
BACKGROUND To develop and internally validate a robust predictive model for radial artery spasm (RAS) to facilitate real-time intra-procedural risk stratification and intraoperative strategy optimization during chronic total occlusion percutaneous coronary intervention (CTO-PCI). RESEARCH DESIGN AND METHODS This retrospective study analyzed 1,327 patients undergoing CTO-PCI between January 2020 and November 2025. The dataset was divided into a derivation cohort (n = 929) and an internal validation cohort (n = 398) using a 7:3 ratio. Independent risk factors for RAS were identified through multivariate analysis to construct a logistic regression model. Model performance was rigorously assessed via AUC, calibration plots, bootstrap validation with optimism correction, Brier score, calibration slope, and decision curve analysis. RESULTS Female gender, anxiety status, diabetes mellitus, hyperlipidemia, frequent catheter exchange, multiple radial artery punctures, and prolonged procedure duration were identified as independent predictors of RAS (p < 0.05). Model demonstrated excellent discriminative ability, with optimism-corrected AUCs of 0.974 in derivation cohort and 0.980 in internal validation cohort. Calibration curves, calibration slopes (0.958 and 0.864), and Brier scores (0.048 and 0.035) revealed strong agreement between predicted and observed outcomes. CONCLUSIONS This model is specifically designed for intra-procedural dynamic risk assessment, integrating procedural factors as cumulative risk indicators. External validation is required before routine clinical implementation.
INTRODUCTION: ECT remains one of the most effective treatments for severe depression, including psychotic and treatment-resistant presentations and high-acuity cases requiring rapid response. This review examines ECT as a parameter-sensitive neuromodulation procedure rather than a fixed convulsive treatment. AREAS COVERED: We review historical development, clinical efficacy, safety, relapse prevention, and mechanistic models involving seizure induction, electric-field effects, inhibitory plasticity, neurochemical and neuroendocrine signaling, network change, and postictal brain states. The literature was identified through searches of PubMed/MEDLINE, Web of Science, Scopus, IEEE Xplore, and Google Scholar from database inception to June 2026, supplemented by reference-list screening, with evidence evaluated according to study design, clinical relevance, and technological maturity. Established components of contemporary ECT practice are distinguished from near-term optimization strategies and experimental technologies. EXPERT OPINION: Precision ECT should be regarded as an emerging framework rather than an established standard of care. Patient-specific electric-field modeling, biomarker-guided dosing, amplitude optimization, and adaptive stimulation are promising strategies for improving the therapeutic index, but require prospective validation against optimized standard ECT using clinical, cognitive, and patient-reported outcomes.
INTRODUCTION Artificial intelligence (AI) is increasingly being used to support glaucoma detection and monitoring, with rapid advances in deep learning, multimodal imaging, and longitudinal prediction. This review evaluates the evidence supporting these developments and identifies barriers to clinical translation. AREAS COVERED A systematic search of PubMed, IEEE Xplore, ScienceDirect, and SpringerLink was conducted following PRISMA guidelines, with the protocol registered in PROSPERO (CRD420261450819). Of 3,758 records identified, 63 eligible peer-reviewed studies published between 2015 and 2026 were included. The review examined AI techniques, imaging modalities, datasets, diagnostic and predictive performance, validation strategies, and reported limitations in Glaucoma care. Most studies used deep learning applied to fundus photography, optical coherence tomography (OCT), OCT angiography, visual fields, or multimodal data. Many models achieved an area under the ROC curve of approximately 0.95. EXPERT OPINION AI has substantial potential to improve glaucoma detection and monitoring, but high reported accuracy alone does not establish clinical readiness. Prospective multicenter validation using diverse populations, explainable and reproducible models, standardized evaluation, and integration into clinical workflows are essential before widespread implementation.