❌

Reading view

↗️

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

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

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

ABSTRACT

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

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

  •  
  • ↗️
↗️

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

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

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

ABSTRACT

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

PMID:41717787 | DOI:10.1080/14796694.2026.2631302

  •  
  • ↗️
↗️

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

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hui Min Wong · Philip Heesen · Pascal Janetzky · Martin Bendszus · Stefan Feuerriegel
arXiv:2602.17308v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for diagnostic tasks in medicine. In clinical practice, the correct diagnosis can rarely be immediately inferred from the initial patient presentation alone. Rather, reaching a diagnosis often involves systematic history taking, during which clinicians reason over multiple potential conditions through iterative questioning to resolve uncertainty. This process requires considering differential diagnoses and actively excluding emergencies that demand immediate intervention. Yet, the ability of medical LLMs to generate informative follow-up questions and thus reason over differential diagnoses remains underexplored. Here, we introduce MedClarify, an AI agent for information-seeking that can generate follow-up questions for iterative reasoning to support diagnostic decision-making. Specifically, MedClarify computes a list of candidate diagnoses analogous to a differential diagnosis, and then proactively generates follow-up questions aimed at reducing diagnostic uncertainty. By selecting the question with the highest expected information gain, MedClarify enables targeted, uncertainty-aware reasoning to improve diagnostic performance. In our experiments, we first demonstrate the limitations of current LLMs in medical reasoning, which often yield multiple, similarly likely diagnoses, especially when patient cases are incomplete or relevant information for diagnosis is missing. We then show that our information-theoretic reasoning approach can generate effective follow-up questioning and thereby reduces diagnostic errors by ~27 percentage points (p.p.) compared to a standard single-shot LLM baseline. Altogether, MedClarify offers a path to improve medical LLMs through agentic information-seeking and to thus promote effective dialogues with medical LLMs that reflect the iterative and uncertain nature of real-world clinical reasoning.
  •  
  • ↗️
↗️

Intent Laundering: AI Safety Datasets Are Not What They Seem

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

Be Wary of Your Time Series Preprocessing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sofiane Ennadir · Tianze Wang · Oleg Smirnov · Sahar Asadi · Lele Cao
arXiv:2602.17568v1 Announce Type: cross Abstract: Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspective. In this work, we present the first formal analysis of how different normalization strategies, specifically instance-based and global scaling, impact the expressivity of Transformer-based architectures for time series representation learning. We propose a novel expressivity framework tailored to time series, which quantifies a model's ability to distinguish between similar and dissimilar inputs in the representation space. Using this framework, we derive theoretical bounds for two widely used normalization methods: Standard and Min-Max scaling. Our analysis reveals that the choice of normalization strategy can significantly influence the model's representational capacity, depending on the task and data characteristics. We complement our theory with empirical validation on classification and forecasting benchmarks using multiple Transformer-based models. Our results show that no single normalization method consistently outperforms others, and in some cases, omitting normalization entirely leads to superior performance. These findings highlight the critical role of preprocessing in time series learning and motivate the need for more principled normalization strategies tailored to specific tasks and datasets.
  •  
  • ↗️
↗️

STAT+: AI-guided cancer treatments, telehealth usage, and other health tech news

✇STAT
By: Mario Aguilar

You’re reading the web edition of STAT’s Health Tech newsletter, our guide to how technology is transforming the life sciences. Sign up to get it delivered in your inbox every Tuesday and Thursday.

Good morning health tech readers!

Please join me in congratulating my colleagues as STAT, who have been honored with a fourth Polk Award for our coverage of the Trump administration’s impacts on the federal health department and American science. The award recognizes the whole newsroom and in particular the work of Lizzy Lawrence covering a dramatic year of changes at the Food and Drug Administration. 

Continue to STAT+ to read the full story…

© Adobe

  •  
  • ↗️
↗️

Live biotherapeutics in cancer therapy

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Rasmita Mishra · Sreelakshmi S Kumar · T Sayamsmruti Panda · Soumendu Mahapatra · Punit Prasad

Prog Mol Biol Transl Sci. 2026;220:361-403. doi: 10.1016/bs.pmbts.2026.01.002. Epub 2026 Jan 23.

