IntroductionEmotional maltreatment has been associated with problematic short-video use during adolescence, but the nature of this association remains unclear. This cross-sectional study examined the association between emotional maltreatment and problematic short-video use, estimated the indirect statistical association through narcissism, and tested whether physical activity moderated the direct association between emotional maltreatment and problematic short-video use.MethodsData were obtained in November 2025 from six schools across three Chinese provinces. The analytic sample included 1,622 adolescents, comprising 772 males and 850 females. Participants completed measures of emotional maltreatment, narcissism, problematic short-video use, and physical activity.ResultsEmotional maltreatment was positively associated with problematic short-video use, and an indirect statistical association was observed through narcissism. Physical activity moderated the direct association between emotional maltreatment and problematic short-video use, which was weaker at higher levels of physical activity.DiscussionConsidering a personality characteristic and a health-related behavior within the same model provides a broader understanding of the circumstances under which emotional maltreatment is associated with problematic short-video use. These findings may inform family- and school-based support concerning adolescents’ emotional needs, healthy short-video use, and regular physical activity.
STAT+: The head of Kennedy’s new autism project served in Iraq War, worked with Sesame Street
If you want to understand the federal government’s new initiative to improve autism care and diagnosis, it’s helpful to understand its leader, Russell Shilling.
Sitting in his Fairfax, Va., office, Shilling is flanked by a colorful tableau: a coterie of medals from his time in the armed forces and a sky blue puppet from his six years working with Sesame Street. He shares his felt doppelganger’s glasses and close-cropped hair, though not its hue.
An experimental psychologist, Shilling has led many lives. During his time in the Navy and at the Defense Advanced Research Projects Agency, he developed virtual reality therapy to help Iraq War veterans with PTSD and constructed early versions of chatbots to destigmatize mental health issues, bringing them into clinics.
Acceptability and Efficacy of a Culturally Adapted, Low-Frequency Parent-Mediated Early Start Denver Model (ESDM) Versus Standard Care in Young Children With Autism
Conditions: Autism Spectrum Disorder
Interventions: Behavioral: Early Start Denver Model
Sponsors: National University Hospital, Singapore
Completed
Interventions: Behavioral: Early Start Denver Model
Sponsors: National University Hospital, Singapore
Completed
AI Mental Health Tool vs. Psychoeducation Control
Conditions: Depressive Disorder; Depressive Symptoms
Interventions: Behavioral: Ash; Behavioral: Brief Therapist-Delivered Telehealth
Sponsors: Slingshot AI
Active, not recruiting
Interventions: Behavioral: Ash; Behavioral: Brief Therapist-Delivered Telehealth
Sponsors: Slingshot AI
Active, not recruiting
A Persian AI-Based CBT Chatbot and Voice Analysis System for Managing Perceived Stress
Conditions: Psychological Stress; Perceived Stress
Interventions: Behavioral: Persian AI-Based CBT Chatbot; Behavioral: Active Mental Health Content
Sponsors: Hamid Reza Marateb; Isfahan University of Medical Sciences; University of Isfahan
Not yet recruiting
Interventions: Behavioral: Persian AI-Based CBT Chatbot; Behavioral: Active Mental Health Content
Sponsors: Hamid Reza Marateb; Isfahan University of Medical Sciences; University of Isfahan
Not yet recruiting
Identifying Suicide Risk Based on the Words People Use
Researchers from the Child Mind Institute and MIT have developed a tool that can identify warning signs in text conversations, helping experts better understand who may need urgent support.
When someone is experiencing a mental health crisis, getting the right help quickly can be lifesaving. But it can be very difficult to determine who is in immediate danger.
New research suggests that the language people use during a crisis may offer important clues.
Daniel Low, PhD, a research scientist who leads the AI, Risk, and Contemplative Science (ARC) Lab at the Child Mind Institute, helped develop a tool that analyzes text conversations for language connected to known suicide risk factors. Dr. Low conducted the work while he was a graduate student at Harvard and MIT, in collaboration with Satrajit Ghosh, PhD, a senior research scientist and director of the Open Data in Neuroscience Initiative in the McGovern Institute at MIT.
