Development of a QT Interval Inaccuracy Index (QTI) using machine learning to automatically identify ECGs requiring expert review in TQT studies, improving efficiency while maintaining accuracy.

Development of deep learning models for automated QT interval measurement in drug safety studies, showing improved accuracy over traditional methods and providing interpretable QT delineation to assist expert review.

Review of cardiac safety monitoring in oncology drug development, discussing QT interval assessment, arrhythmia risks, and the need for standardized cardiotoxicity evaluation in clinical trials.

Clinical study demonstrating gadopiclenol, a new gadolinium-based contrast agent, has no significant QTc interval prolongation at clinical and supraclinical doses in healthy subjects.

Novel method using Non-Negative Matrix Factorization for R-peak detection in Holter ECG signals, showing high accuracy and noise tolerance in MIT-BIH database analysis.

Review examining how artificial intelligence and machine learning can enhance cardiac safety monitoring in clinical trials, with focus on automated ECG analysis and biomarker detection.

Clinical study demonstrating cardiac safety of imeglimin, a novel oral treatment for type 2 diabetes, showing no effect on cardiac QT interval.