Related Experiment Video
Updated: Nov 4, 2025
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
Published on: June 9, 2018
Cortical Thickness from MRI to Predict Conversion from Mild Cognitive Impairment to Dementia in Parkinson Disease: A
Na-Young Shin1, Mirim Bang1, Sang-Won Yoo1
1From the Departments of Radiology (N.Y.S., M.B., K.J.A.) and Neurology (S.W.Y., J.S.K.), College of Medicine, The Catholic University of Korea, Seoul, Korea; Department of Radiology, Severance Hospital, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, Korea (N.Y.S., K.H., S.K.L.); and Department of Biomedical Engineering, College of Bio and Medical Sciences, Daegu Catholic University, Gyeongbuk, Korea (E.Y., U.Y.).
Abstract:
Background Group comparison results associating cortical thinning and Parkinson disease (PD) dementia (PDD) are limited in their application to clinical settings. Purpose To investigate whether cortical thickness from MRI can help predict conversion from mild cognitive impairment (MCI) to dementia in PD at an individual level using a machine learning-based model. Materials and Methods In this retrospective study, patients with PD and MCI who underwent MRI from September 2008 to November 2016 were included. Features were selected from clinical and cortical thickness variables in 10 000 randomly generated training sets. Features selected 5000 times or more were used to train random forest and support vector machine models. Each model was trained and tested in 10 000 randomly resampled data sets, and a median of 10 000 areas under the receiver operating characteristic curve (AUCs) was calculated for each. Model performances were validated in an external test set. Results Forty-two patients progressed to PDD (converters) (mean age, 71 years ± 6 [standard deviation]; 22 women), and 75 patients did not progress to PDD (nonconverters) (mean age, 68 years ± 6; 40 women). Four PDD converters (mean age, 74 years ± 10; four men) and 20 nonconverters (mean age, 67 years ± 7; 11 women) were included in the external test set. Models trained with cortical thickness variables (AUC range, 0.75-0.83) showed fair to good performances similar to those trained with clinical variables (AUC range, 0.70-0.81). Model performances improved when models were trained with both variables (AUC range, 0.80-0.88). In pair-wise comparisons, models trained with both variables more frequently showed better performance than others in all model types. The models trained with both variables were successfully validated in the external test set (AUC range, 0.69-0.84). Conclusion Cortical thickness from MRI helped predict conversion from mild cognitive impairment to dementia in Parkinson disease at an individual level, with improved performance when integrated with clinical variables. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Port in this issue.
Insights
Brain MRI scans showing cortical thickness can predict Parkinson disease dementia conversion in patients with mild cognitive impairment. Combining MRI data with clinical information further improved prediction accuracy for early diagnosis.
Area of Science:
- Neuroimaging
- Neurology
- Machine Learning
Background:
- Clinical prediction of dementia in Parkinson disease (PD) is challenging.
- Group-level associations between cortical thinning and PD dementia (PDD) have limited individual predictive value.
Purpose of the Study:
- To develop and validate a machine learning model predicting individual conversion from mild cognitive impairment (MCI) to PDD using MRI-derived cortical thickness.
- To assess the added value of integrating cortical thickness with clinical variables for enhanced prediction.
Main Methods:
- Retrospective analysis of MRI data from PD patients with MCI.
- Feature selection from cortical thickness and clinical variables using random forest and support vector machine models.
- Model training and validation on resampled datasets and an external test set.
Main Results:
- Models using cortical thickness (AUC 0.75-0.83) and clinical variables (AUC 0.70-0.81) showed fair to good predictive performance.
- Integrating both cortical thickness and clinical variables significantly improved model performance (AUC 0.80-0.88).
- Combined models demonstrated robust validation in an external test set (AUC 0.69-0.84).
Conclusions:
- Cortical thickness from MRI is a valuable predictor of MCI to PDD conversion in individuals with Parkinson disease.
- Integrating neuroimaging and clinical data enhances predictive accuracy for PDD conversion.
- Machine learning models show promise for personalized risk assessment in PD.