The hope is that tools like this could one day help clinicians and crisis counselors spot warning signs more quickly. This way, they’ll have a better understanding of who may need immediate support.
Learning from real crisis conversations
Much of what researchers know about suicide risk comes from surveys asking people to reflect on their thoughts and experiences after a crisis has passed. But memory is not always complete, and a person’s experience may feel different once the immediate crisis is over.
To study what happens in the moment, the researchers partnered with Crisis Text Line, a nonprofit organization that provides confidential mental health support by text message. Following specialized training, the researchers were given protected access to a de-identified dataset of about 16,000 conversations. The data provided a rare opportunity to study what people were saying while actively seeking help during a crisis.
The conversations were grouped into three severity levels based on Crisis Text Line’s risk assessments: non-suicidal, suicidal ideation without imminent risk, and imminent risk. The imminent-risk group included conversations involving a plan for suicide within a 48-hour timeframe, immediate danger, or emergency service intervention.
To analyze the conversations, the team first built a library of words and phrases linked to established suicide risk factors. They used artificial intelligence to generate an initial list, then worked with expert clinicians to review and validate the results. The final lexicon contains thousands of terms spanning 49 suicide risk factors.
Researchers then trained a computer model to identify those patterns in the crisis conversations and estimate risk levels. And because the model is built on the lexicon, it can show which language contributed to a particular assessment. This allows counselors and clinicians to review the evidence behind a result rather than relying solely on a score from a computer — an important feature when decisions involve a person’s safety.
“This is such a complex space that having a human in the loop is, I think, going to be critical for a long, long time,” says Dr. Ghosh.
What the researchers found
Language related to lethal means, substance use, and active thoughts of suicide or self-harm appeared more often in imminent risk conversations. References to anxiety, post-traumatic stress disorder (PTSD), and emotional pain were also associated with risk, but were not among the highest-risk group. And while depression is a well-known risk factor for suicidal ideation, the model found expressions of depressed mood and fatigue were less closely associated with imminent risk than some of the more direct warning signs.
It’s important to note that this does not mean depression or any single warning sign is unimportant. It also does not mean that a word or phrase can predict what one person will do. Instead, the findings show which patterns of language were most strongly associated with the highest-risk conversations in this dataset.
What this could mean for mental health care
This tool is still in the research stage and requires further testing before it could be used in clinical settings.
Still, the work offers a new way to study how distress appears in language. By examining conversations that occur during a crisis rather than after the fact, researchers can gain a clearer picture of the thoughts, feelings, and experiences associated with different levels of risk.
The potential applications extend beyond crisis conversations. The suicide-risk lexicon is already being used to explore how language from sources such as social media and electronic health records might help researchers better understand and estimate suicide risk in other settings. The team has also made the lexicon and software publicly available so other researchers can build on the work and explore additional applications across a range of mental health conditions.
Dr. Low’s work is part of a broader effort at the Child Mind Institute. Through projects such as Mirror Journal, researchers at the Child Mind Institute are exploring how thoughtfully designed digital tools can help young people express what they are experiencing, process their emotions, and connect with support when they need it.
The findings were published in the Journal of Psychopathology and Clinical Science. Read the full paper.
The Suicide Risk Lexicon and tutorials to create lexicons are available here.
If you or someone you know is in immediate danger, call 911.
In the United States, call or text 988 to reach the 988 Suicide & Crisis Lifeline. The Crisis Text Line can be reached by texting HOME to 74174.
The post Identifying Suicide Risk Based on the Words People Use appeared first on Child Mind Institute.
