AI Tool Helps Link BRSK1 Variants to Neurodevelopmental Disorder

For many families affected by rare genetic conditions, genomic testing does not immediately deliver an answer. Now, researchers have combined artificial intelligence, human genetics, and fruit fly experiments to connect variants in BRSK1 with a complex neurodevelopmental disorder. The findings provide a potential diagnosis for several previously unexplained cases while offering clues about how reduced activity of the gene may disrupt nervous system development.

The study, “Monoallelic variants in BRSK1 are associated with a neurodevelopmental disorder with or without epilepsy,” was led by researchers at Baylor College of Medicine, the Duncan Neurological Research Institute at Texas Children’s Hospital, and the Texome Project, together with collaborating institutions. It was published in the American Journal of Human Genetics.

According to Hugo Bellen, PhD, who is co-lead author of the study, the work began with a child enrolled in the Texome Project, which provides genetic testing to medically underserved people with rare, undiagnosed conditions in Texas. Standard analysis of the child’s and parent’s genomes had not identified a cause. AI-MARRVEL, an artificial intelligence–based tool that analyzes genomic and clinical information to prioritize candidate disease variants, highlighted a rare change in BRSK1. Through GeneMatcher, the researchers identified nine additional affected individuals with rare heterozygous variants in the gene, bringing the group to 10 people from seven unrelated families. The team then modeled three patient-derived variants in Drosophila melanogaster to test their effects in a living organism.

The “affected individuals present with developmental delay and variable phenotypes including anxiety, attention-deficit hyperactivity disorder (ADHD), autism, and seizures,” the authors wrote, adding that the severity and symptoms varied. Symptoms differed even among relatives carrying the same variant, suggesting variable expressivity.

“We studied the fly equivalent of BRSK1, called sff (sugar-free frosting), and found that this gene is active primarily in neurons, mirroring the expression pattern seen in humans,” added Mingxi Deng, PhD, who is first author and a postdoctoral fellow in the Bellen lab. “When the fly gene was disabled, the flies developed difficulties moving, showed increased sensitivity to stressors that can trigger seizure-like behavior, became more vulnerable to heat-induced paralysis and lived shorter lives. These findings indicated that the gene is essential for normal nervous system function.”

Introducing normal human BRSK1 largely corrected the behavioral and neurological defects, whereas three variants (BRSK1p.Ile202Val, BRSK1p.Arg237Cys, and BRSK1p.Thr406Ile) found in affected individuals produced only a partial rescue. The patient variants also failed to normalize neuromuscular junction structure or levels of Futsch, a protein involved in organizing neuronal microtubules. Together, the experiments suggest that the variants partially reduce BRSK1 activity rather than eliminating it.

“Microtubule disruption has been linked to several neurodevelopmental and neurological disorders,” Deng said. “Our findings suggest that reduced BRSK1 function interferes with the cellular machinery needed for healthy brain development and communication between neurons.”

BRSK1 encodes a kinase involved in neuronal polarization, synaptic function, and the internal organization of nerve cells. Reduced activity may therefore interfere with the cellular machinery neurons need to develop and communicate. “This work improves our understanding of the genetic causes of neurodevelopmental disorders and highlights the power of combining AI-driven gene discovery with experimental studies in model organisms to uncover new rare diseases and their underlying biology,” Bellen said.

The diagnosis may help participating families understand the source of their condition and could guide recognition of additional cases. Future studies will be needed to determine why the same variant can produce markedly different symptoms and to define more precisely how altered BRSK1 activity affects the developing brain.

The post AI Tool Helps Link <i>BRSK1</i> Variants to Neurodevelopmental Disorder appeared first on GEN – Genetic Engineering and Biotechnology News.

