Publication date: April 2026Source: Artificial Intelligence in Medicine, Volume 174Author(s): Gernot Fiala, Markus Plass, Robert Harb, Peter Regitnig, Kristijan Skok, Wael Al Zoughbi, Carmen Zerner, Paul Torke, Michaela Kargl, Heimo Müller, Tomas Brazdil, Matej Gallo, Jaroslav Kubín, Roman Stoklasa, Rudolf Nenutil, Norman Zerbe, Andreas Holzinger, Petr Holub
Source: Artificial Intelligence in Medicine, Volume 174
Author(s): Gernot Fiala, Markus Plass, Robert Harb, Peter Regitnig, Kristijan Skok, Wael Al Zoughbi, Carmen Zerner, Paul Torke, Michaela Kargl, Heimo Müller, Tomas Brazdil, Matej Gallo, Jaroslav Kubín, Roman Stoklasa, Rudolf Nenutil, Norman Zerbe, Andreas Holzinger, Petr Holub
Background: Online health communities have evolved into digital marketplaces where physicians have to compete for patients. Existing research examines physician-patient dynamics through a patient-centric lens, treating physicians as passive recipients of ratings and reviews, while the strategic role of physician self-disclosure remains unexamined. This gap constrains a comprehensive understanding of how physicians can actively shape patient decisions, making the investigation of strategic self-d
Background: Online health communities have evolved into digital marketplaces where physicians have to compete for patients. Existing research examines physician-patient dynamics through a patient-centric lens, treating physicians as passive recipients of ratings and reviews, while the strategic role of physician self-disclosure remains unexamined. This gap constrains a comprehensive understanding of how physicians can actively shape patient decisions, making the investigation of strategic self-disclosure imperative. Objective: This study aims to investigate the relationship between physician self-disclosure breadth (scope of information) and depth (detailed expertise) and patient decision-making, as well as whether regional digital health care level (DHL) moderates these relationships. Methods: We conducted a cross-sectional analysis of observational data to test these relationships. Data were collected from China’s online health care platform Haodf from September to December 2024. Self-disclosure breadth (including clinical performance, academic experience, and social reputation), self-disclosure depth (including expertise coverage, richness, and granularity), and patient decision-making (total visits) were captured through manual content coding and quantitative measurement. We used structured content analysis to extract the disclosure components, informational scope, and descriptive details of each profile. Then, using validated operational formulas, we calculated the composite indices for disclosure breadth and depth based on the coded dimensions. The study generated 1798 final physician samples with complete data across 14 focal variables. The hypotheses were tested using an ordinary least squares regression model, and 4 robustness checks were conducted, including variable substitution and different resampling techniques. Results: In the primary ordinary least squares regression models, self-disclosure breadth was significantly and positively associated with patient visits (β=0.255, 95% CI 0.054-0.456; P=.01), as was self-disclosure depth (β=0.098, 95% CI 0.030-0.167; P=.005). The breadth×DHL interaction was positive and significant (β=0.261, 95% CI 0.061-0.461; P=.01). Similarly, the depth×DHL interaction was positive and significant (β=0.070, 95% CI 0.002-0.138; P=.045). It should be noted that the association for self-disclosure breadth was stronger than that of self-disclosure depth. DHL strengthened the relationship between the disclosure strategies with patient visits. This contextual amplification indicates that DHL serves as a critical boundary condition, determining the degree to which physician self-disclosure strategies translate into patient acquisition outcomes. Conclusions: This study reconceptualizes physicians as strategic agents shaping patient decision-making through purposeful self-disclosure. Different from existing studies treating physicians as passive recipients of ratings and reviews, our research demonstrates that physicians can strategically shape patient acquisition through self-disclosure breadth and depth. This study brings new insights to digital health markets by demonstrating that self-disclosure operates as a viable patient acquisition mechanism, wherein the DHL acts as a critical boundary condition. The findings have real-world implications: (1) physicians can leverage evidence-based disclosure strategies, (2) platforms should implement context-adaptive features, and (3) policymakers should prioritize digital infrastructure investments to enhance physicians' competitive capabilities and patient decision-making quality.
(MedPage Today) -- Detection of pancreatic cancer, including early-stage disease, improved substantially with a panel of four cancer-associated proteins versus a single protein, a retrospective comparison study showed.
Overall accuracy for any...
(MedPage Today) -- Detection of pancreatic cancer, including early-stage disease, improved substantially with a panel of four cancer-associated proteins versus a single protein, a retrospective comparison study showed.
Overall accuracy for any...
New research from Accenture has discovered insurance executives are planning on increased investment into AI during 2026 despite a widening skills gap in insurance organisations.
Surveying 3,650 C-suite leaders over 20 industries and 20 countries, the Pulse of Change poll revealed 90% of the 218 senior insurance executives intend to spend more on AI over the next year. In all, 85% of the respondents view AI as a tool for revenue expansion not one that reduces costs.
