npj Digital Medicine

Digital phenotyping, which is defined as quantifying someone's behaviour with digital devices, provides unprecedented opportunities for understanding human mental health but is hampered by high levels of inter-individual variability. Here, we propose a new method to address this, parsing inter-individual variability by decomposing the digital phenotype dynamics into latent trajectories and using each individual's trajectory membership as a moderator when modelling psychopathology over the same timeframe. We applied our method in the context of mood symptom exacerbation across the menstrual cycle, where symptom severity and timing are inconsistent between individuals. Using the BiAffect platform to collect smartphone typing dynamics, we found stable trajectories in smartphone movement rate: one group of participants showed substantial movement rate fluctuations across the menstrual cycle, whilst the others did not. Participants with movement fluctuations displayed increased fluctuations across the cycle in prospective anhedonia and depression ratings, but not in anxiety, irritability, and suicidal ideation.

The widespread adoption of clinical large language models (LLMs) introduces significant risks of automation bias, premature closure, and clinician deskilling. Current interpretability paradigms, including latent space trajectories, Concept Activation Vectors, and Concept Bottleneck Models, suffer from topological stagnation, metric distortion, and epistemic occlusion, frequently masking intermediate diagnostic uncertainty behind falsely confident outputs. To address these structural vulnerabilities, this paper introduces a novel closed-loop, multi-agent framework designed to quantify and visualize dynamic epistemic uncertainty in clinical LLM reasoning. By coupling predictive Shannon entropy with non-linear Isometric Feature Mapping (ISOMAP), the architecture projects high-dimensional inference state vectors onto a calibrated two-dimensional latent space, thereby assigning a quantifiable thermodynamic energy state to the reasoning path to track diagnostic velocity, cognitive momentum, and trajectory efficiency across sequential diagnostic rounds. Pilot validation across representative emergency medicine scenarios demonstrated distinct topological and information-theoretic behaviors: unconfounded cases (cerebellar infarction) exhibited smooth geodesic progression toward the ground truth alongside monotonic Shannon entropy decay from 2.15 to 1.74; noisy environments with ambiguous findings (spontaneous pneumothorax) suffered from trajectory wandering, local minimum traps, and high sustained entropy (~2.41) due to insufficient repulsive weighting for negative evidence; and triage-conflicted cases (acute cholangitis) achieved precise geometric proximity to the true node but experienced top-1 rank stagnation because the model conflated acute severity triage (sepsis) with anatomical etiology. By rendering machine hesitation and cognitive divergence visually auditable before final diagnostic crystallization, this geometric-information framework enables dynamic trust calibration and human-AI co-regulation at the point of care while establishing a clear mathematical foundation for future architectural interventions, such as dual-channel safety decoupling and non-linear repulsive weighting. Moving forward, validating these architectural enhancements across large-scale electronic health record databases and prospective clinical trials will be essential to realize its full clinical utility, establishing a foundational blueprint for safe, transparent, and cognitively synergistic AI integration in future medical practice. By rendering the LLM's reasoning process visually auditable, this framework lays the groundwork for capturing and externalizing the clinician's own cognitive patterns within the AI, forming a coupled system. This enables the explicit visualization of cognitive gaps between physician hypotheses and AI inferences, transforming the interaction from simple answer-checking into a dynamic learning process for both human and machine that prevents diagnostic oversight. Ultimately, because the responsibility for final clinical decision-making remains with the human practitioner, this framework serves as a vital decision-support mechanism. Moving forward, validating these architectural enhancements across large-scale electronic health record databases and prospective clinical trials will be essential to realize its full clinical utility, establishing a foundational blueprint for safe, transparent, and cognitively synergistic AI integration in future medical practice.

