Critical Care

Diagnostic Codes in AI prediction models and Label Leakage of Same-admission Clinical Outcomes

Artificial intelligence (AI) and statistical models designed to predict same-admission outcomes for hospitalized patients, such inpatient mortality, often rely on International Classification of Disease (ICD) diagnostic codes, even when these codes are not finalized until after hospital discharge. Investigate the extent to which the inclusion of ICD codes as features in predictive models inflates ...

Clinically meaningful combined improvements of sleep, physical activity, and nutrition (SPAN) in relation to major adverse cardiovascular events

Sleep, physical activity, and nutrition (SPAN) are major modifiable risk factors for cardiovascular disease, yet the minimum and optimal combined improvements for prevention remain unknown. We examined the multi-behaviour associations of SPAN with risk of major adverse cardiovascular events (MACE) and its subtypes (myocardial infarction (MI), heart failure (HF), and stroke). This prospective cohor...

Chronic Obstructive Pulmonary Disease Prediction Using Deep Convolutional Network

Artificial intelligence and deep learning are increasingly applied in the clinical domain, particularly for early and accurate disease detection using...

Developing an ICU Mortality Risk Prediction Model for Acute Myocardial Infarction Patients Based on Machine Learning

Patients with acute myocardial infarction (AMI) are in a critical condition, facing a high risk of death in the intensive care unit (ICU) with signifi...

CardiacGPT™: A Real-Time AI Assistant for Intraoperative Guidance and Postoperative Decision Support in Cardiac Surgery

Cardiac surgery is one of the most complex and high-stakes areas of medicine, where intraoperative decisions must be made within seconds and incomplet...

Wireless Colorimetric Multi-Biomarker Sensing to Enable Critical Neonatal Monitoring

Clinical monitoring in the most vulnerable patients such as newborns relies on invasive and costly procedures and/or wired sensor surveillance, increa...

Predicting ICU Transfer and Short-term Mortality in Emergency Department Atrial Fibrillation Patients: An Enhanced Machine Learning Model Using MIMIC Data

Atrial fibrillation (AF) is a prevalent condition in emergency department (ED) patients and is associated with an elevated risk of intensive care unit...

The HeartMagic prospective observational study protocol – characterizing subtypes of heart failure with preserved ejection fraction

Heart failure (HF) is a life-threatening syndrome with significant morbidity and mortality. While evidence-based drug treatments have effectively redu...

Predicting Rejection Risk in Heart Transplantation: An Integrated Clinical–Histopathologic Framework for Personalized Post-Transplant Care

Cardiac allograft rejection (CAR) remains the leading cause of early graft failure after heart transplantation (HT). Current diagnostics, including hi...

ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care

Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse be...

A machine learning model for prediction of early-onset neonatal sepsis in low- and middle-income countries: Development and validation study

Early-onset sepsis (EOS), which occurs within the first 72 hours of life, can often be fatal for neonates. Machine learning (ML) models demonstrate pr...

Early Prediction of Gestational Diabetes Using Integrated Cell-free DNA Features and Omics-derived Genetic Scores

Gestational diabetes mellitus (GDM) affects 15.6% of pregnancies globally, with Vietnam exhibiting one of the highest prevalences at 21%. Current diag...

Scalable screening for emergency department missed opportunities for diagnosis using sequential eTriggers and large language models

Missed opportunities for diagnosis (MODs), sometimes termed diagnostic errors, are a major cause of patient morbidity and mortality in the emergency d...

Development and Validation of a Machine Learning Model That Uses Voice to Predict Aspiration Risk

Aspiration causes or aggravates a variety of respiratory diseases. Subjective bedside evaluations of aspiration are limited by poor inter-and intra-ra...

Privacy-preserving local language models accurately identify the presence and timing of self-harm in electronic mental health records

Self-harm, defined as intentional self-injury or self-poisoning irrespective of motivation, is the strongest risk factor for suicide and an important ...

Development of Machine Learning Models to Predict Hypoglycemia and Hyperglycemia on Days of Hemodialysis in Patients with Diabetes based on Continuous Glucose Monitoring

Patients with diabetes undergoing hemodialysis (HD) are at risk of asymptomatic hypo- and hypergly-cemia within 24 hours of dialysis. Continuous gluco...

Personalized Hemodynamic Management Using Reinforcement Learning to Prevent Persistent Acute Kidney Injury After Cardiac Surgery

Acute kidney injury (AKI) affects one-third of patients after cardiac surgery and increases morbidity and mortality. AKI lasting over 48 hours, known ...

Using Hourly Aggregated Respiratory Rate and Expiratory Time with Machine Learning to Identify Remote COPD Exacerbations

Exacerbations of chronic obstructive pulmonary disease (COPD) are a major cause of morbidity and mortality. Various models for identifying exacerbatio...

Multi-View Echocardiographic Embedding for Accessible AI Development

Echocardiography serves as a cornerstone of cardiovascular diagnostics through multiple standardized imaging views. While recent AI foundation models ...

Machine learning predicts treatment response to nusinersen in non-sitter Spinal Muscular Atrophy (SMA)

Nusinersen has substantially increased survival and improved disease progression in Spinal Muscular Atrophy (SMA) patients. However, treatment respons...