TY - JOUR
KW - Cognitive impairment
KW - Dementia
KW - Machine Learning
KW - primary care
KW - Screening
AU - Boaz Levy
AU - Courtney Hess
AU - Jacqueline Hogan
AU - Matthew Hogan
AU - James M. Ellison
AU - Sarah Greenspan
AU - Allison Elber
AU - Kathryn Falcon
AU - Daniel F. Driscoll
AU - Ardeshir Z. Hashmi
A1 - 
AB - BACKGROUND: Incorporation of cognitive screening into the busy primary care will require the development of highly efficient screening tools. We report the convergence validity of a very brief, self-administered, computerized assessment protocol against one of the most extensively used, clinician-administered instruments-the Montreal Cognitive Assessment (MoCA). METHOD: Two hundred six participants (mean age = 67.44, standard deviation [SD] = 11.63) completed the MoCA and the computerized test. Three machine learning algorithms (ie, Support Vector Machine, Random Forest, and Gradient Boosting Trees) were trained to classify participants according to the clinical cutoff score of the MoCA (ie, /=26, n = 165), suggesting greater sensitivity to age-related changes in cognitive functioning. CONCLUSION: Future studies should examine ways to improve the sensitivity of the computerized test by expanding the cognitive domains it measures without compromising its efficiency.
AD - 1 Department of Counseling and School Psychology, University of Massachusetts, Boston, MA, USA.; 1 Department of Counseling and School Psychology, University of Massachusetts, Boston, MA, USA.; 1 Department of Counseling and School Psychology, University of Massachusetts, Boston, MA, USA.; 2 McGraw-Hill Education, Boston, MA, USA.; 3 Christiana Care Health System, Department of Psychiatry and Human Behavior, Sidney Kimmel Medical College, Thomas Jefferson University, DE, USA.; 1 Department of Counseling and School Psychology, University of Massachusetts, Boston, MA, USA.; 1 Department of Counseling and School Psychology, University of Massachusetts, Boston, MA, USA.; 1 Department of Counseling and School Psychology, University of Massachusetts, Boston, MA, USA.; 4 Tufts University School of Medicine, Boston, MA, USA.; 5 Cleveland Clinic, Lerner College of Medicine, Cleveland, OH, USA.
BT - Journal of geriatric psychiatry and neurology
C5 - Healthcare Disparities; Measures
CP - 3
CY - United States
DO - 10.1177/0891988719834349
IS - 3
JF - Journal of geriatric psychiatry and neurology
LA - eng
M1 - Journal Article
N2 - BACKGROUND: Incorporation of cognitive screening into the busy primary care will require the development of highly efficient screening tools. We report the convergence validity of a very brief, self-administered, computerized assessment protocol against one of the most extensively used, clinician-administered instruments-the Montreal Cognitive Assessment (MoCA). METHOD: Two hundred six participants (mean age = 67.44, standard deviation [SD] = 11.63) completed the MoCA and the computerized test. Three machine learning algorithms (ie, Support Vector Machine, Random Forest, and Gradient Boosting Trees) were trained to classify participants according to the clinical cutoff score of the MoCA (ie, /=26, n = 165), suggesting greater sensitivity to age-related changes in cognitive functioning. CONCLUSION: Future studies should examine ways to improve the sensitivity of the computerized test by expanding the cognitive domains it measures without compromising its efficiency.
PP - United States
PY - 2019
SN - 0891-9887; 0891-9887
SP - 137
EP - 144
EP - 
T1 - Machine Learning Enhances the Efficiency of Cognitive Screenings for Primary Care
T2 - Journal of geriatric psychiatry and neurology
TI - Machine Learning Enhances the Efficiency of Cognitive Screenings for Primary Care
U1 - Healthcare Disparities; Measures
U2 - 30879363
U3 - 10.1177/0891988719834349
VL - 32
VO - 0891-9887; 0891-9887
Y1 - 2019
Y2 - May
ER -