ObjectiveThis study aimed to develop and evaluate a two-layered machine learning framework that combines admission clinical information with longitudinal nursing observations to identify schizophrenia inpatients at high risk of self-harm or suicidal acts.MethodsWe retrospectively reviewed the records of 477 patients with schizophrenia hospitalised in Liaoning Province between July 2021 and July 2024. According to whether at least one self-injurious or suicidal episode was documented during the index admission, 159 individuals were assigned to a high-risk group and 318 to a non-high-risk group. At admission, 18 baseline variables (including age, sex, history of self-harm, hopelessness/depression, and educational attainment) were extracted from electronic medical records, and 39 nurse-rated behavioural items were scored weekly using the Psychiatric Patient Nursing Observation Scale. Static and dynamic feature sets were used to train six classifiers [regularized logistic regression (LR), support vector machine (SVM), extreme gradient boosting, random forest, multi-layer perceptron, and K-nearest neighbours]. The best static model (regularized LR) and the best dynamic model (SVM) were combined through probability-level weighted fusion to generate a hierarchical risk score.ResultsMultivariable analysis of admission features showed that previous self-harm [odds ratio (OR) = 4.323], hopelessness/depression (OR = 3.090), younger age (OR = 0.938), and higher educational level (OR = 1.357) were independent predictors of self-harm/suicidal behaviour. Among dynamic indicators, negative self-evaluation (OR = 2.303), self-reported depression (OR = 1.812), insomnia (OR = 1.768), talking to oneself (OR = 1.733), crying (OR = 1.700), and reduced conversation with others (OR = 1.422) remained significant. The optimised static LR model achieved an area under the curve (AUC) of 0.7564, and the dynamic SVM model reached an AUC of 0.8531. Their fusion further improved performance (AUC = 0.9048; sensitivity 0.8542; specificity 0.7789; accuracy 0.8042). This hierarchical model outperformed the best flat combined-feature model (SVM; AUC = 0.9022) in sensitivity (0.8542 vs. 0.6667), indicating a more clinically appropriate detection of high-risk patients.ConclusionA hierarchical machine learning approach that integrates baseline clinical history with repeated nursing assessments can effectively flag schizophrenia inpatients at high risk for self-harm and suicidal behaviour, supporting timely and individualised preventive strategies in psychiatric wards.
[Comment] From policy to practice: implementing China’s measures to strengthen student mental health
In October 2025, China’s Ministry of Education issued ten national measures to strengthen mental health work in primary and secondary schools.1 These measures target major school-linked stressors such as academic pressure, physical activity, sleep, and internet use, and they call for whole-staff responsibility and cross-department collaboration. The policy signals a shift from episodic crisis response towards a public mental health agenda spanning prevention, early identification, supportive school environments, and referral pathways.
Wireless Stress Detector Offers Multiple Medical Uses
A next-generation device that detects signs of stress could have wide-ranging applications, from investigating sleep disorders to detecting signs of sepsis.
The polygraph detector, described in Science Advances, is worn on the chest and can even sense when a person is lying.
It allows psychophysiological states to be continuously monitored through a combination of multimodal sensing and wireless data transmission.
The gadget offers an alternative to current approaches such as such as polygraphy and polysomnography (PSG), which involve cumbersome wired sensors that limit their practicality.
“By uncovering mechanistic links between autonomic imbalance, stress reactivity, and health outcomes, these devices have the potential to transform diagnostic workflows, optimize educational programs, and enable personalized therapeutic monitoring across stress medicine, pediatrics, and behavioral health,” reported Sun Hong Kim, PhD, from the University of Seoul in South Korea, and co-workers.
Subtle physiological variations in cardiac, respiratory, electrodermal, and thermal activity often serve as indicators of compromised health or heightened stress responses.
These can be reflected in many scenarios, from pediatric sleep disorders that disrupt neurodevelopment to the psychological strain experienced in high-stakes clinical settings or during polygraph examinations.
Accurate monitoring of psychophysiological states is therefore essential for understanding how stress and autonomic dysfunction manifest across a wide spectrum of medical conditions.
However, most existing devices monitor only one or two parameters or rely on electrochemical sensors that detect sweat biomarkers, thereby failing to reflect the complex and dynamic interplay between multiple physiological systems.
Kim and co-workers therefore designed a single platform to enable comprehensive assessment of autonomic and stress-related physiology in real time.
