Digital twin for neurological conditions: a systematic scoping review

Digital twin technology has emerged as a promising approach for advancing precision medicine in complex diseases, particularly in neurology. This scoping review aimed to systematically map the current literature on digital twin applications in neurological conditions, focusing on study characteristics, modeling approaches, data sources, and clinical applications. A comprehensive search across six databases from inception to February 2026 identified 36 studies that met the inclusion criteria. The findings demonstrated a rapid increase in publications since 2023, with Alzheimer's disease (n = 14) and stroke (n = 12) representing the most frequently studied conditions. Data-driven and machine learning-based models were the most common approaches, followed by mechanistic and hybrid models. Major application domains included clinical trial optimization, disease progression modeling, risk prediction, and personalized treatment. However, most studies were proof-of-concept or retrospective in design, with limited external validation and no randomized controlled trials identified. Additionally, many models lacked continuous real-time data integration, indicating that few met the criteria of fully dynamic digital twins. These findings suggest that while digital twins hold substantial potential to transform precision neurology, significant challenges remain in terms of methodological rigor, standardization, and clinical translation. Future research should prioritize prospective validation, integration of multimodal real-world data, and the development of standardized frameworks to support safe and effective implementation.