❌

Normal view

FUSION: a web-based application for in-depth exploration of multi-omics data with brightfield histology

Nat Commun. 2025 Sep 25;16(1):8388. doi: 10.1038/s41467-025-63050-9.

ABSTRACT

Spatial technologies examining the cell and tissue microenvironment at near single-cell resolution are revealing important molecular insights. However, few tools enable integrated, interactive analysis of spatial-omics with tissue morphology in the same functional tissue unit. Here, we present FUSION (Functional Unit State Identification in Whole Slide Images), a web-based platform for visualizing and analyzing spatial-omics data with high-resolution histology. FUSION provides workflows for assessing cell compositions, quantitative morphometrics, and comparative tissue analyses. We demonstrate applicability across spatial assays, including 10x Visium, Visium HD, 10x Xenium, Cell DIVE, and PhenoCycler, applied to healthy and diseased tissues from kidney, small intestine, lung, and skin in the Human BioMolecular Atlas Program. FUSION is cloud-based, open-source, and accessible at https://fusion.hubmapconsortium.org/ , hosting over 50 paired datasets and tutorials. In a series of use cases, we show its capacity to distinguish renal glomeruli injury states, quantify morphometric changes, and characterize fibrosis with immune infiltration.

PMID:40998789 | PMC:PMC12462499 | DOI:10.1038/s41467-025-63050-9

Application of Nudges to Design Clinical Decision Support Tools: Systematic Approach Guided by Implementation Science

Background: Clinical decision support (CDS) is one strategy to increase evidence-based practices by clinicians. Despite its potential, CDS tools have had mixed results and are often disliked by clinicians. Principles from behavioral economics, including “nudges,” may improve the effectiveness and clinician satisfaction of CDS tools. Objective: This paper outlines a pragmatic approach grounded in implementation science to identify and prioritize how to incorporate different types of nudges into CDS tools. Methods: We applied the Messenger, Incentives, Norms, Defaults, Salience, Priming, Affect, Commitments and Ego (MINDSPACE) nudge framework and the Practical, Robust Implementation and Sustainability Model (PRISM) implementation science framework to systematically and pragmatically identify and prioritize different types of nudges for CDS tools. A case example of a CDS tool to improve guideline-concordant prescribing for patients with heart failure was used to illustrate how these frameworks can be applied in real-life scenarios. We describe a process of how these frameworks can be used pragmatically by clinicians and informaticists or more technical CDS builders to apply nudge theory to CDS tools. Results: Four iterative steps guided by PRISM were defined: 1) engage partners for user-centered design, 2) develop a shared understanding of the nudge types, 3) determine the nudge type for the overarching CDS format, and 4) brainstorm and prioritize nudge types and forms to address each modifiable contextual issue. These steps are iterative and intended to be adapted to align with the local resources and needs of various clinical scenarios and settings. We provide illustrative examples of how this approach was applied to the case example, including who we engaged, details of nudge design decisions, and lessons learned. Conclusions: We present a pragmatic approach to guide the selection and prioritization of nudges, informed by implementation science. This approach can be used to comprehensively and systematically consider key issues in designing CDS to optimize clinician satisfaction, effectiveness, equity, and sustainability while minimizing the potential for unintended consequences. The findings can be adapted and generalized to other health settings and clinical situations, advancing the goals of learning health systems to expedite the translation of evidence into practice.

Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis

npj Digital Medicine, Published online: 25 September 2025; doi:10.1038/s41746-025-01852-3

Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis

Quality safety and disparity of an AI chatbot in managing chronic diseases: simulated patient experiments

npj Digital Medicine, Published online: 25 September 2025; doi:10.1038/s41746-025-01956-w

Quality safety and disparity of an AI chatbot in managing chronic diseases: simulated patient experiments

Ophthalmic drug discovery and development using artificial intelligence and digital health technologies

npj Digital Medicine, Published online: 25 September 2025; doi:10.1038/s41746-025-01954-y

Ophthalmic drug discovery and development using artificial intelligence and digital health technologies

What top VCs want from AI founders: Inside the investor lens with Jon McNeill, Aileen Lee, and Steve Jang at TechCrunch Disrupt 2025

25 September 2025 at 23:00
Jon McNeill (DVx Ventures), Aileen Lee (Cowboy Ventures), and Steve Jang (Kindred Ventures) share what AI founders need to know now: from defensibility to term sheets. TechCrunch Disrupt 2025 takes place October 27–29 in San Francisco. Register before tomorrow ends to save up to $668.

