Modeling Short-Term Symptom Changes and Behavioral Subtypes of Depression and Anxiety in the General Population: Observational Study Using Smartphone Data
Background: Smartphone-based digital phenotyping has emerged as a promising approach for monitoring mental health using passive behavioral data. Prior studies have linked smartphone-derived features to depression and anxiety severity; however, knowledge regarding whether short-term changes in symptoms can be captured using passive smartphone data in general population samples remains limited, as does the understanding of how such findings should be interpreted vis-à-vis behavioral patterns and demographic variability. Objective: This study aimed to model short-term changes in depression and anxiety severity using passive smartphone data, examine model performance across demographic subgroups, and identify behavioral patterns associated with symptom changes. Methods: We collected 2 weeks of smartphone usage data from 95 adults in the general population and assessed depressive and anxiety symptoms using the clinician-rated Hamilton Depression Rating Scale and Hamilton Anxiety Rating Scale, respectively. Behavioral features—including physical activity, app use, and screen usage metrics—were extracted and compressed using an autoencoder and principal component analysis. The resulting features—along with age, sex, and baseline Hamilton scores—were used to train random forest classifiers predicting symptom score changes (increase, decrease, or unchanged). Additionally, we examined whether model performance differed across demographic subgroups and whether models excluding baseline scores retained predictive performance, as baseline severity was expected to be a strong predictor. To add explanatory value beyond prediction, behavioral subtypes associated with symptom changes were identified by applying unsupervised clustering. Results: The model exhibited moderate performance in predicting changes in the Hamilton Depression Rating Scale (mean accuracy=0.70, mean area under the receiver operating characteristic curve=0.74) and Hamilton Anxiety Rating Scale (mean accuracy=0.65, mean area under the receiver operating characteristic curve=0.69) scores. Performance varied according to demographics, with reduced accuracy among younger adults and females, although these differences were not significant in permutation tests. Excluding baseline Hamilton scores diminished performance substantially, suggesting that baseline symptom severity accounted for a substantial proportion of the predictive performance. Clustering revealed 4 distinct behavioral subtypes according to smartphone usage patterns. A cluster characterized by structured, daytime-focused smartphone use and lower temporal entropy demonstrated greater improvement in depressive symptoms, whereas clusters with lower and irregular usage patterns exhibited minimal improvement or worsening. Conclusions: Passive smartphone-derived behavioral data demonstrated moderate ability to model short-term symptom changes in this predominantly nonclinical sample. However, a substantial proportion of the predictive performance was attributable to baseline symptom severity, underscoring that passive smartphone data may provide modest supplementary information rather than robust stand-alone predictive value. Nevertheless, clustering analyses indicated that passive data may still assist in identifying behaviorally distinct subtypes associated with different depressive symptom trajectories. These findings reflect a practical contribution to digital phenotyping research by elucidating both the potential and constraints of passive smartphone data for short-term symptom monitoring in small general population samples.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/2b5b9064697224d28bcc61cc4b38c531" />
Development and Formative Evaluation of a Narrative-Based Serious Game for Pregnancy Education: Mixed Methods Study
Background: Serious games are increasingly used in professional health education and maternal health promotion. However, most pregnancy-related digital interventions target specific behaviors and do not provide a comprehensive, longitudinal simulation of the pregnancy journey that incorporates psychosocial and administrative aspects. Objective: This study aimed to develop and evaluate a narrative-based serious game that simulates the chronological course of pregnancy and to assess its perceived educational usefulness, accessibility, and user acceptance across multiple platforms. Methods: We developed a 9-chapter interactive serious game covering pregnancy recognition, partner communication, public health consultation, mid-pregnancy and late-pregnancy checkups, and home preparation for childbirth. The game was collaboratively created by a pediatrician, 6 medical students, and a student illustrator using a low-cost visual novel engine (TyranoBuilder). It was released in April 2025 on iOS, Android, and Steam. A voluntary, anonymous postgame survey was conducted between April 2025 and January 2026. Descriptive statistics were used to summarize survey responses and platform analytics. This study was approved by the Ethics Committee of Shinshu University Hospital. Results: A total of 65 users completed the postgame questionnaire. Most respondents were aged 10 to 19 years (38/65, 58.5%) and female (55/65, 84.6%). Nearly half of the participants (30/65, 46.2%) completed the game within 1 hour. Gameplay evaluation scores (5-point Likert scale; 3=neutral or appropriate) were balanced: game length (mean 3.37, SD 0.96), difficulty (mean 2.84, SD 