AI Medical Compendium

Machine learning-based approach for predicting the extraction time of a mandibular third molar.

Oral surgery, oral medicine, oral pathology and oral radiology Apr 22, 2026

OBJECTIVE: Predicting the surgical time required for mandibular third molar extraction is challenging because patient-, tooth-, and operator-related factors interact in complex ways. This study aimed to develop an interpretable machine-learning model... read more

Hyperparameter Optimization of Non-linear Machine Learning Models Using Bi-level Data-Driven Optimization.

Computers & chemical engineering Apr 22, 2026

This study presents a systematic decision-making approach for tuning hyperparameters of machine learning (ML) models that employ the cross-validation technique in their learning process. It provides a more efficient and precise alternative to convent... read more

Current evidence and future directions for prophylactic anticoagulation therapy after severe spontaneous intracerebral hemorrhage: a narrative review.

Journal of intensive medicine Apr 22, 2026

Patients with spontaneous intracerebral hemorrhage (sICH) are at high risk for venous thromboembolism (VTE), a complication strongly associated with adverse clinical outcomes. While prophylactic anticoagulation has been shown to effectively reduce VT... read more

Deep learning-based non-contrast cine CMR for optimized prediction of left ventricular adverse remodeling after ST-elevation myocardial infarction.

International journal of cardiology Apr 22, 2026

OBJECTIVES: To evaluate the feasibility of a non-contrast cardiac magnetic resonance (CMR)-based deep learning (DL) model for predicting left ventricular adverse remodeling (LVAR) in patients with acute ST-segment elevation myocardial infarction (STE... read more

Functional cortical network alterations in Parkinson's disease with wearing-off revealed by resting-state fNIRS and graph theory.

Neuroscience Apr 22, 2026

Wearing-off (WO) is a common motor complication in Parkinson's disease (PD), characterized by the re-emergence of symptoms before the next dose of dopaminergic medication and still lacking objective, bedside-available neurophysiological biomarkers. I... read more

Joint use of ground-penetrating radar and hydraulic-partitioning tracer tomography to improve characterization and long-term prediction of DNAPL source zones in multi-facies aquifers.

Journal of contaminant hydrology Apr 22, 2026

Facies-controlled heterogeneity, including fine-grained lenses and abrupt textural transitions, produces irregular and non-Gaussian DNAPL source zone architecture (SZA) that strongly influences mass-transfer and long-term dissolution. Reconstructing ... read more

Future cardiovascular events prediction from invasive coronary angiography: A graph representation learning perspective.

Medical image analysis Apr 22, 2026

Improving risk stratification for coronary artery disease (CAD), the leading global cause of death, remains a daily challenge in clinical practice. This highlights the urgent need for innovative approaches to early prediction of future cardiovascular... read more

Engineering brain-penetrant PROTACs: Bridging molecular design and CNS delivery.

Advanced drug delivery reviews Apr 22, 2026

The drug development for central nervous system (CNS) disorders, particularly neurodegenerative diseases, such as Alzheimer's disease, Parkinson's disease, and Huntington's disease, faces formidable challenges. While proteolysis-targeting chimeras (P... read more

High-quality data selection-driven instruction tuning for biomedical large language models.

Journal of biomedical informatics Apr 22, 2026

This study presents a novel data selection framework for enhancing the training efficiency of large language models (LLMs) in biomedical natural language processing (NLP) tasks. We focus on critical tasks sourced from the biomedical dataset, encompas... read more

Clinical document metadata extraction: A scoping review.