JSM 2014 Home
Online Program Home
My Program

Abstract Details

Activity Number: 249
Type: Contributed
Date/Time: Monday, August 4, 2014 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Consulting
Abstract #313247
Title: Development of a Scoring Algorithm and Classification Procedure for a Computerized Cognitive Assessment Tool
Author(s): Laurel Chiappetta*+ and Gretchen Brauch and Lisa Morrow and Graham Ratcliffe and Anthony Zuccolotto and Amy Eschman and Judith Saxton
Companies: Data Development Integration Verification Analysis and Psychology Software Tools and University of Pittsburgh Medical Center and Clinical Neuropsychology Services and Psychology Software Tools and Psychology Software Tools and Clinical Neuropsychology Services
Keywords: cognitive impairment ; algorithm ; computerized assessment ; memory ; classification
Abstract:

The Computer Assessment of Memory and Cognitive Impairment (CAMCI®) is a portable computerized tool designed to provide a valid assessment of cognitive function in older individuals in an outpatient setting. Normative data was collected on 536 individuals aged > 60 recruited in primary care and community sites. An algorithm involving CAMCI task scores was developed to produce a CAMCI total score that most accurately reflects an individual's level of cognitive function, and permits effective discrimination between groups identified on the basis of the clinical adjudication. Statistical methodology focused on the reduction of false positives and used a 3-group classification procedure allowing for the identification of a group with borderline cognitive dysfunction. A complete description of the re-sampling strategy, variable selection, test and training sample selection, algorithm development, classification procedure, and calibration/scaling of the final score are provided. When interpreted by a qualified healthcare professional, CAMCI will assist in the identification of patients with suspected cognitive impairment for whom further evaluation may be appropriate.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2014 program




2014 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Professional Development program, please contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.