Step into the future: The full AI Stage agenda at TechCrunch Disrupt 2025

24 September 2025 at 22:30
The AI Stage at TechCrunch Disrupt 2025 is officially locked and loaded, featuring the powerhouses shaping the future of artificial intelligence.

Expanding care coordination in an integrated health system through causal machine learning

npj Digital Medicine, Published online: 24 September 2025; doi:10.1038/s41746-025-01925-3

Expanding care coordination in an integrated health system through causal machine learning

Article: InfoQ AI, ML and Data Engineering Trends Report - 2025

This InfoQ Trends Report offers readers a comprehensive overview of emerging trends and technologies in the areas of AI, ML, and Data Engineering. This report summarizes the InfoQ editorial team’s and external guests' view on the current trends in AI and ML technologies and what to look out for in the next 12 months.

By Srini Penchikala, Savannah Kunovsky, Anthony Alford, Daniel Dominguez, Vinod Goje

Fine-Tuning Methods for Large Language Models in Clinical Medicine by Supervised Fine-Tuning and Direct Preference Optimization: Comparative Evaluation

Background: Large language model (LLM) fine tuning is the process of adjusting out-of-the-box model weights using a dataset of interest. Fine tuning can be a powerful technique to improve model performance in fields like medicine, where data access is restricted and LLMs may have poor out-of-the-box performance. Objective: In this study we investigated the benefits of fine tuning with supervised fine tuning (SFT) and direct preference optimization (DPO) across a range of LLM applications for medicine Methods: We use Llama3 7B and Mistral 7B v2 to compare the performance of SFT and DPO across four datasets for common natural language tasks in medicine. The tasks evaluated were simple classification, clinical reasoning, summarization, and clinical triage. Results: Clinical Reasoning accuracy increased 8% and 7% with DPO over SFT for Llama3 (p value 0.003) and Mistral2 (p value 0.004) respectively. Summarization quality, graded on a five point Likert scale, increased 0.13 and 0.10 for Llama3 and Mistral2 (p values

Comparative Evaluation of a Medical Large Language Model in Answering Real-World Radiation Oncology Questions: Multicenter Observational Study

Background: Large language models (LLMs) hold promise for supporting clinical tasks, particularly in data-driven and technical disciplines such as radiation oncology. While prior evaluation studies have focused on examination-style settings for evaluating LLMs, their performance in real-life clinical scenarios remains unclear. In the future, LLMs might be used as general AI assistants to answer questions arising in clinical practice. It is unclear how well a modern LLM, locally executed within the infrastructure of a hospital, would answer such questions compared with clinical experts. Objective: This study aimed to assess the performance of a locally deployed, state-of-the-art medical LLM in answering real-world clinical questions in radiation oncology compared with clinical experts. The aim was to evaluate the overall quality of answers, as well as the potential harmfulness of the answers if used for clinical decision-making. Methods: Physicians from 10 departments of European hospitals collected questions arising in the clinical practice of radiation oncology. Fifty of these questions were answered by 3 senior radiation oncology experts with at least 10 years of work experience, as well as the LLM Llama3-OpenBioLLM-70B (Ankit Pal and Malaikannan Sankarasubbu). In a blinded review, physicians rated the overall answer quality on a 5-point Likert scale (quality), assessed whether an answer might be potentially harmful if used for clinical decision-making (harmfulness), and determined if responses were from an expert or the LLM (recognizability). Comparisons between clinical experts and LLMs were then made for quality, harmfulness, and recognizability. Results: There were no significant differences between the quality of the answers between LLM and clinical experts (mean scores of 3.38 vs 3.63; median 4.00, IQR 3.00-4.00 vs median 3.67, IQR 3.33-4.00; P=.26; Wilcoxon signed rank test). The answers were deemed potentially harmful in 13% of cases for the clinical experts compared with 16% of cases for the LLM (P=.63; Fisher exact test). Physicians correctly identified whether an answer was given by a clinical expert or an LLM in 78% and 72% of cases, respectively. Conclusions: A state-of-the-art medical LLM can answer real-life questions from the clinical practice of radiation oncology similarly well as clinical experts regarding overall quality and potential harmfulness. Such LLMs can already be deployed within the local hospital environment at an affordable cost. While LLMs may not yet be ready for clinical implementation as general AI assistants, the technology continues to improve at a rapid pace. Evaluation studies based on real-life situations are important to better understand the weaknesses and limitations of LLMs in clinical practice. Such studies are also crucial to define when the technology is ready for clinical implementation. Furthermore, education for health care professionals on generative AI is needed to ensure responsible clinical implementation of this transforming technology.

