<![CDATA[Psychiatry faces surging stress-driven illness as psychedelics, lifestyle medicine, and biomarkers reshape precision diagnosis and care.]]>
Complication Risk Classification in Children and Adolescents With Type 1 Diabetes: Interpretable Machine Learning Study Based on Saudi Clinical Guidelines
Background: Complication risks in children and adolescents with type 1 diabetes (T1D) can lead to serious health outcomes if not detected early. Despite the availability of clinical data, there remains a gap in interpretable tools that support risk stratification in this age group, particularly in alignment with local clinical guidelines. Objective: The purpose of this study is to develop a clinically interpretable model that classifies the risk levels of T1D complications—acute, chronic, and low—using real-world data and expert clinical rules derived from the Saudi Diabetes Clinical Practice Guidelines. Methods: A pediatric T1D dataset comprising of 306 patients was preprocessed through structured cleaning and feature engineering. Risk labels were constructed using Saudi Diabetes Clinical Practice Guidelines–derived rules. Feature selection was performed using a hybrid approach that combined the SHAP (Shapley Additive Explanations) analysis with exhaustive feature selection. A decision tree model was trained and optimized via cross-validation, using the -score as the primary performance metric. Results: The final model achieved a high mean -score of 0.9876 with a low variance of 0.0189, using only 5 clinical features: BMI, hypoglycemia, disease duration, hemoglobin A, and impaired glucose metabolism. These features were consistently ranked as the most influential. The resulting decision tree offered a transparent logic path, enhancing its clinical interpretability and usability. Conclusions: This study demonstrates that a simple and interpretable model, guided by national clinical guidelines, can effectively predict the risk levels of T1D complications in children and adolescents. Its strong performance, clarity, and reliance on a small number of clinically meaningful features make it a promising candidate for integration into clinical decision support systems. This supports a shift toward predictive and personalized diabetes care.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/33d5e8004a3c3a9ab20081a26ca2296e" />
Single Psilocybin Dose Relieves Depression for Over Three Months
Researchers in Sweden report that a single dose of psilocybin, a psychedelic compound found in mushrooms, can provide rapid relief from depressive symptoms. Results from a small-scale Phase II trial, published today in JAMA Network Open, show that patients experienced an improvement as soon as two days after treatment, with effects persisting for longer than three months.
”Our results suggest that psilocybin can provide rapid, clinically meaningful improvement in depression and may serve as an alternative to standard treatment when fast symptom reduction is important,” says Hampus Yngwe, MD, consultant psychiatrist and PhD student at the department of clinical neuroscience of the Karolinska Institutet in Stockholm.
Major depressive disorder is commonly treated with selective serotonin reuptake inhibitors (SSRIs), but most patients do not respond to this treatment or become resistant. In addition, their effects can typically take several weeks to be noticeable, and side effects are common.
Previous research had shown that a single dose of psilocybin can have antidepressant effects in people with treatment-resistant depression or anxiety disorders in patients with advanced cancer. The current study looked instead at the effects of this compound on “common” forms of major depressive disorder.
The study recruited a total of 35 people with moderate to severe recurrent depression, between 20 and 65 years of age. They were randomly assigned to receive either a single 25mg dose of psilocybin or niacin, an active placebo that causes a noticeable physical reaction. All patients received psychotherapeutic support before, during, and after treatment.
Participants were evaluated using the Montgomery–Åsberg depression rating scale (MADRS) to assess treatment effects at multiple time points after dosing. After a week, the group who received psilocybin saw an average MADRS score reduction of 9.7 points, compared to 2.4 points in the placebo group, and these effects persisted after two weeks and six weeks. At this point, 53% of participants who received psilocybin were in remission, compared to 6% in the placebo group.
A self-reported version of the MADRS revealed that patients saw antidepressant effects as early as day two after dosing, and continued to experience these positive effects for over three months.
A year after treatment, all patients who received psilocybin treatment remained in remission. However, many of the patients who received the placebo had also recovered at that point, showing no major statistical difference between both groups.
“The long-term effects are uncertain,” says Yngwe. “Repeated treatments may be needed to prevent relapse. This needs to be investigated in larger studies.”
Because the effects of psilocybin are strong and easily recognizable, many participants were able to tell whether they had received the treatment or the placebo. This is a common challenge scientists face when studying psychedelic treatments that can make it difficult for patients and researchers alike to separate the effects of the treatment from their expectations. “We want to understand how factors such as treatment expectations and lack of blinding affect the results, as previous studies may have exaggerated the treatment effects,” notes Yngwe.
Next, the researchers will analyze data from PET scans, blood, and cerebrospinal fluid samples collected from all patients before and after dosing. This will help them understand the physiological changes induced by psilocybin, and how these influence its observed antidepressant effects.
