Advancing artificial intelligence-assisted pre-screening for fragile X syndrome.

BACKGROUND: Fragile X syndrome (FXS), the most common inherited cause of intellectual disability and autism, is significantly underdiagnosed in the general population. Diagnosing FXS is challenging due to the heterogeneity of the condition, subtle physical characteristics at the time of birth and similarity of phenotypes to other conditions. The medical complexity of FXS underscores an urgent need to develop more efficient and effective screening methods to identify individuals with FXS. In this study, we evaluate the effectiveness of using artificial intelligence (AI) and electronic health records (EHRs) to accelerate FXS diagnosis. METHODS: The EHRs of 2.1 million patients served by the University of Wisconsin Health System (UW Health) were the main data source for this retrospective study. UW Health includes patients from south central Wisconsin, with approximately 33 years (1988-2021) of digitized health data. We identified all participants who received a code for FXS in the form of International Classification of Diseases (ICD), Ninth or Tenth Revision (ICD9 = 759.83, ICD10 = Q99.2). Only individuals who received the FXS code on at least two occasions ("Rule of 2") were classified as clinically diagnosed cases. To ensure the availability of sufficient data prior to clinical diagnosis to test the model, only individuals who were diagnosed after age 10 were included in the analysis. A supervised random forest classifier was used to create an AI-assisted pre-screening tool to identify cases with FXS, 5 years earlier than the time of clinical diagnosis based on their medical records. The area under receiver operating characteristic curve (AUROC) was reported. The AUROC shows the level of success in identification of cases and controls (AUROC = 1 represents perfect classification). RESULTS: 52 individuals were identified as target cases and matched with 5200 controls. AI-assisted pre-screening tool successfully identified cases with FXS, 5 years earlier than the time of clinical diagnosis with an AUROC of 0.717. A separate model trained and tested on UW Health cases achieved the AUROC of 0.798. CONCLUSIONS: This result shows the potential utility of our tool in accelerating FXS diagnosis in real clinical settings. Earlier diagnosis can lead to more timely intervention and access to services with the goal of improving patients' health outcomes.

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

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.

Mild Neurological Signs in FMR1 Premutation Women in an Unselected Community-Based Cohort.

BACKGROUND: Premutation-sized (55-200) CGG repeat expansions in the FMR1 gene cause fragile X-associated tremor/ataxia syndrome (FXTAS). Most studies of premutation carriers utilized reverse ascertainment to identify patients, leading to a selection bias for larger repeats. As shorter CGG premutation repeats are common in the population, understanding their impact on health outcomes has a potentially large public health footprint. OBJECTIVE: The study's objective was to compare an unselected group of premutation carriers (n = 35, 55-101 CGG repeats) with matched controls (n = 61, 29-39 CGG repeats) with respect to FXTAS-type signs using structured neurological assessments. METHODS: Three neurologists independently rated signs, using an adapted version of the FXTAS Rating Scale (Leehey MA, Berry-Kravis E, Goetz CG, et al. FMR1 CGG repeat length predicts motor dysfunction in premutation carriers. Neurology. 2008). This was a double-blind study, as genetic status (premutation vs. control) was known neither by the participants nor by any of the neurologists. Analyses controlled potentially confounding comorbid conditions in the electronic health record (eg, osteoarthritis and stroke) and probed the association of age with signs. RESULTS: Although there was no overall difference between carriers and controls, among individuals without any potentially confounding comorbid diagnoses, there was a statistically significant age-associated elevation in FXTAS-type signs in premutation carriers compared to controls. CONCLUSIONS: Among those who do not have other comorbid diagnoses, women who have CGG repeats at the lower end of the premutation range may be at greater risk for ataxia and parkinsonism than their age peers, although their overall risk of developing such clinical features is low. This study should provide reassurance to those who share characteristics with the present cohort. © 2021 International Parkinson and Movement Disorder Society.

Machine learning approach to measurement of criticism: The core dimension of expressed emotion.

