Normal view
-
cs.AI, q-bio.NC updates on arXiv.org
-
Morality in AI. A plea to embed morality in LLM architectures and frameworks
arXiv:2511.20689v1 Announce Type: new Abstract: Large language models (LLMs) increasingly mediate human decision-making and behaviour. Ensuring LLM processing of moral meaning therefore has become a critical challenge. Current approaches rely predominantly on bottom-up methods such as fine-tuning and reinforcement learning from human feedback. We propose a fundamentally different approach: embedding moral meaning processing directly into the architectural mechanisms and frameworks of transforme
-
cs.AI, q-bio.NC updates on arXiv.org
-
From Prediction to Foresight: The Role of AI in Designing Responsible Futures
arXiv:2511.21570v1 Announce Type: new Abstract: In an era marked by rapid technological advancements and complex global challenges, responsible foresight has emerged as an essential framework for policymakers aiming to navigate future uncertainties and shape the future. Responsible foresight entails the ethical anticipation of emerging opportunities and risks, with a focus on fostering proactive, sustainable, and accountable future design. This paper coins the term "responsible computational fo
From Prediction to Foresight: The Role of AI in Designing Responsible Futures
-
cs.AI, q-bio.NC updates on arXiv.org
-
Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes
arXiv:2511.20680v1 Announce Type: cross Abstract: Despite high performance on clinical benchmarks, large language models may reach correct conclusions through faulty reasoning, a failure mode with safety implications for oncology decision support that is not captured by accuracy-based evaluation. In this two-cohort retrospective study, we developed a hierarchical taxonomy of reasoning errors from GPT-4 chain-of-thought responses to real oncology notes and tested its clinical relevance. Using br
Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes
-
cs.AI, q-bio.NC updates on arXiv.org
-
How Do Companies Manage the Environmental Sustainability of AI? An Interview Study About Green AI Efforts and Regulations
arXiv:2505.07317v2 Announce Type: replace-cross Abstract: With the ever-growing adoption of artificial intelligence (AI), AI-based software and its negative impact on the environment are no longer negligible, and studying and mitigating this impact has become a critical area of research. However, it is currently unclear which role environmental sustainability plays during AI adoption in industry and how AI regulations influence Green AI practices and decision-making in industry. We therefore ai
How Do Companies Manage the Environmental Sustainability of AI? An Interview Study About Green AI Efforts and Regulations
-
cs.AI, q-bio.NC updates on arXiv.org
-
Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
arXiv:2506.14652v2 Announce Type: replace-cross Abstract: In AI research and practice, rigor remains largely understood in terms of methodological rigor -- such as whether mathematical, statistical, or computational methods are correctly applied. We argue that this narrow conception of rigor has contributed to the concerns raised by the responsible AI community, including overblown claims about the capabilities of AI systems. Our position is that a broader conception of what rigorous AI researc
Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
-
(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
-
Smart spatial omics (S2-omics) optimizes region of interest selection to capture molecular heterogeneity in diverse tissues
Nat Cell Biol. 2025 Nov 26. doi: 10.1038/s41556-025-01811-w. Online ahead of print.ABSTRACTSpatial omics technologies have transformed biomedical research by enabling high-resolution molecular profiling while preserving the native tissue architecture. These advances provide unprecedented insights into tissue structure and function. However, the high cost and time-intensive nature of spatial omics experiments necessitate careful experimental design, particularly in selecting regions of interest (
Smart spatial omics (S2-omics) optimizes region of interest selection to capture molecular heterogeneity in diverse tissues
Nat Cell Biol. 2025 Nov 26. doi: 10.1038/s41556-025-01811-w. Online ahead of print.
ABSTRACT
Spatial omics technologies have transformed biomedical research by enabling high-resolution molecular profiling while preserving the native tissue architecture. These advances provide unprecedented insights into tissue structure and function. However, the high cost and time-intensive nature of spatial omics experiments necessitate careful experimental design, particularly in selecting regions of interest (ROIs) from large tissue sections. Currently, ROI selection is performed manually, which introduces subjectivity, inconsistency and a lack of reproducibility. Previous studies have shown strong correlations between spatial molecular patterns and histological features, suggesting that readily available and cost-effective histology images can be leveraged to guide spatial omics experiments. Here we present Smart Spatial omics (S2-omics), an end-to-end workflow that automatically selects ROIs from histology images with the goal of maximizing molecular information content in the ROIs. Through comprehensive evaluations across multiple spatial omics platforms and tissue types, we demonstrate that S2-omics enables systematic and reproducible ROI selection and enhances the robustness and impact of downstream biological discovery.
