❌

Reading view

↗️

Implementing a Digital Mental Health Intervention—the Lumi Nova App—to Support Children With Anxiety in Economically Disadvantaged Areas: Mixed Methods Study

✇Journal of Medical Internet Research
By: Pauline Whelan · Heidi Tranter · Lesley-Anne Carter · John Sainsbury · Manjul Rathee · Charlotte Stockton-Powdrell · Niamh Bolton · Kathryn Mary Abel
Background: Anxiety is one of the most common mental health problems experienced by children worldwide. In the UK, many children experiencing anxiety do not receive adequate or timely help. Children living in economically-disadvantaged areas experience more mental health problems than those living in high income areas and are less able to engage in activities that can have a positive or protective impact on their mental health. The need for providing low-cost, accessible and engaging mental health interventions for children living in these areas is high. Objective: The study aimed to explore how a digital mental health therapeutic, ‘Lumi Nova: Tales of Courage’, could be used to support children living with anxiety in economically-disadvantaged areas. Methods: A mixed method study design was used to explore the implementation of Lumi Nova using a supported delivery model with mental health teams based in the North of England. Quantitative data collection on recruitment and engagement patterns were collected and analysed. Qualitative research explored children, parent and practitioner views and experiences with the Lumi Nova app. Results: 113 children were consented to use Lumi Nova and 98 (87%) accessed the intervention at least once. Qualitative semi-structured interviews found that children, their parents and practitioners viewed the Lumi Nova app positively. Quantitative analysis of the recruitment data suggested the feasibility of a future larger roll-out. Analysis of usage data demonstrated varied patterns of engagement with the intervention. The frequency and duration of usage varied across children, as did the activities completed within the game: almost half (49%) completed three in-game challenges indicating progression through the treatment pathway. Conclusions: The study demonstrated that a digital mental health intervention could be successfully deployed within economically-disadvantaged areas in the UK to support children experiencing anxiety. Expected barriers to the deployment of digital mental health interventions in economically-disadvantaged areas (e.g. lack of access to smartphones, data plans, lack of technical skills) were not reported. Digital mental health interventions have the potential to address current gaps in mental health provision for disadvantaged individuals and communities.
  •  
  • ↗️
↗️

Transforming commercial pharma with agentic AI 

✇MIT Technology Review
By: MIT Technology Review Insights

Amid the turbulence of the wider global economy in recent years, the pharmaceuticals industry is weathering its own storms. The rising cost of raw materials and supply chain disruptions are squeezing margins as pharma companies face intense pressure—including from countries like the US—to control drug costs. At the same time, a wave of expiring patents threatens around $300 billion in potential lost sales by 2030. As companies lose the exclusive right to sell the drugs they have developed, competitors can enter the market with generic and biosimilar lower-cost alternatives, leading to a sharp decline in branded drug sales—a “patent cliff.” Simultaneously, the cost of bringing new drugs to market is climbing. McKinsey estimates cost per launch is growing 8% each year, reaching $4 billion in 2022. 

In clinics and health-care facilities, norms and expectations are evolving, too. Patients and health-care providers are seeking more personalized services, leading to greater demand for precision drugs and targeted therapies. While proving effective for patients, the complexity of formulating and producing these drugs makes them expensive and restricts their sale to a smaller customer base.

The need for personalization extends to sales and marketing operations too as pharma companies are increasingly needing to compete for the attention of health-care professionals (HCPs). Estimates suggest that biopharmas were able to reach 45% of HCPs in 2024, down from 60% in 2022. Personalization, real-time communication channels, and relevant content offer a way of building trust and reaching HCPs in an increasingly competitive market. But with ever-growing volumes of content requiring medical, legal, and regulatory (MLR) review, companies are struggling to keep up, leading to potential delays and missed opportunities. 

Download the report.

