BackgroundPharmacy Intravenous Admixture Services (PIVAS) are now an integral part of patient care in modern hospitals. However, personnel working in PIVAS are often exposed to intense perceived stress, making them more susceptible to occupational burnout and anxiety, which may negatively impact their physical and mental health, as well as job performance. This study aims to explore the relationships between perceived stress, occupational burnout, research competence, and anxiety.MethodsA multicenter cross-sectional survey was conducted among PIVAS nurses and pharmacists from hospitals. Data were collected using a structured questionnaire that included sociodemographic information, work experience, perceived stress, and related psychological parameters. Structural equation modeling (SEM) was used to examine the hypothesized direct and indirect relationships among perceived stress, occupational burnout, and anxiety, and to assess the moderating role of research competence.ResultsA total of 609 healthcare professionals from 137 medical institutions in 20 provinces across China participated in the analysis, including 61.6% (375/609) nurses and 38.4% (234/609) pharmacists. 40.9% of participants exhibited symptoms of anxiety. SEM analysis revealed that perceived stress was significantly and positively associated with occupational burnout (z = 6.08, p < 0.05) and anxiety (z = 7.59, p < 0.05), with burnout showing direct and indirect effects within the hypothesized model. Moreover, research competence acted as a positive moderator in the relationships between perceived stress and occupational burnout, perceived stress and anxiety, as well as burnout and anxiety.ConclusionOccupational burnout, anxiety, and perceived stress are common among PIVAS nurses and pharmacists. The findings highlight that perceived stress is significantly associated with higher levels of burnout and anxiety symptoms. Notably, research competence moderated these associations. Healthcare institutions should prioritize effective stress management strategies, enhance employees’ research competence, and provide psychological support to mitigate the association between perceived stress and mental health. Future studies should explore the causal relationships between these variables and investigate targeted intervention approaches.
Correction: Smartphone App–Delivered Mindfulness-Based Intervention for Concussion in Adolescents (MBI-4-mTBI): Feasibility Randomized Controlled Trial
Addendum: Smartphone App–Delivered Mindfulness-Based Intervention for Concussion in Adolescents (MBI-4-mTBI): Feasibility Randomized Controlled Trial In response to the published article by Sicard et al. (doi: 10.2196/84623) in JMIR Rehabilitation and Assistive Technologies, we would like to correct the following errors in the article. The outcome measure used to assess anxiety was the Severity Measure for Generalized Anxiety Disorder—Child Age 11–17 (DSM-5 GAD-C), not the Generalized Anxiety Disorder 7-item scale (GAD-7). This affects 5 locations in the article and 1 reference.
Engagement, Feasibility, and Perceived Alliance With a Large Language Model–Enabled Mental Health Voice and Chatbot: Exploratory Longitudinal Observational Study
Background: Conversational AI systems are increasingly used for web-based mental health support, yet evidence on sustained engagement, therapeutic alliance, and longitudinal outcomes remains limited. Baseline data from 527 self-referred users of the large language model–enabled chatbot Clare indicated high psychological distress and early development of a subjective working alliance. Objective: This exploratory study examined the feasibility and descriptive outcome patterns associated with the use of the multimodal conversational agent Clare over 4 and 8 weeks in a real-world setting, focusing on engagement, perceived working alliance, and mental health measures. Methods: We conducted a naturalistic, single-arm, repeated-measures observational study of self-referred, English-speaking adults recruited online via social media and search advertisements. Participants interacted with Clare over 8 weeks. Two analytic samples were defined by engagement and assessment completion: a 4-week sample (active engagement plus completed 4-week assessment) and an 8-week sample (additionally requiring continued engagement and completed 8-week assessment). Outcomes were assessed at baseline, 4, and 8 weeks: engagement metrics (calls, messages, and call duration), alliance measures (Working Alliance Inventory–Short Revised and Mobile Agnew Relationship Measure), and mental health measures (Patient Health Questionnaire–4, Patient Health Questionnaire–Distress, Mini–Social Phobia Inventory, UCLA Loneliness Scale, and Satisfaction With Life Scale). Changes were evaluated using 2-tailed paired-samples tests with effect sizes; given substantial attrition and reliance on complete-case