Information Technology

Token-Oriented Semantic Communication with Pretrained Vision Transformers

Token communications realize the semantic communication principle at the granularity of transformer tokens, providing a promising direction for client--server collaborative inference in resource-constrained edge systems. However, directly transmitting token embeddings presents two practical challenges: substantial communication cost and limited interoperability across model-specific token embeddin...

Auditable CT Phenotyping Through Report-derived Radiological Observations

Medical image foundation models can predict clinical phenotypes from computed tomography (CT), but strong performance leaves open whether they read disease-specific findings or shortcuts that correlate with the diagnosis. We tested this in 221 electronic-health-record (EHR) phenotypes using Auditable CT phenotyping (ACT), built on report-derived radiological observations. We trained ACT on 38,317 ...

High-Throughput Observational Evidence Generation Using Linked Electronic Health Record and Claims Data

Background: Many of the most consequential treatment decisions concern patients and comparisons that randomized trials never address: off-label and he...

A Structural FHMM for Interpretable Disease Trajectories in T2DM

In this work, we propose a structural variant of the Factorial Hidden Markov Model (FHMM) for the analysis of disease trajectories in patients with Ty...

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

Background: Large language models (LLMs) have shown increasing capability in medical knowledge tasks, yet how they perform in extracting structured cl...

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

Background: Free-text notes in electronic health records (EHRs) contain fine-grained psychiatric information that is essential for psychiatric researc...

Performance, Generalizability, and Fairness of a Peripheral Artery Disease Detection Model Across Patient Phenotypes and Health Systems

Background Peripheral artery disease (PAD) is a major cause of cardiovascular events but remains underdiagnosed. Electronic health record (EHR)-based ...

A Human-in-the-Loop Large Language Model System Based on the Model Context Protocol for Differential Diagnosis from Electronic Medical Records and Literature

Diagnostic errors, including misdiagnoses and delayed clinical diagnoses, could affect outcomes of a significant patient population, particularly indi...

Local retraining mitigates domain shift in sepsis prediction: Lessons from translating a neonatal model to mixed intensive care data

Background: Machine learning models leveraging electronic health records (EHRs) can support earlier detection of sepsis in intensive care units (ICUs)...

DBToken: A Database Tokenizer for Medical Event Foundation Models

Objectives Transformer models for electronic health records require converting clinical data into token sequences, however standardized tokenization a...

TabMedQA: From Structured Data to Question-Answer Datasets in Early Clinical Decision-Making

The rising adoption of Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) in clinical general practice demands datasets that captur...

Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records

Predictive models over structured electronic health records (EHRs) remain central to machine learning for healthcare, but few have jointly emphasized ...

Machine Learning-Supported Efficient VTE Risk Assessment using Routinely Collected Electronic Health Record Data

Venous thromboembolism (VTE) is a leading cause of preventable inpatient mortality, while the real-world performance of mandated risk assessment and t...

Prospective Validation of a Deep Learning Model to Detect Structural Heart Disease from Apple Watch ECGs: The WATCH-SHD Study

Importance: Consumer wearables such as the Apple Watch can record single-lead electrocardiograms (ECGs) but are used mainly to detect rhythm disorders...

Early Detection of Erythropoietic Protoporphyria Using Sequential Machine Learning on Longitudinal Electronic Health Records

Objective: Erythropoietic protoporphyria (EPP) is a rare photodermatosis marked by multi-year diagnostic delays. We developed and externally validated...

REFINE: Closing the Loop Between Large Language Models and Symbolic Rules in Clinical NLP

Symbolic clinical natural language processing (NLP) systems remain widely used for extracting clinical concepts from electronic health record (EHR) na...

Removing Temporal Note Redundancy Improves Multimodal Reinforcement Learning for Medicine

Mechanical ventilation is a critical life-support intervention, requiring dynamic adjustments to ventilator settings as a patient's condition evolves....

AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs

Life science knowledge graphs make large collections of structured data available through SPARQL, but each resource uses its own schema, identifiers, ...

BayesForge: A Bayesian Inference library for Python, R, and Julia

Bayesian modeling is a cornerstone of modern ecological and evolutionary research, offering the flexibility to account for hierarchical structures, im...

Longitudinal Clinical Foundation Models Augmented with Genomics for Early Detection and Risk Stratification of Inherited Cardiomyopathy

Hypertrophic and dilated cardiomyopathy (HCM and DCM) carry substantial morbidity and mortality, yet diagnosis may be delayed, particularly when prese...