”Research suggests that the interaction between parts of the brain is impaired in depression and that this may be linked to changes in the connections between nerve cells, known as synapses,” says Yngwe. “In preclinical studies, psychedelics have been shown to stimulate synaptic growth. We therefore want to investigate whether psilocybin alters synaptic density in the brain.”
The post Single Psilocybin Dose Relieves Depression for Over Three Months appeared first on Inside Precision Medicine.
Large Language Models and Their Applications in Mental Health: Scoping Review
Background: Large language models (LLMs) are poised to transform mental health care, offering advanced capabilities in diagnosis, prognosis, and decision support. Since their inception, numerous mental health-focused LLMs have emerged in the scientific literature, reflecting the growing interest in leveraging these models across various clinical applications. With a broad range of models available, diverse optimization strategies, and multiple use cases, reviewing the current landscape is critical to understanding where future impact lies. Objective: This study aimed to conduct a scoping review investigating the use of LLMs in mental health across diagnostic, prognostic, and decision support tasks. Methods: We screened 3121 papers from PubMed, Scopus, and Web of Science for studies published between January 2023 and October 2025, using terms related to LLM and mental health. After removing duplicates, 2 reviewers (MCL and WWBG) independently screened the studies, with a third (JJK) to resolve conflicting opinions. We extracted and synthesized information on the models, use cases, datasets, and adaptation methods from selected papers. Results: In total, 41 papers were selected. Many studies included evaluations on OpenAI’s GPT series applications: GPT-4 (24 studies, 58.5%) and GPT-3.5 (16 studies, 39%). Others included Bidirectional Encoder Representations from Transformers-derived models (9 studies, 22%), LLaMA (8 studies, 19.5%), and RoBERTa-derived models (6 studies, 14.6%). While all studies initially applied out-of-the-box LLMs, several adapted them through few-shot learning or fine-tuning to better align with specific research goals. The most common use case was in diagnostics (31 studies, 75.6%), while the most common target condition was depression (11 studies, 26.8%). While many studies reported superior performance of LLMs, only a minority of studies (13 studies, 31.7%) validated LLM performance against clinician assessments using real patient data, with the majority relying on proxy outcomes such as clinical vignettes, examination questions, or social media posts. Conclusions: Despite rapid growth and diversity of LLM applications in mental health, the field remains nascent and exploratory. Future developments must emphasize consistent model adaptation procedures to ensure safety and clinical workflow alignment. Models must also be evaluated on robust evaluation criteria by using standardized protocols and real clinical outcome measures.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/c9cc055c6eb86a58602189759f67ab4e" />
STAT+: Takeda will pay $13.6 million to settle allegations it paid kickbacks to doctors
Takeda Pharmaceuticals agreed to pay $13.6 million to settle allegations that it paid kickbacks to doctors to prescribe an antidepressant and, consequently, violated federal law by causing Medicaid to pay false claims, the U.S. Department of Justice said in announcing the settlement.
From January 2014 to October 2020, the company allegedly offered speaking fees and paid for meals at “high-end” restaurants to persuade physicians to prescribe Trintellix. Moreover, certain doctors who attended multiple programs on the same topic and received meals and drinks did not gain any educational benefit from attending the programs.
“This settlement demonstrates the continued commitment of my office to ensure that patients’ best interests remain paramount,” Eric Grant, the U.S. attorney for the Eastern District of California, said in a statement. “Prescribing decisions should not be influenced by drug companies’ payments or side perks made available to physicians.”
