Artificial Intelligence News and Research

Latest Artificial Intelligence News and Research

Multimodal AI improves prediction of PIK3CA mutations in breast cancer

Breast cancer is one of the most common malignancies worldwide, and mutations in the PI3K/AKT/mTOR (PAM) signaling pathway are prevalent in its development.

21 Apr 2026

Microbial "signatures" within the oral cavity and gut may aid in gastric cancer detection

A recent study published in Cell Reports Medicine has identified distinct microbial "signatures" within the oral cavity and gut that serve as robust biomarkers for the early detection of gastric cancer (GC).

20 Apr 2026

AI improves imaging pathology and treatment decisions in breast cancer

Breast cancer is the most common cancer among women, with over 2.3 million new cases diagnosed each year. Traditional diagnostic methods rely heavily on human judgment, which can lead to inconsistent outcomes.

20 Apr 2026

AI model predicts immunotherapy response in lung cancer patients

A biology-guided artificial intelligence model applied to routine pathology slides accurately predicted outcomes and response to immunotherapy in patients with metastatic non-small cell lung cancer (NSCLC), according to a study presented at the American Association for Cancer Research (AACR) Annual Meeting 2026, held April 17-22.

20 Apr 2026

Study reveals what people ask AI chatbots about health most often

Researchers analyzed more than 500,000 de-identified Microsoft Copilot health conversations from January 2026 and found that health information queries were most common, while nearly one in five conversations involved personal symptoms or condition-related concerns. They also found that personal health queries were more common on mobile and at night, while desktop use was more often tied to research, paperwork, and academic support, highlighting how people use AI differently across contexts.

20 Apr 2026

Antiretroviral therapy reduces biological aging in people living with HIV

A major study presented today at ESCMID Global 2026 has found that antiretroviral therapy (ART) reduces accelerated biological ageing in people with HIV (PWH) by nearly four years, a finding that could transform how clinicians monitor HIV treatment and long-term health outcomes.

20 Apr 2026

New geometric brain marker predicts successful surgery for iNPH patients

Researchers at the University of Eastern Finland have identified a new geometric marker of the brain ventricles that could help predict which patients with idiopathic normal pressure hydrocephalus (iNPH) will benefit from shunt surgery, according to a recent study published in Fluids and Barriers of the CNS.

20 Apr 2026

Global proteomics data sharing grows fast as ProteomeXchange scales up

ProteomeXchange’s 2026 update shows that global proteomics data sharing continues to accelerate, with more than 64,000 datasets submitted and nearly half added in just the last three years. The paper also highlights how standards, reuse tools, and AI-ready resources are helping make mass spectrometry proteomics data more findable, accessible, and reusable.

20 Apr 2026

Proteomics and AI bring earlier risk prediction into sharper focus

This review examines how high-throughput proteomics is expanding precision medicine by improving biomarker discovery, disease prediction, and drug development. It also shows how AI is helping researchers interpret complex proteomic data while highlighting major barriers such as standardization, validation, and clinical translation.

19 Apr 2026

Why clinical proteomics faces a mass spectrometry vs. high-throughput profiling dilemma

This Clinical Chemistry and Laboratory Medicine review examines a central challenge in precision medicine: whether medical laboratories should prioritize metrologically sound, proteoform-resolving protein quantification by mass spectrometry or adopt scalable, affinity-based proteome profiling platforms built for high-throughput discovery and machine learning. It concludes that while emerging proteomics technologies expand diagnostic possibilities, careful validation, standardization, and quality assurance will be essential, with a hybrid path likely offering the most practical way forward.

19 Apr 2026

Generative AI may help scientists connect the many layers of cancer

A Cell Perspective argues that generative AI models could help tackle cancer’s multiscale, multimodal complexity by complementing the Hallmarks of Cancer framework. It proposes that models capable of complex pattern recognition, multimodal fusion, and contextual reasoning could improve cancer detection, biological discovery, and precision oncology, while still requiring rigorous validation and human oversight.

19 Apr 2026

Your new therapist: Chatty, leaky, and hardly human

Vince Lahey of Carefree, Arizona, embraces chatbots. From Big Tech products to "shady" ones, they offer "someone that I could share more secrets with than my therapist."

17 Apr 2026

Key gene variants tied to developmental dysplasia of the hip and osteoarthritis

Developmental dysplasia of the hip (DDH) is a polygenetic disorder that increases the risk of hip osteoarthritis.

17 Apr 2026

AI-designed peptides break through the outer defenses of MRSA bacteria

A newly-designed AI-powered tool is effective in developing treatments to attack antibiotic-resistant bacteria by breaking down their outer defenses, according to new research from Houston Methodist.

17 Apr 2026

Fast answers and extra research drive AI healthcare use in America

One in four U.S. adults - the equivalent of over 66 million Americans - report having used artificial intelligence tools or chatbots for physical or mental healthcare information or advice, according to new research released today from the West Health-Gallup Center on Healthcare in America.

17 Apr 2026

Why AI is becoming a powerful tool in cancer drug discovery

This Perspective reviews how AI is moving drug discovery from long, costly experimental pipelines toward earlier clinical translation, with an AI-designed TNIK inhibitor trial serving as an important proof-of-feasibility reference point. It argues that precision oncology could benefit from AI-driven integration of multi-omics, federated learning, and adaptive trial design, but only if validation, fairness, interpretability, and regulatory alignment improve.

16 Apr 2026

Study finds popular AI chatbots often give problematic health advice

Researchers audited five popular public-facing AI chatbots across 250 health prompts and found that 49.6% of responses were problematic, with especially weak performance on open-ended questions and in nutrition and athletic performance. The study also found poor citation quality, difficult readability, and very few refusals to answer, raising concerns about the reliability of chatbots for everyday health information.

16 Apr 2026

Popular chatbots often provide inaccurate and incomplete medical information

A substantial amount of medical information provided by 5 popular chatbots is inaccurate and incomplete, with half of the answers to clear evidence based questions "somewhat" or "highly" problematic, show the results of a study published in the open access journal BMJ Open.

15 Apr 2026

Study finds AI can match clinicians in interview assessment

Clinical interviewing is one of the most important skills physicians develop during their training. It forms the foundation for accurate diagnosis and effective patient care.

15 Apr 2026