Preprint AI y sinh (medRxiv + bioRxiv)

Feed cuốn chiếu 60 preprint mới (50 medRxiv lâm sàng · 10 bioRxiv) có nội dung về AI/học máy, lọc theo chủ đề. Preprint là bản thảo CHƯA bình duyệt — đọc thận trọng. Mỗi bài link thẳng tới bản gốc; tóm tắt thuộc về tác giả.

Nguồn: medRxiv / bioRxiv · cập nhật 21 tháng 9, 2026 Bộ sưu tập ICML 2026 → Feed arXiv AI y sinh →

medRxiv Lâm sàng & Y tế Thần kinh & Não bộ

Computer Vision for Real-Time Pixel-Level Anatomical Segmentation in Neurosurgery: First-in-Human Clinical Evaluation and Iterative Development (IDEAL Stage 1)

D. Z. Khan, Z. Mao, A. Wijekoon, A. Das +11

IntroductionPrecise anatomical navigation is fundamental to safe endoscopic pituitary surgery, a high-stakes procedure characterised by a challenging learning curve. While…

Computer Vision for Real-Time Pixel-Level Anatomical Segmentation in Neurosurgery: First-in-Human Clinical Evaluation and Iterative Development (IDEAL Stage 1)

TRACE: A FINE-TUNED BIOMEDICAL LANGUAGE MODEL FOR DIRECTIONALLY INFORMED DRUG REPURPOSING FROM TRANSCRIPTOME-WIDE ASSOCIATION STUDIES

When can predictive uncertainty be trusted? A methodological evaluation in free-living wearable electrocardiogram signal-quality assessment

Adaptive forecasting of antiretroviral therapy demand using machine learning in India's national HIV programme

Integrating cognitive, linguistic and acoustic features to identify individuals with cognitive impairment: a proof-of-concept study

Multimodal Machine Learning for Predicting Outcomes in the PASS-01 Trial of Systemic Therapy for Metastatic Pancreatic Cancer

Drivers of Oncologist Preference of AI-Generated Literature Review in a Randomized Mixed-Methods Study

Expert-Guided Visual Correction for Characterizing Diagnostic Performance and Error Patterns of Multimodal Large Language Models Using Periodontal In-Service Examination Images

Explainable Deep Learning Reveals Distributed Neurodegeneration Signatures of Neuropsychiatric Symptoms Across the Alzheimer's Continuum

Intent Drift in LLM-Assisted Brain Computer Interface Communication: An In-Silico Benchmark Under Simulated Decoder Corruption

Neural, Behavioral, and Clinical Outcomes of a Voice-based AI Coach for Depression and Anxiety: A Phase 2 Randomized Trial

BioDeformUNet: A Deep Learning Model for Biomechanically Informed Liver Image Registration

Resting-state EEG network markers differentiate people with epilepsy and functional seizures

Personalized Knowledge-based Graph Neural Networks and Regression Analysis for Computational Diagnosis of High-Risk Cardiovascular Disease Patients

Cross-trait and multi-polytranscriptomic score analysis of Parkinson's disease identifies novel associations and improves prediction

Multimodal Transformer Modeling of Rapamycin Treatment in Alzheimer's Disease via Random Forest Feature Filtering

Emotional intelligence and the perception of good leadership in healthcare: a mixed-methods study

Transformer-Based Survival Model for Cardiovascular Risk Prediction from Longitudinal Health Checkup Data

A Two-Stage Multimodal Contrastive Framework for PET-Based Prediction of Obstructive Coronary Artery Disease

Predicting gait patterns from actionable impairments in Duchenne muscular dystrophy: A Machine Learning and Explainable Artificial Intelligence study

Explainable machine learning reveals the challenges of predicting new-onset motor complications in Parkinson's disease

Detecting Self-Repairs from Spontaneous Speech with Prompt Ablation Across LLMs and Fine-Tuned Encoder

MAESTRO: A Public, Generalizable Model for Stroke Lesion Segmentation from T1 MRI Across the Recovery Continuum

Quantifying Large Language Model Influence in Brain Computer Interface Communication for Amyotrophic Lateral Sclerosis

Multimodal artificial intelligence for personalized hepatocellular carcinoma treatment strategy selection