A Novel Haptic Cardiac Simulator: Mixed Methods Pilot Evaluation in Medical Students and Educators
Background: Cardiac auscultation is an essential component of clinical examination but is often challenging to achieve proficiency in. Self-contained, multisensory learning resources that incorporate simultaneous visual and haptic stimuli offer a unique approach to supporting learners in acquiring this core skill. Objective: This pilot study of both medical students and clinical educators evaluated the utility of a novel iPhone app, Haptic Heart, which generates haptic vibrations to simulate heart sounds and murmurs. We aimed to explore the perceptions of students and educators when using haptics as a learning resource and the underlying reasons behind these perceptions and to gather lessons that would inform future development of the resource. Methods: Clinical-year medical students from the Lincoln Medical School with access to an iPhone were invited to trial Haptic Heart between October 2023 and December 2024. Cardiology specialists involved in clinical education were also invited to take part. After using the app, participants were asked to complete a modified version of the 12-item Evaluation of Technology-Enhanced Learning Materials: Learner Perceptions questionnaire that included additional free-text items. Educators were also asked to comment on the resource’s authenticity and perceived usefulness. Quantitative responses were analyzed using descriptive statistics; free-text responses were analyzed for common themes. Results: A total of 21 students and 18 educators completed the evaluation. Both cohorts returned positive responses across nearly all questionnaire items, with students showing near universal agreement that the app was of excellent quality (21/21, 100%), supported their learning needs (21/21, 100%), and would change their clinical practice (20/21, 95.2%). Educators similarly rated the resource highly for learning utility (16/18, 88.9%) and authenticity (13/18, 72.2%). Reported technical difficulties were minimal for students (1/21, 4.8%) and educators (2/18, 11.1%). Analysis of free-text responses suggested that learners valued the ability to “feel” murmurs and to vary heart rate. Educators highlighted the resource’s novelty and innovation, although some noted concerns about audio quality when using a stethoscope to auscultate haptic vibrations directly. Conclusions: This pilot evaluation demonstrates the potential of smartphone-based haptic technology as a tool for medical education. Haptic Heart was perceived by both students and educators as an innovative educational tool for cardiac auscultation. Further work should focus on expanding the range of haptic patterns provided and exploring the effectiveness of these resources on learning.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/b58aaaa105c48f4caeaf6a4a500271b5" />
<![CDATA[APA meeting sessions spotlight how psychiatrists protect wellbeing, embrace creativity, and confront structural racism.]]>
ASGCT Q1 Landscape Report Paints Positive Picture for Gene and RNA Therapy
BOSTON – The CEO of the American Society for Gene and Cell Therapy (ASGCT), David Barrett, JD, presented highlights from the Society’s latest Landscape Report on Cell, Gene and RNA Therapy for the first quarter (Q1) of 2026.
The ASGCT report is developed in conjunction with Citeline, a subsidiary of Norstella (a pharmaceutical intelligence provider covering drug development from preclinical to commercialization).
Barrett said there are currently 42 gene therapies approved worldwide, along with 38 RNA therapies and 76 (non-genetically modified) cell therapies, which are steadily growing the field. Two cell therapies were approved in Japan in Q1.
There was a small increase in deal-making, and a significant 30% increase in startup funding compared to the same period in 2025. “I think that signals and underscores a rebounding sector,” said Barrett.
Of the eight gene therapies approved over the past 12 months, half were in the United States, with three more in China. “The regulatory pace is starting to pick up, another strong indicator for the future of our field,” Barrett said. It is a similar picture in RNA therapies. “We see a steady uptick over the course of the last year,” he added.
Zooming out, Barrett estimated that there are more than 4,200 therapies currently in development, from preclinical through pre-registration. The vast majority of those (more than 4,130) are gene and genetically modified cell therapies, including about 1,300 RNA therapies.
In the field of gene-modified cell therapies, CAR T continues to lead the pipeline for ex vivo gene therapies, with natural killer (NK) and T-cell receptors gaining traction. Not surprisingly, genetically modified cell therapy overwhelmingly targets cancers, but Barrett noted growth in the percentage of these therapies targeting immunological diseases, including lupus, multiple sclerosis, and HIV.
Pipeline growth
Barrett also noted growth and “a promising future” in the clinical trials pipeline. There are currently 350 Phase I, 319 Phase II, and 41 Phase III trials in gene therapy (up from 35 a year ago). “Hopefully, we will see a number of completed trials and FDA decisions in the near term,” said Barrett. A growing proportion of gene therapy trials (exceeding 60 percent) is for non-oncology indications.
In the RNA space, “RNAi therapies are jumping,” said Barrett. The same cannot be said, however, for mRNA. “Unsurprisingly, mRNA therapies continue to slide quarter over quarter,” a symptom of “shaken confidence” in that space, he continued. RNA therapies are targeting primarily non-oncology indications, especially in rare diseases.
Upcoming catalysts
On the business front, Barrett noted there has been “a nice uptick” in Q1 in start-up funding compared to the same quarter last year, which he deemed “a really promising indication.” The number of start-ups historically has tended to hover between 5-20. For Q1, that number was 26.
The Q1 report tracks various business catalysts anticipated through the end of 2027, including increased interest and uptake in expedited review designations—fast track, RMAT, orphan drug breakthroughs and other accelerated approval pathways.
“FDA is getting a lot done… and hopefully we’ll see the same moving forward,” Barrett said.
The full Landscape Report is available online from the ASGCT website.
The post ASGCT Q1 Landscape Report Paints Positive Picture for Gene and RNA Therapy appeared first on GEN – Genetic Engineering and Biotechnology News.
<![CDATA[Study ties higher schizophrenia rates in Black Americans to neighborhood vulnerability, spotlighting faster early-psychosis care and social supports.]]>
<![CDATA[Phase 2 MINDFuL data show XPro trends toward cognitive and biomarker gains in inflammation-defined mild Alzheimer disease, with no ARIA, guiding phase 3 plans.]]>