This content was produced by Insights, the custom content arm of MIT Technology Review. It was not written by MIT Technology Review’s editorial staff. It was researched, designed, and written by human writers, editors, analysts, and illustrators. AI tools that may have been used were limited to secondary production processes that passed thorough human review.

  •  
  • ↗️
↗️

Combined Immersive and Nonimmersive Virtual Reality With Mirror Therapy for Patients With Stroke: Systematic Review and Meta-Analysis of Randomized Controlled Trials

✇Journal of Medical Internet Research
By: Chaoran Gao · Yuan Chen · Yixin Wei · Yitong Qiu · Huiyan Song · Chenfan Gui · Qiang Gao
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
  •  
  • ↗️
↗️

Digital twin models for predicting venetoclax and azacitidine-induced neutropenia in patients with acute myeloid leukemia

✇npj Digital Medicine
By: Yue Zhang · Jonathan Martinez · Bahar Tercan · Heikki Kuusanmäki · Frank Emmert-Streib · Jerome G. Chandraseelan · Amer Farea · Olli Yli-Harja · Caroline A. Heckman · David L. Gibbs · Vesteinn Thorsson · Ilya Shmulevich · Mika Kontro · Guangrong Qin · Boris Aguilar

npj Digital Medicine, Published online: 06 October 2025; doi:10.1038/s41746-025-01978-4

Digital twin models for predicting venetoclax and azacitidine-induced neutropenia in patients with acute myeloid leukemia
  •  
  • ↗️
↗️

Efficient and accurate search in petabase-scale sequence repositories

✇Nature - Issue - nature.com science feeds
By: Mikhail Karasikov · Harun Mustafa · Daniel Danciu · Oleksandr Kulkov · Marc Zimmermann · Christopher Barber · Gunnar Rätsch · André Kahles

Nature, Published online: 08 October 2025; doi:10.1038/s41586-025-09603-w

MetaGraph enables scalable indexing of large sets of DNA, RNA or protein sequences using annotated de Bruijn graphs.
  •  
  • ↗️
↗️

Pathobiology and Genetics

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Christina A Eichstaedt · Andrea Olschewski · Lars Harbaum · Sebastian Cordes · Peter Dorfmüller · Vasile Foris · Wolfgang M Kuebler · Grazyna Kwapiszewska · Soni Pullamsetti · Natascha Sommer · Christoph Tabeling · Norbert Weissmann · Anja Zoll · Katrin Hinderhofer · Ralph T Schermuly

Pneumologie. 2025 Oct;79(10):701-711. doi: 10.1055/a-2625-4648. Epub 2025 Oct 6.

ABSTRACT

Genetics and pathobiology were addressed at the 7th World Symposium on Pulmonary Hypertension in Task Forces 2 and 3. The Genetics Task Force also focused on precision medicine approaches, and the Pathobiology working group concentrated heavily on new omics technologies. Therefore, the following not only summarises the current state of knowledge on genetics, genetic testing methods, and molecular pathophysiological changes, but also places it in context and critically discusses it. In addition, the importance of national and international biobanks and cohorts, as well as the active involvement of patients and families, is emphasized.

PMID:41052524 | DOI:10.1055/a-2625-4648

  •  
  • ↗️
↗️

The Potential of AI in Nursing Care: Multicenter Evaluation in Fall Risk Assessment

