted by the tool were reviewed and confirmed by clinical experts in the condition. The platform's analytic performance, transparency, and ability to generate predictions based on existing real-world health data may allow it to contribute to reducing persistent underdiagnosis of Fabry disease.

Data Analytics from Enroll-HD, a Global Clinical Research Platform for Huntington's Disease.

BACKGROUND: The study of complex neurodegenerative diseases is moving away from hypothesis-driven biological methods toward large scale multimodal approaches, requiring standardized collaborative efforts. Enroll-HD exemplifies such an integrated clinical research platform, designed and implemented to meet the research and clinical needs of Huntington's disease (HD). The aim of this study was to describe the unique organization of Enroll-HD and report baseline data analyses of its core study. METHODS: The Enroll-HD platform incorporates electronic data capture, biosampling, and a longitudinal observational study spanning four continents (ClinicalTrials.gov Identifier: NCT01574053). The primary study population includes HD gene expansion carriers (HDGECs; CAG expansion ≥36), subdivided into manifest/premanifest HD. The control population consists of genotype-negative first-degree relatives and family controls not genetically related. The study includes 10 core clinical assessments covering motor, cognitive, and behavioral domains. RESULTS: This data set comprises 1,534 participants (HDGEC = 1,071; controls = 463). Participant retention was high; 42 participants prematurely withdrew from the study. Mean ± standard deviation SD CAG repeat size was 43.5 ± 3.5 for HDGECs and 19.8 ± 3.4 for controls. Motor and behavioral assessments identified numerical differences between controls and HDGECs (manifest > premanifest > controls). Functional and independence assessments were generally similar for the premanifest and control groups with overlap in range of scores obtained. For the majority of cognitive tests, there were large differences between participants with manifest HD and all other groups. CONCLUSIONS: These first data from the Enroll-HD clinical research platform demonstrate the maturity and potential of the platform in collecting high-quality, clinically relevant data. Future data sets will be substantially larger as the platform expands longitudinally and regionally.