Can machine learning algorithms accurately predict 2-year dementia incidence in memory clinic patients and how do these predictions compare with existing models?
In this prognostic study of data from 15 307 memory clinic attendees without dementia, machine learning algorithms were superior in their ability to predict incident dementia within 2 years compared with 2 existing predictive models. Machine learning algorithms required only 6 variables to reach an accuracy of at least 90%, and had an area under the receiver operating characteristic curve of 0.89.
This prognostic study assesses the ability of novel machine learning algorithms compared with existing risk prediction models to predict dementia incidence within 2 years.
Machine learning algorithms could be used as the basis for clinical decision-making aids to enhance clinical practice.
To assess the ability of machine learning algorithms to predict dementia incidence within 2 years compared with existing models and determine the optimal analytic approach and number of variables required.
This prognostic study used data from a prospective cohort of 15 307 participants without dementia at baseline to perform a secondary analysis of factors that could be used to predict dementia incidence. Participants attended National Alzheimer Coordinating Center memory clinics across the United States between 2005 and 2015. Analyses were conducted from March to May 2021.
The main outcome was incident all-cause dementia diagnosed within 2 years of baseline assessment.
In a sample of 15 307 participants (mean [SD] age, 72.3 [9.8] years; 9129 [60%] women and 6178 [40%] men) without dementia at baseline, 1568 (10%) received a diagnosis of dementia within 2 years of their initial assessment. Compared with 2 existing models for dementia risk prediction (ie, Cardiovascular Risk Factors, Aging, and Incidence of Dementia Risk Score, and the Brief Dementia Screening Indicator), machine learning algorithms were superior in predicting incident all-cause dementia within 2 years. The gradient-boosted trees algorithm had a mean (SD) overall accuracy of 92% (1%), sensitivity of 0.45 (0.05), specificity of 0.97 (0.01), and area under the curve of 0.92 (0.01) using all 258 variables. Analysis of variable importance showed that only 6 variables were required for machine learning algorithms to achieve an accuracy of 91% and area under the curve of at least 0.89. Machine learning algorithms also identified up to 84% of participants who received an initial dementia diagnosis that was subsequently reversed to mild cognitive impairment or cognitively unimpaired, suggesting possible misdiagnosis.
These findings suggest that machine learning algorithms could accurately predict incident dementia within 2 years in patients receiving care at memory clinics using only 6 variables. These findings could be used to inform the development and validation of decision-making aids in memory clinics.