analyses, linear mixed-effects models were run as sensitivity analyses, and findings warrant cautious interpretation. Results: Of 527 baseline participants, 369 enrolled and 348 actively engaged with Clare; 53 out of 348 (15.2%) met the 4-week criteria and 21 out of 348 (6.0%) met the 8-week criteria. Engagement peaked in week 1 (calls: mean 1.77, SD 1.52; messages: mean 10.02, SD 16.68) and declined thereafter. Among T1-T2 complete pairs (n=52), mean Patient Health Questionnaire–Distress scores decreased by 1.13 (95% CI 0.25 to 2.02) points, Patient Health Questionnaire–4 scores decreased by 0.69 (95% CI −0.01 to 1.40) points, Mini–Social Phobia Inventory scores decreased by 1.73 (95% CI 0.88 to 2.58) points, Satisfaction With Life Scale scores increased by 6.23 (95% CI 4.70 to 7.76) points, and UCLA scores increased by 0.48 (95% CI 0.00 to 0.96) points. Among participants with Working Alliance Inventory–Short Revised data (n=53), total scores increased by 0.20 points from T1b to T2 (95% CI −0.01 to 0.42); among the 8-week retained subgroup (n=21), Mobile Agnew Relationship Measure scores increased by 0.22 points from T2 to T3 (95% CI 0.03 to 0.42). Conclusions: Sustained engagement was limited, and outcome estimates were obtained from small, highly selected follow-up samples. The observed changes cannot be attributed to Clare because the study had no control group and substantial, nonrandom attrition.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/cd3f2cc3028bd434440635f4eba17d45" />
Technology-Integrated Art Therapy: Scoping Review of Outcomes and Processes
Background: The rapid integration of digital technologies into art therapy reflects both technological advances and the growing need for flexible, accessible mental health care. Objective: This scoping review aimed to systematically map and synthesize empirical research in English on technology-integrated art therapy published from 2016 to August 2026. Methods: A comprehensive search across 9 electronic sources yielded 697 records, of which 47 empirical studies met the inclusion criteria according to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Results: The included studies were methodologically heterogeneous, comprising qualitative (n=19, 40.4%), quantitative (n=12, 25.5%), and mixed methods (n=16, 34%) designs, and were largely characterized by small samples and exploratory or feasibility-oriented approaches. Among the quantitative and mixed methods studies, 9 used randomized controlled or randomized experimental designs, while the remainder used nonrandomized or other designs. Reported quantitative outcomes included improvements in cognitive functioning, emotional regulation, mental health, behavioral symptoms, and functional outcomes; however, evidence for clinical effectiveness remained limited and heterogeneous. Qualitative and mixed methods studies reported potential benefits related to engagement, reduced performance-related anxiety, agency, emotional expression, and creative exploration. Digital affordances such as editing, layering, and multimodal creation were associated with iterative meaning-making and expanded expressive possibilities. In immersive contexts, particularly virtual reality, participants described altered sensory and embodied experiences. At the same time, technology raises concerns regarding privacy, data security, boundaries and setting, and the potential impact on the therapeutic relationship. Conclusions: Technology-integrated art therapy appears to offer promising possibilities for expanding access, engagement, expression, and therapeutic experience, but the current evidence remains too limited and heterogeneous to establish clinical effectiveness or mechanisms of change.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/ca1b310228d85e85ca9d5d942ac80868" />
The Best Kids’ Books About Mental Health of 2026
Children’s books about mental health can help young readers understand emotions, learn about their (or a friend’s) diagnosis, and build resilience. It seems like there’s a book for nearly any topic, from OCD, anxiety, or autism to body image, grief, or big feelings. That’s because the mental-health kids’ book category is burgeoning: For our third-annual best books list, we looked at nearly 200 titles published in 2026 — more contenders than we’ve ever had before — and narrowed them down to 70 semi-finalists. Then Child Mind Institute clinicians and editorial staff reviewed and rated the books, highlighting ones that accurately depict mental health challenges and how to help kids handle them, to settle on the 20 titles below as their top picks. From an adorable board book about mindfulness that features sensory stimulation to a young-adult novel about a 16-year-old with spiraling social anxiety, this list has something for every age, from toddler to teen.
For more kids’ books about mental health, see our list of past recommendations.