PMID:41298871 | DOI:10.1038/s41556-025-01811-w
-
npj Digital Medicine
-
Information content as a health system screening tool for rare diseases
npj Digital Medicine, Published online: 25 November 2025; doi:10.1038/s41746-025-02096-xInformation content as a health system screening tool for rare diseases
Information content as a health system screening tool for rare diseases
npj Digital Medicine, Published online: 25 November 2025; doi:10.1038/s41746-025-02096-x
Information content as a health system screening tool for rare diseases-
cs.AI, q-bio.NC updates on arXiv.org
-
Human Experts' Evaluation of Generative AI for Contextualizing STEAM Education in the Global South
arXiv:2511.19482v2 Announce Type: replace-cross Abstract: This study investigates how human experts evaluate the capacity of Generative AI (GenAI) to contextualize STEAM education in the Global South, with a focus on Ghana. Using a convergent mixed-methods design, four STEAM specialists assessed GenAI-generated lesson plans created with a customized Culturally Responsive Lesson Planner (CRLP) and compared them to standardized lesson plans from the Ghana National Council for Curriculum and Asses
Human Experts' Evaluation of Generative AI for Contextualizing STEAM Education in the Global South
-
Omics In Lung
-
Rewiring the transcriptome: diagnostic and therapeutic implications of alternative splicing in solid cancers
Mol Biol Rep. 2025 Nov 26;53(1):125. doi: 10.1007/s11033-025-11302-8.ABSTRACTAlternative splicing (AS) is a fundamental mechanism of pre-mRNA processing that allows one gene to create numerous transcript and protein isoforms, thereby substantially increasing the diversity of the human proteome. AS occurs co-transcriptionally (when the nascent pre-mRNA is still being generated from chromatin) or post-transcriptionally after the release of the transcript, and both modalities contribute to the cont
Rewiring the transcriptome: diagnostic and therapeutic implications of alternative splicing in solid cancers
Mol Biol Rep. 2025 Nov 26;53(1):125. doi: 10.1007/s11033-025-11302-8.
ABSTRACT
Alternative splicing (AS) is a fundamental mechanism of pre-mRNA processing that allows one gene to create numerous transcript and protein isoforms, thereby substantially increasing the diversity of the human proteome. AS occurs co-transcriptionally (when the nascent pre-mRNA is still being generated from chromatin) or post-transcriptionally after the release of the transcript, and both modalities contribute to the control of isoform expression in a tissue- and context-dependent manner. Under normal physiological conditions, AS is tightly regulated in a tissue- and context-dependent manner. However, in malignancies, this regulatory precision is often lost, leading to extensive splicing aberrations that promote oncogenic transformation, tumor progression, and resistance to therapy. Solid tumors, in particular, exhibit a high frequency of aberrant splicing events, which frequently give rise to oncogenic isoforms or the suppression of tumor-inhibitory variants. These disruptions contribute to key cancer hallmarks such as uncontrolled proliferation, resistance to apoptosis, neoangiogenesis, and epithelial-mesenchymal transition (EMT). Recent findings underscore the clinical relevance of splicing-derived molecular signatures. Distinct splicing profiles have been correlated with diagnostic, prognostic, and predictive outcomes in multiple solid tumors-including breast, prostate, lung, colorectal, and central nervous system malignancies. Notably, tumor-specific alternative splice variants often generate unique exon-exon junctions (neojunctions) that encode immunogenic peptides, representing a promising class of neoantigens for immunotherapy. These neoantigens are fueling the development of personalized treatment modalities such as splicing-directed vaccines and T cell-based therapies. The advent of advanced technologies-including long-read sequencing, single-cell transcriptomics, and proteogenomics-has enabled high-resolution mapping of cancer-specific splice variants and enhanced our understanding of their functional relevance. Therapeutic strategies targeting aberrant splicing are also advancing, with splice-switching oligonucleotides, small-molecule modulators, and CRISPR-based RNA-editing platforms emerging as innovative approaches. Despite these advances, challenges such as splicing heterogeneity, off-target effects, and incomplete protein-level validation continue to hinder clinical translation. This review offers an integrated overview of the molecular drivers and clinical implications of alternative splicing in cancer. It emphasizes the potential of AS-based diagnostics and therapeutics within precision oncology and highlights the importance of multi-omic integration and clinical validation to fully harness the therapeutic opportunities of splicing dysregulation.