Practical Guide to Large Language Models for Information Extraction in Behavioral Health Notes: Tutorial
Background: Mental health clinical notes contain decision-critical information often absent from structured electronic health record fields. Large language models (LLMs) can extract clinically relevant signals from narrative text; however, variability in output format, limited reproducibility, and inconsistent evaluation remain barriers to clinical deployment. Despite rapid advances in LLM-based information extraction, clear and reproducible guidance for interdisciplinary clinical teams is limited. Objective: This tutorial aims to present a structured workflow for zero-shot information extraction from mental health clinical notes using locally deployed open-source LLMs. It aims to reduce barriers for clinicians and researchers with limited familiarity with natural language processing (NLP) or LLM-based pipelines. Each stage includes key decision points and examples. The workflow is illustrated on two tasks using synthetic notes: (1) detection of self-injurious thoughts and behaviors (SITB) in pediatric emergency department (ED) notes and (2) antipsychotic medication nonadherence detection in outpatient notes, using schema-constrained outputs and standardized evaluation. Methods: We describe a five-stage zero-shot LLM pipeline: (1) infrastructure setup with local deployment via to prevent protected health information (PHI) transmission; (2) task definition specifying the clinical construct, output format, and evaluation; (3) dataset preparation using synthetic notes; (4) iterative prompt development using a hold-out development set with binary and Likert scale outputs constrained via JSON schemas; and (5) output parsing, normalization, and validation. We generated 300 synthetic notes per task using separate LLMs for generation and evaluation; 200 notes were used for evaluation, and 100 notes (50 positive and 50 negative) were used as a prompt-development set and excluded from final metrics. Evaluation used Large Language Model Meta AI (Llama) 3.2 and Llama 3.3 with deterministic decoding (temperature=0). Performance was assessed using accuracy, precision, recall, and -score; Likert thresholds were optimized using the Youden index with bootstrapped CIs. Results: We demonstrated the pipeline’s functionality using 2 example behavioral health detection tasks. Across both examples, the more capable model (Llama 3.3) performed better than the lighter model used earlier in development (Llama 3.2), and we described how the pipeline’s evaluation and error-analysis steps work in practice. These examples also illustrated 2 useful design choices: requiring the model to output in a fixed format reduced errors, and using a graded rating scale, rather than a simple yes/no format, allowed the detection threshold to be adjusted based on clinical risk tolerance. These results are meant to show that the pipeline works as intended, not to serve as a benchmark of real-world accuracy. Conclusions: A schema-driven, zero-shot LLM workflow can support reproducible extraction of clinically relevant information from narrative notes. Local deployment enables processing without transmitting PHI to external servers. This tutorial provides a transferable methodology for institutional adaptation and validation prior to clinical use. All prompts, code, and datasets are publicly available via Zenodo (European Organization for Nuclear Research [CERN]).
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/029d58368b7b6c5236836d88448abd8f" />
Prevalence of positive screens for depression, anxiety, and PTSD symptoms among parents of infants admitted to a NICU: a pilot study
IntroductionParents of infants admitted to the Neonatal Intensive Care Unit (NICU) may experience substantial psychological distress. This study aimed to assess the prevalence of positive screens for depressive, anxiety, and post-traumatic stress disorder (PTSD) symptoms and to explore their associations with gender, education level, and parental age. The study also described the coping strategies reported by participants.MethodsThis cross-sectional pilot study assessed 82 parents of infants admitted to the NICU at Thumbay University Hospital, Ajman. Parents who were primary caregivers and provided consent were included. Data were collected from March to July 2025 using self-administered questionnaires; Patient Health Questionnaire-9 (PHQ-9), Generalized Anxiety Disorder-7 (GAD-7), and PTSD Checklist for DSM-5 (PCL-5). They were then grouped based on whether they met the positive or negative screen criteria for the respective psychiatric symptoms.ResultsOut of the 82 parents who had participated, 22% screened positive for anxiety symptoms, 13.4% for depression symptoms, and 9.8% for PTSD symptoms. Female participants had a higher proportion of positive screen for depressive symptoms than male participants (20.5% vs. 4.8% in men, p = 0.043), and younger participants (≤30 years) had a higher proportion of positive screens for PTSD symptoms than those aged >30 years (17.5% vs. 2.4%; Fisher’s exact p = 0.027), although the small number of positive cases warrants cautious interpretation. No significant associations were found with education level. The most reported coping strategies were religious/spiritual (34.8%) and physical/behavioral (26.1%) methods.ConclusionA notable proportion of parents of infants admitted to the NICU in this UAE pilot cross-sectional study screened positive for symptoms of depression, anxiety, and PTSD, with female participants and younger participants showing higher proportions of positive screening for depressive and PTSD symptoms, respectively. These findings support consideration of mental health screening, promotion of a socially supportive environment, and culturally appropriate psychosocial support for parents of NICU-admitted infants.