✇Journal of Medical Internet Research
By: Ivana Nanevski · Sebastian Jäger · Matthias Schulte-Althoff · Eva-Maria Behnke · Daniel Fürstenau · Felix Biessmann
Background: With 28%-35% of individuals aged 65 years and older experiencing incidents of falling, falls are the second leading cause of unintentional injury–related deaths globally. Limited availability of clinical staff often impedes the timely detection and prevention of potential falls. Advances in artificial intelligence (AI) could complement existing fall risk assessment and help better allocate nursing care resources. Yet, many studies are based on small datasets from a single institution, which can restrict the generalizability of the model, and do not investigate important aspects in AI model development, such as fairness across demographic groups. Objective: This study aimed to provide a comprehensive empirical evaluation of the potential of AI in nursing care, focusing on the case of fall risk prediction. To account for demographic and contextual differences in fall incidences, we analyze data from a university and a geriatric hospital in Germany. To the best of our knowledge, these are the largest fall risk prediction datasets to date with heterogeneous data distributions. We focus on 3 key objectives. First, does AI help in improving fall risk prediction? Second, how can AI models be trained safely across different hospitals? Finally, are these models fair? Methods: This study used 2 datasets for fall risk prediction: one from a university hospital with 931,726 participants, 10,442 of whom experienced falls, and another from a geriatric hospital with 12,773 participants, 1728 of whom have fallen. State-of-the-art AI models were trained with 3 approaches, including 2 decentralized learning paradigms. First, separate models were trained on data from each hospital; second, models were retrained on the respective other dataset; and federated learning (FL) was applied to both datasets. The performance of these models was compared with the rule-based systems as implemented in clinical practice for fall risk prediction. Additional analyses were conducted to test for model fairness. Results: Our findings demonstrate that AI models consistently outperform rule-based systems across all experimental setups, with the area under the receiver operating characteristic curve of 0.735 (90% CI 0.727-0.744) for the geriatric hospital, and 0.926 (90% CI 0.924-0.928) for the university hospital. FL did not improve the fall risk prediction in this setting. Our fairness analysis ruled out disparities in model performance between different sex groups, but we found fairness infringements across age groups. Conclusions: This study demonstrates that AI models consistently outperform traditional rule-based systems across heterogeneous datasets in predicting fall risk. However, it also reveals the challenges related to demographic shifts and label distribution imbalances, which limited the FL models’ ability to generalize. While the fairness analysis indicated fair results across sex subgroups, age-related disparities emerged. Addressing data imbalances and ensuring broader representation across demographic groups will be crucial for developing more fair and generalizable models.
  •  
  • ↗️
↗️

Evaluating Large Language Models and Retrieval-Augmented Generation Enhancement for Delivering Guideline-Adherent Nutrition Information for Cardiovascular Disease Prevention: Cross-Sectional Study

✇Journal of Medical Internet Research
By: Vijaya Parameswaran · Jenna Bernard · Alec Bernard · Neil Deo · Sean Tsung · Kalle Lyytinen · Christopher Sharp · Fatima Rodriguez · David J Maron · Rajesh Dash
Background: Cardiovascular disease (CVD) remains the leading cause of death worldwide, yet many web-based sources on cardiovascular (CV) health are inaccessible. Large language models (LLMs) are increasingly used for health-related inquiries and offer an opportunity to produce accessible and scalable CV health information. However, because these models are trained on heterogeneous data, including unverified user-generated content, the quality and reliability of food and nutrition information on CVD prevention remain uncertain. Recent studies have examined LLM use in various health care applications, but their effectiveness for providing nutrition information remains understudied. Although retrieval-augmented generation (RAG) frameworks have been shown to enhance LLM consistency and accuracy, their use in delivering nutrition information for CVD prevention requires further evaluation. Objective: To evaluate the effectiveness of off-the-shelf and RAG-enhanced LLMs in delivering guideline-adherent nutrition information for CVD prevention, we assessed 3 off-the-shelf models (ChatGPT-4o, Perplexity, and Llama 3-70B) and a Llama 3-70B+RAG model. Methods: We curated 30 nutrition questions that comprehensively addressed CVD prevention. These were approved by a registered dietitian providing preventive cardiology services at an academic medical center and were posed 3 times to each model. We developed a 15,074-word knowledge bank incorporating the American Heart Association’s 2021 dietary guidelines and related website content to enhance Meta’s Llama 3-70B model using RAG. The model received this and a few-shot prompt as context, included citations in a Context Source section, and used vector similarity to align responses with guideline content, with the temperature parameter set to 0.5 to enhance consistency. Model responses were evaluated by 3 expert reviewers against benchmark CV guidelines for appropriateness, reliability, readability, harm, and guideline adherence. Mean scores were compared using ANOVA, with statistical significance set at P<.05. interrater agreement was measured using the cohen coefficient and readability estimated flesch-kincaid score. results: llama model scored higher than perplexity gpt-4o models on reliability appropriateness guideline adherence showed no harm.>70%; P<.001 indicated high reviewer agreement. conclusions: the llama model outperformed off-the-shelf models across all measures with no evidence of harm although responses were less readable due to technical language. scored lower on and produced some harmful responses. these findings highlight limitations demonstrate that rag system integration can enhance llm performance in delivering evidence-based dietary information.>
  •  
  • ↗️
↗️

