❌

Reading view

↗️

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
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.
  •  
  • ↗️
↗️

Reliability of LLMs as medical assistants for the general public: a randomized preregistered study

✇Nature Medicine
By: Andrew M. Bean · Rebecca Elizabeth Payne · Guy Parsons · Hannah Rose Kirk · Juan Ciro · Rafael Mosquera-Gómez · Sara Hincapié M · Aruna S. Ekanayaka · Lionel Tarassenko · Luc Rocher · Adam Mahdi

Nature Medicine, Published online: 09 February 2026; doi:10.1038/s41591-025-04074-y

In a randomized controlled study involving 1,298 participants from a general sample, performance of humans when assisted by a large language model (LLM) was sensibly inferior to that of the LLM alone when assessing ten medical scenarios leading to disease identification and recommendations for treatment.
  •  
  • ↗️
↗️

The Limits of AI Data Transparency Policy: Three Disclosure Fallacies

✇cs.AI, q-bio.NC updates on arXiv.org
By: Judy Hanwen Shen · Ken Liu · Angelina Wang · Sarah H. Cen · Andy K. Zhang · Caroline Meinhardt · Daniel Zhang · Kevin Klyman · Rishi Bommasani · Daniel E. Ho
arXiv:2601.18127v1 Announce Type: cross Abstract: Data transparency has emerged as a rallying cry for addressing concerns about AI: data quality, privacy, and copyright chief among them. Yet while these calls are crucial for accountability, current transparency policies often fall short of their intended aims. Similar to nutrition facts for food, policies aimed at nutrition facts for AI currently suffer from a limited consideration of research on effective disclosures. We offer an institutional perspective and identify three common fallacies in policy implementations of data disclosures for AI. First, many data transparency proposals exhibit a specification gap between the stated goals of data transparency and the actual disclosures necessary to achieve such goals. Second, reform attempts exhibit an enforcement gap between required disclosures on paper and enforcement to ensure compliance in fact. Third, policy proposals manifest an impact gap between disclosed information and meaningful changes in developer practices and public understanding. Informed by the social science on transparency, our analysis identifies affirmative paths for transparency that are effective rather than merely symbolic.
  •  
  • ↗️
↗️

Pretrain Value, Not Reward: Decoupled Value Policy Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chenghua Huang · Lu Wang · Fangkai Yang · Pu Zhao · Zhixu Li · Qingwei Lin · Dongmei Zhang · Saravan Rajmohan · Qi Zhang
arXiv:2502.16944v2 Announce Type: replace-cross Abstract: In this paper, we explore how directly pretraining a value model simplifies and stabilizes reinforcement learning from human feedback (RLHF). In reinforcement learning, value estimation is the key to policy optimization, distinct from reward supervision. The value function predicts the \emph{return-to-go} of a partial answer, that is, how promising the partial answer is if it were continued to completion. In RLHF, however, the standard pipeline first pretrains a reward model and then learns a value function online, even though no new reward signals are available once preference data is collected. This makes critic learning redundant, as the process of training a reward model and then deriving a value model is informationally equivalent to directly pretraining a value model. Importantly, this requires no additional supervision, and our value model is trained on exactly the same data used for reward modeling. Building on this insight, we introduce \emph{Decoupled Value Policy Optimization} (DVPO), a framework that pretrains a \emph{Global Value Model} (GVM) offline and freezes it as a universal critic for policy learning. The GVM provides stable, fine-grained credit assignment without critic drift or trajectory sampling. Experiments across MT-Bench, Alpaca-Eval, and Arena-Hard demonstrate that DVPO matches or surpasses state-of-the-art RLHF methods. These results highlight RLHF can be reframed as policy-only optimization guided by a single pretrained value model.
  •  
  • ↗️
↗️

Medication counseling with large language models: balancing flexibility and rigidity