The device continuously measures changes in heartbeat, skin temperature, and breathing, which are then converted using machine learning into measures of psychological strain.
The device had high fidelity with gold standard systems in quantifying the complex psychological stress induced by polygraph interviews and complex cognitive load tasks as well as the physical stress caused by repeatedly putting a hand in an iced water.
During overnight monitoring of children, it reliably identified arousals, hypopnea, and apnea while revealing disease-specific autonomic signatures among infants with Down syndrome.
Real-world deployment during emergency simulation training showed that multimodal stress signatures correlate inversely with performance, reflecting its value for medical education.
Machine learning analyses across all studies confirmed that multimodal features outperformed single-signal approaches in detecting stress and clinical events with high sensitivity and specificity.
“A particularly notable contribution lies in pediatric sleep medicine,” the authors noted.
“Simultaneous comparison with PSG confirms the ability to detect arousals, hypopnea, and apnea while also providing mechanistic insights into autonomic regulation.
“In infants with Down syndrome, multimodal analysis reveals attenuated sympathetic responsiveness and parasympathetic dominance, consistent with known vulnerabilities in airway patency and autonomic control.
“Such disease-specific autonomic signatures may serve as valuable biomarkers for risk stratification, early diagnosis, and targeted intervention in neurodevelopmental disorders.”
The post Wireless Stress Detector Offers Multiple Medical Uses appeared first on Inside Precision Medicine.
Disrupted sleep-wake cycles and circadian rhythms in a Drosophila model of C9orf72-FTD
Frontotemporal dementia (FTD) is a neurodegenerative disorder that affects behavior, personality, motor activity, speech, cognition, and sleeping patterns. Previous findings support the idea that disruption of sleep and circadian systems may not only be affected by this disease but also work to actively shape the clinical phenotype of FTD. Thus, understanding how sleep-wake cycles are altered may provide insight into mechanisms that influence both disease progression and quality of life. We studied an established Drosophila model of FTD to investigate changes in the sleep-wake cycle of both young and aging flies. A C9orf72-associated FTD model was chosen, as the most common genetic cause of sporadic and hereditary FTD is a hexanucleotide repeat expansion in intron 1 of the C9orf72 gene. We performed behavioral assays to measure locomotor activity in both a 12 h:12 h light/dark (LD) cycle and complete darkness (free running). From this data, we were able to analyze changes in sleep and activity patterns, as well as circadian rhythms in flies modeling C9orf72-FTD. Our data suggests that these flies have increased nighttime activity and decreased sleep at night, which becomes more significant as they age. Older flies also displayed decreased sleep pressure during both day and night and lost rhythmicity. Of specific interest, young flies modeling C9orf72-FTD demonstrated altered day and night sleep latency, decreased sleep depth at night, and reduced rhythmicity in constant darkness. This suggests that changes in their sleep-wake cycle occur early in disease progression and provide an avenue for potential intervention and early diagnostic markers.
ASGCT 2026: Victoria Gray Roadshow Returns to Boston
BOSTON – The annual American Society of Cell and Gene Therapy (ASGCT) conference got underway in Boston this week with a guest appearance by one of gene therapy’s greatest ambassadors and patient advocates.
Victoria Gray, the sickle cell warrior who was successfully treated in the exa-cel clinical trial sponsored by Vertex Pharmaceuticals/CRISPR Therapeutics seven years ago, spoke in an evening workshop organized by the Emily Whitehead Foundation and ScaleReady.
Boston is becoming a regular stomping ground for Victoria. Last November, she spoke at the Genetic Agency Technology Conference, hosted by Dyno Therapeutics. Last month, she finally received an invitation to visit the headquarters of Vertex and speak in a town hall meeting.
In an extemporaneous 20-minute speech, Victoria talked about her lifelong journey with sickle cell disease (SCD). She recalled her first major pain crisis, when she was a young girl—a lightning-type pain that began in one arm before traveling across her chest and down the other arm. “In minutes, my entire body was engulfed in pain,” she said. “The pain felt like getting struck by lightning and hit by a truck. It took me to the floor.” Her grandmother provided hot towels and Tylenol, but nothing worked—not even prayer. After a week in hospital, Victoria returned home but still felt fatigued.
Stricken by regular pain crises, a hallmark of SCD, Victoria encountered numerous disappointments growing up. Her hematologist said she could not join the cheer team. In eighth grade, she was told she could not join the basketball team, because the exertion would provoke a pain crisis. “As a kid, I was like a Timex: I could take a licking and keep on ticking,” she joked.