Expressed emotion (EE), a measure of the family's emotional climate, is a fundamental measure in caregiving research. A core dimension of EE is the level of criticism expressed by the caregiver to the care recipient, with a high level of criticism a marker of significant distress in the household. The Five-Minute Speech Sample (FMSS), the most commonly used brief measure of EE, requires time-consuming manual processing and scoring by a highly trained expert. In this study, we used natural language processing and supervised machine learning techniques to develop a fully automated framework to evaluate caregiver criticism level based on the verbatim transcript of the FMSS. The success of the machine learning algorithm was established by demonstrating that the classification of maternal caregivers as high versus low EE was consistent with the classification of these 298 maternal caregivers of adult children with schizophrenia using standard manual coding procedures, with area under the receiver operating characteristic curve (AUROC) of 0.76. Evidence of construct validity was established by demonstrating that maternal caregivers of adults with schizophrenia, who were classified as having a high level of criticism had higher levels of caregiver burden, reported that their child had more psychiatric symptoms and behaviors and perceived that their child had greater control over these symptoms and behaviors. Additionally, maternal caregivers who had high levels of criticism reported having a poorer quality of relationship with their child with schizophrenia than maternal caregivers low on criticism. Rapid measurement of criticism facilitates the incorporation of this dimension into research across a broad range of caregiving contexts. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Health profiles of adults with autism spectrum disorder: Differences between women and men.

The purpose of the present study was to investigate the hypothesis that women with autism have poorer health compared with men with autism, and compared with women without autism. Utilizing electronic health records drawn from a single health care system serving over 2 million individuals, 2119 adults with diagnosed autism spectrum disorders were compared with age- and sex-matched controls. When considering health care utilization, we found evidence of multiplicative risk for conditions within some domains (i.e., nutrition conditions, neurologic disease, psychiatric conditions, and sleep disorders) such that women with autism spectrum disorder (ASD) experienced double jeopardy-meaning they had greater rates of health care utilization within a domain than what would separately be expected by virtue of being a woman and having ASD. For other domains (i.e., endocrine disorders, gastrointestinal disorders), the risk was additive such that being a female and having ASD were both associated with higher health care utilization, but there were no significant interaction effects. It was only with respect to one domain (cardiovascular) that rates of health care utilization were reflective of neither ASD diagnosis nor sex. Overall, our findings suggest that women with ASD are a vulnerable subgroup with high levels of health care utilization. LAY SUMMARY: This study asked whether women with autism have poorer health compared with men with autism, and compared with women without autism. To answer this question, we used data from electronic health records. We found that women with autism spectrum disorder (ASD) were at the greatest risk for health problems such as nutrition conditions, neurologic disease, psychiatric conditions, and sleep disorders. More research on health of women with ASD is needed.

FMR1 Low Zone CGG Repeats: Phenotypic Associations in the Context of Parenting Stress.

The FMR1 gene on the X chromosome has varying numbers of CGG repeats. The modal number is 30, and expansion to >200 results in fragile X syndrome, but the copy number extends down to 6. Past research suggests that individuals whose CGGs are in the "low zone" (LZ; defined here as ≤ 25 CGGs) may be more environmentally-reactive than those with normal range repeats (26-40 CGGs)-a gene x environment interaction. Using a population-based DNA biobank, in our primary analysis we compared 96 mothers with LZ CGG repeats on both alleles to 280 mothers who had CGG repeats in the normal range. Secondarily, we conducted parallel analyses on fathers. We investigated how parents in these two CGG repeat categories differentially responded to stress, defined as parenting a child with disabilities. Significant gene x environment interactions indicated that LZ mothers who had children with disabilities had greater limitations (in executive functioning, depression, anxiety, daily health symptoms, and balance) than LZ mothers whose children did not have disabilities. In contrast, mothers with normal-range CGG repeats did not differ based on stress exposure. For fathers, a similar pattern was evident for one phenotype only (hand tremors). Although on average LZ CGGs are not associated with compromised functioning, the average masks differential response to the environment.