ADHD
ADHD! Understanding You, Your Brain, and How to Thrive in a Neurodiverse World
Written by Rachel Brian
An illustrated guidebook welcomes in all readers, whether they have ADHD or know someone who does. Each page utilizes graphics like comic panels, word balloons, and line drawings to help break down important topics including “What Is ADHD?” into bite-size pieces of information. It also gives ideas about how to handle challenges, like when big emotions show up or when you feel restless. Says a Child Mind Institute expert: “The visuals and language are child-friendly and will help kids understand an ADHD diagnosis.” Ages 7–10. Published by Little, Brown Books for Young Readers.
Get It Done & Have Fun!: ADHD Hacks for Awesome Kids
Written by Penn and Kim Holderness, illustrated by Vin Vogel
Narrated by a plucky, rhyming squirrel named Squeaky McGee, this book gives kids with ADHD advice on how to complete the mundane tasks that may trouble them. These tips are delivered in boisterous verse (“A hack is a way to take a dull chore — and make it a super-fun game you adore.”), with suggestions for brushing teeth, making the bed, and more. The authors bolster their catchy tale with an appendix that explains the importance of motivation and how parents can further guide their children in creating hacks. “I like how the book explains the components of what makes a good hack, which includes being interesting, challenging, and new,” says an expert from the Child Mind Institute. Ages 6–10. Published by Little, Brown Books for Young Readers.
Anxiety
The Caring Classroom: A Not So Perfect Start
Written by Trudy Ludwig, illustrated by Maribel Lechuga
Thea is just beginning school in this picture book, and she is desperately hoping that her first week will be flawless and her new teacher will like her. But no amount of preparation can ensure everything will go smoothly, and it doesn’t. Happily, Thea’s teacher emphasizes that everybody makes mistakes, and the important thing is being kind to yourself and others. “I really enjoy how the teacher normalizes feelings of anxiety by sharing with the kids that she gets nervous too,” says a Child Mind Institute expert. “The author also provides brief but helpful tips about how it’s okay to make mistakes, and what to do when you feel stuck.” Ages 3–7. Published by Alfred A. Knopf.
I Could Be Eaten by a Shark
Written by Marcela Ferreira, illustrated by Mark Chambers
With a mix of empathy and humor, this picture book helps kids face their fears. A boy is at the beach when he spots a small shark in the water, and he won’t go in. His grandfather takes him fishing on the lake instead, but it’s a no go. Every body of water, even a bubble bath, now makes the boy “jumpy” and “suspicious.” So grandpa decides to tell a story about his fear of bears when he was young and how he learned how to live with them. And it works! In a sweet ending, the boy, now an adult, passes on that wisdom to his grandchild. “I liked that the book discussed that fears are real and can always be present, but that it’s important not to let them get in the way of doing things you love,” says a Child Mind Institute expert. Ages 3–7. Published by Charlesbridge.
Sunday Scaries
Written by Debra Kempf Shumaker, illustrated by Lavanya Naidu
The dread that accompanies the end of the weekend grips Josie every Sunday, so she hatches humorous plans to avoid going back to school. However, when she actually gets to class, the week goes fine. So, why does the fear come back every Sunday, and why are her parents a bit grumpy that night also? The story has the family come up with clever ways to cope with the fear they share by focusing on the things that are worth looking forward to in the days to come. “I loved this book! It’s so realistic for children who experience anxiety about going to school. I enjoyed how her parents were able to acknowledge and empathize with her feelings,” says an expert from the Child Mind Institute. “At the end of the book, it provides simple, yet practical, tools for parents.” Ages 3–7. Published by Alfred A. Knopf.
How to Lose Yourself Completely
Written by Peter Bognanni
In this very engaging young-adult novel about wilderness “adventure therapy,” 16-year-old Case narrates the story, slowly revealing the details behind the loss of his older brother. When the kids’ counselor suddenly disappears, the group has to learn to work together to find their way home. “You’ll feel the crippling grip of social anxiety, the power of finding belonging and understanding with peers thrown together in a wilderness survival situation,” said a Child Mind Institute expert. “While there are some troubling scenes, including a wildfire, this book could and should inspire conversations.” Ages 14–18. Published by Harperteen.