In high school, she signed up to join the United States Navy. “I wanted to serve my country,” Victoria recalled. As she was preparing for basic training, she learned that her disease prevented her from enrolling. “So that was another dream lost.” Next, she turned her attention to nursing. Victoria graduated high school in 2003, but it took another seven years before she could qualify for a nursing program. “Professors didn’t understand because I looked whole and complete. They didn’t think I was sick.”
In 2010, just before Halloween, Victoria had the worst pain crisis of her life, stripping her ability to walk or use her arms to feed herself. “I couldn’t do anything, facing some of the worst pain of my life. I was getting strong pain medicines like Dilaudid, ketamine, but still couldn’t move. Pain had taken over my thoughts.” Unable to sleep or even take a nap, Victoria was desperate to go home to her family.
Later, she asked the doctors if they had heard about a haplo-bone marrow transplant (BMT). “I can’t continue living like this,” she said. The doctors looked at each other and said no. After weeks of prayer, Victoria received a call from her hematologist. “Victoria, I have good news, but I only want to tell you in person.” For the first time in her adult life, Victoria was excited about a doctor’s appointment.
She traveled to Nashville with her brother, who would be her BMT donor, and her husband. She met Haydar Frangoul, MD, whom Victoria calls, “the nicest doctor that I’ve met in my adult life.” Frangoul told her: “Victoria, I wish I had met you ten years ago!’
Although Victoria’s brother was a suitable BMT match, Victoria was scared of the possibility of graft vs. host disease (GVHD). “My purple pill basket was filled to the brim with medicine every day. If I would acquire [GVHD], that basket would have to triple in size.”
“I’m a human!”
On her next visit to Nashville, she had to extend her stay because of another pain crisis. But that stay changed her life. Frangoul sat next to her bedside. “Victoria, have you ever heard of CRISPR?” he asked. Victoria shook her head.
Frangoul used a typo-in-a-textbook analogy and reassured Victoria that there was no chance of GVHD, because she would be receiving her own modified stem cells. “You’ll be the first person to do this, Victoria,” he said. “First human?” she asked. “Yes,” Frangoul said, “but it’s been tested in primates.”
“But I’m a human!” she said.
After being reassured that she could still try a bone marrow transplant if the procedure did not work, Victoria agreed to move forward. The chemotherapy, was “hell on Earth,” she recalled. “I lost my hair, which I was prepared for, but the mucositis, the sores in my mouth, the inability to eat for two weeks, was gruesome.”
Victoria swallowed her tears and decided to fight. This was the first time she had been in the hospital by her choice, to live for her children. About eight months after receiving her CRISPR-edited stem cells in July 2019, she woke up one morning, not feeling anything. “Oh my God, I’m dead,” she thought. She called her kids into the room and hugged them, slowly realizing that “this is what normal feels like.” For the first time in more than 25 years, Victoria did not have any pain in her lower back and hips. She was able to breathe deeply without wincing.
A few years after her therapy, Victoria was finally able to take her first ever flight, to Washington D.C. to visit her husband, who was on deployment. “It was the first time that I was ever able to show up for the man who has shown up for me,” she said. She has since watched her daughter dance in a Christmas parade and supported her son playing high school football. “The little things have brought me great joy,” she said.
Her second flight was a business class trip to London with her husband in March 2023, where she spoke at the third International Summit on Human Genome Editing. “I got to keep my covenant that I made with God, that God, if you do this for me, I would tell the world about what you did.”
Victoria welcomed her first granddaughter on Christmas Eve, 2024. Next week, another milestone: she will be in the audience as her twins graduate high school. And next month, she will publish a children’s book called Hema’s Journey, the tale of her inspiring journey with CRISPR gene therapy. She’s currently training for a group effort to climb Mt. Kilimanjaro.
Perhaps at next year’s ASGCT conference in Philadelphia, she will be invited to present in a plenary session on the main stage. It would be hard to think of a more fitting speaker.
The post ASGCT 2026: Victoria Gray Roadshow Returns to Boston appeared first on GEN – Genetic Engineering and Biotechnology News.