Artificial Intelligence Chatbots and Their Influence on Learning.

This JAMA Pediatrics Patient Page describes what artificial intelligence chatbots are and how they may influence learning among children.

Data-driven phenotype discovery of FMR1 premutation carriers in a population-based sample.

The impact of the FMR1 premutation on human health is the subject of considerable controversy. A fundamental unanswered question is whether carrying the premutation allele is directly correlated with clinical phenotypes. A challenging problem in past genotype-phenotype studies of the FMR1 premutation is ascertainment bias, which could lead to invalid research conclusions and negatively affect clinical practice. Here, we created the first population-based FMR1-informed biobank to find the pattern of health characteristics in premutation carriers. Our extensive phenotyping shows that premutation carriers experience a clinical profile that is significantly different from controls and is evident throughout adulthood. Comprehensive understanding of the clinical risk associated with this genetic variant is critical for premutation carriers, their families, and clinicians and has important implications for public health.

Using machine learning to identify patterns of lifetime health problems in decedents with autism spectrum disorder.

Very little is known about the health problems experienced by individuals with autism spectrum disorder (ASD) throughout their life course. We retrospectively analyzed diagnostic codes associated with de-identified electronic health records using a machine learning algorithm to characterize diagnostic patterns in decedents with ASD and matched decedent community controls. Participants were 91 decedents with ASD and 6,186 sex and birth year matched decedent community controls who had died since 1979, the majority of whom were middle aged or older adults at the time of their death. We analyzed all ICD-9 codes, V-codes, and E-codes available in the electronic health record and Elixhauser comorbidity categories associated with those codes. Diagnostic patterns distinguished decedents with ASD from decedent community controls with 75% sensitivity and 94% specificity solely based on their lifetime ICD-9 codes, V-codes, and E-codes. Decedents with ASD had higher rates of most conditions, including cardiovascular disease, motor problems, ear problems, urinary problems, digestive problems, side effects from long-term medication use, and nonspecific lab tests and encounters. In contrast, decedents with ASD had lower rates of cancer. Findings suggest distinctive lifetime diagnostic patterns among decedents with ASD and highlight the need for more research on health outcomes across the lifespan as the population of individuals with ASD ages. As a large wave of individuals with ASD diagnosed in the 1990s enters adulthood and middle age, knowledge about lifetime health problems will become increasingly important for care and prevention efforts. Autism Res 2018, 11: 1120-1128. © 2018 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: This study looked at patterns of lifetime health problems to find differences between people with autism who had died and community controls who had died. People with autism had higher rates of most health problems, including cardiovascular, urinary, respiratory, digestive, and motor problems, in their electronic health records. They also had lower rates of cancer. More research is needed to understand these potential health risks as a large number of individuals with autism enter adulthood and middle age.

Health Profiles of Mosaic Versus Non-mosaic FMR1 Premutation Carrier Mothers of Children With Fragile X Syndrome.

The FMR1 premutation is of increasing interest to the FXS community, as questions about a primary premutation phenotype warrant research attention. 100 FMR1 premutation carrier mothers (mean age = 58; 67-138 CGG repeats) of adults with fragile X syndrome were studied with respect to their physical and mental health, motor, and neurocognitive characteristics. We explored the correlates of CGG repeat mosaicism in women with expanded alleles. Mothers provided buccal swabs from which DNA was extracted and the FMR1 CGG genotyping was performed (Amplidex Kit, Asuragen). Mothers were categorized into three groups: Group 1: premutation non-mosaic (n = 45); Group 2: premutation mosaic (n = 41), and Group 3: premutation/full mutation mosaic (n = 14). Group 2 mothers had at least two populations of cells with different allele sizes in the premutation range besides their major expanded allele. Group 3 mothers had a very small population of cells in the full mutation range (>200 CGGs) in addition to one or multiple populations of cells with different allele sizes in the premutation range. Machine learning (random forest) was used to identify symptoms and conditions that correctly classified mothers with respect to mosaicism; follow-up comparisons were made to characterize the three groups. In categorizing mosaicism, the random forest yielded significantly better classification than random classification, with overall area under the receiver operating characteristic curve (AUROC) of 0.737. Among the most important symptoms and conditions that contributed to the classification were anxiety, menopause symptoms, executive functioning limitations, and difficulty walking several blocks, with the women who had full mutation mosaicism (Group 3) unexpectedly having better health. Although only 14 premutation carrier mothers in the present sample also had a small population of full mutation cells, their profile of comparatively better health, mental health, and executive functioning was unexpected. This preliminary finding should prompt additional research on larger numbers of participants with more extensive phenotyping to confirm the clinical correlates of low-level full mutation mosaicism in premutation carriers and to probe possible mechanisms.