While organisations are uppin
New research from Accenture has discovered insurance executives are planning on increased investment into AI during 2026 despite a widening skills gap in insurance organisations.
Surveying 3,650 C-suite leaders over 20 industries and 20 countries, the Pulse of Change poll revealed 90% of the 218 senior insurance executives intend to spend more on AI over the next year. In all, 85% of the respondents view AI as a tool for revenue expansion not one that reduces costs.
While organisations are upping their AI investment to drive growth, 35% of leaders acknowledge that true progress depends on getting core data strategies and digital abilities right. 54% of employees reported that low-quality or misleading AI outputs are undermining AI’s benefits, leading to reduced productivity and time-wasting.
AI investment may not be enough, Accenture says. Its survey suggests sustainable growth relies on data quality and trusted outputs.
AI adoption enters enterprise scale
The Pulse of Change survey indicates a shift in AI adoption as it goes beyond experimental phases to large scale organisational levels. With 34% of insurance companies now rolling out AI agents in multiple functions, insurers are heading into operational use and away from isolated experiments.
almost a third of senior C-suite leaders are frequently using generative AI, highlighting increased implementation at the highest level. Therefore, AI is undoubtedly shaping workflows, strategies, and key decisions, affecting all facets of businesses.
Nearly a third of businesses are rebuilding entire processes with AI. No longer is the technology a supporting addition to existing workflows; it has become a central component, signalling a more mature stage of AI adoption.
Despite redesigning processes to include AI, fewer than 10% are redesigning employee roles to match such changes, resulting in many employees feeling unprepared. Just 40% claimed their training has equipped them for new AI responsibilities, and only 20% feel like they have any say in how AI affects their work.
AI adoption by companies may be accelerating, but employee use lags behind. There has been a 10 percentage point drop in regular AI use by employees since summer 2025, while only 39% are trying AI tools independently, a drop of 15 points. For effective AI use and to speed up AI adoption among the workforce, companies must be prepared to redesign job roles, align incentives, and provide improved training programmes as, right now, employees are feeling hesitant and unprepared to use AI on their own.
AI investment still fuelling executive optimism amid bubble fears
Although talks around a potential AI bubble continue to cloud the industry, insurance executives remain confident. 47% claimed they would increase AI spending if the bubble burst, and 37% would escalate recruitment.
Altogether, 6% said they would “decrease investments ([by] 20% or more),” 22% would “somewhat decrease investments ([by] up to 20%),” 24% would make “no change,” 40% would “somewhat increase investments (up to 20%),” and 7% would “increase investments (20% or more).”
Khalid Lahraoui, Accenture’s insurance industry group lead, commented, “It’s clear that insurance leaders are confident in AI’s capacity to drive growth, and as such, they are decisively increasing investments, despite ROI uncertainty.”
Lack of AI skills blocking AI’s potential value
As insurance executives prepare to invest heavily in AI, obstacles lie in wait. For instance, a quarter of executives said skill shortages are a core concern and a key player in determining the value they extract from AI. Although these challenges persist in different industries, just 24% of respondents have implemented continuous learning programmes associated with AI. Moreover, only 5% said they are adjusting job positions to support the adoption of AI.
AI adoption disconnect
The disconnect between C-suite leaders and employees is evident from the survey’s data. Although talent is the main driver of AI scaling, employees feel less confident and secure than leadership assumes. 23% of C-suite leaders said improved access to skilled talent would accelerate their AI implementation strategies. 38% of employees believe their organisation would respond effectively to technological disruption, but just 30% feel confident about how their company would handle talent disruption.
Job security is also waning, with 48% feeling secure in their roles, down from 59% in summer 2025. Meanwhile, 59% of workers believe young professionals are finding it more challenging to find jobs due to automation and AI. Leadership may see talent as an accelerator for AI, but anxiety around job security and organisational readiness persists.
Key focus is on investment
Approximately two thirds of executives are prioritising investments in digital technologies and AI amid the rapid changes facing global industries. 67% reported feeling well-prepared for technological disruption, but only 39% felt confident if there was environmental disruption, and 44% for geopolitical disruption.
Again, there is a divide between leadership and employees, with only 29% of insurance workers feeling confident during economic disruption compared to 43% of leaders.
Optimism among insurance executives and C-suite leaders as a whole remains high, despite 82% expecting further changes in 2026, a 24 percentage gap with employees. 78% anticipate stronger and faster revenue growth in the next year and 82% have plans to increase recruitment.
According to Accenture’s report, the key challenge is not AI technology itself; it’s getting employees on board, engaged, and ready to work with AI.
As the report notes, bridging the gap between technology and people is the key to success. “2026 will favour those that align the confidence in their technological investments with commitment to workforce needs,” the report concludes.