Effects of psychedelic drug use on neurocognitive function and the psychological and social domains of quality of life: an international online study
BackgroundThe past few decades have seen a revived interest in psychedelic-assisted and ketamine-assisted therapy for mental health disorders, but data concerning the acute, subacute, and long-term effects of serotonergic psychedelics on cognitive functioning are scarce. This international, online study (N = 759) sought to investigate the potential acute, subacute, and long-term effects of psychedelic drug use on cognition through cognitive task assessment. Questionnaires assessing mental health and quality of life were also administered.MethodsParticipants completed cognitive tasks assessing working memory, selective attention, and visual/spatial perception, as well as questionnaires assessing mental health outcomes and quality of life. Based on self-reported substance use, participants were classified as non-users, lifetime users, and recent users.ResultsRecent users had significantly lower accuracy across all cognitive tasks, and lifetime users had the highest task accuracy without corresponding reaction time deficits, with the exception of the 2D mental rotation task. Lifetime use was not associated with long-term cognitive decline. Recent users reported more depressive and dissociative symptoms, whereas lifetime users reported lower scores. Lifetime users scored lower on psychological and social quality of life domains, indicating possible long-term psychosocial effects.ConclusionsThese findings highlight the need to differentiate between the acute and long-term effects of psychedelics; lab-controlled, longitudinal studies are needed to enable safe clinical application.
Effect of transcranial alternating current stimulation (NET Device™) on psychostimulant withdrawal severity and time course: a real-world data analysis
BackgroundPsychostimulant use disorder is a life-threatening condition with no FDA-approved treatment. Stimulant withdrawal symptoms impede treatment engagement and are unaddressed by standard of care. The NET Device, a non-invasive transcranial alternating current stimulator, is FDA-cleared for opioid withdrawal suppression. No studies have evaluated whether NET Device use attenuates psychostimulant withdrawal.MethodsElectronic health record and device utilization data were collected from 109 stimulant-only users and 112 stimulant/opioid co-users (N = 221 adults total; Mage=39.2, SDage=10.7; 119M) entering residential addiction treatment (n = 168) or detention centers (n = 53). The Amphetamine Cessation Symptom Assessment (ACSA) was administered at baseline and 1 hour (day 1), and twice daily on days 1–7. A linear mixed model (LMM) with random intercepts and slopes was used to analyze the trajectory of ACSA scores.ResultsACSA severity and time course were similar across settings (residential vs. detention). A two-phase LMM separated acute (baseline to 1 hour) and post-acute withdrawal symptom reductions. Relative to baseline ACSA scores, stimulant-only and co-user groups each reported significant reductions at 1 hour (46% and 33%), day 2 morning (59% and 42%), and decelerating log-time trajectory through day 4 (79 hours), the primary analysis window. Estimates beyond day 4 rest on 6.9% of observations and are reported as exploratory only.ConclusionNET Device monotherapy was associated with rapid reduction in psychostimulant withdrawal severity regardless of setting and opioid co-use. No device-related adverse events were reported. These real-world data support initiation of a sham-controlled randomized trial to evaluate NET Device efficacy for stimulant use disorder.