Machine learning approaches to studying the role of cognitive reserve in conversion from mild cognitive impairment to dementia

Abstract

Objectives The overall aim of the present study was to explore the role of cognitive reserve (CR) in the conversion from mild cognitive impairment (MCI) to dementia. We used traditional and machine learning (ML) techniques to compare converter and nonconverter participants. We also discuss the predictive value of CR proxies in relation to the ML model performance. Methods In total, 169 participants completed the longitudinal study. Participants were divided into a control group and three MCI subgroups, according to the Petersen criteria for diagnosis. Information about the participants was compared using nine ML classification techniques. Seven relevant performance metrics were computed in order to evaluate the accuracy of prediction regarding converter and nonconverter participants. Results ML algorithms applied to socio‐demographic, basic health, and CR proxy data enabled prediction of conversion to dementia. The best performing models were the gradient boosting classifier (accuracy (ACC) = 0.93; F1 = 0.86, and Cohen κ = 0.82) and random forest classifier (ACC = 0.92; F1 = 0.79, and Cohen κ = 0.71). Use of ML techniques corroborated the protective role of CR as a mediator of conversion to dementia, whereby participants with more years of education and higher vocabulary scores survived longer without developing dementia. Conclusions We used ML approaches to explore the role of CR in conversion from MCI to dementia. The findings indicate the potential value of ML algorithms for detecting risk of conversion to dementia in cognitive aging and CR studies. Further research is required to develop an ML‐based procedure that can be used to make robust predictions.

Association of lifespan cognitive reserve indicator with the risk of mild cognitive impairment and its progression to dementia

“…The role of individual CR‐related factors in the progression from MCI to dementia has been explored in a few studies, with some inconsistent findings. One study showed that higher education or vocabulary scores may delay clinical onset of dementia in people with MCI 11 . Another three studies suggested that that later life social or cognitive activities, 12 intellectual social activities, 10 and education 13 were not associated with the conversion from MCI to dementia.…”

“…The associations between individual CR‐related factors and the MCI progression to dementia were relatively weaker or not significant. In our study, to capture CR accumulated through the lifespan, we used SEM to extract the CR indicator based on life‐course (through early, middle, and late life) educational and mentally stimulating activities, and the measure was weighted according to its contribution to the score 9,11 . Thus, it is not surprise that the association of lifespan CR indicator with MCI/dementia was stronger than the association of individual CR‐enhancing factors with MCI/dementia.…”

“…As the factor loading of social network was low making the model fit unsatisfactory, it was excluded from the final model. The final CR indicator was generated from the best‐fitting SEM with the five CR‐enhancing factors (ie, education; early life, midlife, and late‐life cognitive activities; and social activities in late life) 11 (supplementary Figure S1 in Appendix C). The weight for each of the five factors was the coefficient of the corresponding factor derived from the SEM with 0.065 for education, and 0.841 for early life, 1.273 for midlife, and 0.389 for late‐life cognitive activities, as well as 0.212 for late life social activities.…”

“…Several studies that have addressed the relationship between individual CR indicators, and the progression from MCI to dementia in people with MCI have shown inconsistent results. One study has indicated that high education might delay the onset of dementia in people with MCI 11 . Others found that social or cognitive activities 10,12 and education 13 were not associated with the conversion from MCI to dementia.…”

Neuroimaging and analytical methods for studying the pathways from mild cognitive impairment to Alzheimer’s disease: protocol for a rapid systematic review

“…The ability to predict who will progress to AD dementia from MCI will allow identifying the individuals who could benefit the most from clinical trials. As a result, early prediction of AD could provide the potential therapeutic windows to slow down the progression process [8].…”