❌

Normal view

Received — 5 March 2026 ⏭ Favourites

Mental Health Professionals’ Perceptions of Benefits and Disadvantages of Telehealth: International Mixed Methods Study

✇Journal of Medical Internet Research
By: Madeline I Montoya · Cary S Kogan · Brigitte Khoury · José A García-Pacheco · Rebeca Robles · Tahilia J Rebello · Maya Kulygina · Geoffrey M Reed
5 March 2026 at 06:00
Background: Telehealth has become an integral component of mental health care delivery worldwide. Understanding provider perceptions is essential to guiding its continued implementation. Objective: This international study used quantitative and qualitative methodologies to examine and broaden our understanding of the benefits and concerns related to telehealth for mental health care. Methods: An internet-based survey was conducted during the COVID-19 pandemic between November 11 and December 18, 2020, among mental health professionals, primarily psychiatrists and psychologists, registered with the World Health Organization’s Global Clinical Practice Network. Clinicians completed the survey in 1 of 6 languages (Chinese, English, French, Japanese, Russian, or Spanish). Descriptive statistics and logistic regressions were used to analyze quantitative survey data on concerns and implementation of telehealth. Responses to an open-ended question about providers’ perspectives on the benefits of telehealth were analyzed qualitatively. Results: In total, 847 participants completed the telehealth section of the survey, and 496 provided a response to the open-ended question. Quantitative data on telehealth use and concerns revealed that clinicians’ primary concerns focused on technical issues and clinical effectiveness relative to in-person services, specifically, loss of clinical information (eg, nonverbal behavior) and challenges with establishing a therapeutic alliance. Findings varied by profession, World Health Organization region, and telehealth training and experience. Qualitative data examining benefits fell into 3 major areas: accessibility and reach of mental health services, efficiency and flexibility for clinicians, and enhancement of clinical processes and outcomes. Taken together, findings revealed a trade-off between telehealth benefits and disadvantages. Conclusions: From the perspective of mental health professionals, telehealth practice comes with key challenges and valuable benefits. Findings offer important considerations for the implementation of telehealth systems, including the importance of training and education and balancing trade-offs to optimize care.

Artificial Intelligence Applications in Medical Devices for Personalized Health Care Solutions: Systematic Review

✇Journal of Medical Internet Research
By: Hemanth Ponnambalath Mohanadas · A Manikandan · Ahmad Fauzi Ismail · Nick Tucker · Saravana Kumar Jaganathan
5 March 2026 at 04:15
Background: The integration of artificial intelligence (AI) in medical devices is transforming health care by enabling enhanced personalization and precision medicine. AI-driven medical devices can tailor treatments based on individual patient profiles, including genetic data, medical history, and physiological parameters. This advancement holds the potential to refine therapeutic interventions, improve patient outcomes, and streamline health care delivery. However, challenges such as data quality, algorithmic bias, patient privacy, and regulatory complexities hinder the full realization of AI-driven personalization. By 2030, the global AI in health care market is projected to exceed US $187.95 billion, growing at a compound annual growth rate of 37% from US $15.1 billion in 2022. Objective: This review aims to explore the scope and impact of AI-driven personalization in medical devices. It seeks to analyze key technological innovations that have enabled AI integration, identify the critical challenges impeding progress, and evaluate strategies to address these challenges. Additionally, it highlights future research directions and innovation opportunities in this evolving field. Methods: A systematic review was conducted, drawing from scholarly literature, industry analyses, and regulatory advisories. Relevant studies and case examples were analyzed to assess the current applications of AI in medical devices, the barriers to its implementation, and best practices for overcoming these barriers. Ethical, technical, and regulatory considerations were also examined. The review included studies published between 2016 and 2023, covering over 100 peer-reviewed articles and reports. Results: The review highlights significant advancements in AI-driven medical devices, including applications in diagnostics, treatment personalization, wearable health monitoring, and smart prosthetics. AI-based diagnostic tools have achieved up to 98.88% accuracy in multiclass disease classification from X-ray images and 95% accuracy in insulin injection site recognition. It identifies key challenges such as data security risks, algorithmic biases, regulatory constraints, and integration issues with existing health care infrastructures. Currently, more than 70% of clinical decisions rely on diagnostic tests, yet AI-driven automation could reduce diagnostic delays by up to 50%. Several strategies, including improved data validation techniques, regulatory frameworks for AI approval, and ethical guidelines, were found to be effective in mitigating these challenges. Case studies demonstrate how AI has enhanced medical device functionality and patient outcomes. Conclusions: AI-driven personalization in medical devices holds immense potential to revolutionize health care, offering more precise, adaptive, and patient-centered solutions. However, successful implementation requires addressing technical, ethical, and regulatory challenges. Emerging technologies such as quantum computing could improve AI-driven medical diagnoses by 10‐20 times in processing efficiency, while blockchain-based patient data management could reduce security breaches by more than 30%. This review serves as a valuable resource for researchers, health care professionals, policymakers, and industry leaders, fostering informed discussions and guiding future advancements in AI-enabled personalized medicine.

