Hospital-Based Medicine

Event-Wise Stability of Patient-Specific EEG-MEG Deep Learning Spike Detection in Clinical MEG

Objective: Computational magnetoencephalography (MEG) interictal epileptiform discharge (IED) detectors have mainly used generalized MEG-only models, whereas clinical MEG interpretation routinely integrates simultaneous electroencephalography (EEG) and includes MEG-unique or MEG-dominant discharges. We developed a patient-specific EEG-MEG IED detector and evaluated event-wise prediction stability ...

State-dependent aperiodic EEG dynamics track cortical network reorganization in chronic epilepsy

Aperiodic (1/f-like) EEG activity has rapidly become a popular noninvasive marker of cortical network state, proposed to index excitation-inhibition (E/I) balance and increasingly applied across neurological and psychiatric disorders. However, whether this approach remains reliable in the pathological brain, where disease progressively reorganizes neural networks, alters signal morphology, and dri...

Explainable Clinician-Supervised Artificial Intelligence as an Implementation Framework for Cardiovascular-Kidney-Metabolic Population Health: Synthetic Data Validation of the CHAPERONE-CKM Framework

Abstract Background: Cardiovascular-kidney-metabolic (CKM) syndrome is an increasingly prevalent multisystem condition associated with morbidity, frag...

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...

Prediction of Heart Failure based on Multimodal Data from MIMIC-IV

Heart failure (HF) affects over 64 million people worldwide and remains a leading cause of cardiovascular mortality. Early identification of patients ...

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...

TRIAGE: Risk-Controlled Pseudo-Label Admission for Annotation-Efficient Semi-Supervised Retinal OCT Classification

The advanced retinal disease diagnosing imaging modality, optical coherence tomography (OCT), encounters a lack of automation because of the high expe...

Multimodal artificial intelligence using entire electronic health record and complete pathogen genome data for patient outcome prediction from life-threatening infection: the SuperbugAI Platform

Artificial intelligence (AI) has the potential to transform healthcare, with advanced multimodal approaches showing great promise in leveraging divers...

Continuous Value Tokenization Improves Medical Event Foundation Models

Medical foundation models convert patient records into token sequences for autoregressive prediction, but numeric values such as lab results, vital si...

From Siloed Algorithms to Compliance-First Agentic Platforms: A Multi-Layered Architecture for Hospital AI Systems

Hospitals are rapidly adopting artificial intelligence for triage, imaging, scheduling etc., yet most deployments remain isolated point solutions lock...

FedCARE: A Multi-Objective Personalised Federated Learning Framework for Smart Healthcare

Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. H...

DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs

Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments. Yet serious cases are scarc...

Predicting Unplanned Hospital Readmissions in People with Multiple Long-Term Conditions

The prevalence of multiple long-term conditions (MLTCs) is associated with increased healthcare utilisation and an elevated risk of unplanned 30-day h...

Nudging Toward Precision Medical Education: Linking Diagnostic Exposures to Tailored Learning

Problem Authentic patient encounters are the raw material of clinical learning, yet the educational resources learners receive are rarely keyed to the...

MetaAMI: A Novel Meta-Learning Approach for Predicting In-Hospital Mortality in Acute Myocardial Infarction

Acute myocardial infarction (AMI) is one of the leading cardiovascular diseases worldwide and remains a major cause of mortality. Early risk predictio...

Interpretable machine learning prediction of in-hospital mortality in ICU patients with cancer and sepsis using first-day data: Development using MIMIC-IV and external validation in eICU-CRD

Background: Critically ill patients with cancer and sepsis have high in-hospital mortality, but externally validated prediction models are limited. Ob...

Systematic modeling of phenotypic drug response profiles inpatient-derived organoids

Patient-derived tumor organoids provide a physiologically relevant 3D disease model for preclinical drug discovery, surpassing the limitations of conv...

First-24-hour machine learning for 30-day mortality prediction in ICU trauma patients: development in MIMIC-III and cross-database evaluation in MIMIC-IV

ICU trauma patients are clinically heterogeneous, and early mortality risk stratification may support monitoring and resource allocation. We developed...

CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation

Medical world models aim to learn a latent state of patient or organ physiology and a transition function that forecasts how that state evolves under ...

Hierarchical Spatio-Temporal Transformer for Coherent Emergency Department Forecasting

Emergency Departments (EDs) are critical access points in healthcare systems, yet they face persistent pressure from unpredictable patient demand, sea...