Skip to main content
Search

Beth Israel Deaconess Medical Center

8 related articles

Subscribe to updates
  1. No cuff calibration needed: AI-PPG-ACC-HTN flags hypertension in 196 people with 90.0% specificity

    Google Research, with Beth Israel Deaconess Medical Center and Harvard Medical School, used the photoplethysmography and accelerometer signals of a consumer smartwatch to passively identify a persistent hypertensive state without cuff calibration. Rather than estimating systolic and diastolic pressure at a moment in time, the system averages 15-second signal features over multiple days and combines them with height in a regularized logistic regression that outputs a probability. Against 24-hour ambulatory blood pressure monitoring in 196 participants free of known cardiovascular disease and not taking blood pressure medication, initial screening reached 65.8% sensitivity and 90.0% specificity, versus 55.3% sensitivity for concurrent office screening.

  2. Gemini

    Google ships Gemini 4 Argon worldwide and announces Carbon two weeks later, with Carbon held for U.S. government testing

    Google released Gemini 4 Argon, a frontier reasoning model, to developers, enterprises, scientists and consumers in October, then announced Gemini 4 Carbon two weeks later for long-horizon engineering and cybersecurity defense. Argon reached Google AI Studio, the Gemini API, Google Cloud, Search and the Gemini app after early safety testing, with a separate robotics variant; Carbon entered pre-release testing with the U.S. government and trusted cyber defenders in the Fairwind Program before a broader launch.

  3. A cross-field review of seven psychiatric research areas finds big data yields mechanistic insight and transdisciplinary collaboration, but sample size alone does not guarantee more precise estimates and a translational gap remains

    This review spans seven areas—community and register-based surveys, cohort and biobank studies, electronic health records, digital phenotyping, brain imaging, genomics and other -omics, and randomized controlled trials—to assess the advances, constraints and future directions of big data in psychiatry, concluding that big data has fostered transdisciplinarity and illuminated the intricacy, heterogeneity and variability of mechanisms underlying psychiatric disorders, yet sample size alone does not guarantee more precise estimates and a gap remains between big data and clinical application, so future work must attend equally to data quality and methodological rigor, conceptual models, and clinical questions.

  4. MergeRepair merges multiple code-task adapters and lifts automated program repair by 2.38% pass@1 and 4.01% pass@10 on StarCoder2 without extra training

    The study introduces MergeRepair, which trains one LoRA adapter per task on the Python split of CommitPackFT (59,113 samples, with Bug Fixes/APR at 19.02%) for Development, Bug Fixes, Misc, Test & QA, and Improvement, merges them with weight-averaging, ties, and dare-ties under equal weights, and proposes continual merging that adds adapters sequentially; evaluated on StarCoder2 and Granite 3B code models with HumanEvalFix pass@1/pass@10, it finds that merging task-specific adapters can improve APR without additional training, reaching up to 2.38% pass@1 and 4.

  5. How Generative AI Video Models Depict Depression: A Mixed Methods Study of OpenAI's Sora 2

    Using the single-word prompt "Depression," this study generated 100 videos across two access points of Sora 2 (consumer app, n=50; developer API, n=50), had two trained coders independently code narrative structure, visual environments, objects, figure demographics, and figure states, and extracted computational features (visual aesthetics, audio, semantic content, temporal dynamics) for comparison, finding a pronounced recovery bias in app-generated videos (78%, 39/50, featured arcs progressing from depressive states toward resolution versus 14%, 7/50, of API outputs), with app videos brightening over time (mean slope 2.90, SD 2.43 per second vs -0.18, SD 1.24 per second for the API; Cohen d=1.59; q<.001) and containing three times more motion (Cohen d=2.07; q<.

  6. Auditing Sex/Gender Disparities in Emergency Triage with LLM-based Paired Comparisons

    The study introduces a domain-agnostic paired-comparison approach that fine-tunes a large language model to emulate documented emergency triage decisions and then compares predictions on sex-swapped pairs in which only sex is flipped while documented clinical content is held constant, finding that otherwise identical presentations were more likely to receive a lower-severity (less urgent) predicted triage score as female than male, with a pooled per-pair rate of about 1.1% (95% CI 0.9–1.3) across more than 140,000 Bordeaux University Hospital admissions and a directionally consistent but larger 2.2% (1.7–2.7) in MIMIC-IV, while a model retrained on sex-neutralized inputs eliminated the between-sex prediction gap, indicating the asymmetry is mediated by explicit sex markers.

  7. Nature Medicine

    Prospective evidence for conversational medical AI: hard, but non-negotiable

    This Nature Medicine comment argues that trust in clinical AI cannot be benchmarked into existence but must be earned through rigorous prospective studies in real-world clinical settings, noting that the hardest lessons often concern the humans and systems around the AI rather than the technology itself.

  8. A Medically Grounded LLM Agent-Based Tool to Detect Patient Safety Events in Medical Records

    The study presents SAFE-AI, a framework that restricts a large language model to zero-shot entity extraction from emergency medical services charts and then makes determinations through a deterministic rule-based computational graph built from a clinician-defined ontology of clinical guidelines, reporting 97.9% accuracy for detecting epinephrine overdose and 91.6% for detecting delays in epinephrine administration across 300 pediatric out-of-hospital cardiac arrest charts containing 18,402 lines of clinical information, outperforming the compared baseline models.

You’re all caught up