Architecting Trust in Artificial Epistemic Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Nahema Marchal · Stephanie Chan · Matija Franklin · Manon Revel · Geoff Keeling · Roberta Fischli · Bilva Chandra · Iason Gabriel
4 March 2026 at 13:00
arXiv:2603.02960v1 Announce Type: new Abstract: Large language models increasingly function as epistemic agents -- entities that can 1) autonomously pursue epistemic goals and 2) actively shape our shared knowledge environment. They curate the information we receive, often supplanting traditional search-based methods, and are frequently used to generate both personal and deeply specialized advice. How they perform these functions, including whether they are reliable and properly calibrated to both individual and collective epistemic norms, is therefore highly consequential for the choices we make. We argue that the potential impact of epistemic AI agents on practices of knowledge creation, curation and synthesis, particularly in the context of complex multi-agent interactions, creates new informational interdependencies that necessitate a fundamental shift in evaluation and governance of AI. While a well-calibrated ecosystem could augment human judgment and collective decision-making, poorly aligned agents risk causing cognitive deskilling and epistemic drift, making the calibration of these models to human norms a high-stakes necessity. To ensure a beneficial human-AI knowledge ecosystem, we propose a framework centered on building and cultivating the trustworthiness of epistemic AI agents; aligning AI these agents with human epistemic goals; and reinforcing the surrounding socio-epistemic infrastructure. In this context, trustworthy AI agents must demonstrate epistemic competence, robust falsifiability, and epistemically virtuous behaviors, supported by technical provenance systems and "knowledge sanctuaries" designed to protect human resilience. This normative roadmap provides a path toward ensuring that future AI systems act as reliable partners in a robust and inclusive knowledge ecosystem.

The Transformative Potential of Liquid Biopsies and Circulating Tumor DNA (ctDNA) in Modern Oncology

✇MRD
By: Keren Rouvinov · Rashad Naamneh · Alexander Yakobson · Wenad Najjar · Mahmoud Abu Amna · Arina Soklakova · Ez El Din Abu Zeid · Ronen Brenner · Mohnnad Asla · Fahmi Abu Ghalion · Ali Abu Juma'a · Amichay Meirovitz · Walid Shalata
27 February 2026 at 19:00

Diagnostics (Basel). 2026 Feb 9;16(4):523. doi: 10.3390/diagnostics16040523.

ABSTRACT

Background: Liquid biopsy, particularly through the analysis of circulating tumor DNA (ctDNA), represents a significant advancement in oncology. Unlike traditional tissue biopsies, ctDNA offers a minimally invasive, real-time approach to cancer management. It has demonstrated considerable potential in early cancer detection, monitoring of therapeutic responses, and assessing minimal residual disease (MRD) to predict recurrence. By enabling comprehensive molecular profiling through a simple blood test, ctDNA supports the core principles of precision oncology, facilitating more personalized and adaptive treatment strategies. Methods: In the following article we describe the recent developments focused on refining ctDNA detection assays to improve sensitivity and specificity. Advanced technologies, including next-generation sequencing (NGS) and digital PCR, are commonly employed. The integration of artificial intelligence (AI) and multi-omics approaches-such as combining genomic, epigenomic, and transcriptomic data-has further enhanced the analytical power of ctDNA assays. Results: Emerging evidence shows that ctDNA-based liquid biopsy enables dynamic, real-time tracking of tumor evolution and therapeutic resistance. Clinical studies have demonstrated its efficacy in detecting early-stage cancers, guiding treatment selection, and predicting relapse with higher accuracy than some conventional methods. Moreover, AI-enhanced algorithms have improved signal detection, allowing for more precise and earlier identification of actionable mutations and MRD. Conclusions: ctDNA analysis via liquid biopsy is poised to revolutionize cancer care by offering a non-invasive, precise, and adaptive tool for tumor characterization and monitoring. Although obstacles remain-particularly regarding assay sensitivity, standardization, and economic feasibility-ongoing technological innovations and multi-omics integration are rapidly advancing its clinical viability. With continued progress, ctDNA-based liquid biopsy is likely to become a cornerstone of routine oncology practice.

