Hospital-Based Medicine

Assessing AI-Based Decision Support in Early Sepsis and AKI Recognition.

Sepsis and acute kidney injury (AKI) remain among the most critical conditions in acute care, associated with high morbidity and mortality. Early risk recognition is essential but often hampered by nonspecific symptoms. Recent studies have demonstrated that AI- and ML-based Clinical Decision Support Systems (CDSS) can enhance the early detection of sepsis and AKI and support clinical decision-maki...

Evaluation of Graph-Based Algorithms for Early Detection of In-Hospital Mortality.

Enhancing patient care quality depends on preventing health-related adverse events (HAEs), including in-hospital mortality, right from the start of hospitalization. Today, machine learning tools offer innovative solutions for predicting such events. Nevertheless, and despite their predictive potential, graph neural networks (GNNs) remain largely unexplored in the literature for analyzing complex, ...

Improving Explainability in Clinical Mortality Prediction Using Stacking Classifiers over Annotated Clinical Notes.

Heart failure, a leading cause of hospitalization and death, requires early identification of high-risk patients to improve care. This study focuses o...

Participatory Assessment of Ethics in AI: A Review.

INTRODUCTION: Artificial Intelligence (AI) is reshaping digital healthcare by advancing disease detection, treatment options, and individualized patie...

From Report to Record: Prompt-Based Information Extraction from Gynecology Oncology Reports Using LLMs.

The growing capabilities of Large Language Models (LLMs) in understanding and generating clinical text are transforming the processing of unstructured...

A Two-Stage Pipeline for Linking Clinical Notes to SNOMED CT.

Extracting clinically useful information from free-text notes remains challenging due to their unstructured nature, while medical coding is still only...

Evidence-Grounded LLM Validation of MIMIC-IV ICD Labels.

Automatically assigning ICD-10 diagnosis codes from discharge summaries is a central multi-label task in clinical NLP, yet widely used benchmarks such...

Resource-Conscious Modeling for Next-Day Discharge Prediction Using Clinical Notes.

Timely discharge prediction is important for surgical unit operations. Using 3,928 postoperative patient notes (32.2% positive), we compared TF-IDF mo...

Evaluating Large Language Models for Extracting Social Determinants of Health in Substance Use Disorder Notes.

Automated extraction of social determinants of health (SDoH) may support earlier identification of unmet social needs and inform substance use disorde...

From Discharge Letters to Process Traces with LLMs: A Human-in-the-Loop Pipeline.

We present a modular human-in-the-loop pipeline that converts unstructured discharge letters into process-mining-ready event traces. The pipeline uses...

OMOP Extraction of Medical Text Using LLMs: Preliminary Results.

We used medium-sized LLMs to extract medication data from German discharge letters into the OMOP CDM, achieving >85% accuracy and >75% F1-score, demon...

Time to Care-AI Supported Nursing Documentation.

This study conducted a needs assessment to evaluate contextual factors, adoption barriers, and overall readiness of municipal healthcare services to i...

A Tool for Virtual Nursing Utilization in Emergency Reception: An Exploratory Machine Learning Approach.

As virtual nursing (VN) gains traction as a scalable solution to support hospital workflows, identifying patients best suited for VN admission assessm...

Enhancing respiratory virus surveillance among hospitalised children: a machine learning-based predictive model.

BACKGROUND: Viral respiratory tract infections (vRTIs) are a leading cause of paediatric hospitalisation and healthcare utilisation. Existing syndromi...

Evaluating the feasibility of a scalable, digitally supported model for global collaborative surgical research: protocol for a prospective, international, multicentre observational study in cryptoglandular anal fistula treatment (CRAFT).

INTRODUCTION: Management of cryptoglandular anal fistula is characterised by wide variation in diagnostic strategies, surgical techniques and outcome ...

Research on optimization of power grid load forecasting models based on deep learning.

Precise forecasting of power grid load is essential for maintaining the stability and efficiency of contemporary energy systems. Traditional statistic...

An externally validated machine learning algorithm for predicting mental and physical health outcomes three months post-hospitalization for severe viral infection with SARS-CoV-2.

Many individuals hospitalized due to severe viral infections develop mental and physical sequelae, which could potentially be prevented by targeted in...

Enhancing prediction of inpatient deterioration by combining clinical and nurse concern features, with or without temporal clustering.

BACKGROUND: Early warning systems (EWSs) help clinicians identify deteriorating patients using clinical data, such as vital signs. However, standard s...

A Competency Framework for Medical AI Education: Mixed Methods Study.

BACKGROUND: Although artificial intelligence (AI) is increasingly adopted in health care, clinicians face barriers, including insufficient understandi...

Postangiography Prediction of Renal Replacement Therapy in Acute Myocardial Infarction-Related Cardiogenic Shock: Least Absolute Shrinkage and Selection Operator Nomogram Development and Validation.

BACKGROUND: Acute kidney injury critically impacts outcomes in cardiogenic shock secondary to acute myocardial infarction (CS-AMI). Acute kidney injur...