(Image source: “Accenture Building City View Plaza San Jose” by mrkathika is licensed under CC BY-SA 2.0.)
Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is part of TechEx and co-located with other leading technology events. Click here for more information.
AI News is powered by TechForge Media. Explore other upcoming enterprise technology events and webinars here.
When I first heard about OpenAI’s ChatGPT Health, I felt a familiar itch.
Since being diagnosed with a malignant brain tumor 18 years ago, at age 29, I’ve developed a deep curiosity about my own health. That curiosity has driven me to enroll in numerous studies, connect my health records to the NIH All of Us research program, and even donate my brain tissue for research-grade genomic sequencing.Read the rest…
When I first heard about OpenAI’s ChatGPT Health, I felt a familiar itch.
Since being diagnosed with a malignant brain tumor 18 years ago, at age 29, I’ve developed a deep curiosity about my own health. That curiosity has driven me to enroll in numerous studies, connect my health records to the NIH All of Us research program, and even donate my brain tissue for research-grade genomic sequencing.
A new report from Deloitte has warned that businesses are deploying AI agents faster than their safety protocols and safeguards can keep up. Therefore, serious concerns around security, data privacy, and accountability are spreading.
According to the survey, agentic systems are moving from pilot to production so quickly that traditional risk controls, which were designed for more human-centred operations, are struggling to meet security demands.
Just 21% of organisations have implemented stringe
A new report from Deloitte has warned that businesses are deploying AI agents faster than their safety protocols and safeguards can keep up. Therefore, serious concerns around security, data privacy, and accountability are spreading.
According to the survey, agentic systems are moving from pilot to production so quickly that traditional risk controls, which were designed for more human-centred operations, are struggling to meet security demands.
Just 21% of organisations have implemented stringent governance or oversight for AI agents, despite the increased rate of adoption. Whilst 23% of companies stated that they are currently using AI agents, this is expected to rise to 74% in the next two years. The share of businesses yet to adopt this technology is expected to fall from 25% to just 5% over the same period.
Poor governance is the threat
Deloitte is not highlighting AI agents as inherently dangerous, but states the real risks are associated with poor context and weak governance. If agents operate as their own entities, their decisions and actions can easily become opaque. Without robust governance, it becomes difficult to manage and almost impossible to insure against mistakes.
According to Ali Sarrafi, CEO & Founder of Kovant, the answer is governed autonomy. “Well-designed agents with clear boundaries, policies and definitions managed the same way as an enterprise manages any worker can move fast on low-risk work inside clear guardrails, but escalate to humans when actions cross defined risk thresholds.”
“With detailed action logs, observability, and human gatekeeping for high-impact decisions, agents stop being mysterious bots and become systems you can inspect, audit, and trust.”
As Deloitte’s report suggests, AI agent adoption is set to accelerate in the coming years, and only the companies that deploy the technology with visibility and control will hold the upper hand over competitors, not those who deploy them quickest.
Why AI agents require robust guardrails
AI agents may perform well in controlled demos, but they struggle in real-world business settings where systems can be fragmented and data may be inconsistent.
Sarrafi commented on the unpredictable nature of AI agents in these scenarios. “When an agent is given too much context or scope at once, it becomes prone to hallucinations and unpredictable behaviour.”
“By contrast, production-grade systems limit the decision and context scope that models work with. They decompose operations into narrower, focused tasks for individual agents, making behaviour more predictable and easier to control. This structure also enables traceability and intervention, so failures can be detected early and escalated appropriately rather than causing cascading errors.”
Accountability for insurable AI
With agents taking real actions in business systems, such as keeping detailed action logs, risk and compliance are viewed differently. With every action recorded, agents’ activities become clear and evaluable, letting organisations inspect actions in detail.
Such transparency is crucial for insurers, who are reluctant to cover opaque AI systems. This level of detail helps insurers understand what agents have done, and the controls involved, thus making it easier to assess risk. With human oversight for risk-critical actions and auditable, replayable workflows, organisations can produce systems that are more manageable for risk assessment.
AAIF standards a good first step
Shared standards, like those being developed by the Agentic AI Foundation (AAIF), help businesses to integrate different agent systems, but current standardisation efforts focus on what is simplest to build, not what larger organisations need to operate agentic systems safely.
Sarrafi says enterprises require standards that support operation control, and which include, “access permissions, approval workflows for high-impact actions, and auditable logs and observability, so teams can monitor behaviour, investigate incidents, and prove compliance.”
Identity and permissions the first line of defence
Limiting what AI agents can access and the actions they can perform is important to ensure safety in real business environments. Sarrafi said, “When agents are given broad privileges or too much context, they become unpredictable and pose security or compliance risks.”
Visibility and monitoring are important to keep agents operating inside limits. Only then can stakeholders have confidence in the adoption of the technology. If every action is logged and manageable, teams can then see what has happened, identify issues, and better understand why events occurred.