PMID:41750672 | PMC:PMC12938931 | DOI:10.3390/diagnostics16040523

3D, multi-omic imaging reveals molecular biomarkers of the pre-metastatic niche in lung cancer

✇Omics In Lung
By: John Michel · André Forjaz · Vasco Queiroga · Kelly Casella · Kaitlin Stivers · Helen Nguyen · Maria Browne · Feiyu Chen · Ada Tam · Omkar Dhaygude · Hongni Fan · Hitoaki Maehira · Cheng Ting Lin · Elise Gray-Gaillard · Talia L Benducci · Suguru Yamauchi · Ife Shoyombo · Ziying Xu · Eugene Shenderov · Peng Huang · Denis Wirtz · Jennifer H Elisseeff · Yun Chen · Malcolm V Brock · Ashley L Kiemen · Franck Housseau
27 February 2026 at 19:00

bioRxiv [Preprint]. 2026 Feb 18:2026.02.18.706515. doi: 10.64898/2026.02.18.706515.

ABSTRACT

The recurrence rate following complete surgical resection of primary non-small cell lung cancer is as high as 55%, yet no approach currently exists to evaluate the risk of local recurrence. The premetastatic paradigm is the recognition that metastasis is preceded by reprogramming naïve tissues to prime a microenvironment for tumor cell survival and subsequent reactivation. Identification of biomarkers of the pre-metastatic niche would allow us to evaluate a patient's risk of local relapse in the normal lung parenchyma surrounding the resected tumor. We designed a workflow incorporating in vivo modelling, radiology, and deep learning-guided three-dimensional (3D) imaging, spatial proteomics, and transcriptomics to identify previously unreported signals associated with the early transformation of the lung parenchyma announcing regional metastasis. We curated biorepository spanning timepoints before and after resection of primary Lewis Lung Carcinoma (LLC) tumors. Using radiology and cellular resolution 3D histology, we calculated the number and distribution of metastases in mouse lungs and developed an algorithm to guide placement of spatial proteomics and transcriptomics to regions containing early micro-metastases and the pre-metastatic microenvironment. Molecular and tissue features associated with presence, size, and location of metastases guided the identification of both myeloid (F4/80) and senescent (p16/p21) cell signatures in the premetastatic and metastatic environments. Finally, multiparametric flow cytometry of metastatic lungs in a senescence reporter GEMM (tdTomato-p16 INKA mice) resolved senescent cells including alveolar macrophages as the cellular phenotypes associated with these early premetastatic signatures. Altogether, this work highlights a novel AI-assisted approach for detection of biomarkers of tissue remodeling during lung cancer invasion.

PMID:41756853 | PMC:PMC12934922 | DOI:10.64898/2026.02.18.706515

Exploration of multi-omics liquid biopsy approaches for multi-cancer early detection: The PROMISE study

✇(Multiomics OR Omics) AND (Pancreatic)
By: Jianchun Duan · Qiang Gao · Zhijie Wang · Jiachen Xu · Yuzi Zhang · Yanan Wang · Xi Yang · Lei Zhang · Yu Xu · Qiaoxia Zhou · Bo Yang · Xingyu Yang · Guoqiang Wang · Jing Zhao · Xuefei Wang · Di Ge · Lijie Tan · Wenju Chang · Jianmin Xu · Pinghong Zhou · Mengjiang He · Yuanlin Song · Jie Hu · Wenhui Lou · Wenchuan Wu · Tingyan Shi · Rongyu Zang · Yuan Ji · Sunfang Jiang · Youpei Lin · Liangqing Dong · Shangli Cai · Jia Fan · Jie Wang
25 February 2026 at 19:00

Innovation (Camb). 2025 Aug 6;7(1):101076. doi: 10.1016/j.xinn.2025.101076. eCollection 2026 Jan 5.

