MIT and Harvard scientists have designed an advanced type of immune cell called a CAR-NK cell that can destroy cancer while avoiding attack from the body’s own immune defenses. This innovation could allow doctors to create “off-the-shelf” cancer treatments ready for use immediately after diagnosis, rather than waiting weeks for personalized cell therapies.

Scientists identified two types of brain cells, neurons and microglia, that are altered in people with depression. Through genomic mapping of post-mortem brain tissue, they found major differences in gene activity affecting mood and inflammation. The findings reinforce that depression has a clear biological foundation and open new doors for treatment development.

Background: Globally, the number of illegal drug users is rising, posing mental and physical health challenges and increasing societal burdens. Despite a significant need for treatment, only about 10% of these individuals receive it worldwide, often with poor adherence. Traditional treatments, while effective, suffer from high dropout rates due to limitations. The COVID-19 pandemic has spurred the growth of digital interventions like apps and online platforms, offering flexibility and cost-effectiveness that better meet patient needs and improve engagement. However, addressing the persistently high dropout rates in these online treatments is crucial and necessitates further research. Objective: This study aimed to estimate dropout rates among adults with illicit drug use participating in digital psychosocial intervention trials, and to identify factors associated with attrition. Methods: We conducted a systematic search of five major databases for English-language randomized trials published up to January 27, 2025. A total of 40 studies (80 arms; 9,563 participants) reporting 46 dropout rate estimates were included. A random-effects model was used to calculate pooled dropout rates, with meta-regression and subgroup analyses exploring potential moderators. The study was registered on PROSPERO (CRD42024534389). Results: At post-test, the pooled dropout rate in the intervention group across 17 studies was 22.4% (95% CI: 12.4%–37.2%). Dropout was significantly associated with education level, employment status, baseline clinical diagnosis, intervention frequency, and initial medication use. During the longest follow-up (29 studies), the dropout rate was 27.9% (95% CI: 18.8%–39.3%), with marital status, recruitment source, medication frequency, and intervention modality as significant predictors. Control group dropout rates were 25.9% and 28.3%, both higher than those in the intervention group. Conclusions: This meta-analysis revealed substantial dropout among adults with illicit drug use receiving digital psychosocial interventions. Targeted modifications to intervention design may improve engagement and long-term retention. Clinical Trial: The study was registered on PROSPERO (CRD42024534389).

Background: Stroke frequently leads to various functional impairments. Both virtual reality (VR) and mirror therapy (MT) have shown efficacy in stroke rehabilitation. In recent years, the combination of these two approaches has emerged as a potential treatment for stroke patients. Objective: This systematic review and meta-analysis aim to evaluate the efficacy of combined immersive and non-immersive VR with MT in stroke rehabilitation. Methods: Five electronic databases were systematically searched for relevant articles published up to Jan. 2025. Randomized controlled trials (RCTs) that investigated combination treatment of VR and MT for participants with stroke were included. A grey literature search was also conducted. The risk of bias and the certainty of the evidence were assessed using the Cochrane collaboration’s tool and the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) guideline, respectively. Results: A total of 475 participants from 14 RCTs were included, of which 7 were eligible for meta-analysis. Meta-analysis revealed significant improvements in upper extremity (UE) motor function and hand dexterity, as evidenced by Fugl-Meyer assessment of upper extremity (FMA-UE) (MD 3.50, 95% CI 1.47 to 5.53; P=0.0007), manual function test (MFT) (MD 2.15, 95% CI 1.22 to 3.09; P6 months or not) revealed significant differences in the FMA-UE outcome. However, the pooled FMA-UE improvement did not consistently exceed the established minimal clinically important difference (MCID; 4.25–7.25), indicating that while statistically significant, the clinical meaningfulness of the observed effect remains uncertain. Narrative evidence also suggested potential benefits for lower extremity function, dynamic balance, and quality of life, though these findings were not meta-analyzed and should be interpreted with caution. Conclusions: Moderate-quality evidence supports VR-MT as a promising nonpharmacological intervention to improve upper extremity function and hand dexterity in stroke rehabilitation. While the intervention demonstrates statistically significant effects, it does not reach the minimum clinically important difference for the FMA-UE outcome. Preliminary descriptive evidence indicates possible advantages for lower extremity function, balance, and quality of life. Clinical Trial: PROSPERO CRD42024572150