Autism
Wilderness Hacks
Written by Joslin Brorsen
This middle-grade novel features two narrators: 12-year-old Sadie and Radley, who at 13 has become a famous YouTube influencer. Rad claims to be a survivalist, but Sadie has skills taught to her by her late father, whom she still misses. When she enters a contest to meet Rad, on behalf of her autistic brother Silas, the kids are swept into a dangerous adventure. They must contend with injuries, a mountain lion, their differences, and the emotional baggage they carry as they try to make it home alive. “This is a great book and hard to put down! It provides an inside view of what it is like losing a parent and how one copes by sister-smothering her autistic younger sibling,” says a Child Mind Institute expert. Ages 8–12. Published by Alfred A. Knopf.
Body Positivity
Some Body, Every Body
Written and illustrated by Roz Maclean
Utilizing pictures and a fun rhyme scheme to illustrate a myriad of body types, this book presents the scope of humanity, more so than in other books with a similar theme. “The author achieves the message of body positivity very well. The book shows so many body differences that aren’t shown often with well-done art and a diverse cast,” says a Child Mind Institute expert. “It’s an easy recommendation for a child with a disability or anything about their body they’re insecure about.” Ages 3–6. Published by Bloomsbury Children’s Books.
Depression
The Cloud That Stuck
Written by Karen Krossing, illustrated by Dorothy Leung
In this beautifully illustrated picture book, a persistent cloud hangs over Tansy’s head and grows so large that it begins to rain — but only on her. Tansy’s dad gives her a raincoat and umbrella, and her teacher sets up a fan to move the cloud, which help “a little.” Eventually, she begins to accept the cloud and discovers ways to make the best of a difficult situation with the support of friends and family. “The main character’s emotional reactions, including her sadness, frustration, and eventual resilience, are relatable and easy for young readers to connect with,” says a Child Mind Institute expert. “This story highlights perseverance through challenges that do not have an easy fix, while offering a hopeful message about acceptance, coping, and the importance of support from others.” Ages 4–8. Published by Charlesbridge.
Dyslexia
Professor Thomas Cat’s Guide to Understanding the Human Brain: The Dyslexia Files
Written by Rachel Allen, PhD, illustrated by Miguel Díaz Rivas
This graphic novel stars Professor Cat, a slightly arrogant feline scientist who takes Ava on a tour of a brain factory to explain how the mind of a kid with dyslexia works. The author, a neuroscientist, keeps things fun and light but doesn’t sugarcoat Ava’s situation. Ava has struggles, but her dyslexia also gives her strengths. The book includes experiments, such as a Dyslexia Simulator that allows people to see what reading for someone with dyslexia is like. An expert at the Child Mind Institute says that it “really dives into understanding dyslexia, including brain structures, characteristics, and support while being fun and easy to follow.” Ages 9–14. Published by Magination Press.
Emotions
I Need Space
Written by Molly Harris, illustrated by Jon Corby
A rocket ship named Rocco loves blasting around the solar system. For Rocco, the rings of Saturn are like slides and the tethers of space stations are swings. Unfortunately, this out-of-this-world playground also has satellites that hog rides and rovers that steal toys. Eventually the roughhousing of the meteors drives Rocco away from the galaxy, looking for relief. The peaceful calm of an empty region lets him regain his cool, and he is able to brave going back. “The story is a clever play on words with the character needing space and the action taking place in space,” said a Child Mind Institute expert. “It also shows ways you can handle needing space.” A list of great tips is found alongside a brief astronomy guide to some of the wonders Rocco encounters. Ages 4–8. Published by Simon & Schuster.
Waiting for Iced Tea
Written by Karen Gebbia, illustrated by Mette Engell
A cozy, gentle story about patience comes on a hot day when Nana sets out to make Charlotte her real iced tea. There are many steps to Nana’s recipe, so she tells Charlotte to find something useful to do while she waits. But the tea is still not ready! As the hours pass, something surprising happens: Charlotte stops wanting to speed up the tea-making process and starts noticing the beautiful moments inside the waiting. “I like the message of finding ways to tolerate waiting and even finding the fun in them,” says a Child Mind Institute expert. She also appreciates the back matter for parents on how to help kids wait more patiently and enjoy slower moments. Ages 5–9. Published by Lerner Books.