Surgical video interpretation is a promising medical artificial intelligence application. However, no existing video annotation method preserves the spatiotemporal complexity of surgeon reasoning. Here we show that verbal reasoning and visual attention can be converted into structured, machine-actionable records of intraoperative behaviours. Our method decomposes transcribed verbal commentary into video-anchored semantic feedback chunks, which are classified via a large language model, with spatial grounding to surgical scenes via eyegaze or cursor tracking. We demonstrate method validity and scalability on structured and unstructured annotation tasks. For quality feedback on full-length colorectal procedures, the method reached near-human fidelity for chunking (mean cosine similarity: 0.95, SD: 0.01) and semantic classification across observations (mean Cohen's kappa: 0.71, SD: 0.07) and evaluative triggers (mean Cohen's kappa: 0.67, SD: 0.14), with excellent usability ratings. For structured critical view of safety assessment in laparoscopic cholecystectomy, implicit annotation yielded excellent agreement with explicit reviewer ratings (Cohen's kappa: 0.83, 0.49 and 0.81 across three criteria). We anticipate this method will advance surgical data science by enabling scalable construction of meaningfully annotated surgical video datasets.

Active Feature Acquisition (AFA) adaptively selects which diagnostic test to order next and offers a route to reduce unnecessary laboratory testing in acute care. Existing clinical AFA evaluations, however, assume every feature can be retrieved on demand and split data at the visit level, both of which inflate apparent performance. We re-evaluate cost-aware AFA under constraints designed to reflect deployment. From MIMIC-IV we constructed a cohort of 64,766 acute admissions (39,884 patients; 21 conditions; 55 features in 30 test panels) with a patient-level split, a 12-hour decision cutoff, and a per-patient availability mask from what was actually measured, and priced panels using the 2026 Medicare fee schedule under panel-level billing. We evaluated EIG-Cost, which scores each panel by Monte-Carlo Expected Information Gain penalised by its dollar cost, against eight published methods across budgets \30--$60 over five patient-level resamples. At a $30 budget, EIG-Cost achieved the highest macro-F1 (0.188, 95% CI [0.185, 0.191]) at the lowest cost ($17.28), exceeding the strongest baseline in all five resamples (p<0.001; Cohen's d=4.0), and led at every budget. Three of the eight methods collapsed to a vitals-only baseline (macro-F1 approx 0.040), acquiring nothing even at higher budgets, a genuine failure to adapt to availability rather than a budget limitation. Despite modest absolute accuracy, EIG-Cost's probabilities were well-calibrated (expected calibration error $0.048$). Under realistic availability constraints, clinical AFA is substantially harder than full-availability benchmarks imply, several published methods fail outright, and cost-aware information-gain scoring is a robust choice in this harder setting.

Large Language Models (LLMs) are increasingly used by clinicians and patients for medical queries, yet their accuracy and safety at the specialist level in hematology remain insufficiently characterised. We benchmarked ten frontier proprietary and open-weight LLMs across two generations on 1,477 board-style hematology multiple-choice questions (MCQs) derived from five educational datasets spanning nine disease areas and six clinical skill domains, including text-only and multimodal case vignettes. Claude Opus 5 had the highest mean accuracy (92.7% text, 76.9% multimodal), followed closely by Gemini-3.1 Pro (91.4% and 78.7%), Gemini-3.6 Flash (91.0% and 74.8%) and GPT-5.6 Sol (89.9% and 76.7%). Accuracy significantly correlated with model size both for text-only and multimodal MCQs. Between model generations, the largest improvements in accuracy were seen for open-weight models whereas proprietary models showed only marginal gains. In error analysis, top-performing models exhibited highly concordant failure patterns, suggesting shared limitations on challenging cases. Frontier LLMs exhibit substantial specialist hematology knowledge across diverse subspecialist domains and clinical skill sets. Yet, despite high accuracy on board-style questions in hematology, continuous expert-on-the-loop output monitoring is paramount.