Sarrafi continued, “This visibility, combined with human supervision where it matters, turns AI agents from inscrutable components into systems that can be inspected, replayed and audited. It also allows rapid investigation and correction when issues arise, which boosts trust among operators, risk teams and insurers alike.”
Deloitte’s blueprint
Deloitte’s strategy for safe AI agent governance sets out defined boundaries for the decisions agentic systems can make. For instance, they might operate with tiered autonomy, where agents can only view information or offer suggestions. From here, they can be allowed to take limited actions, but with human approval. Once they have proven to be reliable in low-risk areas, they can be allowed to act automatically.
Deloitte’s “Cyber AI Blueprints” suggest governance layers and embedding policies and compliance capability roadmaps into organisational controls. Ultimately, governance structures that track AI use and risk, and embedding oversight into daily operations are important for safe agentic AI use.
Readying workforces with training is another aspect of safe governance. Deloitte recommends training employees on what they shouldn’t share with AI systems, what to do if agents go off track, and how to spot unusual, potentially dangerous behaviour. If employees fail to understand how AI systems work and their potential risks, they may weaken security controls, albeit unintentionally.
Robust governance and control, alongside shared literacy are fundamental to the safe deployment and operation of AI agents, enabling secure, compliant, and accountable performance in real-world environments
(Image source: “Global Hawk, NASA’s New Remote-Controlled Plane” by NASA Goddard Photo and Video is licensed under CC BY 2.0. )
Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is part of TechEx and co-located with other leading technology events. Click here for more information.
AI News is powered by TechForge Media. Explore other upcoming enterprise technology events and webinars here.
Front Mol Biosci. 2026 Jan 12;12:1708518. doi: 10.3389/fmolb.2025.1708518. eCollection 2025.ABSTRACTLiquid biopsy has emerged as a transformative tool in precision oncology, offering a minimally invasive approach for cancer detection, monitoring, and treatment guidance. Unlike traditional tissue biopsies, which are invasive and limited by tumor accessibility and sampling bias, liquid biopsy enables real-time tumor assessment through the analysis of circulating biomarkers in blood and other biofl
Front Mol Biosci. 2026 Jan 12;12:1708518. doi: 10.3389/fmolb.2025.1708518. eCollection 2025.
ABSTRACT
Liquid biopsy has emerged as a transformative tool in precision oncology, offering a minimally invasive approach for cancer detection, monitoring, and treatment guidance. Unlike traditional tissue biopsies, which are invasive and limited by tumor accessibility and sampling bias, liquid biopsy enables real-time tumor assessment through the analysis of circulating biomarkers in blood and other biofluids. This review provides a comprehensive overview of recent advances in liquid biopsy, with a focus on circulating tumor cells (CTCs), circulating tumor DNA (ctDNA), non-coding RNAs, extracellular vesicles (exosomes), and secreted proteins. These biomarkers offer valuable insights into tumor biology, supporting applications in early diagnosis, prognosis, treatment response monitoring, and minimal residual disease detection across various cancer types. We also discuss state-of-the-art methodologies, including next-generation sequencing, digital PCR, microfluidics, proteomics, and emerging artificial intelligence-based approaches that enhance the sensitivity, specificity, and scalability of liquid biopsy assays. Clinical studies demonstrate the potential of liquid biopsy for tailoring targeted therapies, predicting resistance mechanisms, and identifying tumor recurrence earlier than conventional methods. Furthermore, FDA-approved assays and ongoing phase III and IV clinical trials highlight its growing integration into routine clinical practice. Beyond technical innovations, this review examines the global landscape of liquid biopsy, emphasizing opportunities and challenges for implementation across diverse healthcare settings. Disparities in access, particularly between high-income and low- and middle-income countries, underscore the need for strategies that ensure equitable adoption of liquid biopsy technologies worldwide. In summary, liquid biopsy represents a paradigm shift in oncology, bridging innovations in cancer diagnostics with clinical applications. By enabling dynamic, personalized, and less invasive cancer management, it holds great promise for improving patient outcomes and advancing precision medicine.
Nature, Published online: 28 January 2026; doi:10.1038/d41586-026-00037-6Co-optimized design and technology has resulted in cheap, flexible microchips that efficiently run neural-network tasks, as demonstrated in wearable health-care devices.