0.85), and interactivity (mean 3.31, SD 1.10). Educational outcomes were rated highly (5-point Likert scale; higher=more favorable): reduced anxiety (mean 3.84, SD 0.96), perceived educational usefulness (mean 3.98, SD 1.02), perceived knowledge acquisition (mean 4.06, SD 1.06), story empathy (mean 3.80, SD 1.11), and overall satisfaction (mean 4.05, SD 1.04). Across all platforms, the game achieved 925 cumulative downloads. iOS and Android downloads were predominantly from Japan, whereas Steam downloads were geographically diverse. Of the 21 Steam reviews, 20 (95.2%) were positive. Conclusions: A serious pregnancy education game developed through a low-cost clinician-student collaborative model demonstrated high perceived educational usefulness, balanced gameplay characteristics, and broad user acceptance, including substantial engagement among teenagers and international users. Narrative-based serious games represent an accessible and scalable approach to maternal health education. Further research using more rigorous evaluation designs is warranted to assess long-term educational and behavioral impacts.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/e2f36ab34de77d0bdb26718b9c29b61f" />
Very Low Uptake in Workplace Semen Analysis Research: Formative Web-Based Cross-Sectional Follow-Up Survey Distinguishing Employees With Self-Reported Unawareness From Aware Nonparticipants
Background: Very low uptake in workplace semen analysis research is difficult to interpret, particularly in employer-adjacent settings, where nonparticipation may reflect limited recruitment reach, limited understanding of the occupational rationale, low perceived relevance, or procedure-related concerns. Objective: This post hoc formative study described self-reported awareness of a parent workplace semen analysis study as an indicator of effective recruitment reach, reported reasons for nonparticipation under the implemented survey condition, and design issues for exposure-defined workplace reproductive health research. Methods: In April-May 2025, we conducted an anonymous web-based cross-sectional follow-up survey among male employees in Japan who had been eligible for, but had not completed, a parent workplace semen analysis study. The parent study invited approximately 2000 male employees from 3 companies between November 2024 and January 2025; 6 completed the protocol. The follow-up survey invited approximately 900 male employees from 1 company. Part 1 assessed awareness, reasons for nonparticipation, interest in male reproductive health information, and general openness to future related research. Optional Part 2 assessed age, knowledge, concerns, expected reactions, and willingness under simplified conditions. Responses were summarized descriptively using Wilson 95% CIs; no hypothesis testing was performed. Results: We analyzed 108 submitted questionnaires; 83 respondents completed Part 2. Overall, 74/108 (68.5%; 95% CI 59.3‐76.5) respondents reported no awareness of the parent study. Among unaware respondents, 68/74 (91.9%; 95% CI 83.4‐96.2) selected “did not know the study existed.” Among aware nonparticipants, the most frequent reasons were perceived irrelevance and resistance to collecting semen (each 9/34, 26.5%; 95% CI 14.6‐43.1), embarrassment or reluctance (8/34, 23.5%; 95% CI 12.4‐40), and hassle (7/34, 20.6%; 95% CI 10.3‐36.8). In Part 2, anxiety about unfavorable results was reported by 52/83 (62.7%; 95% CI 51.9‐72.3) respondents, concerns about collection location or privacy protection by 48/83 (57.8%; 95% CI 47.1‐67.9), and self-reported resistance by 42/83 (50.6%; 95% CI 40.1‐61.1). Under simplified conditions, 36/83 (43.4%; 95% CI 33.2‐54.1) respondents indicated willingness to undergo semen analysis. Conclusions: Very low uptake in this employer-adjacent semen analysis study was not interpretable as a single phenomenon. This post hoc formative process evaluation identified limited awareness, suggesting limited effective recruitment reach under the implemented procedures, and characterized the reason profile among aware nonparticipants, including low perceived relevance and semen collection–related concerns. Rather than identifying primary causal determinants of nonparticipation, the findings support a bounded recruitment-methodological interpretation and highlight recruitment-cascade components for prospective measurement: objective exposure to recruitment materials, information access, understanding of the occupational rationale, voluntary postinformation declination, privacy concerns, logistical burden, and specimen-return completion. Informed acceptability after occupational reproductive-hazard education should be evaluated in future designs that include such education and comprehension assessment.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/5074771fda02afb1286842c831d3f8f2" />
Efficacy of a Gamified Blended Mindfulness Program to Reduce Burnout, Stress, and Anxiety in Nursing Students: A Randomized Controlled Trial
Interventions: Behavioral: Psychoeducation and Free App Recommendation; Behavioral: Standard Blended Mindfulness Program; Behavioral: Gamified Blended Mindfulness Program
Sponsors: Universidad de Granada
Completed
Maintaining Emotional Boundaries as a Parent
Parents often emphasize to children the importance of respecting others’ boundaries — don’t tickle another kid if they say they don’t like it, for example. Don’t kiss someone unless they welcome it. But within the family, we can fail to notice our own difficulty setting and respecting boundaries with our children, especially emotional boundaries.