Background. Cardiovascular-outcomes trials are lengthy, costly, and associated with substantial uncertainty prior to readout. In-silico trial simulation using real-world data (RWD) has emerged as a potential tool to support earlier decision-making; however, evidence of prospective predictive validity, generated prior to trial result disclosure, remains limited. Methods. We applied a semi-mechanistic machine learning framework integrating real-world patient data with biologically informed drug representations to prospectively simulate the VESALIUS-CV trial evaluating evolocumab versus placebo. The simulation model was trained on a combination of patient-level real-world data and a drug-centric knowledge graph and validated for both patient-level and trial-level retrospective predictive performance. The model was then used to simulate VESALIUS-CV before public disclosure of trial results, using a locked model and prespecified eligibility criteria and primary endpoint aligned with the clinical protocol. A patient-level time-to-event model was used to generate virtual trial arms, from which cumulative incidence curves, hazard ratios, confidence intervals, and p-values for major adverse cardiovascular events (MACE) were estimated. Results. In retrospective validation, the model demonstrated strong patient-level discrimination, with time-dependent ROC-AUC values ranging from 0.80 to 0.90 across follow-up horizons. For trial-level validation, 22 randomized cardiovascular-outcomes trials were simulated, and hazard ratios for 3-point MACE across 24 between-arm comparisons showed consistent directional agreement and quantitative correlation with published results such that the model accurately predicted trial success, achieving an F1 score of 0.83, with precision of 0.79 and sensitivity of 0.89. In a fully prospective application, the simulation predicted a statistically significant reduction in 3-point MACE with evolocumab versus placebo, estimating a hazard ratio of 0.78 (95% CI, 0.70-0.87) at 54 months. These predictions were consistent with the subsequently reported VESALIUS-CV results, which demonstrated a hazard ratio of 0.75 (95% CI, 0.65-0.86) at 55 months of median follow-up. Conclusions. In a fully prospective setting, a RWD-driven, AI-based simulation accurately predicted the direction, magnitude, and temporal dynamics of treatment effects observed in the VESALIUS-CV trial. These results demonstrate that in-silico trial simulation can anticipate clinical outcomes in the prospective setting, supporting its use as a complementary tool for early decision-making, trial design optimization, and de-risking in cardiovascular drug development.

Influenza vaccine effectiveness (VE) is estimated from a limited number of clinics using a test-negative design. These standard estimates face geographic, temporal, and operational constraints. Using Twitter/X data, we applied few-shot chain-of-thought prompting to identify self-reported vaccination status and influenza test results, then implemented a test-negative-like design to estimate VE. Our estimates fell within the range of interim reports and could complement current systems, improving feasibility, timeliness, and scalability.

Automatic coding from clinical notes has been studied extensively for International Classification of Diseases (ICD) codes, yet broad Current Procedural Terminology (CPT) and Healthcare Common Procedure Coding System (HCPCS) recommendation remains comparatively underexplored. Existing studies often focus on one specialty, a limited code vocabulary, or a single model family, leaving it unclear how different artificial intelligence (AI) paradigms perform under a common, clinically meaningful evaluation. We formulate CPT and HCPCS coding as an AI-assisted recommendation task in which a physician or professional coder reviews a short, ranked list of candidate codes supported by the clinical note. Using operative notes from Vanderbilt University Medical Center (VUMC) and discharge summaries from Medical Information Mart for Intensive Care IV (MIMIC-IV), we compare lexical retrieval, Clinical-Longformer, GPT-5.6-Sol, MedGemma-27B, and an inspectable agentic-style retrieve-and-verify system under a controlled review budget. Micro-averaged recall within a fixed number of recommendations measures whether reference codes reach the reviewable list; micro-F1 is reported only where reference labels are sufficiently complete. Zero-shot GPT-5.6-Sol achieves the highest recall within five and ten candidates: 0.717 and 0.800 on VUMC and lower-bound values of 0.689 and 0.738 on MIMIC-IV. The retrieve-and-verify system reaches 0.695 and 0.784 on VUMC and lower-bound values of 0.575 and 0.657 on MIMIC-IV, with a candidate-linked evidence window attached to each retained recommendation. Diagnostic analyses reveal distinct failure sources, including output-length underfilling, confusion among closely related codes, out-of-knowledge-base generation, and incomplete evidence support. These findings establish a systematic evaluation framework for procedure-code recommendation and identify practical requirements for future systems that are accurate, review-efficient, and grounded in clinical evidence.

