193 papers
To address the scarcity of publicly available resources for clinical speech de-identification, this paper introduces the SREDH-AICup corpus, a time-aligned dataset comprising 20 hours of English and Mandarin audio annotated with 7,830 sensitive health information entities across 38 categories to support automated privacy protection research.
This paper presents a reproducible Python-based workflow that simulates and integrates early-phase oncology clinical, biomarker, and pharmacokinetic data to generate analysis-ready datasets, visualizations, and exploratory predictive models for translational decision support.
This study demonstrates that multimodal machine learning models integrating structured electronic health record data with clinical note embeddings can accurately predict high inpatient opioid exposure, thereby supporting targeted opioid stewardship efforts.
The paper introduces the Time-Aware G-Transformer, a deep learning model that combines causal G-computation with time-aware attention to accurately predict counterfactual treatment effects on irregular, heterogeneous clinical data, outperforming existing methods in long-horizon forecasting and uncertainty calibration for personalized medicine.
This mixed-methods study of West African clinicians and technical experts reveals a strong preference for independent regulatory oversight, transparent algorithms, and clear accountability frameworks to ensure safe and equitable AI integration in clinical practice, while highlighting significant concerns regarding vendor control and potential unfair liability for medical errors.
This study demonstrates that a hybrid machine learning framework combining gradient boosting and Hidden Semi-Markov Models can accurately classify four menstrual cycle phases using only self-reported symptoms, achieving 67.6% accuracy and establishing symptom dynamics as a scalable, device-free digital biomarker for reproductive health.
This prospective pilot study demonstrates that DR. INFO, an agentic AI clinical assistant, significantly improves time efficiency and clinical decision support for physicians in Portuguese healthcare settings, achieving high satisfaction scores and a Net Promoter Score of 81.2 without evidence of attrition bias.
This paper introduces MedScope, a lightweight benchmarking framework that systematically evaluates six open-source large language models on medical multiple-choice questions using multi-dimensional metrics and visual analyses, revealing significant performance heterogeneity and highlighting their current unsuitability for unsupervised high-risk clinical deployment despite their value as transparent baselines.
This survey of the top 40 public and private clinical trial sponsors in Europe reveals a significant sectoral imbalance in data sharing governance, where private sponsors generally offer more detailed and accessible operational documentation compared to public sponsors, who tend to provide high-level commitments lacking trial-specific guidance despite shared adherence to GDPR requirements.
This study presents and evaluates a multi-stage pipeline that combines a fine-tuned Bio-ClinicalBERT token classifier with locally deployed open-source large language models for revision, demonstrating that this hybrid approach significantly improves the accuracy and efficiency of extracting structured Age-Friendly 4M (What Matters, Medication, Mentation, and Mobility) information from informal nursing home text messages compared to single-stage models.
This study demonstrates that small language models (SLMs) can effectively and efficiently extract longitudinal serum creatinine data from unstructured French clinical notes for rare kidney diseases, offering a privacy-preserving and resource-efficient alternative to traditional methods despite challenges with text duplication and language nuances.
MedResearchBench introduces the first multi-domain benchmark specifically designed to evaluate AI research agents on clinical medical tasks by leveraging public datasets and high-quality ground truth to assess performance across seven clinical domains using six medical-specific dimensions, thereby addressing the critical gap in evaluating AI's ability to conduct publication-quality, clinically sound research.
The authors developed BSOAD, the first ontology to systematically represent and harmonize behavioral and social factors influencing Alzheimer's disease and related dementias by integrating existing ontologies and literature-derived relationships, while validating its structure and coverage through expert review and an LLM-assisted evaluation framework.
This paper introduces and validates VaaS, a multi-layer, cost-effective pipeline that reduces AI hallucinations in scientific citation generation to near-zero levels through iterative refinement and rigorous benchmarking, thereby enabling reliable AI-assisted biomedical research at production scale.
This paper introduces ClinicalTAAT, a time-aware transformer model that learns interpretable, patient-specific representations from sparse and irregular clinical event sequences to outperform existing methods in acuity classification, subgroup identification, and anomaly detection, thereby offering a scalable framework for data-driven healthcare process analysis.
The SwissPedGrowth project demonstrates the feasibility of extracting high-quality anthropometric data from heterogeneous Swiss children's hospital electronic health records for growth research, despite challenges regarding data completeness and the need for weighting to ensure population representativeness.
This study introduces a diagnostic framework and the Sequential Information Prioritization Scaffold (SIPS) to reveal and quantify a critical "Access-Stability Dissociation" in LLMs during sequential clinical reasoning, demonstrating that while structured scaffolding eliminates pathological convergence failures by making reasoning auditable, it exposes a model-specific trade-off between hypothesis retention and final diagnostic accuracy.
This paper presents MOE-ECG, a multi-objective ensemble fusion framework that utilizes particle swarm optimization and Dempster-Shafer theory to simultaneously optimize predictive performance and model diversity, achieving robust and accurate atrial fibrillation detection across multiple ECG datasets.
This study demonstrates that a human-in-the-loop, LLM-assisted prescreening workflow achieved high accuracy and low cost ($0.12 per patient) across 26 diverse clinical trials by effectively leveraging coordinator feedback to automate and refine patient eligibility screening.
The paper proposes HealthFormer, a dual-level, time-aware Transformer framework pretrained on large-scale longitudinal EHRs using multi-task self-supervision to learn hierarchical, event-centric patient representations that achieve state-of-the-art performance in incident cancer prediction through straightforward fine-tuning.