The Role of Data in Public Health and Health Innovation: Perspectives on Social Determinants of Health, Community-Based Data Approaches, and AI

✇Journal of Medical Internet Research
By: Kaakpema Yelpaala · Michael Christopher Gibbons · Ines Maria Vigil · Jennifer Leaño · Terika McCall · Ijeoma Opara · Anne Zink · Marcella Nunez-Smith · Bhramar Mukherjee · Megan Ranney
Public health is undergoing profound transformation driven by data from the global health sector and related fields. To address systemic health disparities, scholars and practitioners are increasingly applying a data equity lens, an approach that has become even more urgent as the United States faces the erosion of public health data infrastructure. This paper summarizes insights from an April 2024 convening by the Yale School of Public Health—The Role of Data in Public Health Equity and Innovation—with intersectoral stakeholders from academia, government (local, state, and federal), healthcare, and private industry. The convening included keynote presentations and roundtables regarding the depiction of social determinants of health (SDOH) in data; effects of artificial intelligence (AI) on health data equity; and community-based models for data, providing a framework for cross-cutting discussions. Through a narrative synthesis, themes were identified and synthesized from systematically gathered information from presentations and roundtables. This process led to a set of actionable, cross-cutting recommendations to guide inclusive and impactful data practices for policymakers, public health professionals, and health innovators across diverse contexts: (1) Enable big data and interoperability connecting SDOH and health outcomes; (2) Include diverse, non-technical voices in AI and health discussions; (3) Fund research on data equity and AI in health sciences; (4) Modernize Health Insurance Portability and Accountability Act (HIPAA) with new guidelines for AI and big data; and (5) Research and conceptual frameworks are needed to elucidate interconnections between data equity and health equity.
  •  
  • ↗️
↗️

Generative artificial intelligence in medicine

✇Nature Medicine
By: Zhen Ling Teo · Arun James Thirunavukarasu · Kabilan Elangovan · Haoran Cheng · Prasanth Moova · Brian Soetikno · Christopher Nielsen · Andreas Pollreisz · Darren Shu Jeng Ting · Robert J. T. Morris · Nigam H. Shah · Curtis P. Langlotz · Daniel Shu Wei Ting

Nature Medicine, Published online: 06 October 2025; doi:10.1038/s41591-025-03983-2

This Review summarizes recent technical advancements in generative AI, outlines how new models might improve healthcare and discusses validation approaches—using lessons from recent successes and failures in the field.
  •  
  • ↗️
↗️

Single-cell and multi-omics analysis identifies TRIM9 as a key ubiquitination regulator in pancreatic cancer

✇(Multiomics OR Omics) AND (Pancreatic)
By: Liang Chen · Xiaomei Ying · Chenfeng Ma · Qikai Tang · Shuai Chen

Front Immunol. 2025 Sep 19;16:1631708. doi: 10.3389/fimmu.2025.1631708. eCollection 2025.

