Marsha R. Mailick, PhD – Slide of the Week

Marsha R. Mailick, PhD - Slide of the Week

Title: Artificial intelligence mines medical records to identify individuals with fragile X syndrome five years earlier than the time of clinical diagnosis

Legend:  Artificial intelligence–assisted diagnosis. A) Receiver operating characteristic curve of classifier performances identifying individuals with fragile X syndrome (FXS) using their electronic health record (EHR) data five years prior to receiving clinical diagnosis. Cases and controls are matched on sex and year of birth with 1:100 ratio. B) Timeline of median age of diagnosis for key conditions associated with FXS. ADHD: attention-deficit hyperactivity disorder, AI-FXS: artificial intelligence–assisted prediction of FXS diagnosis, Clinical Dx-FXS: clinical diagnosis of FXS as reported in the medical report, DD: developmental delay, ID: intellectual disability, S/LD: speech and language disorders. Our artificial intelligence (AI)-assisted approach is able to identify cases five years earlier than the time of clinical diagnosis.

Citation: Movaghar, A., Page, D., Scholze, D. Hong, J., Smith DaWalt, L., Kuusisto, F., Stewart, R., Brilliant, M., Mailick, M., Artificial intelligence–assisted phenotype discovery of fragile X syndrome in a population-based sample. Genet Med (2021).

Abstract: Fragile X syndrome (FXS), the most prevalent inherited cause of intellectual disability, remains under-diagnosed in the general population. Clinical studies have shown that individuals with FXS have a complex health profile leading to unique clinical needs. However, the full impact of this X-linked disorder on the health of affected individuals is unclear and the prevalence of co-occurring conditions is unknown. We mined the longitudinal electronic health records from more than one million individuals to investigate the health characteristics of patients who have been clinically diagnosed with FXS. Additionally, using machine-learning approaches, we created predictive models to identify individuals with FXS in the general population. Our discovery-oriented approach identified the associations of FXS with a wide range of medical conditions including circulatory, endocrine, digestive and genitourinary, in addition to mental and neurological disorders. We successfully created predictive models to identify cases five years prior to clinical diagnosis of FXS without relying on any genetic or familial data. Although FXS is often thought of primarily as a neurological disorder, it is in fact a multi-system syndrome involving many co-occurring conditions, some primary and some secondary, and they are associated with a considerable burden on patients and their families.

About the Lab: The Lifespan Family Research Program conducts research about families who have a member with a disability, with a special emphasis on how these families change over the lifespan. Currently, our program of research encompasses longitudinal and population-based studies of autism and fragile X syndrome, and we develop evidence-based interventions for affected families. Recent research mines the electronic health records and biobank of the Marshfield Clinic to conduct discovery-oriented and hypothesis-testing research on intellectual and developmental disabilities.

Slide of the Week Archives