Association of temporal and masseter muscle thickness with cognitive function and clinical severity in Alzheimer’s disease: a retrospective study

BackgroundTemporal muscle thickness (TMT) has emerged as an imaging marker of skeletal muscle status and may be associated with cognitive decline in Alzheimer’s disease (AD). However, its relationship with AD severity remains unclear, and the clinical relevance of masseter muscle thickness (MMT) is unknown.ObjectiveTo evaluate the associations of TMT and MMT with cognitive function and disease severity in AD.MethodsThis retrospective study included 242 patients with AD between December 2023 and April 2025. TMT and MMT were measured on axial T1-weighted MRI, cognitive function was assessed using standardized neuropsychological tests, and disease severity was determined by Clinical Dementia Rating (CDR).ResultsThe intraclass correlation coefficients (ICC) for the mean TMT and MMT were 0.868 and 0.896, respectively, indicating good consistency. As the severity of AD progresses, TMT tends to be thinner in severe AD than in mild AD. Spearman’s correlation analysis revealed that both TMT and MMT were correlated with the Mini-Mental State Examination (MMSE) and CDR. After adjusting for various confounding factors using ordered logistic regression and multiple linear regression, TMT was found to be independently associated with AD severity (OR: 0.424, 95% CI: 0.290–0.618, p < 0.001) and positively correlated with MMSE scores. MMT showed only a weak independent association with CDR staging (OR: 0.830, 95% CI: 0.724–0.952, p = 0.008), while no significant correlation was observed with the MMSE. Stratified analysis revealed that the TMT maintained a consistent association in both male and female patients, whereas the MMT achieved statistical significance only in females in ordered logistic regression; all other findings were not statistically significant.ConclusionTemporal muscle thickness is associated with cognitive impairment and clinical severity in patients with AD and may serve as a simple, noninvasive imaging marker; in contrast, the independent associations of MMT with disease severity were weak and sex-specific, suggesting that its clinical utility may be limited and requires further validation.

Trait, state, and behavior in adolescent NSSI addiction: a serial mediation model linking childhood trauma to NSSI addiction

BackgroundDespite growing recognition of non-suicidal self-injury (NSSI) as a potential behavioral addiction, the sequential mechanisms linking childhood trauma to NSSI addiction remain unclear. This study examined a serial mediation model testing whether trait impulsivity and depressive symptoms sequentially mediate this relationship, with NSSI function as a behavioral coping mechanism.MethodsThis cross-sectional study included 163 Chinese adolescents diagnosed with major depressive disorder and a history of NSSI. Participants completed the Childhood Trauma Questionnaire-Short Form, the Short UPPS-P Impulsive Behavior Scale, the Children’s Depression Inventory, and the Ottawa Self-Injury Inventory (Functions and Addictive Features subscales). Serial mediation analysis (PROCESS Model 6, 5,000 bootstrap resamples), controlling for demographic and clinical covariates, tested the hypothesized five-step sequential model.ResultsChildhood trauma was positively associated with NSSI addiction, and this association was predominantly mediated: the total indirect effect accounted for 56.2% of the total effect. Indirect effects involving NSSI function in combination with upstream mediators were significant, including the full sequential path (B = 0.0033, 95% CI [0.0007, 0.0083]), whereas simple mediations via impulsivity, depression, or NSSI function alone were not.ConclusionThese findings support a trait-state-behavior-addiction cascade in which childhood trauma is associated with trait impulsivity and depressive symptoms that, in combination with the reinforcing function of NSSI, are linked to addictive features of NSSI. The model advances theoretical understanding of NSSI addiction and offers actionable clinical targets for prevention and intervention. Longitudinal studies are needed to confirm causal directions.