The Child Mind Institute Hosts 2026 Spring Luncheon “Future-Proofing Your Kids: Empowered Parenting in the Digital Age”
New York Times bestselling author Lisa Damour, PhD, led a thoughtful discussion to honor Mental Health Awareness Month
New York, NY – The Child Mind Institute, the leading independent nonprofit dedicated to transforming the lives of children struggling with mental health and learning disorders, hosted its 2026 Spring Luncheon on Monday, May 11. The event featured a dynamic discussion between Lisa Damour, PhD, a three-time New York Times bestselling author and host of the podcast, Ask Lisa: The Psychology of Raising Tweens & Teens, and Dave Anderson, PhD, Vice President of Public Engagement and Education and a senior psychologist at the Child Mind Institute. Their conversation was moderated by Ali Wentworth, an actress, comedian, author, and host of the television show, The Parent Test.
The event brought together advocates and distinguished individuals dedicated to equipping children and families with the skills they need to thrive in today’s rapidly evolving online and social environments. Attendees included Carson and Siri Daly, Jeannie Gaffigan, Kyle MacLachlan, Zibby Owens, and Alysia Reiner.
“We are raising children in a world fundamentally different from any generation before them…a world where childhood unfolds not just in homes and schools but online,” said Harold S. Koplewicz, MD, founding president and medical director of the Child Mind Institute. “Technology brings creativity and connection but also real risks: constant comparison, disrupted sleep, compulsive engagement, and exposure to harmful content. Our job is to help kids build the skills to navigate this world with resilience, confidence, and balance.”
The discussion centered on kids and families and how they can build healthy habits and resilience as they face the demands and distractions of a world increasingly reliant upon and centered around digital technology.
“My umbrella concern is what the conversation about technology is doing to the relationship between adults and kids. The single most powerful force for youth mental health is strong relationships with caring adults,” said Dr. Damour.
“If we focus on driving causal factors — such as family relationships, academic success, in-person friendships, sleep, and movement — we end up promoting a child’s wellness far more than by taking technology away,” said Dr. Anderson.
The luncheon raised over $260,000 to support the Child Mind Institute’s mission to change the lives of children with mental health and learning disorders in the United States and around the world.
The luncheon was co-chaired by Chris Mack, Lisa and Guy Metcalfe, Zibby Owens, and Jil Schaps. The host committee included Robyn and Paul Goldschmid, Desiree Gruber, Molly Jong-Fast, Breanna and John Khoury, Isabelle Krishana, Arielle Tepper, and Sarah J. Wetenhall.
Photos from the luncheon can be found here.
This special event is part of the Child Mind Institute’s programming during Mental Health Awareness Month. The Child Mind Institute recently launched its latest campaign, Mental Health Fitness. Physical fitness doesn’t just happen — it takes skills, regular practice, and a supportive environment. The same is true for mental health. Alongside relatable content from influencers and world-renowned athletes, the Mental Health Fitness resources from the Child Mind Institute provide kids and families with five core mental health skills they can practice every day.
About the Child Mind Institute
The Child Mind Institute is dedicated to transforming the lives of children and families struggling with mental health and learning disorders by giving them the help they need. We’ve become the leading independent nonprofit in children’s mental health by providing gold-standard, evidence-based care, delivering educational resources to millions of families each year, training educators in underserved communities, and developing tomorrow’s breakthrough treatments.
Visit Child Mind Institute on social media: Instagram, Facebook, X, LinkedIn
For press questions, contact our press team at childmindinstitute@ssmandl.com or our media officer at mediaoffice@childmind.org.
The post The Child Mind Institute Hosts 2026 Spring Luncheon “Future-Proofing Your Kids: Empowered Parenting in the Digital Age” appeared first on Child Mind Institute.
Phenotype, Genetics, and Interpretation: Further Considerations on Atypical Depression
We read with great interest the recent article by Shin et al. (1). The authors leveraged the substantial Australian Genetics of Depression Study (AGDS) cohort to provide compelling evidence for the clinical and biological validity of the atypical depression subtype. Their integrative analysis of clinical features, polygenic scores (PGSs) for mental, metabolic, and circadian traits, and self-reported treatment outcomes is a significant contribution to the field. The particularly robust finding of an association between a genetic predisposition for eveningness (lower-chronotype PGS) and atypical depression, which persisted after adjustment for body mass index (BMI), is noteworthy and points to a potentially core, BMI-independent pathway.
