Search

Abstract Background The progression of Alzheimer’s dementia (AD) can be classified into three stages: cognitive unimpairment (CU), mild cognitive impairment (MCI), and AD. The purpose of this study was to implement a machine learning (ML) framework for AD stage classification using the standard uptake value ratio (SUVR) extracted from 18F-flortaucipir positron emission tomography (PET) images. We demonstrate the utility of tau SUVR for AD stage classification. We used clinical variables (age, sex, education, mini-mental state examination scores) and SUVR extracted from PET images scanned at baseline. Four types of ML frameworks, such as logistic regression, support vector machine (SVM), extreme gradient boosting, and multilayer perceptron (MLP), were used and explained by Shapley Additive Explanations (SHAP) to classify the AD stage. Results Of a total of 199 participants, 74, 69, and 56 patients were in the CU, MCI, and AD groups, respectively; their mean age was 71.5 years, and 106 (53.3%) were men. In the classification between CU and AD, the effect of clinical and tau SUVR was high in all classification tasks and all models had a mean area under the receiver operating characteristic curve (AUC) > 0.96. In the classification between MCI and AD, the independent effect of tau SUVR in SVM had an AUC of 0.88 (p

Background and ObjectiveIdentifying biomarkers for predicting progression to dementia in patients with mild cognitive impairment (MCI) is crucial. To this end, the comprehensive visual rating scale (CVRS), which is based on magnetic resonance imaging (MRI), was developed for the assessment of structural changes in the brains of patients with MCI. This study aimed to investigate the use of the CVRS score for predicting dementia in patients with MCI over a 2-year follow-up period using various machine learning (ML) algorithms.MethodsWe included 197 patients with MCI who were followed up more than once. The data used for this study were obtained from the Japanese-Alzheimer's Disease Neuroimaging Initiative study. We assessed all the patients using their CVRS scores, cortical thickness data, and clinical data to determine their progression to dementia during a follow-up period of over 2 years. ML algorithms, such as logistic regression, random forest (RF), XGBoost, and LightGBM, were applied to the combination of the dataset. Further, feature importance that contributed to the progression from MCI to dementia was analyzed to confirm the risk predictors among the various variables evaluated.ResultsOf the 197 patients, 108 (54.8%) showed progression from MCI to dementia. Tree-based classifiers, such as XGBoost, LightGBM, and RF, achieved relatively high performance. In addition, the prediction models showed better performance when clinical data and CVRS score (accuracy 0.701–0.711) were used than when clinical data and cortical thickness (accuracy 0.650–0.685) were used. The features related to CVRS helped predict progression to dementia using the tree-based models compared to logistic regression.ConclusionsTree-based ML algorithms can predict progression from MCI to dementia using baseline CVRS scores combined with clinical data.