Adolescent non-suicidal self-injury scale – short form: revision and evaluation of its reliability and validity

ObjectiveNon-suicidal self-injury (NSSI) is a clinically significant concern among adolescents, and its accurate yet efficient assessment is essential for research, early identification, and intervention. Existing Chinese instruments—most notably the 19-item Adolescent Self-Harm Questionnaire (ASHS)—are relatively lengthy and ill-suited to rapid, large-scale screening. The present study had two aims: (a) to develop a short form of the ASHS, the Adolescent Non-Suicidal Self-Injury Scale–Short Form (ANSSI-SF), by integrating classical test theory (CTT) item analysis with genetic algorithm (GA) cross-validation, and (b) to evaluate its reliability, validity, and screening utility relative to the parent scale.MethodsUsing a convenience sample of 1,090 primary and secondary school students, seven items—one for each of seven behavioral categories derived from a functional–typological framework of self-harm—were selected on the basis of CTT item statistics and GA cross-validation. The scale was evaluated through item analysis, internal-consistency and split-half reliability, exploratory and confirmatory factor analysis (EFA/CFA), correlations with theoretically related constructs, known-groups comparisons (gender; smartphone addiction), and consistency and screening-accuracy analyses against the full 19-item ASHS.ResultsIt indicated that all items demonstrated strong correlations with the total score, and both internal consistency and split-half reliability reached satisfactory levels.A unidimensional factor structure also exhibited good model fit. Additionally, scale scores were significantly positively correlated with related psychological indicators such as depression, anxiety, and sleep problems, and effectively differentiated differences in self-injurious behavior across gender and smartphone addiction groups.GA cross-validation confirmed that the selected items balanced parsimony with full coverage of all seven behavioral categories.DiscussionThese findings indicate that the ANSSI-SF is a brief, reliable, and valid instrument that preserves the content breadth of the parent ASHS while substantially reducing administration burden. It is well suited to rapid, large-scale screening and early identification of at-risk adolescents, facilitating timely referral and prevention. Limitations include convenience sampling from a single region and the absence of test–retest reliability; future research should validate the scale in clinical and diverse cultural samples and examine its predictive validity.

The chain-mediating effect of societal pressure on appearance and body image on fear of negative evaluation and social anxiety in women with polycystic ovary syndrome: a cross-lagged panel analysis

Objective(Prospective Longitudinal Observational Study) This study aimed to examine the longitudinal chain mediating roles of physical appearance social pressure and body image in the relationship between fear of negative evaluation (FNE) and social anxiety among women with polycystic ovary syndrome (PCOS), and to clarify the temporal sequencing among these variables.MethodsConvenience sampling was used to recruit 264 women with PCOS. Participants completed the Sociocultural Attitudes Towards Appearance Questionnaire-4 Revised (SATAQ-4R), Body Image States Scale (BISS), Brief Fear of Negative Evaluation Scale (BFNE), and Social Anxiety Scale (SAS) at baseline (T0), 3 months (T1), and 6 months (T2), yielding 242 valid cases. Data were analyzed using measurement invariance testing, cross-lagged panel analysis (CLPA), and bootstrapping.ResultsFull measurement invariance was established across the three timepoints (ΔCFI ≤0.01, ΔTLI ≤0.01). The final CLPA model demonstrated excellent fit (CFI = 0.988, TLI = 0.959, RMSEA = 0.023, 90% CI: 0.021–0.026). T0 FNE positively predicted T1 appearance social pressure (β = 0.25, P <0.001) and T1 SA (β = 0.23, P <0.001), and negatively predicted T1 body image (β = −0.19, P <0.001). T1 appearance social pressure positively predicted T2 SA (β = 0.22, P <0.001). T1 body image negatively predicted T2 SA (β = −0.18, P <0.01). T1 SA positively predicted T2 FNE (β = 0.13, P <0.001). Bootstrap analyses revealed significant indirect effects via T1 appearance social pressure (β = 0.055, 95% CI: 0.028–0.082) and T1 body image (β = 0.034, 95% CI: 0.015–0.053), as well as a significant chain mediation effect (β = 0.018, 95% CI: 0.007–0.029).ConclusionLongitudinal evidence supports a chain mediating pathway wherein elevated fear of negative evaluation at baseline is prospectively associated with subsequent increases in appearance social pressure and declines in body image, which in turn correspond to higher levels of social anxiety in women with PCOS. Findings support the potential utility of early psychological screening and targeted interventions addressing maladaptive cognitions and body image disturbances, although causal efficacy requires validation via randomized controlled trials.