What are emotional boundaries
Emotional boundaries refer to an individual’s sense of autonomy and ability to control how they think, feel, and engage with others. Those boundaries are crossed either when you try to control someone else’s thoughts or feelings or they try to control yours.
Difficulty setting your own and respecting others’ emotional boundaries often comes from a place of care and concern. Parents are usually concerned that their child is not going to make safe choices or are trying to protect their child from distressing emotions. But the intrusion can have a negative impact on children’s emotional development as well as parents’ mental health, especially when it’s done repeatedly. Everyone has boundaries, even parents, and it’s important for kids to learn that.
How parents overstep their child’s emotional boundaries
Parents can inadvertently encroach on their child’s right to their own thoughts and feelings through:
- Over-involvement in children’s academic and social life: Your child has a whole life outside the home, and it can be anxiety-provoking to trust them to manage their homework, advocate for themselves with teachers, and navigate conflicts with peers. It can alleviate your anxiety to get involved, but that can feel highly intrusive to your child. For example, if your kid feels snubbed by a friend, you might feel the urge to contact that friend’s parent to try to smooth things over. However, over-involvement in these tasks can prevent your kid from developing the skills they need to manage challenging situations successfully and can impact their confidence in their ability to cope independently.
- Overconcern to protect your child’s safety: Fears that something negative will happen to your child are understandable, but aggressive monitoring can backfire. This can include strict control over the ingredients in your teen’s food, the information they consume online, or what activities they do. This may temporarily alleviate anxiety about the child’s health and safety but it can lead to resentment and rebellion.
- Ignoring or rejecting children’s requests for privacy: It is normal for children and adolescents to want more privacy as they mature, from showering alone to keeping a private diary.Unless your child engages in an activity that suggests they are being unsafe, it is important to trust your child and let them decide what to share with you.
- Sharing private information without the child’s permission: Parents telling anecdotes about their children, much to their kids’ embarrassment, is hardly new. However, that sharing now includes photographs and videos posted on social media that is broadcast far beyond close friends.It is important to include your child in decisions about what information is shared with others (excluding, of course, medical professionals). When in doubt, consider what information you would feel comfortable with them sharing about you.
- Telling children what is or isn’t acceptable to value, think, or feel: Many parents, in an effort to help their child feel better, say things like, “Don’t worry about that” or “You can’t think that way.” These seemingly innocuous phrases can come across as attempts to control how the child feels. We can forget that kids are real people just like adults. And if they’re mad or upset about something, they want to be able to feel those feelings, not be told that that their feelings are wrong.
How parents fail to set their own emotional boundaries
Letting kids change your own values, thoughts, and feelings can also be unhealthy. Here are some common ways in which parents fail to set their own boundaries:
- Allowing your child’s thoughts and feelings to influence your own too much: Your child may act like it will be the end of the world if they don’t get into the right college. If their anxiety becomes your anxiety, then it’s going to be very hard for you to encourage your kid to have fun on the weekend or to go to bed with work left undone. What they need you to do is validate their feelings but challenge those worry thoughts and help them to relax.
- Implying that your child is responsible for how you feel: As a parent, your child’s well-being is your priority, and your emotional state is affected by your child’s behavior. But phrases like, “You are making me crazy” or “I cannot cope with one more word from you” unintentionally suggest that the child has control over your feelings. It’s not healthy for children to feel that they are responsible for your well-being.
- Depending on your child for emotional support: If you’re a parent under stress and you’re not getting support elsewhere, it makes sense that you’re going to vent to a child. It’s not necessarily meant to burden a kid with financial stressors or relationship drama, and the child might be a sympathetic ear. But it blurs the boundaries between the parent role and the kid role, and that often causes difficulties for the kid in accepting parental authority in other domains. If they see themselves as equals in terms of emotional support, then they might think, why can you tell me what to do?
- Sharing age-inappropriate information: Many children want to be treated as older than they are (at least in certain ways). So they might requestinformation about finances, romantic relationships, or family stressors that are inappropriate for their age. Although it can be tempting to share, it is not helpful long-term. It may alleviate the child’s current anxiety (and stop the nagging), but it will impair their ability to respect boundaries as well as interfere with them just being a kid.