ABSTRACT

Cancer poses a global challenge in diagnostics and therapeutics. Treatments like chemotherapy, radiotherapy, surgery, and immunotherapy have significantly decreased the fatality rate, but drug resistance, therapy side effects, and relapse remain as major concerns. Live biotherapeutics are microorganisms that can be developed as therapeutic agents to modulate cancer pathophysiology and aid in disease management. Live biotherapeutic products (LBPs) have the potential to suppress tumour growth, enhance the effectiveness of conventional therapies, and reduce treatment-related side effects. Dysbiosis in the gut and cancer-specific tissues is linked to cancers of the colon, stomach, pancreas, and liver. Live biotherapeutics aim either to re-establish microbial balance or to employ microbes directly as anticancer tools. Both native and engineered LBPs (bacteria and viruses) represent promising interventions that may form part of next-generation cancer treatment strategies. Their clinical application draws on the integration of microbiology, immunology, synthetic biology, and oncology. LBPs can be used to target cancer cells by delivering antitumour payloads such as immune modulators, toxins, exposing cancer antigens, and molecules for targeted killing. LBPs offer advantages such as reduced systemic toxicity, overcoming drug resistance, and synergy with chemo-, radio-, and immunotherapies. Despite challenges in safety, manufacturing, regulation, and personalization, advances in synthetic biology and omics are enabling precision approaches. Future innovations such as bacteriobots, biocontainment systems, and patient-specific microbiome integration highlight their potential as next-generation cancer therapeutics.

PMID:41714084 | DOI:10.1016/bs.pmbts.2026.01.002

  •  
  • ↗️
↗️

Hunt Globally: Deep Research AI Agents for Drug Asset Scouting in Investing, Business Development, and Search & Evaluation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Alisa Vinogradova · Vlad Vinogradov · Luba Greenwood · Ilya Yasny · Dmitry Kobyzev · Shoman Kasbekar · Kong Nguyen · Dmitrii Radkevich · Roman Doronin · Andrey Doronichev
arXiv:2602.15019v1 Announce Type: new Abstract: Bio-pharmaceutical innovation has shifted: many new drug assets now originate outside the United States and are disclosed primarily via regional, non-English channels. Recent data suggests >85% of patent filings originate outside the U.S., with China accounting for nearly half of the global total; a growing share of scholarly output is also non-U.S. Industry estimates put China at ~30% of global drug development, spanning 1,200+ novel candidates. In this high-stakes environment, failing to surface "under-the-radar" assets creates multi-billion-dollar risk for investors and business development teams, making asset scouting a coverage-critical competition where speed and completeness drive value. Yet today's Deep Research AI agents still lag human experts in achieving high-recall discovery across heterogeneous, multilingual sources without hallucinations. We propose a benchmarking methodology for drug asset scouting and a tuned, tree-based self-learning Bioptic Agent aimed at complete, non-hallucinated scouting. We construct a challenging completeness benchmark using a multilingual multi-agent pipeline: complex user queries paired with ground-truth assets that are largely outside U.S.-centric radar. To reflect real deal complexity, we collected screening queries from expert investors, BD, and VC professionals and used them as priors to conditionally generate benchmark queries. For grading, we use LLM-as-judge evaluation calibrated to expert opinions. We compare Bioptic Agent against Claude Opus 4.6, OpenAI GPT-5.2 Pro, Perplexity Deep Research, Gemini 3 Pro + Deep Research, and Exa Websets. Bioptic Agent achieves 79.7% F1 versus 56.2% (Claude Opus 4.6), 50.6% (Gemini 3 Pro + Deep Research), 46.6% (GPT-5.2 Pro), 44.2% (Perplexity Deep Research), and 26.9% (Exa Websets). Performance improves steeply with additional compute, supporting the view that more compute yields better results.
  •  
  • ↗️
↗️

MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenjie Li · Yujie Zhang · Haoran Sun · Xingqi He · Hongcheng Gao · Chenglong Ma · Ming Hu · Guankun Wang · Shiyi Yao · Renhao Yang · Hongliang Ren · Lei Wang · Junjun He · Yankai Jiang
arXiv:2602.13332v1 Announce Type: cross Abstract: Long-form clinical videos are central to visual evidence-based decision-making, with growing importance for applications such as surgical robotics and related settings. However, current multimodal large language models typically process videos with passive sampling or weakly grounded inspection, which limits their ability to iteratively locate, verify, and justify predictions with temporally targeted evidence. To close this gap, we propose MedScope, a tool-using clinical video reasoning model that performs coarse-to-fine evidence seeking over long-form procedures. By interleaving intermediate reasoning with targeted tool calls and verification on retrieved observations, MedScope produces more accurate and trustworthy predictions that are explicitly grounded in temporally localized visual evidence. To address the lack of high-fidelity supervision, we build ClinVideoSuite, an evidence-centric, fine-grained clinical video suite. We then optimize MedScope with Grounding-Aware Group Relative Policy Optimization (GA-GRPO), which directly reinforces tool use with grounding-aligned rewards and evidence-weighted advantages. On full and fine-grained video understanding benchmarks, MedScope achieves state-of-the-art performance in both in-domain and out-of-domain evaluations. Our approach illuminates a path toward medical AI agents that can genuinely "think with videos" through tool-integrated reasoning. We will release our code, models, and data.
  •  
  • ↗️
↗️