Effect of age-friendly community degree on the cognitive function of older adults

IntroductionThe relationship between individual environmental indicators and the physical and mental health of older adults has been widely studied. However, the holistic impact of age-friendly communities on the wellbeing of older adults has not beenclearly elucidated. This study aimed to explore the correlation between the degree of community friendliness and cognitive function of older adults and provide scientific evidence for healthy aging.MethodsThis cross-sectional study enrolled 450 residents aged ≥60 years with cognitive impairment in Ningbo, Zhejiang Province, from June to September 2024. Participants provided personal demographic data, and their community’s age-friendly status and cognitive function were assessed using the Age-Friendly Community (AFC) Evaluation Scale and the Alzheimer’s Disease 8 Questionnaire. A multivariate logistic regression analysis was performed to examine the relationship between demographic characteristics and cognitive function of the older adults.ResultsAmong the five dimensions of the AFC evaluation scale, community participation scored the highest at 3.56 ±’ 1.21 points. Multivariate linear regression analysis revealed that personal demographic factors (age, sex, education level, economic status, housing conditions, alcohol consumption, and chronic diseases) significantly infiuenced cognitive function (all P < 0.05). Furthermore, residential environment, transportation, and community environment were identified as significant predictors of cognitive impairment (all P < 0.05).DiscussionLow scores in residential environment, transportation, community environment, and social inclusion in AFC are independent risk factors for cognitive dysfunction. Measures to enhance community age-friendly environments could help improve the cognitive function of older adults.

Pilot clinical study of Taxifolin Aqua effect in patients with amnestic mild cognitive impairment

Taxifolin (dihydroquercetin), a potent antioxidant flavonoid, shows promise for neurodegenerative conditions. Our pilot study aimed at evaluation the efficacy and safety of Taxifolin in patients with amnestic mild cognitive impairment (aMCI) and monitored a set of blood measures. Twenty-three patients (18 female; aged 53-87) received dihydroquercetin oral solution for 8 weeks with a 4-week follow-up period in an open-label study design. Thirteen patients with aMCI were monitored as controls. Outcomes were assessed using cognitive status (MMSE, MoCA, FCSRT-IR), neuropsychiatric symptoms’ (NPI-Q, HDRS), and rater’s impression (CGI) scales, along with blood measures monitoring (glutathione reductase (GR), glutamate dehydrogenase (GDH), and superoxide dismutase (SOD); plasma neutrophil elastase (NE), alpha-1-proteinase inhibitor (alpha-1PI)). Responder classification using composite Z-score changes was based on all clinical scales. Results: Eleven patients were classified as responders, showing significant MMSE and MoCA improvement (mean +2.73 points, p=0.001) sustained through 4-week follow-up. Non-responders and control group showed slight cognitive decline. Composite Z-score changes at the 4-week follow-up revealed differences between responders/non-responders (ANOVA F(2,20)=17.38, p=0.001); biomarker analysis revealed difference in NE/alpha-1PI ratio (p=0.034), SOD (p=0.023), and GR dynamics (p=0.022), which correlated negatively with clinical response (R=-0.547, p=0.007), and baseline GDH (p=0.049). Conclusion: Taxifolin treatment resulted in significant cognitive benefits in ~half of aMCI patients, with effects sustained for one month post-treatment. Biomarker changes reveal possible mechanisms involving oxidative stress modulation and inflammatory pathways. These findings support further controlled trials of Taxifolin in populations at risk of Alzheimer’s disease.

