Search

Introduction: Cerebral small vessel disease (SVD) contributes to 45% of dementia cases worldwide. Only a minority of SVD patients develop dementia, yet we lack a reliable model for predicting incident dementia in SVD. Most attempts to date have relied on traditional statistical approaches, whereas machine learning (ML) methods are increasingly used for clinical prediction in other settings. Methods: We investigated whether ML methods improved prediction of incident dementia in SVD over traditional statistical. We included three cohorts with varying SVD severity (RUN DMC, n=503; SCANS, n=121; HARMONISATION, n=265). Baseline demographics, vascular risk factors, cognitive scores, and MRI features of SVD were used for prediction. We conducted both survival analysis and classification analysis predicting 3-year dementia risk. For each analysis, several ML methods were evaluated against standard Cox or logistic regression. Finally, we compared the feature importance ranking by different models. Results: We included 789 participants without missing data in the survival analysis, among whom 108 (13.7%) developed dementia during a median (IQR) follow-up period of 5.4 (4.1, 8.7) years. After excluding those censored before three years, we included 750 participants in the classification analysis, among whom 48 (6.4%) developed dementia by year 3. Comparing statistical and ML models, only the regularised Cox/logistic regression models outperformed their statistical counterparts overall, but not significantly so in survival analysis. Baseline cognitive scores were highly predictive, and all methods ranked global cognition as the most important feature. Discussion: ML survival or classification models brought little improvement over traditional statistical approaches in predicting incident dementia in SVD. ML approaches may be better suited to prediction problems using a larger number of input variables.

Background: Cerebral small vessel disease (SVD) contributes to 45% of dementia cases worldwide, yet we lack a reliable model for predicting dementia in SVD. Past attempts largely relied on traditional statistical approaches. Here, we investigated whether machine learning (ML) methods improved prediction of incident dementia in SVD from baseline SVD-related features over traditional statistical methods. Methods: We included three cohorts with varying SVD severity (RUN DMC, n = 503; SCANS, n = 121; HARMONISATION, n = 265). Baseline demographics, vascular risk factors, cognitive scores, and magnetic resonance imaging (MRI) features of SVD were used for prediction. We conducted both survival analysis and classification analysis predicting 3-year dementia risk. For each analysis, several ML methods were evaluated against standard Cox or logistic regression. Finally, we compared the feature importance ranked by different models. Results: We included 789 participants without missing data in the survival analysis, amongst whom 108 (13.7%) developed dementia during a median follow-up of 5.4 years. Excluding those censored before three years, we included 750 participants in the classification analysis, amongst whom 48 (6.4%) developed dementia by year 3. Comparing statistical and ML models, only regularised Cox/logistic regression outperformed their statistical counterparts overall, but not significantly so in survival analysis. Baseline cognition was highly predictive, and global cognition was the most important feature. Conclusions: When using baseline SVD-related features to predict dementia in SVD, the ML survival or classification models we evaluated brought little improvement over traditional statistical approaches. The benefits of ML should be evaluated with caution, especially given limited sample size and features.

Summary: Ultra-high field (UHF) neuroimaging affords the sub-millimeter resolution that allows researchers to interrogate brain computations at a finer scale than that afforded by standard fMRI techniques. Here, we present a step-by-step protocol for using UHF imaging (Siemens Terra 7T scanner) to measure activity in the human brain. We outline how to preprocess the data using a pipeline that combines tools from SPM, FreeSurfer, ITK-SNAP, and BrainVoyager and correct for vasculature-related confounders to improve the spatial accuracy of the fMRI signal.For complete details on the use and execution of this protocol, please refer to Jia et al. (2020) and Zamboni et al. (2020).

Alzheimer's disease (AD) is characterised by a dynamic process of neurocognitive changes from normal cognition to mild cognitive impairment (MCI) and progression to dementia. However, not all individuals with MCI develop dementia. Predicting whether individuals with MCI will decline (i.e. progressive MCI) or remain stable (i.e. stable MCI) is impeded by patient heterogeneity due to comorbidities that may lead to MCI diagnosis without progression to AD. Despite the importance of early diagnosis of AD for prognosis and personalised interventions, we still lack robust tools for predicting individual progression to dementia. Here, we propose a novel trajectory modelling approach based on metric learning (Generalised Metric Learning Vector Quantization) that mines multimodal data from MCI patients in the Alzheimer's disease Neuroimaging Initiative (ADNI) cohort to derive individualised prognostic scores of cognitive decline due to AD. We develop an integrated biomarker generation– using partial least squares regression– and classification methodology that extends beyond binary patient classification into discrete subgroups (i.e. stable vs. progressive MCI), determines individual profiles from baseline (i.e. cognitive or biological) data and predicts individual cognitive trajectories (i.e. change in memory scores from baseline). We demonstrate that a metric learning model trained on baseline cognitive data (memory, executive function, affective measurements) discriminates stable vs. progressive MCI individuals with high accuracy (81.4%), revealing an interaction between cognitive (memory, executive functions) and affective scores that may relate to MCI comorbidity (e.g. affective disturbance). Training the model to perform the same binary classification on biological data (mean cortical β-amyloid burden, grey matter density, APOE 4) results in similar prediction accuracy (81.9%). Extending beyond binary classifications, we develop and implement a trajectory modelling approach that shows significantly better performance in predicting individualised rate of future cognitive decline (i.e. change in memory scores from baseline), when the metric learning model is trained with biological (r = −0.68) compared to cognitive (r = −0.4) data. Our trajectory modelling approach reveals interpretable and interoperable markers of progression to AD and has strong potential to guide effective stratification of individuals based on prognostic disease trajectories, reducing MCI patient misclassification, that is critical for clinical practice and discovery of personalised interventions.