Predicting disease risk from prior diagnoses is fundamental to clinical decision-making, particularly during health emergencies such as the COVID-19 pandemic, when individuals with long-term conditions may be disproportionately vulnerable to adverse outcomes. Despite intense interest in developing models to predict disease risk from prior diagnoses (1-3), most prediction models do not estimate effects of each prior diagnosis on disease risk conditional on other diagnoses, limiting interpretability and clinical utility. We developed the Comorbidity Risk Score (CRS), trained on 13 million individuals (age 40-69) from linked electronic health record (EHR) datasets of the entire population of England, to predict COVID-19 hospitalisation and 87 other disease outcomes. CRS was trained at close to saturated sample size and precisely estimated the effects of 212 prior diagnoses on the 88 disease outcomes, conditional on all other prior diagnoses. Correlations of CRS effect sizes across outcomes (e.g. 0.76 for myocardial infarction vs. hyperlipidaemia) matched the corresponding genetic correlations (e.g. 0.79 for myocardial infarction vs. hyperlipidaemia), confirming that comorbidity architectures capture disease aetiology. On average, CRS identified 5% of the population with 3.4-fold higher disease risk, including myocardial infarction (4.4-fold), lung cancer (6.5-fold), and COVID-19 hospitalisation (6.3-fold). Using prior diagnoses alone, CRS outperformed state-of-the-art clinical COVID-19 models (4). Furthermore, CRS (N=13 million) substantially outperformed state-of-the-art AI (1) (N=0.5 million) and linear (3) (N=0.5 million) models in predicting disease risk, suggesting that training sample size outweighs model complexity. CRS attained near-perfect transferability across self-reported ethnicities (e.g., Black vs. White: AUROC ratio = 97.3%). Finally, CRS distinguished independently predictive comorbidities from indirect associations, e.g., lipid metabolism disorder was a strong predictor of myocardial infarction risk but not ischaemic stroke, after conditioning on other prior diagnoses. In conclusion, CRS provides a comprehensive resource for understanding the impact of comorbidities on COVID-19 and other future diseases, revealing disease aetiology while enabling powerful prediction of disease risk.

Artificial intelligence applied to routine electrocardiograms (ECGs) has largely focused on detecting existing disease or predicting individual cardiovascular outcomes. Whether ECGs can support prediction of multiple future diseases across organ systems remains unclear. We developed ECG-RISK, a multitask survival model for 67 incident three-character ICD-10 endpoints using ECG waveforms, demographic characteristics and routinely collected laboratory data from 86,673 MIMIC-IV patients. Discrimination was highest for heart, brain, kidney and lung endpoints, with organ-level C-indices ranging from 0.796 to 0.825, whereas liver and pancreatic endpoints showed lower discrimination. The ECG-only model achieved strong discrimination across most endpoints, whereas the incremental improvement gained by incorporating ECG and laboratory inputs beyond demographic information varied substantially across endpoints. Across the nine exploratory aggregated outcomes, Kaplan Meier curves showed clear separation among model-score tertiles. Discrimination was highest for dementia (C-index, 0.891) and heart failure (C-index, 0.857). These findings support the feasibility of ECG-based longitudinal risk prediction across multiple diseases. External validation and competing-risk analyses are required to assess generalisability and clinical utility.

Breast cancer survivors frequently experience upper-limb impairments, making continuous monitoring essential for effective rehabilitation. We propose REINA (Recognize-Then-Infer Wearable-to-App AI Framework), a two-stage deep-learning approach for remote monitoring of motor function during breast cancer rehabilitation using wearable-device data. Inertial measurement unit (IMU) signals from wearable devices are first used to recognize physical activities via supervised learning, followed by an activity-specific recurrent neural network (RNN) to infer corresponding electromyography (EMG) signals. REINA establishes reliable inference of neuromuscular activity from wearable IMU data, enabling real-time, cost-effective assessment of motor function recovery in real-world settings.