This paper explores the integration of generative artificial intelligence (AI) into psychotherapeutic practice through the lens of mentalization theory, with a particular focus on epistemic trust—a critical relational mechanism that facilitates psychological change. We critically examine AI’s capability to replicate core therapeutic components, such as empathy, embodied mentalizing, biobehavioral synchrony, and reciprocal mentalizing. Although current AI systems, especially large language models, demonstrate significant potential in simulating emotional responsiveness, cognitive empathy, and therapeutic dialogue, fundamental limitations persist. AI’s inherent lack of genuine emotional presence, reciprocal intentionality, and affective commitment constrains its ability to foster authentic epistemic trust and meaningful therapeutic relationships. Additionally, we outline significant risks, notably for individuals with complex trauma or relational vulnerabilities, highlighting concerns regarding pseudo-empathy, mistaking phenomenal experience for objective reality (psychic equivalence), fruitless ungrounded pursuit of social understanding (hypermentalization), and epistemic exploitation of individuals in whom artificial understanding by AI triggers excessive credulity. Nonetheless, we propose ethically informed pathways for integrating AI to enhance clinical practice, therapist training, and client care, particularly in augmenting human capacities within group and adjunctive therapy contexts. Paradoxically, AI could support psychotherapists in improving their capacity to mentalize, improve their understanding of their clients, and provide such understanding within the moral constraints that normally govern their work. This paper calls for careful ethical regulation similar to that limiting genetic manipulation, interdisciplinary research, and clinician involvement in shaping future AI-based psychotherapeutic models, emphasizing that AI’s role should complement rather than replace the irreplaceable relational core of psychotherapy.

Researchers have cracked the code behind how plants make mitraphylline, a rare cancer-fighting molecule. Their discovery of two critical enzymes explains how nature builds complex spiro-shaped compounds. The work paves the way for sustainable, lab-based production of valuable natural medicines. Supported by international collaborations, the findings spotlight plants as powerful natural chemists.

Nature Medicine, Published online: 10 October 2025; doi:10.1038/s41591-025-04033-7

We call for more studies exploring the implementation of AI technologies and what happens when humans and AI interact in the clinic.

An experimental gene therapy from Sarepta Therapeutics increased levels of the gene missing in an ultra-rare form of muscular dystrophy, according to data the company presented Friday.

The company has said it plans to file for approval in the disease, known as limb-girdle muscular dystrophy (LGMD) 2E. That would make it the first approved treatment in LGMD, a broad collection of highly rare diseases that can deprive patients of the ability to walk and in some cases shorten life. But it is likely to face a significant uphill battle. 

The LGMD 2E therapy relies on the same gene-ferrying virus that Sarepta uses in its other treatments, including its approved gene therapy for Duchenne muscular dystrophy, Elevidys, and experimental gene therapies for several other LGMD subtypes. 

Continue to STAT+ to read the full story…

© Charles Krupa/AP

npj Digital Medicine, Published online: 10 October 2025; doi:10.1038/s41746-025-01993-5

Automated AI based identification of autism spectrum disorder from home videos

DNA methylation is an epigenetic modification that regulates gene expression by adding methyl groups to DNA, affecting cellular function and disease development. Machine learning, a subset of artificial intell...

国务院总理李强日前签署国务院令，公布《生物医学新技术临床研究和临床转化应用管理条例》（以下简称《条例》），自2026年5月1日起施行。《条例》旨在规范生物医学新技术临床研究和临床转化应用，促进医学科学技术进步和创新，保障医疗质量安全，维护人的尊严和健康。（新华社）

Nature, Published online: 09 October 2025; doi:10.1038/d41586-025-02681-w

By refusing to bend the rules I set for myself, I created structure and a better environment for my mental health.

Publication date: December 2025

Source: Artificial Intelligence in Medicine, Volume 170

Author(s): Hamed Jafarpour, Guosong Wu, Cheligeer (Ken) Cheligeer, Jun Yan, Yuan Xu, Danielle A. Southern, Cathy A. Eastwood, Yong Zeng, Hude Quan

Science, Ahead of Print.

