Systematic review of statistical, traditional machine learning, and deep learning approaches for predicting brain age in Parkinson's disease, covering workflows and current clinical applications.

Brain-age prediction methods can provide noninvasive biomarkers for early diagnosis, disease monitoring, and trial stratification in PD, improving translational research and clinical evaluation despite not directly revealing therapeutic mechanisms.

With the increasing aging worldwide, the age-related neurodegenerative diseases are becoming more and more prevalent. Brain age, as a critical biological marker for assessing normal brain aging and indicating disease progression, has been widely applied in the early diagnosis and evaluation of neurodegenerative diseases such as Parkinson's disease (PD). This paper systematically elaborates on three types of methods for PD brain age prediction: statistical methods, traditional Machine learning (ML), and Deep learning (DL), from the perspectives of methodological overview and clinical application of PD brain age predication. For the first aspect, the PD brain age prediction workflow, statistical methods, ML methods, and DL methods are sequentially outlined; in the second aspect, the current clinical application status of the three types of PD brain age prediction methods is introduced. Finally, a summary and outlook are provided. This review not only provides important references for research on PD brain age prediction, but also offers novel approaches for evaluating human brain health, thus holding significant scientific and clinical value.