✇cs.AI, q-bio.NC updates on arXiv.org
By: Joar Sabel, Mattias Wingren, Andreas Lundell, S\"oren Andersson, Sara Rosenberg, Susanne H\"agglund, Linda Estman, Malin Andtfolk
arXiv:2601.11544v1 Announce Type: cross Abstract: The introduction of large language models (LLMs) has greatly enhanced the capabilities of software agents. Instead of relying on rule-based interactions, agents can now interact in flexible ways akin to humans. However, this flexibility quickly becomes a problem in fields where errors can be disastrous, such as in a pharmacy context, but the opposite also holds true; a system that is too inflexible will also lead to errors, as it can become too rigid to handle situations that are not accounted for. Work using LLMs in a pharmacy context have adopted a wide scope, accounting for many different medications in brief interactions -- our strategy is the opposite: focus on a more narrow and long task. This not only enables a greater understanding of the task at hand, but also provides insight into what challenges are present in an interaction of longer nature. The main challenge, however, remains the same for a narrow and wide system: it needs to strike a balance between adherence to conversational requirements and flexibility. In an effort to strike such a balance, we present a prototype system meant to provide medication counseling while juggling these two extremes. We also cover our design in constructing such a system, with a focus on methods aiming to fulfill conversation requirements, reduce hallucinations and promote high-quality responses. The methods used have the potential to increase the determinism of the system, while simultaneously not removing the dynamic conversational abilities granted by the usage of LLMs. However, a great deal of work remains ahead, and the development of this kind of system needs to involve continuous testing and a human-in-the-loop. It should also be evaluated outside of commonly used benchmarks for LLMs, as these do not adequately capture the complexities of this kind of conversational system.
  •  
  • ↗️
↗️

Contaminating plasmid sequences and disrupted vector genomes in the liver following adeno-associated virus gene therapy

✇Nature Medicine
By: Sarah Buddle · Li-An K. Brown · Sofia Morfopoulou · Oscar Enrique Torres Montaguth · Mariacristina Scoto · Vanessa Herder · Anil Dhawan · Julianne R. Brown · Laura Atkinson · Angelika Kopec · Dee Davis · Nathaniel Storey · Luis Campos · Neil Sebire · Hannah Macpherson · Jasmaine Lee · Richard Orton · Giovanni Baranello · Patawee Asamaphan · Georgios Ilia · Rajvinder Karda · Holly Belfield · Malcolm Gracie Semple · J. Kenneth Baillie · John Counsell · Simon N. Waddington · Emma C. Thomson · Francesco Muntoni · Judith Breuer

Nature Medicine, Published online: 16 January 2026; doi:10.1038/s41591-025-04073-z

Analyses of liver biopsies from a child with spinal muscular atrophy treated with adeno-associated virus gene therapy who developed hepatitis reveal contaminating manufacturing plasmids and disrupted vector genomes, possibly resulting from recombination events.
  •  
  • ↗️
↗️

MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers

✇cs.AI, q-bio.NC updates on arXiv.org
By: Arash Ahmadi · Sarah Sharif · Yaser M. Banad
arXiv:2504.08999v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly augmented with external tools through standardized interfaces like the Model Context Protocol (MCP). However, current MCP implementations face critical limitations: they typically require local process execution through STDIO transports, making them impractical for resource-constrained environments like mobile devices, web browsers, and edge computing. We present MCP Bridge, a lightweight RESTful proxy that connects to multiple MCP servers and exposes their capabilities through a unified API. Unlike existing solutions, MCP Bridge is fully LLM-agnostic, supporting any backend regardless of vendor. The system implements a risk-based execution model with three security levels-standard execution, confirmation workflow, and Docker isolation - while maintaining backward compatibility with standard MCP clients. However, reliable execution within this framework requires models that can strictly adhere to protocol schemas. To this end, we also fine-tuned the Qwen3 4B and 8B model family on the Agent-Ark/Toucan-1.5M dataset using four Reinforcement Learning techniques: Group Relative Policy Optimization (GRPO), Dr. GRPO, Beta Normalization Policy Optimization (BNPO), and Decoupled Alignment Policy Optimization (DAPO). Evaluated on the MCPToolBench++ benchmark, our optimized model achieves an F1 score of 73.0% that outperforms GPT-OSS-120B (62.17%) and remains competitive with the 70B+ parameter baselines. Evaluation demonstrates that MCP Bridge successfully addresses the constraints of direct MCP connections while providing enhanced security controls and cross-platform compatibility, enabling sophisticated LLM-powered applications in previously inaccessible environments.
  •  
  • ↗️
↗️

Key Information Influencing Patient Decision-Making About AI in Health Care: Survey Experiment Study