Background: Unstructured biomedical data, such as echocardiography reports, are rich in information but time consuming to analyze at scale. Rule-based, regular expression-driven terminology mapping can only extract individual variables while large language models (LLMs) offer scalable and clinically meaningful interpretations of heterogeneous disease processes. Right ventricular dysfunction (RVD) is an example of a multifactorial disease state in which key structural and physiologic features are captured both narratively and in structured fields, making it an ideal test case for evaluating whether LLMs can recover complex phenotypes that rules based methods routinely miss. Purpose: To compare an LLM-based extraction method to a conventional rules-based schema for identifying and phenotyping echocardiographic features associated with RVD in a large TTE dataset. Methods: MIMIC-III NOTE2NUM echocardiography reports (n = 45,794) were analyzed using GPT-4o-based LLM extraction deployed within a secure health system enclave and were benchmarked against echocardiographic measurements defined in the MIMIC-III dictionary schema. In MIMIC-III, PH was recorded qualitatively (mild/moderate/severe) based on tricuspid regurgitant (TR) jet velocity and then re-coded as present vs. absent. LLM based extraction defined RVD as (1) RV structural abnormality (>= 1 of hypertrophy, dilation, or wall hypo-/akinesis) or (2) RV pressure/volume overload (>= 2 of the following: estimated right atrial pressure > 8 mmHg, TR jet velocity > 2.8 m/s, fractional area change < 35%, tricuspid annular planar systolic excursion < 17 mm, S' < 9.5 cm/s, or E/e' > 14), with PH defined as estimated pulmonary artery systolic pressure > 35 mmHg or qualitative documentation of PH. Results: LLM extraction identified PH in 15,394 (33.6%), RV pressure/volume overload in 14,449 (31.6%), and RV structural abnormalities in 11,955 (26.1%). Co-occurrence was common: overload + structural changes in 9,380 (20.5%), overload + PH in 9,756 (21.3%), structural changes + PH in 6,183 (13.5%), and all three in 5,620 (12.3%). Using the MIMIC-III dictionary schema, PH prevalence was similar (15,371; 33.6%), but RV overload fields were captured less often (pressure overload 1,357 [3.0%], volume overload 1,128 [2.5%], pressure + volume overload 1,093 [2.4%]; any overload field 3,578 [7.8%]), and RV pressure/volume overload with PH was identified in only 731 (1.6%). Conclusions: LLM-based extraction outperforms rules-based schemas for identifying complex disease states not defined by any single variable. By synthesizing multifactorial signals, LLMs can phenotype RVD with higher fidelity and support population-level assessment. Further validation using multimodality imaging, invasive hemodynamics, and clinical outcome data is needed.

Objectives To evaluate whether access to a certified large language model (LLM)-based clinical decision support system improves physician diagnostic performance in rheumatology compared with conventional diagnostic resources alone. Methods In this multicentre, open-label, randomised controlled trial, 82 physicians from seven hospitals in two countries were randomised 1:1 to conventional diagnostic resources plus Prof. Valmed or conventional resources alone. Participants assessed three rheumatology vignettes before and after assistance. The primary outcome was top-1 diagnostic accuracy. Secondary outcomes included top-3 accuracy, diagnostic reasoning, confidence, case-processing time and perceived support quality. Results Top-1 accuracy increased from 22.2% to 33.3% in the intervention group and from 23.3% to 35.0% in the control group, with no between-group difference in improvement (adjusted OR 0.99, 95% CI 0.45 to 2.19; p=0.979). Differences in top-3 accuracy, diagnostic reasoning and confidence were also not significant. Assisted case-processing time was substantially shorter with LLM support (94 vs 206 s; adjusted mean difference -112 s, 95% CI -141 to -83; p<0.001). Information timeliness and perceived diagnostic support quality were rated significantly higher in the intervention group. Exploratory analyses showed persistent overconfidence and substantial AI over-reliance. Conclusions Certified LLM-based diagnostic support did not improve diagnostic accuracy compared with conventional resources, but substantially reduced case-processing time and improved perceived support quality. These findings suggest potential workflow benefits while highlighting overconfidence and over-reliance as important safety considerations.

