Predicting cognitive decline in Parkinson's disease using multimodal MRI features and serum inflammatory markers
Bibliographic record
Abstract
Cognitive decline is a significant concern in Parkinson's disease, affecting patient quality of life and increasing healthcare burden. This study aims to construct and validate a risk prediction model for cognitive decline in Parkinson's disease patients using multimodal MRI features and serum inflammatory markers. A retrospective case-control study was conducted involving 413 Parkinson's disease patients with normal cognition at baseline. These patients were divided into a primary cohort (n = 321) and an external validation cohort (n = 92). Patients were followed for 1–4 years, and patients with disease progression were compared with those without progression. Multimodal MRI scans and serum inflammatory marker assessments were performed. Univariate, multivariate logistic regression, and receiver operator characteristic (ROC) analyses were used to identify predictors of cognitive decline. Compared with the non-progression group, the progression group showed significant differences in T1 characteristics, including cortical thickness of the left hemisphere (LH) postcentral gyrus (P = 0.008), left hippocampal volume (P = 0.005), and right hippocampal volume (P = 0.004). The progression group showed significant differences in Susceptibility-Weighted Imaging (SWI) characteristics. Symptoms on the opposite side of Substantia Nigra pars compacta (SNc) were more pronounced in the non-progression group compared to the progression group (P = 0.006). Similarly, for symptoms on the same side of SNc, the non-progression group showed more prominent findings than the progression group (P < 0.001). Serum inflammatory marker analysis indicated that the progression group also showed significant differences in lymphocyte count (P = 0.023), neutrophil-to-lymphocyte ratio (NLR) (P = 0.002), lymphocyte-to-monocyte ratio (LMR) (P = 0.003), and albumin-to-fibrinogen ratio (AFR) (P = 0.004). The combined prediction model demonstrated high diagnostic accuracy, with an area under the curve (AUC) of 0.809 in the primary cohort and 0.812 in the external validation cohort. The developed model combining multimodal MRI features and serum inflammatory markers effectively identifies key factors influencing cognitive decline in Parkinson's disease, offering high diagnostic accuracy and valuable clinical insights for early detection and personalized treatment.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".