Conversational diagnostic artificial intelligence in ambulatory primary care: a prospective feasibility study.

October 8, 2026| Source: Lancet (London, England)

Artificial intelligence (AI)-based systems show promise for assisting primary care providers (PCPs) with patient care. We aimed to evaluate the safety and quality of clinical conversations of a patient-facing conversational AI system, which engaged in real-world urgent primary care appointments. In this prospective, single-centre, single-arm feasibility study, English-speaking patients aged at least 18 years interacted with the Articulate Medical Intelligence Explorer (AMIE) up to 5 days before a single-complaint urgent primary care appointment. Physician safety supervisors monitored all interactions and were trained to intervene on the basis of predefined safety criteria. AMIE transcripts and summaries were shared with PCPs before the visit. Primary outcomes were the number of supervised conversation safety stops, AMIE's conversation quality assessed by clinical evaluators, and patient and PCP experiences per surveys. This study is registered with ClinicalTrials.gov (NCT06911398). From April to November, 2025, 114 patients were enrolled with 98 completing both the AMIE interaction and the PCP appointment. Zero conversation safety stops were required on the basis of prespecified criteria. Safety supervisors noted one hallucination and added clinical information in five interactions. AMIE's conversations were rated favourably in 87-100% of cases (17 criteria) by clinical evaluators, and 48-96% (16 criteria) by patients. Patient attitudes towards AI improved after interacting with AMIE and remained elevated after the patient's visit with their physician. PCPs completed post-surveys in 60 of 98 cases, including 44 cases in which they reviewed the AMIE transcript before the visit. PCPs found AMIE helpful for visit preparation in 33 of 44 cases and reported that it might have changed their behaviour in 25 of 44 cases. Although further research is needed, this study shows the initial feasibility of conversational AI in a real-world setting-assessed via conversation safety and quality, as well as user acceptance-and represents a crucial step towards clinical translation. Alphabet.

Read the original source →

Deep learning of fossil pollen morphology reveals 25,000 y of ecological change in eastern African grasslands.

Grass (Poaceae) pollen is largely overlooked in investigations of grassland evolution because the pollen of most species cannot be differentiated using traditional optical microscopy. However, the combination of superresolution microscopy and deep learning enables the capture and quantification of distinct morphological variation across the pollen of grass species. Using a semisupervised deep-learning strategy, we trained convolutional neural networks (CNNs) on superresolution images of known mo

Artificial IntelligenceOctober 13, 2026

Tyrosine phosphorylation unfolds nucleophosmin and disrupts its integration into the nucleolus.

Nucleophosmin (NPM1) is a multifunctional nucleolar protein essential for ribosome biogenesis, genome stability, and stress responses. Its integration into the nucleolus depends on its oligomerization and multivalent interactions that enable liquid-liquid phase separation (LLPS). Here, we investigate how tyrosine phosphorylation at Tyr17, Tyr29, and Tyr67 located within the interface between monomers at the N-terminal oligomerization domain regulates NPM1 structure and function. Replacing tyrosi

Artificial IntelligenceOctober 8, 2026

Shared patterns of human milk composition link mammary gland function to infant growth.

The mammary gland produces nutrient-rich human milk (HM), yet how mammary functional state shapes HM composition and infant outcomes remains poorly understood. We used HM multi-omics - metabolomics, proteomics, micronutrients, macronutrients, and HM oligosaccharides - across 1,543 samples from three cohorts, including two randomized trials, as a noninvasive readout of mammary functional state. Trajectory modeling and multi-omic integration showed that maternal supplementation improved recovery f

Artificial IntelligenceOctober 6, 2026

Large-scale semidefinite programming with graphics processing units.

Semidefinite programming (SDP) provides a powerful framework in applied mathematics with applications spanning optimization, machine learning, quantum computing, and beyond. However, the computational cost of solving large-scale SDP problems remains a significant practical limitation. We break this long-standing computational bottleneck through a synergistic codesign of low-rank algorithms and graphics processing unit (GPU) architectures, developing accelerated first-order methods that leverage

Artificial IntelligenceOctober 6, 2026

Genome stability disrupted by the circRBM39(4,5,6)-RPA2 axis represses breast tumorigenesis.

Genome instability (GI) is a hallmark of cancer. GI is associated with accumulative DNA damage and tumor-specific defects in DNA repair. Multiple antitumor drugs have been developed to promote persistent GI and to drive DNA damage beyond a threshold that tumor cells can survive. However, regulatory roles of circular RNAs (circRNAs) in GI and DNA damage remain elusive. Through circRNA profiling and a small interfering RNA (siRNA)-mediated screen, we have identified a circRNA termed circRBM39(4,5,