Background. Routine service databases are attractive sources of training labels for clinical prediction models, but the processes that write those labels are rarely audited before the labels are used. In a deployed community cognitive-screening programme, we audited the routine cognitive-status label, built a matrix of twenty-four model arms over the same patients under a specialist reference standard, and measured what each supervision choice bought or cost. Methods. The study cohort is the 672 individuals whose cognitive status was recorded by a titled (attending-or-above) physician, that record being the reference standard; after holding out one institution entirely, a development panel of 642 individuals at 38 institutions. The routine cognitive-status label these individuals also carry was first audited at the operator level: for each data-entry account we counted diagnoses entered and the proportion recording any impairment, and tested a competing bulk-timestamp explanation. Twenty-four arms span the supervision choices such a programme faces: an incumbent 21-variable logistic regression; local language models (Qwen2.5-1.5B/3B, Qwen3-4B/8B) zero-shot, with chain-of-thought, fine-tuned on physician labels, on routine labels with and without decontamination, or on a proxy scale-band task; preference-optimised (DPO) and reinforcement-trained (GRPO) variants; a proprietary frontier model queried zero-shot; and knowledge distillation of that frontier model into the regression and into the local 4B, using 943 teacher-labelled records from the programme's unlabelled pool. All arms are scored out-of-fold under one five-fold split grouped on registry-resolved institution clusters (no cluster spans a fold); paired contrasts use a 2,000-draw cluster bootstrap. Results. 181 operator accounts (each entering at least 100 diagnoses with zero recorded impairments) account for 45,315 rows - 40.5% of the outcome column; recorded impairment falls monotonically with account volume (15.7% for 1-9 rows to 0.7% for 500-999); a bulk-timestamp explanation was tested and refuted, identifying the write-time column as a migration artefact. Under the specialist standard, no locally fine-tuned arm beat the incumbent regression (AUROC 0.926): physician-label SFT reached 0.924 (4B), DPO 0.881, and GRPO 0.789; the pre-registered two-stage proxy-then-RL recipe was worse than its single-stage contaminated baseline (-0.030, 95% CI -0.077 to -0.004). Chain-of-thought reduced discrimination at every size (-0.072, -0.080, -0.041 at 1.5B/3B/4B; -0.012, n.s., at 8B). The frontier model scored 0.932 (vs. regression +0.007, n.s.). The distilled 4B reached 0.940 - above the incumbent (+0.014, 0.004 to 0.031) and above its own teacher (+0.008, 0.001 to 0.017) - with near-teacher calibration; it reached the teacher's level by 50 teacher labels and changed little beyond 200. Conclusions. The audit and the arm matrix support one deployment recipe: audit the routine label at the operator level before training on it; do not expect fine-tuning, preference optimisation, or reinforcement learning on a few hundred specialist cases to beat a well-calibrated regression; and if a frontier model is available but undeployable, spend a bounded number of queries on it as a labelling instrument and distil. A companion paper uses these frozen predictions to quantify how evaluation design choices compare with model choice.

In this work, we demonstrate the unprecedented value of NIH's "All of Us Research Program" (AoURP) dataset in studying maternal morbidity and building predictive machine learning (ML) models across heterogeneous populations in the United States. We developed robust and data-driven preprocessing pipelines to curate a longitudinal, multi-site, multimodal, and demographically diverse pregnancy dataset (20,253 subjects; 27,525 pregnancy episodes) from AoURP data, using electronic health records (EHR) (Conditions, Labs, Measurements) and survey responses (Social Determinant of Health (SDoH)), focusing on 7 crucial maternal health adverse outcomes. After characterizing data quality, missingness, and heterogeneity, we performed statistical correlation analysis to identify risk factors. We subsequently developed XGBoost and sequential LSTM models to predict the adverse outcomes, reaching state-of-the-art performance for multiple outcomes. We conducted model interpretability post-hoc analysis to understand success points and fairness analysis to evaluate implications for socio-economic disparities. Four practicing physicians reviewed the set of statistically significant and ML model identified features to assess their clinical validity and novelty. Most features identified through either statistical correlations or ML feature importance analysis aligned with known clinical risk factors. Several features were identified that the ML models used but that are not currently used in clinical practice and may merit further clinical investigation. Fairness analysis revealed certain associations with SDoH and age highlight areas that warrant continued monitoring. Overall, we demonstrate that meaningful populational level patterns can be extracted, and high-performing machine learning models can be trained on this longitudinal, diverse, multi-site dataset. Important risk features, particularly novel ones identified, if validated, could inform new strategies for maternal care or enable development and validation of outcome-specific, clinically deployable ML models.