Circulating tumor DNA in patients with cancer: insights from clinical laboratory

Adv Lab Med. 2025 Jun 16;6(3):259-276. doi: 10.1515/almed-2025-0010. eCollection 2025 Sep.

ABSTRACT

Blood-based circulating tumor DNA (ctDNA) analysis has emerged as a highly relevant non-invasive method for molecular profiling of solid tumors, offering valuable information about the genetic landscape of cancer. Somatic mutation analysis of ctDNA is now used clinically to guide targeted therapies for advanced cancers. Recent advancements have also revealed its potential in early detection, prognosis, minimal residual disease assessment, and prediction/monitoring of therapeutic response. In recent years, significant progress has been made with the development of various PCR and NGS-based methods designed for assessing gene variants in ctDNA of patients with cancer. However, despite the transformative possibilities that ctDNA analysis presents, challenges persist. Standardization of preanalytical and analytical protocols, assay sensitivity, and the interpretation of results remain critical hurdles that need to be addressed for the widespread clinical implementation of ctDNA testing. In addition to somatic mutations, emerging studies on DNA methylation (epigenomics) and fragment size patterns (fragmentomics) in several types of biological fluids are yielding promising results as non-invasive biomarkers for effective cancer management. This review addresses the clinical applications of somatic gene variants in ctDNA, emphasizes their potential as cancer biomarkers, and highlights essential factors for successful implementation in clinical laboratories and cancer management.

PMID:40977813 | PMC:PMC12446922 | DOI:10.1515/almed-2025-0010

A statistical physics approach to integrating multi-omics data for disease-module detection

Cell Rep Methods. 2025 Sep 19:101183. doi: 10.1016/j.crmeth.2025.101183. Online ahead of print.

ABSTRACT

Genes associated with the same disease frequently engage in mutual biological interactions, e.g., perturbation within a specific neighborhood in the molecular interactome, often referred to as the disease module. This has propelled the advancement of network-based approaches toward elucidating the molecular bases of human diseases. Although many computational methods have been developed to integrate the molecular interactome and omics profiles to extract such context-dependent disease modules, approaches that leverage multi-omics for disease-module detection are still lacking. Here, we developed a statistical physics approach based on the random-field O(n) model (RFOnM) to fill this gap. We applied the RFOnM approach to integrate gene-expression data and genome-wide association studies or mRNA data and DNA methylation for several complex diseases with the human interactome. We found that the RFOnM approach outperforms existing single omics methods in most of the complex diseases considered in this study.

PMID:40975055 | DOI:10.1016/j.crmeth.2025.101183

Implementation of a Virtual Hospital in the Home Service for Patients With COVID-19 in Queensland, Australia: Mixed Methods Evaluation Using the RE-AIM Framework