✇Journal of Medical Internet Research
By: Xuan Zhu · Austin M Stroud · Sarah A Minteer · Dong Whi Yoo · Jennifer L Ridgeway · Maryam Mooghali · Jennifer E Miller · Barbara A Barry
Background: Artificial Intelligence (AI)-enabled devices are increasingly used in healthcare. However, there has been limited research on patients’ informational preferences, including which elements of AI device labeling enhance patient understanding, trust, and acceptance. Clear and effective patient-facing communication is essential to address patient concerns and support informed decision-making regarding AI-enabled care. Objective: Using simulated AI device labels in a cardiovascular context, we evaluated three aims. First, we identified key information elements that influence patient trust and acceptance of an AI device. Second, we examined how these effects varied based on patient characteristics. Third, we explored how patients evaluated informational content of AI labels and their perceived effectiveness of the AI labels in informing decision-making about the use of AI device, building trust in the device, and shaping their intention to use it in their healthcare. Methods: We recruited 340 US patients from ResearchMatch.org to participate in a web-based survey that contained two experiments. In the discrete choice experiment (DCE), participants indicated preferences in terms of trust and acceptance regarding 16 pairs of simulated AI device labels that varied across eight types of information needs identified in our previous qualitative work. In the single profile factorial experiment (SPFE), participants evaluated four randomly assigned label prototypes regarding the label’s legibility, comprehensibility, information overload, credibility, and perceived effectiveness in informing about the AI device, as well as participants’ trust in the AI device and intention to use the device in their healthcare. Data was analyzed using mixed effects binary or ordinal logistic regression. Results: The DCE showed that information about regulatory approval, high device performance, provider oversight, and AI’s value added to usual care significantly increased the likelihood of patient trust by 14.1-19.3% and acceptance by 13.3-17.9%. Subgroup analyses revealed variations based on patient characteristics such as familiarity with AI, health literacy, and recency of last medical checkup. The SPFE showed that patients reported good label comprehension, and that information about provider oversight, regulatory approval, device performance, and AI’s added value improved perceived credibility and effectiveness of the AI label (odds ratios [ORs] range 1.35-2.05), reduced doubts in the AI device (ORs range 0.61- 0.77), and increased trust and intention to use the AI device (ORs range 1.47-1.73). However, information about data privacy and safety management protocols are less influential. Conclusions: Patients value information about an AI device’s performance, provider oversight, regulatory status, and added value during decision-making. Providing transparent, easily understandable information about these aspects is critical to support patient determinations of trust and acceptance of AI-enabled healthcare. Information elements’ impact on patient trust and acceptance varies by patient characteristics, highlighting the need for a tailored approach to address the concerns of diverse patient groups about AI in healthcare.
  •  
  • ↗️
↗️

AI-exposed jobs deteriorated before ChatGPT

✇cs.AI, q-bio.NC updates on arXiv.org
By: Morgan R. Frank · Alireza Javadian Sabet · Lisa Simon · Sarah H. Bana · Renzhe Yu
arXiv:2601.02554v1 Announce Type: cross Abstract: Public debate links worsening job prospects for AI-exposed occupations to the release of ChatGPT in late 2022. Using monthly U.S. unemployment insurance records, we measure occupation- and location-specific unemployment risk and find that risk rose in AI-exposed occupations beginning in early 2022, months before ChatGPT. Analyzing millions of LinkedIn profiles, we show that graduate cohorts from 2021 onward entered AI-exposed jobs at lower rates than earlier cohorts, with gaps opening before late 2022. Finally, from millions of university syllabi, we find that graduates taking more AI-exposed curricula had higher first-job pay and shorter job searches after ChatGPT. Together, these results point to forces pre-dating generative AI and to the ongoing value of LLM-relevant education.
  •  
  • ↗️
↗️

A Multicenter Benchmark of Multiple Instance Learning Models for Lymphoma Subtyping from HE-stained Whole Slide Images

