10.3389/fnagi.2018.00144.s001
John Wallert
John
Wallert
Eric Westman
Eric
Westman
Johnny Ulinder
Johnny
Ulinder
Mathilde Annerstedt
Mathilde
Annerstedt
Beata Terzis
Beata
Terzis
Urban Ekman
Urban
Ekman
Data_Sheet_1_Differentiating Patients at the Memory Clinic With Simple Reaction Time Variables: A Predictive Modeling Approach Using Support Vector Machines and Bayesian Optimization.docx
Frontiers
2018
cognitive impairment
dementia
elderly patients
simple reaction time variables
supervised machine learning
2018-05-22 07:15:46
Dataset
https://frontiersin.figshare.com/articles/dataset/Data_Sheet_1_Differentiating_Patients_at_the_Memory_Clinic_With_Simple_Reaction_Time_Variables_A_Predictive_Modeling_Approach_Using_Support_Vector_Machines_and_Bayesian_Optimization_docx/6298838
<p>Background: Mild Cognitive Impairment (MCI) and dementia differ in important ways yet share a future of increased prevalence. Separating these conditions from each other, and from Subjective Cognitive Impairment (SCI), is important for clinical prognoses and treatment, socio-legal interventions, and family adjustments. With costly clinical investigations and an aging population comes a need for more cost-efficient differential diagnostics.</p><p>Methods: Using supervised machine learning, we investigated nine variables extracted from simple reaction time (SRT) data with respect to their single and conjoined ability to discriminate both MCI/dementia, and SCI/MCI/dementia, compared to—and together with—established psychometric tests. One-hundred-twenty elderly patients (age range = 65–95 years) were recruited when referred to full neuropsychological assessment at a specialized memory clinic in urban Sweden. A freely available SRT task served as index test and was administered and scored objectively by a computer before diagnosis of SCI (n = 17), MCI (n = 53), or dementia (n = 50). As reference standard, diagnosis was decided through the multidisciplinary memory clinic investigation. Bonferroni-Holm corrected P-values for constructed models against the null model are provided.</p><p>Results: Algorithmic feature selection for the two final multivariable models was performed through recursive feature elimination with 3 × 10-fold cross-validation resampling. For both models, this procedure selected seven predictors of which five were SRT variables. When used as input for a soft-margin, radial-basis support vector machine model tuned via Bayesian optimization, the leave-one-out cross-validated accuracy of the final model for MCI/dementia classification was good (Accuracy = 0.806 [0.716, INS [0].877], P < 0.001) and the final model for SCI/MCI/dementia classification held some merit (Accuracy = 0.650 [0.558, 0.735], P < 0.001). These two models are implemented in a freely available application for research and educatory use.</p><p>Conclusions: Simple reaction time variables hold some potential in conjunction with established psychometric tests for differentiating MCI/dementia, and SCI/MCI/dementia in these difficult-to-differentiate memory clinic patients. While external validation is needed, their implementation within diagnostic support systems is promising.</p>