Heart disease is the leading cause of mortality globally. Electrocardiograms (ECGs) are standard instruments for the examination of heart conditions, but traditional analysis is time-consuming and prone to errors. Novel advances in artificial intelligence have improved ECG classification. However, some limitations remain, such as poor interpretability, computational cost, and class imbalance. This study proposes a novel deep learning algorithm based on Depthwise Separable Residual Attention called DRA-ECG and a customized Adaptive Focal Cross-Entropy (AFCE) loss function for cardiac condition classification. This proposed methodology leverages the Continuous Wavelet Transform (CWT) method to transform 1D raw ECG signals into 2D scalograms to enhance feature representation and training. The proposed customized AFCE loss function incorporated into the DRA-ECG model addresses the class imbalance problem and boost the performance of the model. More so, this study incorporates edge feature detection as a preprocessing technique to denoise and enhance the trainable features of the 2D scalograms for optimal feature representation. The proposed DRA-ECG model achieves a high accuracy of 98.17%, recall of 95.78%, F1-score of 95.82%, and precision of 95.89%. This study shows that the results achieved by the proposed DRA-ECG surpass the current state-of-the-art and existing research works, concerning classification performance and generalization ability in ECG classification, which underlines the effectiveness of the novel AFCE loss function for ensuring high-classification accuracy and robustness. The proposed novel methodology enhances heart disease classification and provides a robust and reliable solution for medical diagnosis, addressing the major drawbacks of existing models.

Depression is a prevalent mental health disorder that presents significant challenges for timely diagnosis and intervention. Automated Depression Detection (ADD) systems using text and audio offer scalable mental health assessment solutions. This review systematically evaluates 65 studies published between 2018 and 2024, focusing on ADD methods that utilize machine learning models with multimodal data. We examine key methodologies, including data augmentation, multimodal fusion, and feature extraction, along with state-of-the-art ADD systems. The review emphasizes the need for culturally adaptable, high-quality datasets and interpretable models for clinical use. We also identify gaps in longitudinal data and real-world applications. Future research should focus on developing clinically integrated, cross-cultural ADD systems that are interpretable, scalable, and robust. The findings of this review contribute to the research field by providing a comprehensive overview of existing methodologies, identifying gaps in the current literature, and offering insights for future advancements in depression detection using speech and text analysis.

Earlier this year, Tom Stanis was puzzling through what was next for his startup Story Health, which helps providers care for people with heart failure. The company had some big-name customers and plans to expand, but it last raised money in 2022. Stanis saw two options: shake more cash out of a stingy venture capital market, or sell.

Armed with $275 million in fresh funding and a built-in customer base, artificial intelligence company Innovaccer made the answer easy. It gobbled up Story Health for an undisclosed mix of equity and cash in September. 

Story Health is the fourth Innovaccer acquisition in about a year as it aims to become the default AI platform for health systems. CEO Abhinav Shashank plans to rapidly expand and to “accelerate that development through M&A,” he told STAT.

Innovaccer’s shopping spree is just one example of a trend playing out in digital health: big, well-funded companies with momentum are snapping up smaller players.

Continue to STAT+ to read the full story…

© Adobe

About a year ago, I logged into MyChart the day before my annual wellness visit and saw a new consent form. My doctor wanted to record our visit so artificial intelligence could create notes and update my medical record. I agreed. Just hours after my visit ended, a comprehensive, accurate visit summary appeared in MyChart.

As a career clinical trialist, I immediately wondered: What if this tool were used for trial visits? Could it enable a breakthrough in research or patient engagement? How will clinical research adapt to what could be a “new normal” in medical documentation?

Driven by a crisis of clinician burnout, ambient digital scribes (ADS) like the one my doctor used are being rapidly adopted. Studies suggest these digital scribes can reduce documentation burden, improve clinician efficiency, and potentially enhance the patient experience. By digitizing conversations in real time, these scribes open possibilities beyond routine care, particularly in clinical research and trials.

Continue to STAT+ to read the full story…

© Adobe

Our objective was to investigate how artificial intelligence (AI) predictions calculated on structured hospital data are presented to clinicians. We performed a systematic review of 5 databases and 9 other reviews, identifying 31 studies on 21 implemented clinical AI systems. We report current approaches to presenting AI predictions to clinicians, whether and how interaction on the user interface (UI) is used, how UIs have been evaluated and the extent to which clinicians have been involved in UI design and testing. The results indicate variation across systems in presentation content and styles, evaluation methods, and interaction approaches. Half of the systems implemented a co-design approach to UI development. Our findings provide valuable insights for future AI-based clinical decision support system designers, clinical AI researchers and healthcare organisations seeking to implement clinical AI solutions.