Artificial intelligence–assisted phenotype discovery of fragile X syndrome in a population-based sample

Abstract

Purpose Fragile X syndrome (FXS), the most prevalent inherited cause of intellectual disability, remains underdiagnosed 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. Methods 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. Results 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. Conclusion Although FXS is often thought of primarily as a neurological disorder, it is in fact a multisystem syndrome involving many co-occurring conditions, some primary and some secondary, and they are associated with a considerable burden on patients and their families.

Heterogeneity in Fragile X Syndrome Highlights the Need for Precision Medicine-Based Treatments

“…In another recent study, electronic health records from more than one million people were mined to investigate health characteristics of individuals clinically diagnosed with FXS. This resulted into (1) the identification of previously unnoticed significative co-occurring health conditions in patients with FXS (heart and circulatory disorders, medication side effects, and among others), and (2) the development of a predictive model to identify patients with FXS in the general population without using any genetic data, successfully identifying cases 5 years prior to clinical diagnosis of FXS ( 80 ). While this AI-assisted diagnosis method was instrumental to identify cases in the general population prior to the onset of more severe symptoms ( 80 ), no computational methods have been oriented toward stratifying patients with FXS into more homogenous subgroups, which is the first step needed to enrich future clinical trials in FXS with responder patients.…”

“…This resulted into (1) the identification of previously unnoticed significative co-occurring health conditions in patients with FXS (heart and circulatory disorders, medication side effects, and among others), and (2) the development of a predictive model to identify patients with FXS in the general population without using any genetic data, successfully identifying cases 5 years prior to clinical diagnosis of FXS ( 80 ). While this AI-assisted diagnosis method was instrumental to identify cases in the general population prior to the onset of more severe symptoms ( 80 ), no computational methods have been oriented toward stratifying patients with FXS into more homogenous subgroups, which is the first step needed to enrich future clinical trials in FXS with responder patients. Recently, the use of patient-derived induced pluripotent stem cells was proposed to model the disease in a patient-specific manner and to develop new therapeutic opportunities ( 81 ); nevertheless, to our knowledge, there is still no clinical trials in FXS involving therapeutic treatments developed using patient-derived induced pluripotent stem cells.…”

Prevalence of Underdiagnosed Fragile X Syndrome in 2 Health Systems

“…Fragile X syndrome (FXS) is the most common inherited cause of intellectual disability and autism with substantial challenges for patients and their families. [1][2][3] Diagnosing FXS is challenging because of its clinical heterogeneity, absence of evident physical characteristics at birth, variation of phenotypes between the sexes, and similarity of phenotypes with other conditions. [1][2][3][4] It is recommended that all individuals with developmental delay, intellectual disability, and/or autism of an unknown cause should be genetically tested for FXS.…”

Screening for FMR1 CGG Repeat Expansion in Thai Patients with Autism Spectrum Disorder

“…The majority of males who carry the full mutation FXS have mild to moderate ID, while about half of females with the full mutation have only normal or borderline intellectual function because of cellular mosaicism resulting from X-chromosome inactivation. As with most aspects of the FXS phenotype, behavioral phenotypes in FXS are quite variable and include attention deficits, hyperactivity, hyperarousal, aggression and self-injury, social anxiety, and autism [ 13 , 14 ]. Some studies have reported that some behavioral symptoms of patients with FXS are similar to autistic patients and it is sometimes difficult to distinguish them from each other, especially in young children [ 15 – 18 ].…”

“…In individuals with the full FXS mutations, up to 60% of males meet the diagnostic criteria for ASD and approximately 30-50% of males with FXS meet the full DSM-IV criteria for autism [ 17 , 20 – 25 ]. Additionally, more than 90% of males with FXS display some autistic characteristics [ 14 , 16 , 17 ]. The percentage of autism is lower (3-20%) in females with FXS [ 17 , 21 , 26 , 27 ].…”