Set My Feelings Free
Written by Jon Fogel, illustrated by Jess Fogel
A brilliant rhyming picture book that can be sung to the tune of “Twinkle, Twinkle Little Star” covers many emotions, from frustration to disappointment. It pairs the feelings with mindfulness strategies to work through them. For example, when a child is frustrated, the book encourages kids to “Run in circles, twist and shout. Let the feelings all come out.” Says a Child Mind Institute expert: “This book would be good for both the grown-up and child reading it because it gives grown-ups a way to help kids express and manage feelings. The note to caregivers at the end is very digestible and helpful, as are the emotion regulation games.” Ages 3–5. Published by Beaming Books.
Grief
Everything New Again
Written by Renée Watson
This young-adult novel introduces readers to 17-year-old Bliss, who in the span of two weeks meets and falls in love with her co-narrator Solomon. Bliss’s family runs a funeral home, which gives her both a reputation as being a bit strange and an interesting perspective on grief. Both kids are confronted by death, even as their romance begins, but the story retains a sense of hope thanks to Bliss’s attitude. “The book was a very engaging read. Among the themes is learning to accept the realities of life and death,” said a Child Mind Institute expert. “Woven into the narrative is how to navigate these situations in a healthy way.” Ages 12–18. Published by Bloomsbury.
More Than a Tree
Written by Sarah Kurpiel
A young girl processes loss when her beloved backyard tree has to be removed. Although the parents knew the day will come, the girl isn’t prepared and struggles emotionally with the inevitable. The family presses some of its leaves as a remembrance. “Gentle and reassuring, this book can help foster conversations about sadness, loss, coping with change, the circle of life, and resilience,” says a Child Mind Institute expert. “The story ends on a hopeful note as she plants a new tree in its place and takes on the role of caregiver, illustrating how new life can emerge after loss and how love, memories, and growth can continue even as things change.” Ages 4–8. Published by Penguin Random House.
Mindfulness
Breathe a Rainbow
Written and illustrated by Julie Koon
In this board book, children can trace their fingers over eight die-cut, differently textured surfaces that take the shape of natural wonders like stars, waves, mountains, flowers, and, of course, rainbows. While they touch these colorful pictures, they’re instructed to breathe in and out to cope with any difficult feelings they may be experiencing. “I love how this simple book pairs feelings and the mindfulness technique of shape breathing,” said an expert from the Child Mind Institute. “The book is easy to read with cute visuals and applies the senses through using different textures.” Ages 2–4. Published by Abrams Books.
Neurodivergence
All the Ways We Learn
Written by Chloe Ito Ward, illustrated by Yaroslava Apollonova
Starting with the prompt “What does learning look like?” the book begins with an image of circle time, and the idea: “Sometimes learning looks like…crisscross applesauce, hands in your lap.” But one of the kids isn’t happy, and she supplies an alternative: “But I don’t learn like that. I tap my feet on the floor with arms bouncing on my knees or squeezing a ball. When my body moves, I can learn.” And so it goes, with different kids sharing a broad range of learning practices. “I liked that this book normalizes all the different accommodations and ways kids learn!” says a Child Mind Institute expert. “I also appreciated the glossary of terms and possible accommodations at the end. I think this book would be good for both children with learning differences and those without, to normalize the experience.” Ages 3–6. Penguin Random House.
OCD
Exposures
Written and illustrated by Lily Williams
Peyton is a young girl dealing with OCD (obsessive-compulsive disorder), which has caused her to stop doing many of the things she enjoys. She’s frightened that she might hurt herself or her sister, unless she avoids some things around her, such as the color red. The graphic novel’s art and lettering brilliantly depict her thoughts as intrusive and all-consuming. However, there is also a sweetness and warmth to the characters that makes readers want to root for Peyton as she bravely enters therapy. The author, who also has OCD, realistically depicts ERP (exposure and response prevention), in which “you are repeatedly exposed to your fears until they become less scary.” A Child Mind Institute expert believes that the story “describes OCD and ERP well through very adolescent-friendly language.” Ages 8–12. Published by First Second.