Co-optimized design and technology has resulted in cheap, flexible microchips that efficiently run neural-network tasks, as demonstrated in wearable health-care devices.
arXiv:2601.18799v1 Announce Type: cross
Abstract: As digital twins (DTs) evolve to become more agentic through the integration of artificial intelligence (AI), they acquire capabilities that extend beyond dynamic representation of their target systems. This paper presents a taxonomy of agentic DTs organised around three fundamental dimensions: the locus of agency (external, internal, distributed), the tightness of coupling (loose, tight, constitutive), and model evolution (static, adaptive, rec
arXiv:2601.18799v1 Announce Type: cross
Abstract: As digital twins (DTs) evolve to become more agentic through the integration of artificial intelligence (AI), they acquire capabilities that extend beyond dynamic representation of their target systems. This paper presents a taxonomy of agentic DTs organised around three fundamental dimensions: the locus of agency (external, internal, distributed), the tightness of coupling (loose, tight, constitutive), and model evolution (static, adaptive, reconstructive). From the resulting 27-configuration space, we identify nine illustrative configurations grouped into three clusters: "The Present" (existing tools and emerging steering systems), "The Threshold" (where emergent properties appear and coupling becomes constitutive), and "The Frontier" (where systems gain reconstructive capabilities).
Our analysis explores how agentic DTs exercise performative power--not merely representing physical systems but actively participating in constituting them. Using traffic navigation systems as examples, we show how even passive tools can exhibit emergent performativity, while advanced configurations risk performative lock-in. Drawing on performative prediction theory, we trace a progression from passive tools through active steering to ontological reconstruction, examining how constitutive coupling enables systems to create self-validating realities. Understanding these configurations is essential for navigating the transformation from DTs as mirror worlds to DTs as architects of new ontologies.
arXiv:2601.18814v1 Announce Type: cross
Abstract: Background: Coronary angiography (CAG) is the cornerstone imaging modality for evaluating coronary artery stenosis and guiding interventional decision-making. However, interpretation based on single-frame angiographic images remains highly operator-dependent, and conventional deep learning models still face challenges in modeling complex vascular morphology and fine-grained texture patterns.Methods: We propose a Lightweight Quantum-Enhanced ResN
arXiv:2601.18814v1 Announce Type: cross
Abstract: Background: Coronary angiography (CAG) is the cornerstone imaging modality for evaluating coronary artery stenosis and guiding interventional decision-making. However, interpretation based on single-frame angiographic images remains highly operator-dependent, and conventional deep learning models still face challenges in modeling complex vascular morphology and fine-grained texture patterns.Methods: We propose a Lightweight Quantum-Enhanced ResNet (LQER) for binary classification of coronary angiography images. A pretrained ResNet18 is employed as a classical feature extractor, while a parameterized quantum circuit (PQC) is introduced at the high-level semantic feature space for quantum feature enhancement. The quantum module utilizes data re-uploading and entanglement structures, followed by residual fusion with classical features, enabling end-to-end hybrid optimization with a strictly controlled number of qubits.Results: On an independent test set, the proposed LQER outperformed the classical ResNet18 baseline in accuracy, AUC, and F1-score, achieving a test accuracy exceeding 90%. The results demonstrate that lightweight quantum feature enhancement improves discrimination of positive lesions, particularly under class-imbalanced conditions.Conclusion: This study validates a practical hybrid quantum--classical learning paradigm for coronary angiography analysis, providing a feasible pathway for deploying quantum machine learning in medical imaging applications.
arXiv:2601.19380v1 Announce Type: cross
Abstract: Using multiple open-access models trained on public datasets, we developed Tri-Reader, a comprehensive, freely available pipeline that integrates lung segmentation, nodule detection, and malignancy classification into a unified tri-stage workflow. The pipeline is designed to prioritize sensitivity while reducing the candidate burden for annotators. To ensure accuracy and generalizability across diverse practices, we evaluated Tri-Reader on multi
arXiv:2601.19380v1 Announce Type: cross
Abstract: Using multiple open-access models trained on public datasets, we developed Tri-Reader, a comprehensive, freely available pipeline that integrates lung segmentation, nodule detection, and malignancy classification into a unified tri-stage workflow. The pipeline is designed to prioritize sensitivity while reducing the candidate burden for annotators. To ensure accuracy and generalizability across diverse practices, we evaluated Tri-Reader on multiple internal and external datasets as compared with expert annotations and dataset-provided reference standards.
arXiv:2508.10530v2 Announce Type: replace
Abstract: The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences. Recently, Direct Preference Optimization~(DPO) was proposed as a LM alignment method that directly optimize the policy from static preference data, and further improved by incorporating on-policy sampling~(i.e., pre
arXiv:2508.10530v2 Announce Type: replace
Abstract: The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences. Recently, Direct Preference Optimization~(DPO) was proposed as a LM alignment method that directly optimize the policy from static preference data, and further improved by incorporating on-policy sampling~(i.e., preference candidates generated during the training loop) for better LM alignment. However, we show on-policy data is not always optimal, with systematic effectiveness difference emerging between static and on-policy preference candidates. For example, on-policy data can result in a $3\times$ effectiveness compared with static data for Llama-3, and a $0.4\times$ effectiveness for Zephyr. To explain the phenomenon, we propose the alignment stage assumption, which divides the alignment process into two distinct stages: the preference injection stage, which benefits from diverse data, and the preference fine-tuning stage, which favors high-quality data. Through theoretical and empirical analysis, we characterize these stages and propose an effective algorithm to identify the boundaries between them. We perform experiments on $5$ models~(Llama, Zephyr, Phi-2, Qwen, Pythia) and $2$ alignment methods~(DPO, SLiC-HF) to show the generalizability of alignment stage assumption and the effectiveness of the boundary measurement algorithm.
