A clinically interpretable model for Parkinson’s disease: insights from complementary MRI modalities

Clicks: 19
ID: 332271
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #105 of 194 articles by views in Brain communications

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 194 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Abstract Accurate identification of Parkinson’s disease (PD) may remain challenging in certain clinical scenarios, highlighting the need for clinical decision-support model based on complementary MRI modalities. The case-control study included 462 participants, split into training (247 PD, 122 Normal Controls (NC)) and testing (60 PD, 33 NC) cohorts to construct and validate clinical decision-support model. We employed Lasso and logistic regression analysis to develop the model utilizing quantitative susceptibility mapping, arterial spin labeling and T1-weighted images. The model was assessed for calibration, discrimination and clinical utility, with individual predicted scores correlated to PD clinical symptoms. The model’s performance was also evaluated independently in Multiple System Atrophy (MSA), Progressive Supranuclear Palsy (PSP) and Essential Tremor (ET), with Delong test comparisons. The model was trained in training cohort (PD: 61.39 ± 8.06 years old, 134 males; NC: 61.29 ± 7.56 years old, 54 males) with the Area Under the ROC Curve (AUC) of 0.842 (95% Confidence Interval 0.798-0.883), and 0.771 (95% Confidence Interval 0.657-0.870) in testing cohort, whose clinical utility was confirmed. The predicted scores were positively correlated with Unified Parkinson’s Disease Rating Scale II (P = 0.034) and III (P = 0.015), while negatively with Purdue Pegboard totally (P = 0.010) and assembly scores (P = 0.007). When discriminating each disease group from NC, the model’s performance to identify MSA and PSP with AUC of 0.881 and 0.895 was superior than ET with AUC of 0.709 before false discovery rate correction (MSA-NC vs. ET-NC: P = 0.041; PSP-NC vs. ET-NC: P = 0.010). The model based on complementary MRI modalities was a objective clinical decision support measure for PD with potential applications in other parkinsonism (MSA, PSP).
Reference Key
openalex_W7221691488 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Qianshi Zheng, Jiaqi Wen, Weijin Yuan, Jianmei Qin, Xiaojie Duanmu, Haoting Wu, Zihao Zhu, Tao Guo, Chenqing Wu, Cheng Zhou, Jingjing Wu, Jingwen Chen, Yuelin Fang, Bingting Zhu, Yaping Yan, Jun Tian, Baorong Zhang, Hongjian He, Minming Zhang, Xiaojun Guan, Xiaojun Xu
Are you one of these authors? Claim your profile
Journal Brain communications
Year 2026
DOI
10.1093/braincomms/fcag383
URL
https://doi.org/10.1093/braincomms/fcag383
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.