- Difficulty saying no: If you’re exhausted, the last thing you want is an argument. One way to avoid an argument is to say yes to your kid’s requests to buy a toy, stay up 15 more minutes, or have a different dinner. If you have boundaries around what you will spend, how much sleep you need, or what you will cook, you are still a good parent. Sticking to your limits teaches your child to accept other people’s boundaries without whining or threats.
- Allowing your child to treat you unkindly: Many parents allow their children to treat them in ways they would never tolerate from another person. This includes calling the parent mean or profane names, hitting them, or disregarding their needs (for money, sleep, leisure time, etc.). Allowing this kind of behavior prevents the child from learning how to respect boundaries and tolerate the emotions they experience when they face them.
Factors that contribute to boundary concerns
There are specific circumstances that can make it difficult for a parent to know where the appropriate boundaries are. They include a child’s late development, psychiatric challenges, and history of unsafe choices. For example, a child may have delays in language, executive functioning, or social or emotional skills. These things can make it challenging to determine how involved you need to be in your child’s daily life and how much independence they can handle.
- Poor risk assessment and impulsivity: Many disorders can impact children’s ability to think clearly, regulate emotionally, and act safely. For example, a teen experiencing a manic episode may overestimate their abilities, underestimate risk, and act impulsively. Or a child with ADHD might hard to control on crowded city streets or in restaurants, so you avoid taking them out or letting them do activities on their own with friends.
- Lack of confidence: Anxious children may underestimate their abilities and request continued support past when they are capable of independence. For example, a socially anxious child may ask their parent to order for them at a restaurant or keep track of their homework assignments. When a parent accommodates these requests, it confirms their belief that they still need help.
- Executive functioning deficits: Children who struggle with executive functioning may need more scaffolding to complete daily self-care tasks than other kids their age. This can look like parents providing frequent reminders of assignments, events, or even hygiene tasks — as well as cleaning their room for them long past when an child with ADHD should be doing it themselves. Consider how you can scaffold the skills (packing their bookbag!) without doing tasks for them, and gradually remove the supports over time.
- History of not successfully navigating tasks: A child’s history of poorly handling a responsibility (safe use of technology, completion of homework, brushing their teeth) often reduces parents’ confidence in the child’s abilities and increases their inclination to step in. Although extra supervision and support may be needed initially, it is important to reassess your child’s abilities over time as they can learn and grow if you let them!
How to get better at boundaries
Once you have recognized the challenges in respecting your child’s boundaries and protecting your own, the next step is to figure out what those boundaries are.
- Identify your boundaries: What things are most important to support your child’s growing independence and sense of autonomy? What boundaries do you need to set to protect your own mental health? Consider what level of involvement you want to have in their academics, friendships, emotion regulation, and appearance and what you want to disclose to them about your own relationship, emotions, or work.
- Practice setting these boundaries: It is much easier to set a boundary when you are not forced to make the choice with a child’s puppy dog eyes looking at you. Rehearsing how you will say no, decline to share certain information, or respond to an anxiety-provoking situation can prepare you to respond more effectively and in line with your values in a moment of conflict.
- Share your reasons for boundaries: Children can be quick to interpret lack of boundaries as “more caring,” but being consistent in language around why boundaries are being set can help prevent this. When setting a boundary, it is helpful to couch it in care. For example, “I care about you enjoying your childhood, so I do not feel comfortable sharing with you about our family’s finances.”
When kids want more independence than you are sure they are ready to handle, identifying steps toward their goal can be effective. Giving them opportunities to show maturity, with success at one step leading to more responsibility, can help you trust your child with greater independence. What can your kids show you that will help you feel confident in their ability to manage their emotions themselves or make well thought-out decisions?
Kids also need to recognize that they sometimes overestimate their own abilities, that there are times they have not assessed risk accurately and still need their parents. It is important to teach your child that you should be alerted if they are experiencing something that is unsafe or concerning (such as a friend talking about suicide or sharing an inappropriate photo). Discussions with your kid can sort out how to work toward new milestones and help everybody feel confident that they have the skills to do it.
Modeling a healthy respect for boundaries will set your child up to establish their own and respect others’ boundaries throughout their life.
Frequently Asked Questions
Emotional boundaries are the limits that protect each person’s right to their own thoughts, feelings, values, and decisions. In families, healthy boundaries allow children to develop independence while helping parents avoid taking responsibility for emotions or choices that belong to their child.