ABSTRACT

Although circulating cell-free DNA (cfDNA) methylation has emerged as the mainstream approach in multi-cancer detection blood tests (MCDBTs), the potential of integrating proteins and mutations, to enhance its performance remains unclear. The PROMISE study (NCT04972201) was conducted to investigate the feasibility of a multi-omics integration strategy in MCDBTs across nine types of cancers in head and neck (excluding nasopharynx), esophagus, lung, stomach, liver, biliary tract, pancreas, colorectum, and ovary. Blood samples were prospectively collected from 1,706 participants (840 non-cancer; 866 cancer) and then randomly divided into training and validation sets. The complementarity between various omics were investigated, and specific omics features were carefully selected for further multimodal model construction. The methylation-based classifier outperformed both the mutation-based and protein-based classifiers. As 95.0% of cancer cases detected by the mutation-based classifier were simultaneously identified by the methylation-based classifier, while 14.0% of the protein-positive samples were missed, protein markers may provide complementary value to the methylation-based classifier. Compared with the methylation-based classifier, the multimodal classifier combining methylation and protein features exhibited an improved sensitivity of 75.1% (95% confidence interval [CI], 69.3%-80.3%) at the same specificity of 98.8% with the accuracy of top predicted origin (TPO1) of 73.1% (95% CI, 66.2%-79.2%). Notably, the TPO1 accuracy reached 100% in liver and ovarian cancers with negative results of the methylation-based classifier. Collectively, these data suggest that the integration of protein markers in the multimodal classifier can offer additional benefits to the methylation-based classifier, particularly in identifying liver and ovarian cancers.

PMID:41737326 | PMC:PMC12925926 | DOI:10.1016/j.xinn.2025.101076

Received — 25 February 2026 ⏭ Favourites

Metabolic dysregulation: Its role in diabetes mellitus and cancers

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Shuang Dai · Jiacheng Li · Jing Xia · Yingtong Liu · Yan Li
24 February 2026 at 19:00

Mol Aspects Med. 2026 Feb 23;108:101461. doi: 10.1016/j.mam.2026.101461. Online ahead of print.

ABSTRACT

Diabetes mellitus (DM) is a significant risk factor for several cancers, particularly cancers of the liver, pancreas, and endometrium. This review aims to understand the connections between diabetic pathophysiology and cancer biology. We synthesize how core metabolic disturbances-hyperinsulinemia, hyperglycemia, and inflammation-promote tumorigenesis by dysregulating canonical oncogenic pathways such as IGF-1 signaling, DNA damage repair, and immunometabolism. Subsequently, we focus on how key molecular integrators-such as p38 MAPK, Wnt/β-catenin, and the AGEs-RAGE axis-mediate metabolic stress to confer proliferative and invasive advantages to tumor cells. However, a direct translational application of these mechanisms, particularly in the context of repurposing antidiabetic drugs for cancer therapy, remains challenging due to inconsistent clinical outcomes. To address this gap, we suggest that a fundamental shift in approach is required. We propose that future research must move beyond simple pathway categorization and instead utilize spatial analysis techniques to reveal how diabetic metabolites reshape the tumor microenvironment (TME). By integrating single-cell and spatial omics technologies, the field can begin to map the precise cellular niches within tumors where diabetic metabolites exacerbate malignant progression and foster treatment resistance. This perspective is essential for developing targeted strategies to mitigate cancer risk and improve outcomes for the expanding population of patients with DM and cancer.

PMID:41734405 | DOI:10.1016/j.mam.2026.101461

AI and Wearables for Early Detection of Cognitive Impairment and Dementia: Systematic Review