ABSTRACT

This study investigates the role of ubiquitination-related genes in pancreatic cancer (PC) using single-cell RNA sequencing (scRNA-seq), spatial transcriptomics, and multi-omics approaches. scRNA-seq data (GSE155698) from PC samples identified 12 cell types, with endothelial cells exhibiting high ubiquitination scores (High_ubiquitin-Endo) and enriched interactions with fibroblasts/macrophages via WNT, NOTCH, and integrin pathways. Spatial transcriptomics (GSE235315) validated cell-type localization. Mendelian randomization (SMR) analysis prioritized TRIM9 as a PC-protective gene, downregulated in tumors and correlated with better survival. WGCNA revealed TRIM9-co-expressed modules linked to prognosis. A machine learning-based prognostic model (CoxBoost+RSF) integrating seven genes (TSPAN6, TSC1, RNF167, PBXIP1, LRRC49, KATNAL2, IGF2BP2) stratified patients into high/low-risk groups with distinct survival, mutation burdens, and immune infiltration. TRIM9 overexpression suppressed PC cell proliferation/migration in vitro, while knockdown enhanced malignancy. Mechanistically, TRIM9 promoted K11-linked ubiquitination and proteasomal degradation of HNRNPU, dependent on its RING domain. In vivo, TRIM9 overexpression reduced tumor growth, rescued by HNRNPU co-expression. Integrated analyses highlight TRIM9 as a tumor suppressor and prognostic biomarker, mediated via ubiquitination-dependent regulation of HNRNPU stability. This work provides insights into ubiquitination-driven PC pathogenesis and therapeutic targeting.

PMID:41050689 | PMC:PMC12491318 | DOI:10.3389/fimmu.2025.1631708

  •  
  • ↗️
↗️

A computational medicine framework integrating multi-omics, systems biology, and artificial neural networks for Alzheimer's disease therapeutic discovery

✇(Multiomics OR Omics) AND (Pancreatic)
By: Yisheng Yang · Yizhu Diao · Lulu Jiang · Fanlu Li · Liye Chen · Ming Ni · Zheng Wang · Hai Fang

Acta Pharm Sin B. 2025 Sep;15(9):4411-4426. doi: 10.1016/j.apsb.2025.07.018. Epub 2025 Jul 16.

ABSTRACT

The translation of genetic findings from genome-wide association studies into actionable therapeutics persists as a critical challenge in Alzheimer's disease (AD) research. Here, we present PI4AD, a computational medicine framework that integrates multi-omics data, systems biology, and artificial neural networks for therapeutic discovery. This framework leverages multi-omic and network evidence to deliver three core functionalities: clinical target prioritisation; self-organising prioritisation map construction, distinguishing AD-specific targets from those linked to neuropsychiatric disorders; and pathway crosstalk-informed therapeutic discovery. PI4AD successfully recovers clinically validated targets like APP and ESR1, confirming its prioritisation efficacy. Its artificial neural network component identifies disease-specific molecular signatures, while pathway crosstalk analysis reveals critical nodal genes (e.g., HRAS and MAPK1), drug repurposing candidates, and clinically relevant network modules. By validating targets, elucidating disease-specific therapeutic potentials, and exploring crosstalk mechanisms, PI4AD bridges genetic insights with pathway-level biology, establishing a systems genetics foundation for rational therapeutic development. Importantly, its emphasis on Ras-centred pathways-implicated in synaptic dysfunction and neuroinflammation-provides a strategy to disrupt AD progression, complementing conventional amyloid/tau-focused paradigms, with the future potential to redefine treatment strategies in conjunction with mRNA therapeutics and thereby advance translational medicine in neurodegeneration.

PMID:41049755 | PMC:PMC12491700 | DOI:10.1016/j.apsb.2025.07.018

  •  
  • ↗️
↗️

MOFNet: a deep learning framework for multi-omics data fusion in cancer subtype classification

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Guangji Zhang · Chunxiao Zhang · Pengpai Li · Duanchen Sun · Zhixia Yang · Zhi-Ping Liu

Mol Omics. 2025 Oct 1. doi: 10.1039/d5mo00221d. Online ahead of print.