Feasibility of Integrating Wearable Devices and Ecological Momentary Assessment for Real-Time Environmental Exposure Estimation: Proof-of-Concept Study
Background: Environmental exposures such as heat and air pollution are critical determinants of health, yet traditional assessment methods rely on stationary monitors or residential address proxies that fail to capture the exposures that individuals experience throughout the day. Objective: This pilot study aimed to assess the feasibility of integrating ecological momentary assessment (EMA), wearable devices, and continuous GPS tracking to capture real-time environmental exposures and to explore associations with concurrent health outcomes. Methods: In total, 7 young adults (aged approximately 16 to 24 years; 5/7, 71% female) wore Fitbit Charge 6 watches from July 2025 to August 2025 (mean 28.1, SD 1.1 days), recording sleep quality and duration, resting heart rate, breathing rate, heart rate variability, and physical activity. GPS location measured at up to 5-minute intervals (mean 19.7, SD 25.8 measurements per day) was linked to ambient temperature, humidity, and air pollution data (particulate matter <2.5 um or <10 um in diameter, nitrogen dioxide, sulfur dioxide, ozone, and carbon monoxide) derived from monitoring stations, satellites, and climate models using data-integration algorithms accessed via an application programming interface. EMA surveys administered 3 times per day captured participants’ emotional states and location (inside or outside). Feasibility targets were ≥3 GPS measurements per day, ≥1 survey completed per day, and complete sleep data on ≥50% of days. We examined exploratory bivariate correlations between environmental exposures, physiological measures, and self-reported mood, adjusting for multiple comparisons using false discovery rate correction. Results: Of the 7 participants, 5 (71%) met predefined feasibility targets. Mean compliance included 565 (SD 457) GPS coordinates per participant, 1.4 (SD 0.2) EMA surveys per day, and complete Fitbit sleep data on 64% (SD 27%) of days. Surveys identified barriers to compliance, including perceived complexity of the system and forgetting to put the Fitbit watch back on after removing it. Exploratory correlations (6/7, 86% of participants with complete Fitbit data) revealed associations between nitrogen dioxide and heat exposure and reduced heart rate variability (a marker of parasympathetic tone), and between air pollutants (sulfur dioxide) and increased negative emotions. Heat exposure showed a paradoxical pattern of lower self-reported sadness but reduced heart rate variability with higher levels of heat exposure. Given the small sample size, these correlations should be considered preliminary and hypothesis generating rather than definitive findings. Conclusions: This study demonstrates that the multimodal integration of wearable devices, GPS tracking, and EMA is feasible for capturing real-time environmental exposures and concurrent health outcomes in young adults. This approach addresses critical exposure misclassification issues in environmental health research that relies on residential addresses as proxies. Preliminary patterns suggest complex relationships between environmental exposures and both physiological and emotional outcomes, warranting further investigation in larger, more diverse samples. This approach could inform future personalized environmental health interventions.
Sleep and circadian rhythm disruptions in animal models of temporal lobe epilepsy
Temporal lobe epilepsy (TLE) is frequently accompanied by disruptions to sleep and circadian rhythms, which substantially contribute to disease burden. Human studies are often confounded by antiseizure medications, limiting insight into underlying mechanisms. Animal models therefore provide critical opportunities to examine causal interactions, yet their translational validity has not been systematically evaluated. In this review, we first outline the relevance of rodent models for studying epilepsy- and sleep-related processes. We then examine current evidence for sleep and circadian disturbances across three commonly used TLE models: the pilocarpine (PILO) model, the kainic acid (KA) model, and the traumatic brain injury (TBI) model. We summarize circadian patterns of seizure occurrence, alterations in sleep–wake architecture, and changes in core circadian clock gene expression, as well as alterations in subcortical brain regions involved in sleep–wake regulation. Across models, sleep is consistently fragmented, and circadian molecular machinery is profoundly disrupted, although the direction and magnitude of changes vary by species, protocol, and epilepsy stage. By comparing findings across animal models and patient studies, this review highlights convergences, discrepancies, and key research gaps. Despite variability, animal models remain indispensable for probing the bidirectional links between epilepsy and sleep–circadian regulation.
Pediatric Prolonged-Release Melatonin for Sleep Disturbances in Children and Adolescents With Anorexia Nervosa (MELSom-ANOREXIA)
Conditions: Anorexia Nervosa; Sleep Disorders in Children
Interventions: Drug: Pediatric Prolonged-Released Melatonin (PedPRM); Drug: Placebo
Sponsors: Assistance Publique Hopitaux De Marseille
Not yet recruiting
Interventions: Drug: Pediatric Prolonged-Released Melatonin (PedPRM); Drug: Placebo
Sponsors: Assistance Publique Hopitaux De Marseille
Not yet recruiting