✇Journal of Medical Internet Research
By: Ander Cejudo · Markel Arrojo · Cristina Martín · Aitor Almeida
24 February 2026 at 03:00
Background: Traditional cognitive screening relies on episodic clinical assessments and may miss early changes preceding cognitive impairment and dementia. Wearable and mobile health technologies enable continuous monitoring of sleep, physical activity, and circadian rhythms, generating digital biomarkers that may support scalable early detection and prevention. However, current evidence remains fragmented across devices, analytic approaches, and cognitive outcomes. Objective: This study synthesizes and critically evaluates recent evidence on wearable devices for early detection and prevention of cognitive impairment and dementia, focusing on device categories, cognitive outcomes, analytic approaches, and prevention relevance. Methods: We searched PubMed, Scopus, ACM Digital Library, and SpringerLink for peer-reviewed studies published between January 2020 and December 1, 2025. Eligible studies included human participants with a mean age ≥50 years, continuous wearable-derived data collected for ≥24 hours, and validated cognitive outcomes; reviews, protocols, smartphone-only studies, and pharmacological interventions were excluded. Two reviewers independently screened studies, extracted data, and assessed risk of bias using the Appraisal Tool for Cross-Sectional Studies, Newcastle-Ottawa Scale, Cochrane Risk of Bias tool, and Quality Assessment of Diagnostic Accuracy Studies-2. Owing to substantial heterogeneity in devices, outcomes, and analytic methods, quantitative meta-analysis was not feasible; a structured narrative synthesis was conducted in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidance. This study was not prospectively registered. Results: We included 49 studies, with sample sizes ranging from 14 to 91,948 participants (>200,000 total) and a median sample size of 145. Most used research-grade actigraphy (43/49, 87.8%), while fewer used commercial wearables (7/49, 14.3%). Cognitive outcomes most frequently relied on global screening instruments, including the Mini-Mental State Examination (18/49, 36.7%), followed by ICD-10 (International Statistical Classification of Diseases, Tenth Revision)–based clinical diagnoses (7/49, 14.3%) and the Montreal Cognitive Assessment (7/49, 14.3%). Analytic approaches were predominantly statistical (36/49, 73.5%), with fewer studies applying machine learning (7/49, 14.3%) or deep learning methods (6/49, 12.2%). Statistical analyses linked disrupted sleep, circadian rhythm fragmentation, and irregular activity patterns to worse cognitive outcomes, with modest-to-moderate effect sizes. Machine learning and deep learning approaches reported classification performance with area under the curve values between approximately 0.70 and 0.95. Approximately one-quarter of the studies (13/49, 26.5%) addressed early detection or prevention through longitudinal risk estimation or predictive modeling. Key limitations included small sample sizes, short monitoring durations, and limited external validation. Conclusions: Wearable-derived behavioral markers show promise for early risk stratification. This review advances the field by shifting from descriptive associations toward a digital phenotyping framework evaluating artificial intelligence–driven prediction in the preclinical window. Unlike prior reviews focused on established dementia, it differentiates direct predictive evidence from indirect correlational findings and critically assesses methodological maturity. Continuous, passive monitoring may enable scalable detection of subtle behavioral changes, supporting earlier and more personalized risk reduction strategies. Trial Registration:
Received — 23 February 2026 ⏭ Favourites

Evolving roles of liquid biopsy in precision medicine for colorectal cancer: from single-gene analysis to broad genomic profiling

✇MRD
By: Giulia Martini · Stefania Napolitano · Davide Ciardiello · Luca Boscolo Bielo · Erika Martinelli · Teresa Troiani · Maria Giulia Zampino · Nicola Fazio · Giuseppe Curigliano · Fortunato Ciardiello
20 February 2026 at 19:00

Nat Rev Clin Oncol. 2026 Feb 20. doi: 10.1038/s41571-026-01126-1. Online ahead of print.

ABSTRACT

Colorectal cancer (CRC) is a heterogeneous malignancy, with various alterations in molecular signalling pathways driving disease progression and resistance to therapy. Liquid biopsy, as a source of circulating tumour DNA (ctDNA), has been utilized to characterize tumour molecular heterogeneity, facilitating the identification of actionable targets for precision medicine-guided therapies and the detection of emerging genomic drivers of drug resistance in patients with metastatic CRC. In addition, liquid biopsy-based analysis of ctDNA has been validated as a tool for detecting minimal residual disease (MRD) following locoregional treatment in patients with localized colon or rectal cancer, offering improved prognostic stratification and supporting the tailoring of adjuvant systemic therapy. Methodological evolution from PCR analysis of a few known mutations in one gene or a small panel of genes to the assessment of hundreds of genes and pathogenic variants by next-generation sequencing has enabled comprehensive genomic profiling (CGP), thereby improving knowledge of cancer molecular complexity at the individual patient level. In this respect, liquid biopsy-based CGP is an easily repeatable and minimally invasive approach that can provide a dynamic portrait of CRC molecular heterogeneity to guide personalized and adaptive treatment based on biomarkers of response and resistance. In this Review, we discuss current and potential roles of liquid biopsy-based ctDNA analysis in the clinical management of metastatic CRC. We also discuss the evidence supporting implementation of liquid biopsy-based assessment of MRD to refine the management of locoregional CRC and potentially improve cure rates while reducing overtreatment of many patients.