Postpartum Depression
Together for Mama: A Story of Hope and Healing
Written by Pooja Makhijani, illustrated by Nadia Alam
This gentle picture book follows Asha, who is so thrilled to welcome her newborn sister Maya home from the hospital that she is bubbling over with excitement. However, she’s surprised that her mother doesn’t seem to share her joy. As a matter of fact, Mama is distracted, anxious, and teary. Fortunately, her Papa doesn’t hesitate to call in Asha’s grandmothers as reinforcements. Together, the family eases Mama’s daily burdens and gives her the time and space she needs to recover. “This is a simple story that teaches kids about postpartum depression,” says an expert from the Child Mind Institute. “The book is helpful for mothers or other caregivers to read to youngsters, allowing them to acknowledge the sadness their child is likely already aware of, and not keeping that information hidden.” Ages 5–8. Published by Penguin Random House.
Self-Esteem
Hanna Asks for Help
Written and illustrated by Tom Percival
In this charming picture book, Hanna excels in sports, but math leaves her confused. Her initial plan to just pretend that she understands naturally doesn’t work out. She’s visited by a spritely, glowing ball of energy called Help, who encourages her to ask for assistance. Sure enough, this works for finding things and tying her laces, but can it help with arithmetic? When it does, Hanna realizes she can offer help herself to others who struggle with the things that she finds easy. “The book has a good description of learning challenges, the hesitancy around asking for help, and a really nice resource at the end about everyone having different strengths,” says a Child Mind Institute expert. Ages 3–6. Published by Bloomsbury Children’s Books.
The post The Best Kids’ Books About Mental Health of 2026 appeared first on Child Mind Institute.
Preventive and Personalized Digital Emotion Regulation Skills Intervention to Reduce Depression and Anxiety in Youths With Adverse Childhood Experiences
Conditions: Adverse Childhood Experience; Depression / Major Depressive Disorder; Anxiety Depression; Anxiety
Interventions: Behavioral: Lifestyle psychoeducation intervention; Behavioral: Personalized digital psychoeducation intervention on emotion regulation
Sponsors: Institute of Mental Health, Singapore
Not yet recruiting
Interventions: Behavioral: Lifestyle psychoeducation intervention; Behavioral: Personalized digital psychoeducation intervention on emotion regulation
Sponsors: Institute of Mental Health, Singapore
Not yet recruiting
Modeling of Therapist-Client Dynamics in Psychotherapy Using Large Language Model–Based Assessments: Retrospective Observational Study of 1573 Psychotherapy Sessions
<strong>Background:</strong> Psychotherapy is a primary treatment for many mental health conditions, yet the dynamic interplay among therapist behaviors, client responses, and the therapeutic relationship remains difficult to disentangle at scale. Traditional process research relies on labor-intensive human coding, limiting the ability to model moment-to-moment therapeutic dynamics across large datasets. <strong>Objective:</strong> This study aimed to develop and validate a computational framework for modeling therapist-client interaction processes and to examine how therapist behaviors and relational qualities relate to client self-disclosure and emotional expression in psychotherapy sessions. <strong>Methods:</strong> We developed automated assessment pipelines using large language models (LLMs) to measure therapist behaviors (empathy or exploration), relational quality (rapport), and client outcomes (self-disclosure, self-directed negative emotion, or outward-directed negative emotion). Model-generated scores were validated against human annotations. We then applied these measures to approximately 2000 hours of psychotherapy transcripts from the Alexander Street corpus. This yielded an estimation sample of 119,233 client utterances from 1573 sessions and 37 clients. Because utterances are nested within sessions and sessions within clients, we estimated a saturated multivariate structural equation model with SEs clustered at the session level. Results were confirmed in a multilevel regression model with random intercepts for session and client. <strong>Results:</strong> Following comparative validation of 6 candidate language models, automated measures showed good to excellent agreement with human annotations (intraclass correlation coefficient [ICC]=0.60-0.81) for rapport (ICC=0.81), self-disclosure (ICC=0.78), empathy components (ICC=0.60-0.75), and emotion measurements (ICC=0.66-0.80). Structural equation modeling analyses revealed that therapist empathy and exploration were each associated with increased client disclosure (empathy: β=.086, 95% CI 0.078-0.095; exploration: β=.086, 95% CI 0.078-0.094; both <i>P</i><.001) and increased expression of self-directed negative emotions, comprising sadness, anxiety, fear, and depression (empathy: β=.118, 95% CI 0.110-0.127; exploration: β=.078, 95% CI 0.070-0.087; both <i>P</i><.001). Both behaviors were also associated with reduced expressions of enjoyment (empathy: β=–.037; exploration: β=–.041; both <i>P</i><.001). Surprisingly, rapport in the prior session showed no association with client self-disclosure or negative emotion expression. <strong>Conclusions:</strong> This study demonstrates that LLM-based measurement combined with structural modeling can capture core therapeutic processes at scale. Empathy and exploration showed small but consistent turn-level associations with client disclosure and emotional expression, whereas prior-session rapport did not show a robust association. These findings provide a computational foundation for precision modeling of psychotherapy processes and may offer actionable insights for scalable therapist training and AI-supported clinical education systems.