Offline Reinforcement Learning for Out-of-Distribution ICU Sepsis Decision Support

AUTONOMOUS LOOP CONSTRUCTION AND SUPERVISION FOR CLINICIAN-ORIENTED MEDICAL-AI RESEARCH

Large Language Model Embeddings of Surgical Procedural Names for Confounding Adjustment in Perioperative Observational Studies

CHIASM: A Self-Supervised Visual Field Encoder for Neuro-Ophthalmology

Outbreak and Postnatal Antibiotic Exposures Drive the Development Trajectory of the Nasopharyngeal Microbiota in the First Year of Life

Evaluating computational assays of chronic fatigue using UK Biobank data

Construction of a Standardized Time-Lapse Imaging Database and a Gradient Boosting Ensemble Framework for Integrating Zygote Morphokinetic Parameters with Conventional Embryo Assessment

Developing an open-source framework for LLM evaluation of patients using EHR clinical documentation; performance of LLMs relative to medical professionals

Evaluating Clinical Concept Extraction and Evidence-Bounded Terminology Linking: Multisite Model Comparison and Pilot Ablation Study

Glucagon-like peptide-1 receptor agonist initiation and risk of clinically recorded Alzheimer's disease-type dementia in older adults with type 2 diabetes: a target trial emulation using causal machine learning

Automated Detection of Extrahepatic Bile Duct Stones on Intraoperative Cholangiography Using Deep Learning

WISE-Screen: A Smartphone-Based Analytical Framework for Automated ASD Screening and Phenotyping via High-Fidelity Eye-tracking

Labeling and Disclosure of AI-generated Mental Health Content on TikTok

Development of a Deep Learning Model for Opportunistic Screening of Osteoporosis using Chest Radiographs

Does Data Preprocessing Affect Tree-Based Super Learners? An Investigation of Ensemble Optimization and Oracle Properties in Clinical Classification.

Velocity Reflection Index and Chronological Age: Confounder-Adjusted Statistical and Machine-Learning Analyses of Carotid Doppler Waveforms

Modifiable Contributors to Socioeconomic Inequality in Brain Aging

Mapping the flow of digital data in clinical trials and assessing its carbon footprint

MTS-Bench: A Manchester Triage System Benchmark for Language Model Triage Safety

Deep Learning-Based Single-View Echocardiographic Analysis for Prediction of Left Ventricular Outflow Tract Gradient Elevation After Transcatheter Aortic Valve Replacement

An Explainable Deep Learning Framework for Imaging Genetics: Deriving Brain-Genotype Scores From MRI to Link Genetic Variation, Brain Structure, and Cognition

A Vision-Language Model for Coronary Angiography Interpretation and Clinical Decision Support

AFIDs-Validator: An Open-Access AI-Guided Platform for Learning Anatomical Landmark Placement

Biphasic Temporal Remodeling Of The Proteome In A Polyglutamine-Expanded Huntingtin In Vitro Aggregation Cell Model: From Early Rna-Regulatory Compensation To Selective Mitochondrial Energy Failure

Scaling genome annotation across the eukaryotic tree of life with OrionGeno

IMMF: An Interpretable Multi-Modal Framework for Hypothesis-Driven Biomarker Discovery in Triple-Negative Breast Cancer Using Public Data

Integration of proteomic data from cell lines and tumors

A mechanism-annotated benchmark reveals limited fidelity to drug-response signatures in single-cell perturbation models

Plant Bioengineering Atlas: A Knowledge Graph of Genes, DNA Constructs, and Plant Traits.

WITHDRAWN: The richness of little voices: using artificial intelligence to understand early language development

Cooperative Modular Representation Learning for Lung Adenocarcinoma Survival Prediction from Transcriptomic and Clinical Data

Neural Mechanisms of Willed Attention Control

CorSeg-CineSAX: An Open-Source Deep Learning Framework for Fully Automatic Segmentation of Short-Axis Cine Cardiac MRI Across Multiple Cardiac Diseases

Implementation of a clinical decision support tool for acute diarrhea management in Tanzania and the United States: A Qualitative study using the Consolidated Framework for Implementation Research

Large-Scale Psychiatric Concept Extraction from Electronic Health Records: A Comparative Study of Encoder-Based Language Models