Healthy emotional boundaries support children’s confidence, autonomy, and ability to solve problems on their own. They also protect parents’ well-being by preventing them from becoming overly responsible for their child’s feelings, worries, or decisions.
Common signs include getting overly involved in a child’s friendships or school life, refusing age-appropriate privacy, sharing personal information without permission, or telling a child what they should think or feel. While these behaviors often come from a place of love and concern, they can undermine a child’s confidence and independence.
Parents can start by considering where their child is developmentally and what level of support versus independence is appropriate. A good guideline is to provide enough structure to keep children safe while gradually giving them more responsibility and privacy as they demonstrate readiness.
The post Maintaining Emotional Boundaries as a Parent appeared first on Child Mind Institute.
Efficacy of digital interventions in social anxiety disorder: a systematic review and Bayesian network meta-analysis
Autistic- and attention-deficit/hyperactivity disorder-like traits: differential associations with burnout, depression and anxiety, and empathy among Japanese junior residents
Loneliness, rumination, and adolescent psychological crisis in China: a pilot moderated mediation study
Virtual Patients Will Train Future Mental Health Clinicians
Researchers from the University of Pennsylvania and New York University have received a $4 million grant from the Wellcome Trust to develop an AI-driven platform to train mental health clinicians using simulations of real patients.
Within the next two years, the partners will work on the development of the STELLAR platform, which stands for Steering-Vector Enhanced LLM Agents for Realistic Digital Twins in Mental Health. The platform will create digital twins of patients that trainees can use to practice conducting clinical interviews and evaluating psychiatric symptoms.
“STELLAR brings together behavioral data, clinical expertise, and AI to ask a very practical question,” said Sharath Chandra Guntuku, PhD, associate professor of computer and information science at Penn Engineering. “Can we build training tools that better prepare clinicians for how varied and complex patients are?”
Preparing future mental health clinicians for clinical interviews can be challenging as patients will often report overlapping symptoms that shift over time and subjective experiences that can be expressed differently by each individual. STELLAR will give trainees an ethical option for trainees to simulate interviewing patients with a broad range of symptoms, backgrounds, and clinical scenarios.
“In psychiatry, the details of symptom experience matter: how someone describes distress, how symptoms overlap, how severity changes over time, and how context shapes the clinical interaction,” said Raquel E. Gur, MD, PhD, professor of psychiatry, neurology, and radiology at Penn’s Perelman School of Medicine.
Patient simulations will be created drawing from clinical data from the Philadelphia Neurodevelopmental Cohort, a repository including psychiatric assessments and clinical interviews from thousands of young people created by Penn Medicine and the Children’s Hospital of Philadelphia. Rather than copying individual patients, the simulations will create composites based on real-world data for clinicians to practice realistic conversations in the context of a clinical interview.
This will allow trainers to precisely control the symptoms students encounter, their intensity, and how they interact with each other. For instance, a trainee may practice interviewing a patient with mild anxiety and another whose anxiety overlaps with depression or psychosis to learn how to distinguish the differences in presentation between both.
Because many mental health symptoms manifest beyond formal clinical settings, the platform will also be trained using data from social media platforms, where people discuss mental health symptoms in everyday language.
“Patient simulations will only be useful for clinician training if they are grounded in real clinical speech and evaluated as clinical interactions, not just plausible AI dialogue,” said Neville Ryant, PhD, researcher at Penn’s Linguistic Data Consortium. “[Our] role is to bring speech and language science into the core of the project: adapting speech-recognition tools to clinical interviews, creating high-quality transcripts and annotations, and helping evaluate both what the simulations say and how they say it. That includes assessing the language generated by the models, the naturalness of synthetic voices, how well those voices reflect target speech patterns, and the behavior of the avatar during real trainee interactions.”
To ensure the conversations are realistic, respectful, and useful to trainees, the team will involve people with lived experience of mental health conditions as well as family members and caregivers to provide their perspective into the evaluation process. Their feedback will help researchers assess the accuracy of simulations, avoid stereotyping patients, and prepare trainees for complex and nuanced clinical conversations with real patients.
“The promise of this approach is that we can move beyond stylized and potentially biased simulations,” said João Sedoc, PhD, assistant professor of technology, operations and statistics at NYU’s Stern School of Business. “If we can create digital patients that simulate controllable plausible symptom expression and responsibly evaluate, we can augment current clinician training practices with the kinds of conversations that are essential to better mental health care.”
The post Virtual Patients Will Train Future Mental Health Clinicians appeared first on Inside Precision Medicine.