ABSTRACT

BACKGROUND: cancer exhibits high molecular and clinical heterogeneity, making accurate subtyping essential for personalized treatment. Traditional single-omics approaches often fail to capture this complexity. Multi-omics integration offers a more holistic understanding, but many existing methods either lack interpretability or fail to model cross-omics correlations effectively.

METHODS: we developed MOFNet, a novel supervised deep learning framework for multi-omics integration, incorporating a similarity graph pooling (SGO) module and a view correlation discovery network (VCDN). MOFNet processes omics data-including mRNA expression, DNA methylation, and miRNA expression-via omics-specific graph learning and cross-omics label space fusion. Three cancer types-breast cancer (BRCA), low-grade glioma (LGG), and stomach adenocarcinoma (STAD)-were analyzed using datasets from the cancer genome atlas (TCGA). Statistical evaluation was performed using accuracy, weighted F1 score, and macro F1 score across stratified training/testing splits.

RESULTS: MOFNet achieved superior performance across all datasets. For BRCA, it obtained an accuracy of 85.17%, F1_weighted of 85.36%, and macro F1 of 80.93%, outperforming all baseline models by up to 18.25%. In LGG and STAD, MOFNet also showed robust gains, with maximum improvements of 23.72% and 21.56%, respectively. Omics ablation studies demonstrated enhanced performance with multi-omics integration. Functional enrichment analysis revealed that MOFNet-identified key features were involved in biologically relevant pathways such as cell cycle regulation, synaptic signaling, and ion transport.

CONCLUSIONS: MOFNet enables scalable and interpretable multi-omics data fusion for cancer subtype classification, significantly improving predictive accuracy while retaining only 25% of input features. The integration of SGO and VCDN modules offers both biological interpretability and computational efficiency. These results suggest MOFNet's promising application in precision oncology and biomarker discovery.

PMID:41031935 | DOI:10.1039/d5mo00221d

  •  
  • ↗️
↗️

The tumour microenvironment in pancreatic cancer - new clinical challenges, but more opportunities

✇(Multiomics OR Omics) AND (Pancreatic)
By: Heng-Chung Kung · Kevin W Zheng · Jacquelyn W Zimmerman · Lei Zheng

Nat Rev Clin Oncol. 2025 Oct 3. doi: 10.1038/s41571-025-01077-z. Online ahead of print.

ABSTRACT

Patients with advanced-stage pancreatic ductal adenocarcinoma (PDAC) predominantly receive chemotherapy, and despite initial responses in some patients, most will have disease progression and often dismal outcomes. This lack of clinical effectiveness partly reflects not only cancer cell-intrinsic factors but also the presence of a tumour microenvironment (TME) that precludes access of both systemic therapies and circulating immune cells to the primary tumour, as well as supporting the growth of PDAC cells. Combined with improved preclinical models of PDAC, advances in single-cell spatial multi-omics and machine learning-based models have provided novel methods of untangling the complexities of the TME. In this Review, we focus on the desmoplastic stroma and both the intratumoural and intertumoural heterogeneity of PDAC, with an emphasis on cancer-associated fibroblasts and their surrounding immune cell niches. We describe new approaches in converting the immunologically 'cold' PDAC TME into a 'hot' TME by priming T cell activation, overcoming T cell exhaustion and unravelling myeloid cell-mediated immunosuppression. Furthermore, we explore integrated targets involving the TME, such as points of convergence among tumour, stromal and immune cell metabolism as well as oncogenic KRAS signalling. Finally, building on our experience with failed clinical trials in the past, we consider how this evolving comprehensive understanding of the TME will ensure future success in developing more effective therapies for patients with PDAC.

PMID:41044427 | DOI:10.1038/s41571-025-01077-z

  •  
  • ↗️
❌