arXiv:2510.02091v4 Announce Type: replace
Abstract: Recent studies suggest that the deeper layers of Large Language Models (LLMs) contribute little to representation learning and can often be removed without significant performance loss. However, such claims are typically drawn from narrow evaluations and may overlook important aspects of model behavior. In this work, we present a systematic study of depth utilization across diverse dimensions, including evaluation protocols, task categories, a
arXiv:2510.02091v4 Announce Type: replace
Abstract: Recent studies suggest that the deeper layers of Large Language Models (LLMs) contribute little to representation learning and can often be removed without significant performance loss. However, such claims are typically drawn from narrow evaluations and may overlook important aspects of model behavior. In this work, we present a systematic study of depth utilization across diverse dimensions, including evaluation protocols, task categories, and model architectures. Our analysis confirms that very deep layers are generally less effective than earlier ones, but their contributions vary substantially with the evaluation setting. Under likelihood-based metrics without generation, pruning most layers preserves performance, with only the initial few being critical. By contrast, generation-based evaluation uncovers indispensable roles for middle and deeper layers in enabling reasoning and maintaining long-range coherence. We further find that knowledge and retrieval are concentrated in shallow components, whereas reasoning accuracy relies heavily on deeper layers -- yet can be reshaped through distillation. These results highlight that depth usage in LLMs is highly heterogeneous and context-dependent, underscoring the need for task-, metric-, and model-aware perspectives in both interpreting and compressing large models.
arXiv:2601.12542v2 Announce Type: replace
Abstract: Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding real-time researcher guidance. This paper introduces Deep Research, a multi-agent system enabling interactive scientific investigation with turnaround times measured in minutes. The architecture comprises specializ
arXiv:2601.12542v2 Announce Type: replace
Abstract: Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding real-time researcher guidance. This paper introduces Deep Research, a multi-agent system enabling interactive scientific investigation with turnaround times measured in minutes. The architecture comprises specialized agents for planning, data analysis, literature search, and novelty detection, unified through a persistent world state that maintains context across iterative research cycles. Two operational modes support different workflows: semi-autonomous mode with selective human checkpoints, and fully autonomous mode for extended investigations. Evaluation on the BixBench computational biology benchmark demonstrated state-of-the-art performance, achieving 48.8% accuracy on open response and 64.4% on multiple-choice evaluation, exceeding existing baselines by 14 to 26 percentage points. Analysis of architectural constraints, including open access literature limitations and challenges inherent to automated novelty assessment, informs practical deployment considerations for AI-assisted scientific workflows.
arXiv:2304.13894v2 Announce Type: replace-cross
Abstract: The proliferation of the Internet of Things (IoT) has introduced a massive influx of devices into the market, bringing with them significant security vulnerabilities. In this diverse ecosystem, robust IoT device identification is a critical preventive measure for network security and vulnerability management. This study proposes a deep learning-based method to identify IoT devices using the Aalto dataset. We employ Convolutional Neural N
arXiv:2304.13894v2 Announce Type: replace-cross
Abstract: The proliferation of the Internet of Things (IoT) has introduced a massive influx of devices into the market, bringing with them significant security vulnerabilities. In this diverse ecosystem, robust IoT device identification is a critical preventive measure for network security and vulnerability management. This study proposes a deep learning-based method to identify IoT devices using the Aalto dataset. We employ Convolutional Neural Networks (CNN) to classify devices by converting network packet payloads into pseudo-images. Furthermore, we compare the performance of this payload-based approach against a feature-based fingerprinting method. Our results indicate that while the fingerprint-based method is significantly faster (approximately 10x), the payload-based image classification achieves comparable accuracy, highlighting the trade-offs between computational efficiency and data granularity in IoT security.