Latent profile analysis of sleep quality and associated factors in Chinese adolescents with major depressive disorder
BackgroundSleep disturbances are pervasive among adolescent patients with major depressive disorder (MDD), yet the heterogeneity of sleep phenotypes within this population remains underexplored. This study aimed to identify latent profiles of sleep quality in Chinese adolescent patients with MDD and to examine their associations with sociodemographic, clinical, and psychosocial factors.MethodsA total of 1,467 adolescent patients with MDD were assessed using the Pittsburgh Sleep Quality Index (PSQI), Generalized Anxiety Disorder-7 (GAD-7), Patient Health Questionnaire-9 (PHQ-9), the Borderline Personality Features Scale for Children (BPFS-C), and a self-designed sociodemographic and clinical inventory. Latent profile analysis (LPA) was conducted using the seven PSQI component scores as profile indicators. Multinomial logistic regression was subsequently performed to determine factors associated with profile membership.ResultsA five-profile solution was identified: Normal Sleep Group (13%), Mild Disturbance-Low Hypnotic Use (36%), Mild Disturbance-High Hypnotic Use (22%), Severe Disturbance-Low Hypnotic Use (16%), and Severe Disturbance-High Hypnotic Use (13%). Logistic regression revealed that the presence of non-suicidal self-injury (NSSI) and exposure to negative life events significantly increased the odds of belonging to more severe sleep disturbance profiles (OR = 2.92-8.37 and 2.33-2.60, respectively; all p < 0.05). Notably, patients without left-behind experiences exhibited higher odds of being classified into the Severe Disturbance-High Hypnotic Use profile compared to those with such histories (OR = 0.46, p < 0.001). Furthermore, profiles characterized by poorer sleep quality and profiles characterized by more frequent self-reported sleep medication use were cross-sectionally associated with greater anxiety and borderline features in this study.ConclusionSleep quality among adolescent patients with MDD exhibits distinct typological heterogeneity, characterized primarily by severity and hypnotic use patterns. These findings provide preliminary exploratory evidence for the development of personalized, profile-informed clinical interventions for this vulnerable population.
Social Desirability Bias in Health Screening Questionnaire Responses Generated by OpenAI Models: Quantitative Experimental Study
<strong>Background:</strong> Social desirability bias, the tendency to respond in ways that present the respondent favorably, is well documented in human self-report and has recently been observed in large language models (LLMs) completing personality inventories. Whether it also affects LLM responses to validated health screening instruments, where LLMs are increasingly proposed as simulated patients or synthetic respondents, has not been examined. <strong>Objective:</strong> This formative study aimed to determine whether 4 OpenAI models alter their responses to health screening questionnaires when the instrument and its evaluative purpose can be inferred from the prompt and to quantify the size and direction of any shift. <strong>Methods:</strong> GPT-4o, GPT-4o mini, o1-mini, and o1 were prompted through the OpenAI application programming interface in April 2025 to complete the Generalized Anxiety Disorder-7 (GAD-7), Patient Health Questionnaire-9 (PHQ-9), Alcohol Use Disorders Identification Test (AUDIT), and FANTASTIC lifestyle assessment while adopting the persona of a random member of the public. Each instrument was administered under a naive condition, wherein every item was presented alone in a separate call so that the instrument could not be recognized, and an informed condition, in which all items were presented together, with 100 completed trials per model, instrument, and condition. Naive and informed scores were compared within each model using independent-samples 2-tailed <i>t</i> tests with Bonferroni correction for 16 comparisons, with effect sizes expressed as Cohen <i>d</i> and in units of published general-population SDs. Published human norms served only as descriptive reference points. <strong>Results:</strong> In 14 of 16 model-instrument combinations, scores shifted significantly toward the socially desirable pole when the instrument was recognizable (all <i>P</i><.001): fewer anxiety and depressive symptoms, lower reported alcohol use, and healthier lifestyle