Automated screening for Fragile X premutation carriers based on linguistic and cognitive computational phenotypes.

Millions of people globally are at high risk for neurodegenerative disorders, infertility or having children with a disability as a result of the Fragile X (FX) premutation, a genetic abnormality in FMR1 that is underdiagnosed. Despite the high prevalence of the FX premutation and its effect on public health and family planning, most FX premutation carriers are unaware of their condition. Since genetic testing for the premutation is resource intensive, it is not practical to screen individuals for FX premutation status using genetic testing. In a novel approach to phenotyping, we have utilized audio recordings and cognitive profiling assessed via self-administered questionnaires on 200 females. Machine-learning methods were developed to discriminate FX premutation carriers from mothers of children with autism spectrum disorders, the comparison group. By using a random forest classifier, FX premutation carriers could be identified in an automated fashion with high precision and recall (0.81 F1 score). Linguistic and cognitive phenotypes that were highly associated with FX premutation carriers were high language dysfluency, poor ability to organize material, and low self-monitoring. Our framework sets the foundation for computational phenotyping strategies to pre-screen large populations for this genetic variant with nominal costs.

Evolvix BEST Names for semantic reproducibility across code2brain interfaces.

Names in programming are vital for understanding the meaning of code and big data. We define code2brain (C2B) interfaces as maps in compilers and brains between meaning and naming syntax, which help to understand executable code. While working toward an Evolvix syntax for general-purpose programming that makes accurate modeling easy for biologists, we observed how names affect C2B quality. To protect learning and coding investments, C2B interfaces require long-term backward compatibility and semantic reproducibility (accurate reproduction of computational meaning from coder-brains to reader-brains by code alone). Semantic reproducibility is often assumed until confusing synonyms degrade modeling in biology to deciphering exercises. We highlight empirical naming priorities from diverse individuals and roles of names in different modes of computing to show how naming easily becomes impossibly difficult. We present the Evolvix BEST (Brief, Explicit, Summarizing, Technical) Names concept for reducing naming priority conflicts, test it on a real challenge by naming subfolders for the Project Organization Stabilizing Tool system, and provide naming questionnaires designed to facilitate C2B debugging by improving names used as keywords in a stabilizing programming language. Our experiences inspired us to develop Evolvix using a flipped programming language design approach with some unexpected features and BEST Names at its core.

High-Content Analysis of CRISPR-Cas9 Gene-Edited Human Embryonic Stem Cells.

CRISPR-Cas9 gene editing of human cells and tissues holds much promise to advance medicine and biology, but standard editing methods require weeks to months of reagent preparation and selection where much or all of the initial edited samples are destroyed during analysis. ArrayEdit, a simple approach utilizing surface-modified multiwell plates containing one-pot transcribed single-guide RNAs, separates thousands of edited cell populations for automated, live, high-content imaging and analysis. The approach lowers the time and cost of gene editing and produces edited human embryonic stem cells at high efficiencies. Edited genes can be expressed in both pluripotent stem cells and differentiated cells. This preclinical platform adds important capabilities to observe editing and selection in situ within complex structures generated by human cells, ultimately enabling optical and other molecular perturbations in the editing workflow that could refine the specificity and versatility of gene editing.