Background: Hospital in the home (HITH) provides home-based care as an alternative to traditional hospitalization. In response to the COVID-19 Omicron wave, a public hospital in the rural Western portion of Southeast Queensland implemented a virtual HITH service to support adults, maternity patients, and children with moderate COVID-19 symptoms and additional health concerns. Although the pandemic accelerated the uptake of virtual care within HITH models, existing literature has focused on clinical outcomes, with limited evidence on key implementation outcomes. Objective: Using the RE-AIM (reach, effectiveness, adoption, implementation, and maintenance) framework, this study evaluated the implementation of the virtual COVID-19 HITH service and identified factors influencing its implementation, to inform ongoing service development and support potential scaling of this model of care. Methods: The RE-AIM implementation science framework was selected to guide the evaluation, capturing both clinical and contextual dimensions of implementation at both individual and organizational levels. Quantitative data on service usage and costs were retrospectively extracted from electronic medical records and finance records, while patient experience data were drawn from patient-reported experience measures surveys. Qualitative data were collected through one-on-one interviews with patients and staff. All data sources were analyzed separately and then triangulated within the RE-AIM framework to understand what occurred, how, and why. Results: The service admitted 3192 patients, most of whom were female (2027/3192, 63.5%), English-speaking (3140/3192, 98.4%), and residing in socioeconomically disadvantaged areas (1879/3192, 58.9%) (reach). The model was feasible and safe to implement, managing 3240 admissions with no reported deaths. Patients valued continuous access to care and described better recovery experiences at home (effectiveness). Staff viewed the model as appropriate for identifying and managing high-risk patients in the community, easing pressure on hospital beds (adoption). The service cost Aus $ 5.4 million (US $3.5 million) over 11 months. Implementation barriers included the urgency of the pandemic scenario, limited infrastructure and human resources, and changing requirements in relation to COVID-19. These were mitigated by several people factors that were critical to its successful implementation, including a consultant-led structure, staff commitment, and adaptability (implementation). The service saved 16,651 inpatient bed days before being integrated into core HITH operations. The experience strengthened staff capabilities in emergency response, virtual care delivery, and strategic planning. The model shows promise for broader application into pediatric care, though further work is needed to enhance interdepartmental collaboration and staff recognition (maintenance). Conclusions: This study demonstrated that a virtual HITH model can be implemented effectively and safely at scale. Findings support its potential for integration into routine care, provided that adequate resource planning, a skilled and multidisciplinary workforce, well-defined care pathways, and equity-focused strategies are in place.

Opinion: Four reasons why generative AI chatbots could lead to psychosis in vulnerable people

18 September 2025 at 16:30

Three scholars discovered a strange mirror deep in the forest. It spoke to them in a soothing voice and answered all their questions warmly, knowledgeably, and eloquently.

The captivated scholars became obsessed, whispering one secret after another to the mirror. It replied with affection, promise, and meaning that kept them returning to it. They began ignoring one another, each convinced the mirror “understood” them best.

Read the rest…

© Adobe

From frameworks to finance: how sharing benefits from the use of digital sequence information can evolve to contribute to biodiversity conservation

Nature Biotechnology, Published online: 18 September 2025; doi:10.1038/s41587-025-02820-8

The COP16 decision established a multilateral mechanism for digital sequence information (DSI) benefit-sharing. This Comment brings together insights from academia and commercial DSI researchers to assess what has been accomplished so far, identify remaining challenges and describe elements under discussion to support collective goals.

Diagnostic Performance of Computed Tomography–Based Artificial Intelligence for Early Recurrence of Cholangiocarcinoma: Systematic Review and Meta-Analysis