Large language models perform well on medical examinations, but users routinely challenge their answers and invoke professional roles, and it is unclear what a system does when a medical credential and a stated task-specific accuracy point in opposite directions. In a factorial experiment on 480 items from four Polish specialty examination sets and three consumer large language model systems (ChatGPT, Claude, Gemini), each item and system received eleven independent conversations. Conditions crossed attributed source role (medical student, experienced specialist), stated prior accuracy on similar questions (2/10, 8/10) and suggestion correctness. The primary outcome was adoption of a prespecified incorrect option when the baseline answer matched the official key, comparing a specialist described as 2/10 with a student described as 8/10. Baseline agreement with the key was 87.2% across 15,683 analyzable conversations. The incorrect option was adopted more often from the specialist described as 2/10 than from the student described as 8/10 (10.2% vs. 7.6%; adjusted risk difference +2.82 percentage points, 95% CI +0.65 to +4.99). Estimates varied across the three systems and only one system-specific interval excluded zero. In a prespecified exploratory analysis with a shared eligibility rule, correct suggestions were adopted far more often than incorrect ones (risk difference +35.7 percentage points, 95% CI +30.8 to +40.7), indicating selective rather than indiscriminate compliance. An incorrect suggestion from a specialist with low stated accuracy was therefore slightly more influential than the same suggestion from a student with high stated accuracy, although the difference was modest and varied across systems. Agreement reached only after a user has disclosed a preferred answer should not automatically be treated as an independent second opinion, and medical large language model systems should be evaluated on how they revise answers after such disclosure, not solely on initial accuracy.

Stroke remains a leading cause of mortality and long-term disability worldwide, yet rapid diagnosis is often limited by the shortage of trained radiologists, particularly in resource-constrained settings. Automated analysis of CT imaging offers a potential solution, but existing methods often struggle to achieve clinically generalisable performance while jointly addressing multiple diagnostic tasks. Here we present the Intelligent Integrated Stroke Diagnosis System IISDS, an end-to-end deep learning framework built upon StrokeGNN, a graph-based architecture that integrates 3D contextual feature extraction with U-Net-based 2D lesion segmentation to enable comprehensive stroke analysis from non-contrast CT scans. IISDS performs stroke subtype classification, lesion segmentation and lesion volume estimation within a unified pipeline. To develop and validate the system, we collected and curated BGD-ISD through a collaboration between AI researchers, neurologists, radiologists and clinicians, resulting in a large multi-centre dataset comprising 1,507 CT scans from 597 stroke cases acquired across six hospitals and medical centres in Bangladesh. Across BGD-ISD and multiple publicly available datasets, IISDS achieves state-of-the-art performance on all tasks, improving segmentation accuracy by [&ge;]0.011 Dice score, reducing lesion volume estimation error by [&ge;]0.3 average symmetric surface distance (ASSD), and increasing classification performance by [&ge;]0.018 area under the receiver operating characteristic curve (AUC) compared with existing approaches. These results demonstrate the potential of graph-based deep learning to enable clinically generalisable, automated and scalable stroke diagnosis from CT imaging, supporting rapid clinical decision-making, particularly in healthcare environments with limited access to expert radiological interpretation.

Early identification of Alzheimer's disease and related dementias (ADRD) remains challenging despite its importance for timely intervention, management of modifiable risk factors, and care planning. We developed and evaluated ADRD onset prediction models using longitudinal electronic health records (EHRs) from the All of Us Research Program at clinically meaningful lead times of 6, 12, 24, and 36 months before diagnosis, benchmarking interpretable count-based representations against four publicly available pretrained clinical foundation models (CLMBR-T, GPT-style, LLaMA-style, and Mamba) across multiple ADRD phenotype definitions. Count-based models consistently achieved the highest discrimination and calibration across all cohorts and prediction horizons. Predictive performance declined with increasing lead time for all approaches; however, the performance gap between count-based and pretrained representations progressively narrowed, with foundation models achieving comparable AUROC of 0.719 (compared to the AUROC of 0.738 of count-based model) at the 36-month horizon while providing higher sensitivity and F1 scores under a fixed operating threshold. External validation with zero-shot evaluation on UChicago EHRs exhibited limited generalizability for count-based and pretrained clinical foundation model based representations. These findings demonstrate that transparent count-based EHR representations remain the strongest overall approach for ADRD onset prediction, while pretrained clinical foundation models provide complementary advantages for long-term risk identification and establish a benchmark for evaluating transferable clinical representations in temporal ADRD risk prediction.

