Tag: MIMIC-IV

A retrospective study of hospitalized heart failure patients in China and ICU patients in the United States links a higher ...

A retrospective dual-database study found that calculated serum osmolality above 300 mOsm/kg before extubation was associated with higher 48-hour invasive ...

A new counterfactual machine learning framework estimates how alternative acute nursing care strategies would individually affect critically ill oncology patients ...

Researchers have built a temporal-aware retrieval-augmented generation framework that helps large language models generate safer, evidence-based treatment plans for idiopathic ...

A retrospective cohort study using the MIMIC-IV database found that elevated blood urea nitrogen within 24 hours of ICU admission ...

A hybrid quantum-classical model outperformed XGBoost and other classical baselines in predicting ICU mortality across nearly 39,000 MIMIC-IV admissions, though ...

A study of 5,580 ICU patients with coronary heart disease shows that combining the stress hyperglycemia ratio with a laboratory-based ...

Researchers built an eight-variable machine learning model that predicts in-hospital mortality in patients with sepsis-related myocardial injury and validated its ...

A new data-driven framework called STREAM models ICU patients as trajectories through a multidimensional physiological space, identifying state outliers whose ...

A retrospective MIMIC-IV analysis of 2,093 ICU patients found that a higher serum creatinine-to-albumin ratio was strongly associated with increased ...