Routine Online Psychological Therapy in an Insurance-Based Care Setting: Retrospective Service Evaluation of Real-World Outcomes

<strong>Background:</strong> Depression, anxiety, and stress-related difficulties represent a major global health burden. Online psychological therapy has emerged as a promising approach to increasing access to care, yet evidence from routine, real-world clinical settings, particularly for services delivered without standardized treatment protocols, remains limited. <strong>Objective:</strong> This study aimed to describe symptom change and patient-reported satisfaction associated with routine online psychological therapy delivered within an insurance-based care setting. <strong>Methods:</strong> A retrospective observational service evaluation was conducted using deidentified routine care data. Clients aged 15 years and older who initiated online psychological therapy and completed baseline and end-of-treatment assessments on all 3 outcome measures were included. Symptoms of depression, anxiety, and perceived stress were measured using the 9-item Patient Health Questionnaire (PHQ-9), 7-item Generalized Anxiety Disorder (GAD-7), and 10-item Perceived Stress Scale (PSS-10), respectively. Changes in symptoms were examined using paired sample <i>t</i> tests, within-sample effect sizes (Cohen <i>d</i> and Cohen <i>d<sub>z</sub></i> with 95% CIs), and reliable change indices. Robustness was assessed with therapist-clustered mixed models and attrition sensitivity analyses. A ≥50% reduction in symptom scores was reported as a descriptive response criterion. Patient satisfaction was assessed with single-item ratings at the end-of-treatment assessment. <strong>Results:</strong> A total of 1221 clients were included. Clients completed a mean of 4.7 (SD 1.67) therapy sessions over an average treatment duration of 62.7 (SD 40.4) days. Significant reductions with large within-sample effect sizes were observed for depression (Cohen <i>d</i>=1.25, 95% CI 1.17-1.32), anxiety (Cohen <i>d</i>=1.49, 95% CI 1.41-1.57), and perceived stress (Cohen <i>d</i>=1.46, 95% CI 1.38-1.54). A ≥50% symptom reduction was observed in 60.7% (741/1220) of clients for depression, 67.5% (824/1221) for anxiety, and 30.8% (376/1221) for perceived stress. At the end-of-treatment assessment, 80.7% (985/1221) scored below the clinical cutoff for depression (PHQ-9&lt;10) and 79.2% (967/1221) for anxiety (GAD-7&lt;8). Reliable improvement was observed in 56% (688/1221) to 65% (794/1221) of clients, with deterioration below 2% on all measures. Mean patient-reported satisfaction scores ranged from 8.55 (SD 1.71) to 8.96 (SD 1.45) on a 10-point scale, and mean recommendation likelihood was 8.61 (SD 1.88). Therapist-level intraclass correlation coefficients were ≤0.029; effect sizes were 1.27-1.50 under inverse-probability weighting and 0.41-0.50 under zero-change imputation for baseline-screened clients without end-of-treatment assessments. <strong>Conclusions:</strong> Routine online psychological therapy delivered within an insurance-based care setting was associated with substantial pre-post symptom reductions, high proportions of clients meeting a descriptive ≥50% reduction criterion and showing reliable improvement, and high patient-reported satisfaction. Because the evaluation used an uncontrolled pre-post design restricted to clients with paired assessments, observed changes cannot be attributed causally to treatment. High satisfaction among responding clients is consistent with acceptability of the model to those clients; feasibility was not formally assessed, and inferences about comparative effectiveness require controlled designs.

Possible Role and Function of AI Conversational Agents in Dialectical Behavior Therapy for Borderline Personality Disorder: Qualitative Interview Study