behaviors. Mean shifts were 3.2 to 8.2 points on the GAD-7, 2.4 to 11.9 on the PHQ-9, 2.8 to 4.5 on the AUDIT for the o1 models, and 8.2 to 13.5 on the FANTASTIC lifestyle assessment (Cohen <i>d</i>=1.0-8.6). GPT-4o’s AUDIT shift (0.36 points; <i>P</i>=.04) did not survive correction, and GPT-4o mini shifted in the opposite direction on the AUDIT (–2.69 points; <i>P</i><.001). The largest shifts on the mental health instruments occurred in GPT-4o mini, whereas the largest AUDIT shifts occurred in the 2 reasoning models. <strong>Conclusions:</strong> When a screening instrument was recognizable, the 4 OpenAI models tested consistently produced more socially desirable responses than when the same items were presented in isolation. The design cannot separate evaluative inference from other consequences of presenting items together, and the findings are confined to one vendor’s models. Therefore, they constitute formative evidence that social desirability bias may extend to health screening contexts—not evidence of a general property of LLMs. Studies using LLMs as simulated patients or synthetic respondents should report prompt framing and audit for framing-dependent shifts before relying on generated data. <strong>Trial Registration:</strong>
Engagement Patterns and Clinical Outcomes Among Adolescents and Young Adults Enrolled in the Somethings Digital Peer Support Platform: Retrospective Observational Study
Background: Adolescent mental health needs remain largely unmet, particularly among youth in geographically underserved communities. Digital peer support is a promising approach to expanding access to mental health support, yet real-world evidence on engagement patterns and clinical outcomes remains limited. Objective: The purpose of this study was to characterize engagement patterns and real-world outcomes among adolescents and young adults enrolled in a commercially available, text-based peer support platform. Methods: This retrospective observational study analyzed secondary data from 5673 adolescents and young adults enrolled in a commercially available digital peer support platform from January 29, 2023, through June 3, 2026. Engagement was operationalized as communication days per month. Standardized clinical outcome measures (Patient Health Questionnaire-9 [PHQ-9], Generalized Anxiety Disorder-7 [GAD-7], and World Health Organization-Five Well-Being Index [WHO-5]) were administered as part of routine measurement-based care. Ordinary least squares regression was used to examine predictors of engagement, and complete-case pre-post change scores were evaluated across 4 assessment windows among participants with paired assessments. Results: The sample was predominantly female (4600/5673, 81.1%) with a mean age of 16.4 (SD 2.1) years and moderate-to-severe symptom burden at baseline (PHQ-9: mean 12.6, SD 6.1; GAD-7: mean 10.7, SD 5.0; WHO-5: mean 44.8, SD 21.0). Of enrolled adolescents and young adults, 98.1% (5565/5673) had at least one recorded engagement with the platform, with a mean of 4.56 (SD 6.12) communication days per month. Female sex was a significant positive predictor of engagement intensity (β=.64, SE 0.22; =.004). Hispanic and Latino adolescents and young adults engaged significantly more frequently than White or non-Hispanic adolescents and young adults (β=.61, SE 0.26; =.02). Health Professional Shortage Area (HPSA) shortage score was significantly and positively associated with engagement intensity (β=.08, SE 0.02; <.001). Baseline symptom severity was not associated with engagement intensity (β=.094, SE 0.23; =.68). Among participants with complete baseline and follow-up data (1437/5673, 25.3%), an exploratory complete-case analysis found within-measure paired scores improved significantly from baseline to follow-up across the PHQ-9, GAD-7, and WHO-5. At last assessment, 31.9% (237/742), 36.6% (222/606), and 37.8% (168/442) of adolescents and young adults met clinically meaningful improvement thresholds on the PHQ-9, GAD-7, and WHO-5, respectively. Conclusions: Text-based peer support shows preliminary promise as a scalable approach to expanding mental health access for underserved adolescents, though clinical improvement estimates are based on the subpopulation exposed to the digital peer support platform and may not generalize to the full enrolled population. Prospective, controlled studies with more complete outcome ascertainment are needed to establish causal efficacy.