arXiv:2406.16821v2 Announce Type: replace-cross
Abstract: Structure-based drug design (SBDD) aims to generate ligands that bind strongly and specifically to target protein pockets. Recent diffusion models have advanced SBDD by capturing the distributions of atomic positions and types, yet they often underemphasize binding affinity control during generation. To address this limitation, we introduce \textbf{\textnormal{\textbf{BADGER}}}, a general \textbf{binding-affinity guidance framework for d
arXiv:2406.16821v2 Announce Type: replace-cross
Abstract: Structure-based drug design (SBDD) aims to generate ligands that bind strongly and specifically to target protein pockets. Recent diffusion models have advanced SBDD by capturing the distributions of atomic positions and types, yet they often underemphasize binding affinity control during generation. To address this limitation, we introduce \textbf{\textnormal{\textbf{BADGER}}}, a general \textbf{binding-affinity guidance framework for diffusion models in SBDD}. \textnormal{\textbf{BADGER} }incorporates binding affinity awareness through two complementary strategies: (1) \textit{classifier guidance}, which applies gradient-based affinity signals during sampling in a plug-and-play fashion, and (2) \textit{classifier-free guidance}, which integrates affinity conditioning directly into diffusion model training. Together, these approaches enable controllable ligand generation guided by binding affinity. \textnormal{\textbf{BADGER} } can be added to any diffusion model and achieves up to a \textbf{60\% improvement in ligand--protein binding affinity} of sampled molecules over prior methods. Furthermore, we extend the framework to \textbf{multi-constraint diffusion guidance}, jointly optimizing for binding affinity, drug-likeness (QED), and synthetic accessibility (SA) to design realistic and synthesizable drug candidates.
arXiv:2601.12946v3 Announce Type: replace-cross
Abstract: Generative artificial intelligence (AI) is rapidly populating medical records with synthetic content, creating a feedback loop where future models are increasingly at risk of training on uncurated AI-generated data. However, the clinical consequences of this AI-generated data contamination remain unexplored. Here, we show that in the absence of mandatory human verification, this self-referential cycle drives a rapid erosion of pathologic
arXiv:2601.12946v3 Announce Type: replace-cross
Abstract: Generative artificial intelligence (AI) is rapidly populating medical records with synthetic content, creating a feedback loop where future models are increasingly at risk of training on uncurated AI-generated data. However, the clinical consequences of this AI-generated data contamination remain unexplored. Here, we show that in the absence of mandatory human verification, this self-referential cycle drives a rapid erosion of pathological variability and diagnostic reliability. By analysing more than 800,000 synthetic data points across clinical text generation, vision-language reporting, and medical image synthesis, we find that models progressively converge toward generic phenotypes regardless of the model architecture. Specifically, rare but critical findings, including pneumothorax and effusions, vanish from the synthetic content generated by AI models, while demographic representations skew heavily toward middle-aged male phenotypes. Crucially, this degradation is masked by false diagnostic confidence; models continue to issue reassuring reports while failing to detect life-threatening pathology, with false reassurance rates tripling to 40%. Blinded physician evaluation confirms that this decoupling of confidence and accuracy renders AI-generated documentation clinically useless after just two generations. We systematically evaluate three mitigation strategies, finding that while synthetic volume scaling fails to prevent collapse, mixing real data with quality-aware filtering effectively preserves diversity. Ultimately, our results suggest that without policy-mandated human oversight, the deployment of generative AI threatens to degrade the very healthcare data ecosystems it relies upon.
Background: Ambulatory oxygen therapy is prescribed for patients with chronic lung diseases who experience exertional hypoxemia. However, available devices may not adequately meet user requirements, and their performance characteristics are heterogeneous. Objective: This study aims to identify devices available for delivery of ambulatory oxygen therapy, the technologies that they use to generate oxygen, the performance characteristics of each device, and the development status. Methods: We used
Background: Ambulatory oxygen therapy is prescribed for patients with chronic lung diseases who experience exertional hypoxemia. However, available devices may not adequately meet user requirements, and their performance characteristics are heterogeneous. Objective: This study aims to identify devices available for delivery of ambulatory oxygen therapy, the technologies that they use to generate oxygen, the performance characteristics of each device, and the development status. Methods: We used medical and engineering databases to identify peer-reviewed papers (eg, MEDLINE, IEEE). Gray literature was used to identify additional descriptions of ambulatory oxygen devices in military medicine, space exploration, or patents. The last search was conducted in September 2025. Documents that described a device that can deliver oxygen in an ambulatory context (defined as weighing less than 10 kg) and were written in English were included. Search results were screened for inclusion by 2 independent reviewers. Data were synthesized by descriptively mapping the performance of each product, the technology used, and the development status of emerging technologies. Results: From 9702 records identified, a total of 166 met eligibility criteria (106 scientific publications and 60 gray literature). We identified 33 portable oxygen concentrators (POCs; 29 commercially available), 10 oxygen cylinders, and 6 portable liquid oxygen (LOX) devices. The