Background: Borderline personality disorder (BPD) is associated with substantial distress and a high risk for suicide. Individuals with BPD may be unable to access evidence-based treatments like dialectical behavior therapy (DBT). Artificial intelligence conversational agents (AI-CA) are increasingly discussed as scalable tools for mental health support, but little is known about how DBT clinicians understand the possible role of AI-CA in treatment. Objective: This study aimed to explore DBT psychologists’ perspectives on integrating AI-CA into DBT for BPD in the future. Methods: Seventeen psychologists in Sweden, each with at least 1 year of clinical DBT experience (mean 6.4 years, SD 5.6), participated in semistructured interviews as part of this qualitative study. Interviews were conducted in Swedish, transcribed verbatim, and analyzed using reflexive thematic analysis within a constructivist framework. Participants did not test a specific AI-CA. Results: Three main themes were developed from the data. The first main theme, “Who Are We in Therapy?” explored how participants defined AI-CA relationally, positioning it variously as a tool, team member, or supervisor, and a sometimes harmful competitor. How these positionings were configured shaped what AI-CA was seen as allowed to do. The second main theme, “The Stoic Helper,” captured how AI-CA was constructed as an extension of the ideal helper: available, competent, adaptable, and tireless, able to provide support in moments when human therapists could not or preferred not to be present. Participants’ hopes for what AI-CA could become often mirrored qualities they found difficult to sustain in their own clinical work. The third main theme, “The Well-Intended Accommodator,” captured concerns that AI-CA may reinforce dependency and function as a safety behavior by supporting reassurance-seeking rather than autonomy. A central concern was not whether AI-CA could generate validating responses, but whether it could know when validation supports change and when it becomes maladaptive accommodation (AI functional ambiguity). Conclusions: Perceived benefits mainly centered on accessibility and support for DBT skills generalization, whereas key concerns involved alliance disruption, reinforcement of behaviors that would ideally be targeted for change, dependency, and questions regarding responsibility in high-risk situations. Integrating AI-CA into DBT is not only a technical question but a relational and ethical one. How AI-CA is positioned in relation to the therapist, person in treatment, and team shapes which tasks are considered acceptable and what form integration can take. The findings highlight the need for implementation frameworks that account for relational dynamics, treatment-specific considerations, and AI functional ambiguity that may arise when AI-CA operates in complex therapeutic contexts.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/f9ad53bc498740286d1d8cf4d14a712a" />

Assessing the Need for Mental Health Support From Free-Text Responses: Development and Validation of Language-Based Assessments in Adults With Internalizing Symptoms

Background: Machine learning and natural language processing have demonstrated significant potential for mental health assessment: describing your mental health in your own words can offer a more ecologically valid approach than traditional rating scales. However, most models focus on specific diagnoses, conditions, or symptoms, which may prematurely assign labels and potentially reinforce stigma in the context of early-stage mental health screening. Objective: This study develops a language-based assessment model that assesses the need for mental health support based on probed natural language and validates it against best-estimate assessments from multiple experienced psychotherapists. Methods: We analyzed an enriched online sample (n=600 for development and n=212 for validation), in which about half reported experiencing internalizing symptoms (depression or anxiety). Participants described their mental health using open-ended responses regarding (1) mental health, (2) suicidal thoughts, (3) medical history, and (4) depression. The responses were converted into contextual word embeddings using a large language model and entered as predictors in a ridge regression using nested cross-validation. Two to three experienced psychotherapists assessed each participant’s need for mental health support on a scale from 1 (no support needed) to 5 (potential crisis). Their assessments were based on longitudinal clinical data (natural language, validated scales, clinical interview, sociodemographics, and clinical history) and were averaged into a best-estimate assessment for model validation. We used the Sequential Evaluation With Model Preregistration framework, which separates model development from validation in a held-out set to support robust estimations and generalizability. Results: The language-based assessments closely aligned with the best-estimate assessments (=0.82) and showed strong correlations with established clinical rating scales for depression (Patient Health Questionnaire-9), anxiety (Generalized Anxiety Disorder 7-Item Scale), stress (Perceived Stress Scale 10), and suicidality (Inventory of Depression and Anxiety Symptoms; =0.62-0.77). Language-based visualizations of topics and word embeddings showed that low need for support assessments was associated with mentioning well-being and good health, while high assessments were related to depression, anxiety, and suicidality. Conclusions: This study demonstrates that natural language responses analyzed through large language models and machine learning can be used to assess individuals’ need for mental health support in close alignment with best-estimate assessments from experienced psychotherapists. Using less than 5 minutes of respondent time, this approach offers a practical tool for early-stage mental health screening in both clinical and self-guided screening contexts.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/40f89418adeebd12d72f99461723a61b" />