Parkinson’s disease is associated with cognitive decline, misfolded protein deposition and brain atrophy. We herein hypothesized that structural abnormalities may be mediators between plasma misfolded proteins and cognitive functions. Neuropsychological assessments including five domains (attention, executive, speech and language, memory and visuospatial functions), ultra-sensitive immunomagnetic reduction-based immunoassay (IMR) measured misfolded protein levels (phosphorylated-Tau, Amyloidβ-42 and 40, α-synuclein and neurofilament light chain) and auto-segmented brain volumetry using FreeSurfur were performed for 54 Parkinson’s disease (PD) patients and 37 normal participants. Our results revealed that PD patients have higher plasma misfolded protein levels. Phosphorylated-Tau (p-Tau) and Amyloidβ-42 (Aβ-42) were correlated with atrophy of bilateral cerebellum, right caudate nucleus, and right accumbens area (RAA). In mediation analysis, RAA atrophy completely mediated the relationship between p-Tau and digit symbol coding (DSC). RAA and bilateral cerebellar cortex atrophy partially mediated the Aβ-42 and executive function (DSC and abstract thinking) relationship. Our study concluded that, in PD, p-Tau deposition adversely impacts DSC by causing RAA atrophy. Aβ-42 deposition adversely impacts executive functions by causing RAA and bilateral cerebellum atrophy.

This study aims to evaluate an AI model designed to automatically classify skull fractures and visualize segmentation on emergent CT scans. The model’s goal is to boost diagnostic accuracy, alleviate radiologists’ workload, and hasten diagnosis, thereby enhancing patient outcomes. Unique to this research, both pediatric and post-operative patients were not excluded, and diagnostic durations were analyzed. Our testing dataset for the observer studies involved 671 patients, with a mean age of 58.88 years and fairly balanced gender representation. Model 1 of our AI algorithm, trained with 1499 fracture-positive cases, showed a sensitivity of 0.94 and specificity of 0.87, with a DICE score of 0.65. Implementing post-processing rules (specifically Rule B) improved the model’s performance, resulting in a sensitivity of 0.94, specificity of 0.99, and a DICE score of 0.63. AI-assisted diagnosis resulted in significantly enhanced performance for all participants, with sensitivity almost doubling for junior radiology residents and other specialists. Additionally, diagnostic durations were significantly reduced (p < 0.01) with AI assistance across all participant categories. Our skull fracture detection model, employing a segmentation approach, demonstrated high performance, enhancing diagnostic accuracy and efficiency for radiologists and clinical physicians. This underlines the potential of AI integration in medical imaging analysis to improve patient care.