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rao Muhammad Umer · Daniel Sens · Jonathan Noll · Christian Matek · Lukas Wolfseher · Rainer Spang · Ralf Huss · Johannes Raffler · Sarah Reinke · Wolfram Klapper · Katja Steiger · Kristina Schwamborn · Carsten Marr
arXiv:2512.14640v1 Announce Type: cross Abstract: Timely and accurate lymphoma diagnosis is essential for guiding cancer treatment. Standard diagnostic practice combines hematoxylin and eosin (HE)-stained whole slide images with immunohistochemistry, flow cytometry, and molecular genetic tests to determine lymphoma subtypes, a process requiring costly equipment, skilled personnel, and causing treatment delays. Deep learning methods could assist pathologists by extracting diagnostic information from routinely available HE-stained slides, yet comprehensive benchmarks for lymphoma subtyping on multicenter data are lacking. In this work, we present the first multicenter lymphoma benchmarking dataset covering four common lymphoma subtypes and healthy control tissue. We systematically evaluate five publicly available pathology foundation models (H-optimus-1, H0-mini, Virchow2, UNI2, Titan) combined with attention-based (AB-MIL) and transformer-based (TransMIL) multiple instance learning aggregators across three magnifications (10x, 20x, 40x). On in-distribution test sets, models achieve multiclass balanced accuracies exceeding 80% across all magnifications, with all foundation models performing similarly and both aggregation methods showing comparable results. The magnification study reveals that 40x resolution is sufficient, with no performance gains from higher resolutions or cross-magnification aggregation. However, on out-of-distribution test sets, performance drops substantially to around 60%, highlighting significant generalization challenges. To advance the field, larger multicenter studies covering additional rare lymphoma subtypes are needed. We provide an automated benchmarking pipeline to facilitate such future research.
  •  
  • ↗️
↗️

Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sreemaee Akshathala · Bassam Adnan · Mahisha Ramesh · Karthik Vaidhyanathan · Basil Muhammed · Kannan Parthasarathy
arXiv:2512.12791v2 Announce Type: replace-cross Abstract: Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable coordinated reasoning, planning, and execution across diverse domains, allowing agents to collaboratively automate complex workflows. Despite these advances, evaluation and assessment of LLM agents and the multi-agent systems they constitute remain a fundamental challenge. Although various approaches have been proposed in the software engineering literature for evaluating conventional software components, existing methods for AI-based systems often overlook the non-deterministic nature of models. This non-determinism introduces behavioral uncertainty during execution, yet existing evaluations rely on binary task completion metrics that fail to capture it. Evaluating agentic systems therefore requires examining additional dimensions, including the agent ability to invoke tools, ingest and retrieve memory, collaborate with other agents, and interact effectively with its environment. These challenges emerged during our ongoing industry collaboration with MontyCloud Inc., when we deployed an agentic system in production. These limitations surfaced during deployment, highlighting practical gaps in the current evaluation methods and the need for a systematic assessment of agent behavior beyond task outcomes. Informed by these observations and established definitions of agentic systems, we propose an end-to-end Agent Assessment Framework with four evaluation pillars encompassing LLMs, Memory, Tools, and Environment. We validate the framework on a representative Autonomous CloudOps use case, where experiments reveal behavioral deviations overlooked by conventional metrics, demonstrating its effectiveness in capturing runtime uncertainties.
  •  
  • ↗️
↗️

Somatic evolution following cancer treatment in normal tissue

✇Nature - Issue - nature.com science feeds
By: Oriol Pich · Sophia Ward · Andrew Rowan · Cristina Naceur-Lombardelli · Oliver Shutkever · Carlos Martinez-Ruiz · Siân Harries · Sonya Hessey · Babu Naidu · James D. Brenton · John Le Quesne · Anne Thomas · Cathy Richards · Matthew G. Krebs · Samra Turajlic · Sanjay Jogai · Simone Zaccaria · David Moore · Crispin T. Hiley · Kai-Keen Shiu · John Bridgewater · Daniel Hochhauser · Martin Forster · Siow Ming Lee · Tanya Ahmad · Dionysis Papadatos-Pastos · Sam Janes · Peter Van Loo · Katey Enfield · Ariana Huebner · Sergio Quezada · Stephan Beck · Tariq Enver · David R. Pearce · Mary Falzon · Ron Sinclair · Zoe Rhodes · Teresa Marafioti · Miriam Mitchison · Mark Linch · Sebastian Brandner · Selvaraju Veeriah · Heather Shaw · Gerhardt Attard · Faye Gishen · Maise Al-Bakir · Nnenna Kanu · Francisco Gimeno-Valiente · Emilia L. Lim · James Reading · Benny Chain · Adrienne Flanagan · Emma Colliver · Mihaela Angelova · James Black · Olivia Lucas · William Hill · Wing Kin Liu · Alexander Frankell · Roberto Salgado · Kristiana Grigoriadis · Takahiro Karasaki · Abigail Bunkum · Sara