Background: Despite artificial intelligence (AI) models demonstrating high predictive accuracy for early cholangiocarcinoma recurrence, their clinical application faces challenges, such as reproducibility, generalizability, hidden biases, and uncertain performance across diverse datasets and populations, raising concerns about their practical applicability. Objective: This meta-analysis aims to systematically assess the diagnostic performance of AI models using computed tomography (CT) imaging to predict early recurrence of cholangiocarcinoma. Methods: A systematic search was conducted in PubMed, Embase, and Web of Science for studies published up to May 2025. Studies were selected based on the Participants, Index test, Target condition, Reference standard, Outcomes, and Setting (PITROS) framework. Participants included patients diagnosed with cholangiocarcinoma (including intrahepatic and extrahepatic locations). The index test was AI techniques applied to CT imaging for early recurrence prediction (defined as within 1 year), while the target condition was early recurrence of cholangiocarcinoma (positive group: recurrence; negative group: no recurrence). The reference standard was pathological diagnosis or imaging follow-up confirming recurrence. Outcomes included sensitivity, specificity, diagnostic odds ratio (DOR), and area under the receiver operating characteristic curve (AUC), assessed in both internal and external validation cohorts. The setting comprised retrospective or prospective studies using hospital datasets. Methodological quality was assessed using an optimized version of the revised Quality Assessment of Diagnostic Accuracy Studies-2 tool. Heterogeneity was assessed using the I² statistic. Pooled sensitivity, specificity, DOR, and AUC were calculated using a bivariate random-effects model. Results: A total of 9 studies with 30 datasets involving 1537 patients were included. In internal validation cohorts, CT-based AI models showed a pooled sensitivity of 0.87 (95% CI 0.81-0.92), specificity of 0.85 (95% CI 0.79-0.89), DOR of 37.71 (95% CI 18.35-77.51), and AUC of 0.93 (95% CI 0.90-0.94). In external validation cohorts, pooled sensitivity was 0.87 (95% CI 0.81-0.91), specificity was 0.82 (95% CI 0.77-0.86), DOR was 30.81 (95% CI 18.79-50.52), and AUC was 0.85 (95% CI 0.82-0.88). The AUC was significantly lower in external validation cohorts compared to internal validation cohorts (P<.001). Conclusions: Our results show that CT-based AI models predict early cholangiocarcinoma recurrence with high performance in internal validation sets and moderate performance in external validation sets. However, the high heterogeneity observed may impact the robustness of these results. Future research should focus on prospective studies and establishing standardized gold standards to further validate the clinical applicability and generalizability of AI models.

Large Language Models’ Clinical Decision-Making on When to Perform a Kidney Biopsy: Comparative Study

Background: Artificial intelligence (AI) and Large Language models (LLMs) are increasing in sophistication and are being integrated into many disciplines. The potential for LLMs to augment clinical decisions is an evolving area of research. Objective: This study compared the responses of over 1000 kidney specialist physicians (nephrologists) to outputs of commonly used LLMs using a questionnaire determining when a kidney biopsy should be performed. Methods: This research group completed a large online questionnaire for nephrologists to determine when a kidney biopsy should be performed. The questionnaire was co-designed with patient participation, refined through multiple iterations, then piloted locally before international dissemination. It was the largest international study in the field and demonstrated variation between human clinicians in biopsy propensity relating to human factors such as sex and age, as well as systemic factors such as country, job seniority and technical proficiency. The same questions were put to both human doctors and LLMs in an identical order in a single session. Eight commonly used LLMs were interrogated: Chat GPT 3.5, Mistral Hugging Face, Perplexity, Microsoft Co-pilot, Llama 2, GPT 4.0, MedLM and Claude 3. The most common response given by clinicians (human mode) to each question was taken as the baseline for comparison. Questionnaire responses to the indications and contraindications for biopsy generated a score (0-44) reflecting biopsy propensity, in which a higher score was used as a surrogate marker for an increased tolerance of potential associated risks. Results: The ability of LLMs to reproduce human expert consensus varied widely with some models demonstrating a balanced approach to risk in a similar manner to humans, whilst other models reported outputs at either end of the spectrum for risk tolerance. In terms of agreement with the human mode, Chat GPT 3.5 and GPT 4.0 (Open AI) had the highest levels of alignment, with the human mode selected in 6/11 questions. The total biopsy propensity score generated from the human mode was 23/44. Both Open AI models produced similar propensity scores between 22 and 24, however Llama 2 and MS Co-pilot also reported scores within this range, but with poorer response alignment to the human mode at only 2/11 questions. The most risk averse model in this study was MedLM with a propensity score of 11 and the least risk averse model was Claude 3 with a score of 34. Conclusions: LLM outputs demonstrated a modest ability to replicate human clinical decision making in this study, however the performance varied widely between LLM models. Questions with more uniform human responses produced LLM outputs with greater alignment, whereas in questions with low levels of human consensus there was poor output alignment. This may limit the practical use of LLMs in real world clinical practice.
❌