PMID:41720942 | DOI:10.1038/s41571-026-01126-1

Received — 21 February 2026 ⏭ Favourites
  • ✇STAT
  • STAT+: Nature Medicine to investigate study that found cancer treatment is better in morning Angus Chen
    The notion that oncologists could boost immunotherapy responses simply by giving infusions in the morning, rather than late afternoon, is an attractive one. So when a clinical trial published in Nature Medicine this month showed that lung cancer patients treated in the morning had a massive reduction in the risk of progression compared to those treated in the afternoon, many scientists were intrigued, if skeptical. Now that study is coming under fire, as multiple scientists and sleuths raise
     
  • 🏷️
  • ↗️

STAT+: Nature Medicine to investigate study that found cancer treatment is better in morning

✇STAT
By: Angus Chen
21 February 2026 at 09:13

The notion that oncologists could boost immunotherapy responses simply by giving infusions in the morning, rather than late afternoon, is an attractive one. So when a clinical trial published in Nature Medicine this month showed that lung cancer patients treated in the morning had a massive reduction in the risk of progression compared to those treated in the afternoon, many scientists were intrigued, if skeptical.

Now that study is coming under fire, as multiple scientists and sleuths raise serious concerns about the data and point out inconsistencies in the trial.

These have called the study’s conclusions even further into question, which experts told STAT already lacked strong biological plausibility, and Nature Medicine appended a note on the study on Thursday that it is starting an investigation into the concerns.

Continue to STAT+ to read the full story…

© Jenny Kane/AP

Gastric cancer occurrence and heterogeneity: integration of clinical data, multi-omics and tumor microenvironment

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Ping Li · Yafang Huang · Wanting Jiang · Haocheng Zheng · Runhua Chen · Xia Ding
20 February 2026 at 19:00

Future Oncol. 2026 Feb 20:1-14. doi: 10.1080/14796694.2026.2631302. Online ahead of print.

ABSTRACT

Gastric cancer (GC) is an epithelial malignant tumor with high morbidity and mortality. In recent years, more and more studies have strengthened our understanding of how GC develops, including the origin of GC cells, precancerous lesions, gene mutations, transcriptional changes, protein translation and the tumor microenvironment. With the concept of accurate tumor therapy gradually applied to clinical practice, these data provide more reference and basis for early prevention, early screening, early detection and accurate treatment of GC.

PMID:41717787 | DOI:10.1080/14796694.2026.2631302

MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hui Min Wong · Philip Heesen · Pascal Janetzky · Martin Bendszus · Stefan Feuerriegel
20 February 2026 at 13:00
arXiv:2602.17308v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for diagnostic tasks in medicine. In clinical practice, the correct diagnosis can rarely be immediately inferred from the initial patient presentation alone. Rather, reaching a diagnosis often involves systematic history taking, during which clinicians reason over multiple potential conditions through iterative questioning to resolve uncertainty. This process requires considering differential diagnoses and actively excluding emergencies that demand immediate intervention. Yet, the ability of medical LLMs to generate informative follow-up questions and thus reason over differential diagnoses remains underexplored. Here, we introduce MedClarify, an AI agent for information-seeking that can generate follow-up questions for iterative reasoning to support diagnostic decision-making. Specifically, MedClarify computes a list of candidate diagnoses analogous to a differential diagnosis, and then proactively generates follow-up questions aimed at reducing diagnostic uncertainty. By selecting the question with the highest expected information gain, MedClarify enables targeted, uncertainty-aware reasoning to improve diagnostic performance. In our experiments, we first demonstrate the limitations of current LLMs in medical reasoning, which often yield multiple, similarly likely diagnoses, especially when patient cases are incomplete or relevant information for diagnosis is missing. We then show that our information-theoretic reasoning approach can generate effective follow-up questioning and thereby reduces diagnostic errors by ~27 percentage points (p.p.) compared to a standard single-shot LLM baseline. Altogether, MedClarify offers a path to improve medical LLMs through agentic information-seeking and to thus promote effective dialogues with medical LLMs that reflect the iterative and uncertain nature of real-world clinical reasoning.
  • ✇cs.AI, q-bio.NC updates on arXiv.org
  • Intent Laundering: AI Safety Datasets Are Not What They Seem Shahriar Golchin · Marc Wetter
    arXiv:2602.16729v1 Announce Type: cross Abstract: We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice. In isolation, we examine how well these datasets reflect real-world attacks based on three key properties: driven by ulterior intent, well-crafted, and out-of-distribution. We find that these datasets overrely on "triggering cues": words or phrases with overt negative/sensitive connotations that are intended to trigger sa
     