Nature, Published online: 10 December 2025; doi:10.1038/s41586-025-09792-4

High-depth sequencing of non-cancerous tissue from patients with metastatic cancer reveals single-base mutational signatures of alcohol, smoking and cancer treatments, and reveals how exogenous factors, including cancer therapies, affect somatic cell evolution.
  •  
  • ↗️
↗️

Multi-omic profiling provides insights into the heterogeneity, microenvironmental features, and biomarker landscape of small-cell lung cancer

✇Omics In Lung
By: Mingchao Xie · Miljenka Vuko · Shashank Saran · Siyu Liu · Andrew G Chambers · Hana Baakza · Helen K Angell · Felicia Ng · Carl M Gay · Robert J Cardnell · Felix J Segerer · Alma Andoni · Jaime Rodriguez-Canales · Paul M Waring · Markus Schick · J Carl Barrett · Lauren A Byers · Giulia Fabbri

Mol Cancer. 2025 Dec 2. doi: 10.1186/s12943-025-02514-4. Online ahead of print.

ABSTRACT

BACKGROUND: Greater understanding of differential therapeutic sensitivity, specifically to immunotherapy, in small-cell lung cancer (SCLC) is required.

METHODS: We explored SCLC heterogeneity through integrated molecular characterization of tumor tissue samples from 159 treatment-naive patients, utilizing genetic, epigenetic, transcriptional, and proteomic profiling, immunohistochemistry staining for multiple biologically relevant markers including transcriptional subtype-defining proteins, and spatial immune profiling using multiplex immunofluorescence.

RESULTS: Multi-omics analysis confirmed high heterogeneity across/within neuroendocrine and non-neuroendocrine subtypes. Methylomics analysis identified four methylome clusters that may enhance subtype prediction, prognosis, and longitudinal monitoring of subtype evolution. Immunohistochemistry analysis showed high MHC-I expression in non-neuroendocrine subtypes, which have greatest potential benefit from adding immunotherapy to chemotherapy; high DLL3 expression associated with neuroendocrine subtypes and an immune-cold tumor microenvironment. Multiplex immunofluorescence demonstrated associations of MHC-I with spatial arrangement and phenotypic features of immune cells in the tumor microenvironment of high-MHC-I-expressing SCLC, providing mechanistic rationale for MHC-I as a potential biomarker of immunotherapy response.

CONCLUSIONS: This multimodal profiling analysis provides further insights into the biologic complexity of SCLC and highlights potential therapeutic vulnerabilities of distinct disease subtypes.

PMID:41331472 | DOI:10.1186/s12943-025-02514-4

  •  
  • ↗️
↗️

Integrative Analysis of Multi-Omics Data for Biomarker Discovery

✇Omics in Hepatocellular
By: Rency S Varghese · Xinran Zhang · Sarada Giridharan · Hoi Yan Katharine Chau · Radhika Unnikrishnan · Md Mamunur Rashid · Muhammad Salman Sajid · Habtom W Ressom

Annu Int Conf IEEE Eng Med Biol Soc. 2025 Jul;2025:1-7. doi: 10.1109/EMBC58623.2025.11254134.

ABSTRACT

The complexity of biological systems and the limitations of analyzing individual omics studies for biomarker discovery have raised the need for a holistic approach by multi-omics integration. By integrating data from multiple layers, researchers can gain insights into the entire system rather than just individual components. Also, integrative analysis can help identify molecular signatures that are more accurate in predicting disease onset, progression, and response to treatment, leading to better-targeted therapies and personalized medicine. In this paper, we explored statistical and deep learning methods for integrative analysis of metabolomics, lipidomics, peptidomics, proteomics, and glycoproteomics data acquired by LC-MS/MS analysis of serum samples from 20 hepatocellular carcinoma (HCC) cases and 20 patients with liver cirrhosis (CIRR). The goal is to identify a panel of multi-omics features that distinguish HCC cases from cirrhotic controls. A pathway analysis using these features identified biological pathways such as LXR/RXR Activation and Acute Response signaling as significantly enriched in our multi-omics datasets.