POC products showed a trade-off between portability and oxygen delivery capacity (maximum flow rate ranging from 2.0 to 6.0 L/min; device weight ranging from 1.0 to 9.1 kg). Pressure swing adsorption with zeolite was the most common oxygen generation technology in POCs on the market. The mean maximum continuous operating time of POCs was 3.8 hours. Two prototype POCs (maximum flow rate of 4-6 L/min and device weight of 8-9 kg) were developed for space exploration using modified adsorbents. LOX devices were the lightest and had the longest continuous operating time. Innovations in delivery included the downsizing of a POC by using nanozeolite as an adsorbent and pulse oximeter oxygen saturation (SpO2)–targeted automatic titration of oxygen delivery based on the user’s SpO2. Conclusions: This scoping review is the first study to integrate medical, engineering, and gray literature on ambulatory oxygen devices and their development. Although prior literature has narratively explained the products and technologies, no previous research has systematically investigated them. This review showed that POCs available to consumers may not meet the needs of patients in terms of flow rate, portability, and operating time. LOX devices offered superior performance but are limited by high costs. Limitations of this review include the difficulty of comparing product performance across oxygen delivery settings and that the records were largely obtained from English-language sources. Innovation in ambulatory oxygen technology has been limited over the past decade, highlighting urgent need for research and development of new lightweight devices with higher oxygen delivery. Clinical Trial: OSF Registries 10.17605/OSF.IO/QS7FX; https://osf.io/qs7fx
Discov Oncol. 2026 Jan 27. doi: 10.1007/s12672-026-04515-1. Online ahead of print.ABSTRACTBACKGROUND: Pancreatic neuroendocrine tumor (pNET) is a heterogeneous tumor originating from pancreatic endocrine cells. Emerging evidence suggests that oxidative stress plays a crucial role in pNET pathogenesis, yet the precise molecular mechanisms and their interplay with the tumor microenvironment remain unclear. This study aims to systematically elucidate how oxidative stress-related pathways drive pNET
Discov Oncol. 2026 Jan 27. doi: 10.1007/s12672-026-04515-1. Online ahead of print.
ABSTRACT
BACKGROUND: Pancreatic neuroendocrine tumor (pNET) is a heterogeneous tumor originating from pancreatic endocrine cells. Emerging evidence suggests that oxidative stress plays a crucial role in pNET pathogenesis, yet the precise molecular mechanisms and their interplay with the tumor microenvironment remain unclear. This study aims to systematically elucidate how oxidative stress-related pathways drive pNET progression through an integrated multi-omics approach.
METHODS: We designed a three-tier analytical strategy to address interconnected scientific questions. First, to identify which oxidative stress-related genes are dysregulated in pNET, we performed differential expression analysis and weighted gene co-expression network analysis (WGCNA) on the GSE73338 dataset (63 pNET samples, 5 controls), intersecting the. results with oxidative stress gene sets to obtain 71 candidate genes. Second, to understand the functional implications of these genes, we conducted GO/KEGG enrichment analysis and constructed protein-protein interaction (PPI) networks, from which we identified BCL2L1 and PHGDH as key hub genes using three independent algorithms. We then assessed their diagnostic value through ROC analysis and built a prognostic nomogram model. Third, to explore how these key genes influence the tumor microenvironment, we performed immune infiltration analysis using CIBERSORTx. Fourth, to reveal upstream regulatory mechanisms, we constructed ceRNA networks and predicted transcription factors. Fifth, to identify potential therapeutic interventions, we conducted drug prediction and molecular docking analyses. Finally, to validate our findings at cellular resolution and understand cellular heterogeneity, we analyzed single-cell RNA sequencing data from GSE256136 (20 samples), identifying cell types, quantifying cell-cell communications, and confirming key gene expression patterns across different cell populations.
RESULTS: Our systematic analysis revealed that oxidative stress-related genes in pNET were significantly enriched in the PI3K-Akt signaling pathway, cysteine and methionine metabolism, and HIF-1 signaling pathway. BCL2L1 and PHGDH emerged as central regulators with excellent diagnostic performance (AUC > 0.9). Immune infiltration analysis demonstrated significant alterations in activated dendritic cells, memory B cells, and resting NK cells, which correlated strongly with BCL2L1 and PHGDH expression, suggesting these genes link oxidative stress to immune dysfunction. The ceRNA network centered on KCNQ1OT1 and hsa-miR-15a-5p revealed multi-layered transcriptional and post-transcriptional regulation. Drug prediction identified sertindole and cabozantinib as promising therapeutic candidates. Single-cell analysis identified 11 cell types and confirmed that endocrine cells are the primary site of BCL2L1 and PHGDH dysregulation, with extensive crosstalk between endocrine cells and T cells potentially mediating immune evasion.
CONCLUSION: Through integrated multi-omics analysis, we established that oxidative stress pathways may drive pNET progression through a coordinated mechanism involving metabolic reprogramming (via BCL2L1 and PHGDH downregulation), immune microenvironment remodeling (through altered dendritic cell and NK cell function), and complex regulatory networks. BCL2L1 and PHGDH represent potential diagnostic biomarkers and candidate therapeutic targets that require experimental validation, providing new directions for precision medicine in pNET.
Login
(MedPage Today) -- Detection of pancreatic cancer, including early-stage disease, improved substantially with a panel of four cancer-associated proteins versus a single protein, a retrospective comparison study showed.
Overall accuracy for any...