PMID:41296088 | DOI:10.1007/s11033-025-11302-8
-
(Multiomics OR Omics) AND (Pancreatic)
-
Molecular pathology of intraductal papillary mucinous neoplasms of the pancreas: current understanding and perspectives on malignant progression
J Gastroenterol. 2025 Nov 26. doi: 10.1007/s00535-025-02328-7. Online ahead of print.ABSTRACTIntraductal papillary mucinous neoplasms (IPMNs) of the pancreas are bona fide cystic precursor lesions to pancreatic ductal adenocarcinoma (PDAC), which is the cancer type with the most dismal prognosis. Since IPMNs are detectable by imaging, they offer a rare window of opportunity for early intervention for PDAC development. Despite their clinical visibility, the molecular pathogenesis of IPMNs remaine
Molecular pathology of intraductal papillary mucinous neoplasms of the pancreas: current understanding and perspectives on malignant progression
J Gastroenterol. 2025 Nov 26. doi: 10.1007/s00535-025-02328-7. Online ahead of print.
ABSTRACT
Intraductal papillary mucinous neoplasms (IPMNs) of the pancreas are bona fide cystic precursor lesions to pancreatic ductal adenocarcinoma (PDAC), which is the cancer type with the most dismal prognosis. Since IPMNs are detectable by imaging, they offer a rare window of opportunity for early intervention for PDAC development. Despite their clinical visibility, the molecular pathogenesis of IPMNs remained incompletely understood, and no effective non-surgical therapeutic strategies have been established to date. In the past few decades, however, substantial progress has been made in elucidating their molecular pathology. Next-generation sequencing technologies demonstrated the comprehensive genetic mutation profile of IPMNs in the early 2010s. Elucidation of these mutation profiles enabled the establishment of genetically engineered mouse models, successfully recapitulating the natural development of human IPMNs and their progression to invasive cancer. Rapid evolution of "omics" technologies in recent years has facilitated the application of mass spectrometry, single-cell sequencing and spatial transcriptomics to IPMNs, significantly advancing our understanding of their pathophysiology. These techniques elucidated the changes in transcriptome, proteome, metabolome, microbiome, and tumor microenvironment associated with IPMN development and progression. This review summarizes current insights into the molecular and cellular landscapes of IPMN tumorigenesis, with particular emphasis on the mechanisms driving malignant progression.
PMID:41296011 | DOI:10.1007/s00535-025-02328-7
Whatβs Next for Smart Implants in Health Care?
-
cs.AI, q-bio.NC updates on arXiv.org
-
Hybrid Neuro-Symbolic Models for Ethical AI in Risk-Sensitive Domains
arXiv:2511.17644v1 Announce Type: new Abstract: Artificial intelligence deployed in risk-sensitive domains such as healthcare, finance, and security must not only achieve predictive accuracy but also ensure transparency, ethical alignment, and compliance with regulatory expectations. Hybrid neuro symbolic models combine the pattern-recognition strengths of neural networks with the interpretability and logical rigor of symbolic reasoning, making them well-suited for these contexts. This paper su
Hybrid Neuro-Symbolic Models for Ethical AI in Risk-Sensitive Domains
-
cs.AI, q-bio.NC updates on arXiv.org
-
Leveraging Evidence-Guided LLMs to Enhance Trustworthy Depression Diagnosis
arXiv:2511.17947v1 Announce Type: new Abstract: Large language models (LLMs) show promise in automating clinical diagnosis, yet their non-transparent decision-making and limited alignment with diagnostic standards hinder trust and clinical adoption. We address this challenge by proposing a two-stage diagnostic framework that enhances transparency, trustworthiness, and reliability. First, we introduce Evidence-Guided Diagnostic Reasoning (EGDR), which guides LLMs to generate structured diagnosti
Leveraging Evidence-Guided LLMs to Enhance Trustworthy Depression Diagnosis
-
cs.AI, q-bio.NC updates on arXiv.org
-
KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs
arXiv:2511.18364v1 Announce Type: new Abstract: Building high-quality knowledge graphs (KGs) from diverse sources requires combining methods for information extraction, data transformation, ontology mapping, entity matching, and data fusion. Numerous methods and tools exist for each of these tasks, but support for combining them into reproducible and effective end-to-end pipelines is still lacking. We present a new framework, KGpipe for defining and executing integration pipelines that can comb
KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs
-
cs.AI, q-bio.NC updates on arXiv.org
-
Embedding Generative AI into Systems Analysis and Design Curriculum: Framework, Case Study, and Cross-Campus Empirical Evidence
arXiv:2511.17515v1 Announce Type: cross Abstract: Systems analysis students increasingly use Generative AI, yet current pedagogy lacks systematic approaches for teaching responsible AI orchestration that fosters critical thinking whilst meeting educational outcomes. Students risk accepting AI suggestions blindly or uncritically without assessing alignment with user needs or contextual appropriateness. SAGE (Structured AI-Guided Education) addresses this gap by embedding GenAI into curriculum de
Embedding Generative AI into Systems Analysis and Design Curriculum: Framework, Case Study, and Cross-Campus Empirical Evidence
-
cs.AI, q-bio.NC updates on arXiv.org
-
Explainable Deep Learning for Brain Tumor Classification: Comprehensive Benchmarking with Dual Interpretability and Lightweight Deployment
arXiv:2511.17655v1 Announce Type: cross Abstract: Our study provides a full deep learning system for automated classification of brain tumors from MRI images, includes six benchmarked architectures (five ImageNet-pre-trained models (VGG-16, Inception V3, ResNet-50, Inception-ResNet V2, Xception) and a custom built, compact CNN (1.31M params)). The study moves the needle forward in a number of ways, including (1) full standardization of assessment with respect to preprocessing, training sets/pro
Explainable Deep Learning for Brain Tumor Classification: Comprehensive Benchmarking with Dual Interpretability and Lightweight Deployment
-
cs.AI, q-bio.NC updates on arXiv.org
-
Predicting Healthcare Provider Engagement in SMS Campaigns
arXiv:2511.17658v1 Announce Type: cross Abstract: As digital communication grows in importance when connecting with healthcare providers, traditional behavioral and content message features are imbued with renewed significance. If one is to meaningfully connect with them, it is crucial to understand what drives them to engage and respond. In this study, the authors analyzed several million text messages sent through the Impiricus platform to learn which factors influenced whether or not a docto
Predicting Healthcare Provider Engagement in SMS Campaigns
-
cs.AI, q-bio.NC updates on arXiv.org
-
Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations
arXiv:2511.17828v1 Announce Type: cross Abstract: Foundation models hold promise for specialized medical imaging tasks, though their effectiveness in breast imaging remains underexplored. This study leverages BiomedCLIP as a foundation model to address challenges in model generalization. BiomedCLIP was adapted for automated BI-RADS breast density classification using multi-modality mammographic data (synthesized 2D images, digital mammography, and digital breast tomosynthesis). Using 96,995 ima
Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations
-
cs.AI, q-bio.NC updates on arXiv.org
-
Towards Automating Data Access Permissions in AI Agents
arXiv:2511.17959v1 Announce Type: cross Abstract: As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission models are inadequate for the automated agentic execution paradigm. We therefore propose automated permission management for AI agents. Our key idea is to conduct a user study to identify the factors influenci
Towards Automating Data Access Permissions in AI Agents
-
cs.AI, q-bio.NC updates on arXiv.org
-
Reinforcement Learning for Portfolio Optimization with a Financial Goal and Defined Time Horizons
arXiv:2511.18076v1 Announce Type: cross Abstract: This research proposes an enhancement to the innovative portfolio optimization approach using the G-Learning algorithm, combined with parametric optimization via the GIRL algorithm (G-learning approach to the setting of Inverse Reinforcement Learning) as presented by. The goal is to maximize portfolio value by a target date while minimizing the investor's periodic contributions. Our model operates in a highly volatile market with a well-diversif