BACKGROUND Generative AI (genAI) chart summarization tools embedded in electronic health records (EHRs) are being rapidly deployed across U.S. health systems. Although these tools represent a promising solution to alleviate cognitive burdens, their effects have not been examined in randomized-clinical trials (RCTs). METHODS In this pragmatic RCT at a single academic health system, 284 outpatient clinicians across forty-two specialties were assigned 1:1 to Epic's outpatient chart summarization tool or a usual-care control arm over 90 days, from February 23 to May 23, 2026. The primary outcome was physician task load (PTL) adapted for pre-charting. Prespecified exploratory outcomes included additional validated psychometrics as well as usability, safety, and time-based measures. Descriptive statistics included interaction and usage of the tool. RESULTS Of 74,474 AI chart summaries generated, 14.2% were interacted with by a clinician; the proportion of generated summaries interacted with declined from 21.5% in month 1 to 10.5% in month 3, and the proportion of clinicians using the tool at least once per month declined from 88.7% to 66.2%. The adjusted between-arm difference in PTL at follow-up favored the intervention arm (scale 0-400; -27.4; 95% CI, -49.4 to -5.3; P=0.02). Among the Professional Fulfillment Index (PFI; scale 0-4, lower=better) psychometrics, overall burnout (-0.20; 95% CI, -0.38 to -0.01) and work exhaustion (-0.24; 95% CI, -0.47 to -0.02) were lower in the intervention arm, with little difference in overall professional fulfillment (+0.04; 95% CI, -0.16 to 0.25). Charting time per encounter showed no significant between-arm difference during steady state (-1.2 seconds; 95% CI, -19.0 to 16.6). The net promoter score was -22, indicating that on average, clinicians did not recommend the tool. Among free-text respondents, 57.1% reported at least one concern, most commonly tool limitations or inaccurate information. No adverse patient safety events or near-misses were reported. CONCLUSION An EHR-integrated AI chart summarization tool modestly reduced physician task load and was associated with lower burnout, without time savings and against declining engagement. Sustained usage and oversight of reported inaccuracies remain open challenges.

Importance: Patients are increasingly learning Alzheimers disease (AD) genetic and biomarker results through electronic health portals. Evaluation of alternative scalable delivery models for return of AD risk information is needed to best support patient understanding and psychological well-being. Objective: To determine whether a patient-centered digital platform is comparable to clinician-mediated telehealth sessions for returning APOE and plasma pTau-217 results on outcomes of knowledge and psychological well-being. Design: The Evaluation of Self-Mediated Alternatives for Risk Testing Education and Return of Results (eSMARTER) study was a noninferiority trial of a patient-centered digital platform compared to clinician-mediated disclosure of APOE genotype and optional pTau-217 disclosure. Setting: Decentralized, fully remote trial enrolled participants in the contiguous United States (U.S.) between October 2024 and February 2025, with follow-up completed in November 2025. Participants: Eligible participants were aged 60-80 and had previously undergone APOE genotyping (without disclosure) via the GeneMatch program, passed psychological screening, had internet access, and were English-speaking. Interventions: Participants were randomized, 2:1, to the eSMARTER digital platform or clinician-mediated disclosure of APOE genotype. Following the 6-month post-APOE assessment, participants were offered optional pTau-217 disclosure via the same randomized modality. Main Outcomes and Measures: Primary outcomes at 1-7 days following APOE disclosure included changes in anxiety, disease-specific distress, and AD-related knowledge within a priori non-inferiority margins. Results: 674 persons (mean [SD] age 68 [4.7] years; 451 [67%] female; mean [SD] telephone MoCA=19 [2]) were eligible and provided demographic information. 651 participants were randomized to clinician-mediated (n=216) or digital disclosure (n=435) and completed APOE disclosure (66 [10%] APOE4 homozygotes, 377 [58%] heterozygotes, 208 [32%] non-carriers). 604 participants completed the study; 500 completed optional pTau-217 disclosure. Baseline characteristics were balanced across groups. At 1-7 days following APOE disclosure, scores on AD-related knowledge, PROMIS Anxiety, and disease-specific distress measures met non-inferiority. Conclusions and Relevance: Disclosure of APOE genotype by the eSMARTER digital platform is non-inferior to clinician-mediated telehealth disclosure. No significant between group differences were found following disclosure of pTau-217 results. Together, these results suggest that this digital platform may provide an evidence-based scalable approach for returning AD genetic and biomarker results.