PMID:41336317 | PMC:PMC12694951 | DOI:10.1109/EMBC58623.2025.11254134

  •  
  • ↗️
↗️

DNA-Based Liquid Biopsy for Evaluating Surgical and Postsurgical Outcomes in Gynecologic Malignancies: A Systematic Review

✇MRD
By: Samaneh Yavari · Sepide Javankiani · Foroozan Yarahmadi · Rojin Sarallah · Behandokht Rezaei · Maryam Maroufi · Mona Khabbazkar Amlashi · Mahshid Imankhan · Mahnaz Marvi · Neda Aslani · Arezou Soltanattar · Zahra Mohammadi · Alireza Azani · Pegah Kavousinia

J Clin Lab Anal. 2025 Dec 1:e70139. doi: 10.1002/jcla.70139. Online ahead of print.

ABSTRACT

INTRODUCTION: DNA-based liquid biopsies, including circulating tumor DNA (ctDNA) and cell-free DNA (cfDNA), are emerging as minimally invasive biomarkers for monitoring surgical and postsurgical outcomes in gynecologic malignancies. These tools offer the potential to guide early intervention, refine risk stratification, and improve prognostic accuracy. This systematic review aimed to assess the clinical utility of DNA-based liquid biopsies in evaluating recurrence, surgical success, and preoperative diagnosis in gynecologic cancers.

METHODS: A systematic review was conducted in accordance with PRISMA guidelines, covering studies published from 2017 to 2025. Literature searches were performed in PubMed, Scopus, and Web of Science. A total of 32 eligible observational studies involving 3210 patients with ovarian, endometrial, uterine, and other gynecologic malignancies were included. Study quality was assessed using the Newcastle-Ottawa Scale (NOS).

RESULTS: The studies showed a broad geographic and methodological diversity, with a median NOS score of 7. CtDNA and cfDNA demonstrated promise in three key areas: (1) Recurrence prediction-postoperative ctDNA positivity was associated with higher relapse rates and reduced disease-free survival; (2) Monitoring surgical outcomes and treatment response-ctDNA dynamics more accurately reflected tumor burden than traditional markers like CA125; (3) Preoperative diagnostic support-cfDNA methylation profiling and cfDNA/CA125 models enhanced malignancy detection and risk stratification. Ovarian and endometrial cancers were most frequently studied.

CONCLUSIONS: DNA-based liquid biopsies show strong potential in perioperative care for gynecologic cancers. Their integration into clinical workflows could improve the detection of minimal residual disease and inform individualized surgical planning.

PMID:41327898 | DOI:10.1002/jcla.70139

  •  
  • ↗️
↗️

CLINB: A Climate Intelligence Benchmark for Foundational Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Michelle Chen Huebscher · Katharine Mach · Aleksandar Stani\'c · Markus Leippold · Ben Gaiarin · Zeke Hausfather · Elisa Rawat · Erich Fischer · Massimiliano Ciaramita · Joeri Rogelj · Christian Buck · Lierni Sestorain Saralegui · Reto Knutti
arXiv:2511.11597v1 Announce Type: new Abstract: Evaluating how Large Language Models (LLMs) handle complex, specialized knowledge remains a critical challenge. We address this through the lens of climate change by introducing CLINB, a benchmark that assesses models on open-ended, grounded, multimodal question answering tasks with clear requirements for knowledge quality and evidential support. CLINB relies on a dataset of real users' questions and evaluation rubrics curated by leading climate scientists. We implement and validate a model-based evaluation process and evaluate several frontier models. Our findings reveal a critical dichotomy. Frontier models demonstrate remarkable knowledge synthesis capabilities, often exhibiting PhD-level understanding and presentation quality. They outperform "hybrid" answers curated by domain experts assisted by weaker models. However, this performance is countered by failures in grounding. The quality of evidence varies, with substantial hallucination rates for references and images. We argue that bridging this gap between knowledge synthesis and verifiable attribution is essential for the deployment of AI in scientific workflows and that reliable, interpretable benchmarks like CLINB are needed to progress towards building trustworthy AI systems.
  •  
  • ↗️
↗️

