Hospital-Based Medicine

Interpretable multimodal machine learning model for predicting health risks of patients with heart failure.

Heart failure (HF) is one of the major causes of morbidity and mortality globally, necessitating accurate tools for health outcome prediction and risk stratification. In this study, we propose an interpretable multimodal machine learning framework integrating four clinical data modalities (i.e., demographics, medications, laboratory tests, and electrocardiograms [ECGs]) to predict 30-day all-cause...

Development and external validation of a machine learning model for predicting in-hospital mortality in acute liver failure.

BACKGROUND: Acute liver failure (ALF) is a rapidly progressive and life-threatening condition that requires accurate risk stratification. Existing prognostic tools have limited sensitivity and generalizability. This study aimed to develop and externally validate a machine learning-based modeling framework for early in-hospital dynamic prediction of in-hospital mortality in patients with acute live...

Neural Vision Restoration in Ophthalmology.

Neural vision restoration is a rapidly advancing discipline at the intersection of neuroscience, bioengineering, and ophthalmology. This review synthe...

Interpretable four-factor day-1 nomogram for predicting sepsis-associated encephalopathy in septic ICU patients with AKI: Development and internal validation in MIMIC-IV.

Sepsis-associated encephalopathy (SAE) is common in the intensive care unit (ICU) and portends worse short- and long-term outcomes. To enable real-tim...

Overview of a User-Centered, Mixed-Methods Process for Designing Interconnected and Focused Mobile Applications on Patient Care Environment (InterFACE): Augmented-Reality Decision Support System for Pediatric Resuscitation.

BACKGROUND: Pediatric cardiopulmonary resuscitation (CPR) is a highly complex and time-critical process that demands precise team coordination and str...

Development and explanation of electrocardiogram-based deep learning for predicting short-term mortality in heart failure patients.

BACKGROUND: Heart failure mortality has risen sharply after years of decline, highlighting the limitations of current risk assessment tools in accurac...

Predicting the need for electroconvulsive therapy via machine learning trained on electronic health record data.

OBJECTIVES: Electroconvulsive therapy (ECT) is an effective treatment of severe manifestations of mental illness. Since delay in initiation of ECT can...

How threshold customisation affects the performance of a multiclass X-ray AI model for primary care triage: a retrospective study.

OBJECTIVES: To describe the structured process of threshold optimisation for a commercially available multiclass chest X-ray (CXR) deep learning model...

Predicting Persistent Renal Failure Necessitating Dialysis in Patients Undergoing Elective, Open Thoracoabdominal Aortic Aneurysm Repair.

BACKGROUND: Acute renal failure remains a significant complication after open thoracoabdominal aortic aneurysm (TAAA) repair and is associated with hi...

Architecting Synergy: Knowledge Graphs for Representing Complex, Multi-Domain Patient Information.

Healthcare systems exchange more data than ever, yet gaps in care persist: missed referrals, unsafe polypharmacy, and loss of continuity. This paper a...

Development and validation of a machine learning model for prediction of 1-year mortality following ST-elevation myocardial infarction: a retrospective cohort study.

OBJECTIVES: To develop a machine learning (ML)-based risk prediction model for 1-year mortality in ST-elevation myocardial infarction (STEMI) patients...

Machine Learning Tools for Predicting Pediatric Urinary Tract Infections Caused by ESBL-producing Bacteria.

BACKGROUND: The prevalence of pediatric urinary tract infections (UTIs) caused by extended-spectrum β-lactamases (ESBL)-producing bacteria is increasi...

Explainable machine learning model based on clinical and radiological features for predicting hematoma expansion or rebleeding after decompressive craniectomy in traumatic brain injury: a bicentric cohort study.

BACKGROUND: Hematoma expansion or rebleeding after decompressive craniectomy (DC) is a critical determinant of poor prognosis in traumatic brain injur...

Simplifying radiology reports with large language models: privacy-compliant open- versus closed-weight models.

OBJECTIVES: Large language models (LLMs) like generative pre-trained transformer (GPT) can simplify radiology reports for medical laypersons, but priv...

Translating human capital amid varying intentions to stay: An integrative conceptual review of the immigrant employment attainment process.

Immigrants face a unique challenge in translating their home country human capital to secure employment in their host country's labor market, potentia...

[Application of a novel robot-assisted navigation system in CT-guided percutaneous lung biopsy].

Objective: To compare the clinical efficacy and safety of robot-assisted navigation systems with those of the conventional puncture localization metho...

Machine learning-based on model for explain risk of 24-hour death in critically ill patients in the prehospital setting: A retrospective cohort study.

This study aimed to develop and validate a machine learning-based model for predicting 24-hour mortality in critically ill patients using prehospital ...

Enhancing Inpatient Mortality Prognostication in Cirrhosis Patients Through Machine Learning Techniques.

Machine Learning in Cirrhosis: Moving From Static Admission Risk to Dynamic Decision Support.

Temporally consistent survival prediction for non-uniform longitudinal data.

OBJECTIVE: Traditional survival prediction models use a patient's covariates at a single time point to estimate the time until a specific event occurs...