Randomized-controlled trial of skills-based vr vs. distraction vr vs. sham VR for chronic low back pain

✇npj Digital Medicine
By: Brennan M. R. Spiegel · Samuel A. Eberlein · Susan Persky · Mariko L. Ishimori · Swamy Venuturupalli · Joseph Tu · Fadi Alhatem · Mary A. Vijjeswarapu · Zoe Krut · Tom Norris · So Yung Choi · Mourad Tighiouart · Lindsey Ross · Mark Vrahas · Omer Liran · Itai Danovitch · Tinh Vuong · Joshua Fouladian

npj Digital Medicine, Published online: 16 February 2026; doi:10.1038/s41746-026-02437-4

Randomized-controlled trial of skills-based vr vs. distraction vr vs. sham VR for chronic low back pain
  •  
  • ↗️
↗️

Rare, Yet Targetable: New Perspectives on Ampullary Carcinomas

✇(Multiomics OR Omics) AND (Pancreatic)
By: James Gutmans · Alex Friedlaender · Hiba Mechahougui

Int J Mol Sci. 2026 Feb 6;27(3):1597. doi: 10.3390/ijms27031597.

ABSTRACT

Ampullary carcinoma (AC) is a rare gastrointestinal malignancy with dual intestinal and pancreatobiliary differentiation, complicating diagnosis, staging, and treatment. This review synthesizes current epidemiology, pathology, and multi-omic data to outline a pragmatic care pathway: lineage-first at presentation, mutation-fast at progression. Histology remains the primary classifier: the intestinal subtype generally aligns with colorectal regimens, whereas pancreatobiliary and mixed subtypes favor pancreaticobiliary therapy. In selected fit patients, modified FOLFIRINOX may address mixed phenotypes. Next-generation sequencing adds precision by identifying therapeutically relevant alterations, including ERBB2/HER2 amplifications, MSI-high/dMMR, BRAF V600E, and rare NTRK or RET fusions, while KRAS mutations are enriched in pancreatobiliary tumors. We recommend early application of a rapid-core panel (KRAS/BRAF, MSI/dMMR, ERBB2/HER2, RNA-based fusions) to capture high-impact targets, followed by comprehensive profiling at first progression. Liquid biopsy, plasma circulating tumor DNA (ctDNA), or bile-derived DNA may complement tissue and help identify the dominant lineage. Research priorities include ampulla-enriched umbrella trials, explicit AC subcohorts in tissue-agnostic studies, and ctDNA-informed endpoints. This lineage-first, mutation-fast paradigm supports precision care and evidence generation in AC.

PMID:41684016 | PMC:PMC12897727 | DOI:10.3390/ijms27031597

  •  
  • ↗️
↗️

OpenAI Scales Single Primary Postgresql to Millions of Queries per Second for ChatGPT

✇InfoQ
By: Leela Kumili

OpenAI described how it scaled PostgreSQL to support ChatGPT and its API platform, handling millions of queries per second for hundreds of millions of users. By running a single-primary PostgreSQL deployment on Azure with nearly 50 read replicas, optimizing query patterns, and offloading write-heavy workloads to sharded systems, OpenAI maintained low-latency reads while managing write pressure.

By Leela Kumili
  •  
  • ↗️
↗️

STAT+: Researchers take another look at Apple’s hypertension feature

✇STAT
By: Mario Aguilar

You’re reading the web edition of STAT’s Health Tech newsletter, our guide to how technology is transforming the life sciences. Sign up to get it delivered in your inbox every Tuesday and Thursday.

Good morning health tech readers!

Today, we’ve got a ton of updates including news about venture capital funding, telehealth policy, the government’s progress on information blocking, and research into the accuracy of Apple’s new hypertension feature.

Continue to STAT+ to read the full story…

© Business Wire via AP

  •  
  • ↗️
❌