REFA: Reference Free Alignment for multi-preference optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Taneesh Gupta · Rahul Madhavan · Xuchao Zhang · Chetan Bansal · Saravan Rajmohan
arXiv:2412.16378v4 Announce Type: replace-cross Abstract: To mitigate reward hacking from response verbosity, modern preference optimization methods are increasingly adopting length normalization (e.g., SimPO, ORPO, LN-DPO). While effective against this bias, we demonstrate that length normalization itself introduces a failure mode: the URSLA shortcut. Here models learn to satisfy the alignment objective by prematurely truncating low-quality responses rather than learning from their semantic content. To address this, we introduce REFA, a new alignment framework that proposes probabilistic control on a structural token that controls termination. Our core innovation is a new class of regularizers that operate directly on the probability of the End-of-Sequence (EOS) token, a previously unexploited control lever. This token-level intervention provides a principled solution to the URSLA shortcut, ensuring genuine quality improvements. Furthermore, it unlocks a versatile mechanism for managing the alignment-efficiency tradeoff, enabling practitioners to fine-tune models that adhere to specific token budgets. Empirically, REFA achieves a 60.29% win rate and a 52.17% length-controlled win rate on AlpacaEval2 with Llama-3-8B-Instruct, demonstrating the power of our token-level control paradigm.
  •  
  • ↗️
↗️

Wearable Artificial Intelligence for Epilepsy: Scoping Review

✇Journal of Medical Internet Research
By: Sarah Aziz · Amal A M Ali · Hania Aslam · Noor ul Ain · Amna Tariq · Zain Sohail · Sofia Murtaza · Hafiza Iqra Mahmood · Muhammad Irfan Wazeer · Fozia Murtaza · Alaa Abd-alrazaq · Mohammed Alsahli · Rafat Damseh · Rawan AlSaad · Tariq Shahzad · Arfan Ahmed · Javaid Sheikh
Background: Epilepsy affects approximately 50 million people globally and imposes a substantial clinical and societal burden, requiring continuous and personalized monitoring for effective management. Wearable artificial intelligence (AI) technologies offer a promising solution by leveraging physiological signals and machine learning for seizure detection and prediction. While various approaches have been proposed, a comprehensive overview summarizing these advances and challenges is still needed. Objective: This review aims to comprehensively explore and map the existing literature on AI-driven wearable technologies for epilepsy, identifying device characteristics, AI methodologies, biosignal measurements, validation approaches, and research gaps. Methods: A scoping review was conducted following the PRISMA-ScR guidelines. A systematic search was performed across six electronic databases (Scopus, MEDLINE, EMBASE, ACM Digital Library, IEEE Xplore, and Google Scholar) to identify relevant studies published up to December 2023. We included studies that developed AI algorithms for epilepsy using non-invasive wearable devices (e.g., smartwatches, smart clothing) and excluded those using non-wearables or in-body devices. Eligible publication types included journal articles, conference papers, and dissertations. Study selection and data extraction were performed independently by six reviewers. The extracted data was synthesized narratively. Results: A total of 68 studies met the inclusion criteria. Research in this domain has increased significantly since 2021, with India, the United States, and China leading contributions. The studies examined both commercial (45.6%) and non-commercial (47.1%) wearable devices, with Empatica smart bands being the most frequently used. The primary biosignals monitored included activity measures (54.4%), cardiovascular metrics (45.6%), brain activity (35.3%), and electrodermal activity (33.8%). The most common AI models were support vector machines (42.6%), random forests (22.1%), and convolutional neural networks (16.2%). Most models focused on seizure detection (77.5%) compared to seizure prediction (22.5%), reflecting a research imbalance that suggests the need for further development in predictive analytics. Sensitivity (80.9%) was the most frequently reported performance metric, indicating a focus on identifying seizures; however, comprehensive clinical validation remains limited. Closed-source data predominated (64.7%), limiting the generalizability of findings. The most used validation methods were leave-one-out cross-validation (30.9%) and k-fold cross-validation (29.4%), while video-EEG served as the primary reference standard (42.6%). Conclusions: Wearable AI technologies show significant promise in epilepsy management, offering real-time, continuous monitoring and early seizure detection. To realize clinical impact, future research should prioritize the standardization of validation methods, promote open data exchange for reproducibility, and develop energy-efficient algorithms that support real-world deployment in wearable devices.
  •  
  • ↗️
❌