  • 🏷️
  • ↗️

Intent Laundering: AI Safety Datasets Are Not What They Seem

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shahriar Golchin · Marc Wetter
20 February 2026 at 13:00
arXiv:2602.16729v1 Announce Type: cross Abstract: We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice. In isolation, we examine how well these datasets reflect real-world attacks based on three key properties: driven by ulterior intent, well-crafted, and out-of-distribution. We find that these datasets overrely on "triggering cues": words or phrases with overt negative/sensitive connotations that are intended to trigger safety mechanisms explicitly, which is unrealistic compared to real-world attacks. In practice, we evaluate whether these datasets genuinely measure safety risks or merely provoke refusals through triggering cues. To explore this, we introduce "intent laundering": a procedure that abstracts away triggering cues from attacks (data points) while strictly preserving their malicious intent and all relevant details. Our results indicate that current AI safety datasets fail to faithfully represent real-world attacks due to their overreliance on triggering cues. In fact, once these cues are removed, all previously evaluated "reasonably safe" models become unsafe, including Gemini 3 Pro and Claude Sonnet 3.7. Moreover, when intent laundering is adapted as a jailbreaking technique, it consistently achieves high attack success rates, ranging from 90% to over 98%, under fully black-box access. Overall, our findings expose a significant disconnect between how model safety is evaluated and how real-world adversaries behave.

Be Wary of Your Time Series Preprocessing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sofiane Ennadir · Tianze Wang · Oleg Smirnov · Sahar Asadi · Lele Cao
20 February 2026 at 13:00
arXiv:2602.17568v1 Announce Type: cross Abstract: Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspective. In this work, we present the first formal analysis of how different normalization strategies, specifically instance-based and global scaling, impact the expressivity of Transformer-based architectures for time series representation learning. We propose a novel expressivity framework tailored to time series, which quantifies a model's ability to distinguish between similar and dissimilar inputs in the representation space. Using this framework, we derive theoretical bounds for two widely used normalization methods: Standard and Min-Max scaling. Our analysis reveals that the choice of normalization strategy can significantly influence the model's representational capacity, depending on the task and data characteristics. We complement our theory with empirical validation on classification and forecasting benchmarks using multiple Transformer-based models. Our results show that no single normalization method consistently outperforms others, and in some cases, omitting normalization entirely leads to superior performance. These findings highlight the critical role of preprocessing in time series learning and motivate the need for more principled normalization strategies tailored to specific tasks and datasets.
  • ✇STAT
  • STAT+: Key study of Grail’s cancer detection test fails in setback for company Matthew Herper and Angus Chen
    A blood test for detecting cancer early being developed by the diagnostics firm Grail failed to meet its main goal in a giant study being conducted with England’s National Health Service, the company said Thursday. Grail’s test has been the standard bearer for new technologies that promise a blood test can be used to detect many different types of cancer early and eventually even to indicate to scientists where in the body to look for tumors. The company already sells its test, called Galleri
     
  • 🏷️
  • ↗️

STAT+: Key study of Grail’s cancer detection test fails in setback for company

✇STAT
By: Matthew Herper and Angus Chen
20 February 2026 at 06:38

A blood test for detecting cancer early being developed by the diagnostics firm Grail failed to meet its main goal in a giant study being conducted with England’s National Health Service, the company said Thursday.

Grail’s test has been the standard bearer for new technologies that promise a blood test can be used to detect many different types of cancer early and eventually even to indicate to scientists where in the body to look for tumors. The company already sells its test, called Galleri, for a list price of $1,000, although it is not yet approved by the Food and Drug Administration. Grail said Thursday it sold 185,000 tests in 2025, generating $136.8 million. 

The company’s shares were down 47% in after-hours trading.

Continue to STAT+ to read the full story…

© Adobe

❌