AI-Assisted Pre-Screening for Fragile X Syndrome
Abstract: Fragile X syndrome (FXS) is the most prevalent monogenic cause of intellectual disability and autism. Clinical studies on patients being seen in specialized clinics have shown that this X-linked disorder has a substantial impact on the health and well-being of patients and families. FXS remains significantly underdiagnosed despite increased emphasis on identification of individuals with FXS, patient advocacy, and accessibility of genetic testing. An unmet need exists to develop novel pre-screening approaches that are able to alert physicians to potentially undiagnosed cases and refer them for genetic testing. In this presentation, we will report on our results in detecting the rate of FXS diagnosis (and under-diagnosis) in patients from two health care systems (UW Health and the Marshfield Clinic). We will discuss strategies for constructing an AI-assisted pre-screening approach to identify potential cases with FXS who have not yet been diagnosed and describe our current efforts to validate the tool with racially and ethnically diverse patient groups.
Bios: Marsha R. Mailick is the Emeritus Vice Chancellor for Research and Graduate Education, and the Vaughan Bascom and Elizabeth M. Boggs Professor at the University of Wisconsin-Madison. Prior to serving as Vice Chancellor, she served as the Director of the Waisman Center from 2002 to 2014. For the past 16 years, the major focus of Dr. Mailick’s research has been on variations in the FMR1 gene (the gene that causes fragile X syndrome) and its impact on the family, many of whom carry the premutation of the gene. Since 2008, she and her colleagues have carried out a longitudinal study of adolescents and adults with FXS and two population-level studies of the FMR1 premutation. This program of research incorporates social-psychological approaches, epidemiological methods, analysis of electronic health records, biomarkers, and genetics, and has been funded by the NIH and the CDC.
Arezoo Movaghar, PhD, is an Assistant Professor in the Department of Pediatrics and Center for Artificial Intelligence Research at Wake Forest University, School of Medicine. She obtained her PhD in Biomedical Informatics from the University of Wisconsin-Madison and completed her postdoctoral training at the Waisman Center. The focus of her research is on developing innovative and accessible diagnosis and prognosis frameworks for complex disorders using artificial intelligence (AI), electronic health records, and biopsychosocial data. She has a special interest in identifying factors contributing to diagnostic disparities and health inequalities in patients. Her research offers insights into clinical risks associated with various conditions, brings advancements of AI in genetic research, and provides a potential pathway to early diagnosis and intervention.