BACKGROUND: The goal of this work is to develop a digital version of a standard cognitive assessment, the Trail Making Test (TMT), and assess its utility. OBJECTIVE: This paper introduces a novel digital version of the TMT and introduces a machine learning based approach to assess its capabilities. METHODS: Using digital Trail Making Test (dTMT) data collected from (N = 54) older adult participants as feature sets, we use machine learning techniques to analyze the utility of the dTMT and evaluate the insights provided by the digital features. RESULTS: Predicted TMT scores correlate well with clinical digital test scores (r = 0.98) and paper time to completion scores (r = 0.65). Predicted TICS exhibited a small correlation with clinically derived TICS scores (r = 0.12 Part A, r = 0.10 Part B). Predicted FAB scores exhibited a small correlation with clinically derived FAB scores (r = 0.13 Part A, r = 0.29 for Part B). Digitally derived features were also used to predict diagnosis (AUC of 0.65). CONCLUSION: Our findings indicate that the dTMT is capable of measuring the same aspects of cognition as the paper-based TMT. Furthermore, the dTMT's additional data may be able to help monitor other cognitive processes not captured by the paper-based TMT alone.
BACKGROUND: The goal of this work is to develop a digital version of a standard cognitive assessment, the Trail Making Test (TMT), and assess its utility. OBJECTIVE: This paper introduces a novel digital version of the TMT and introduces a machine learning based approach to assess its capabilities. METHODS: Using digital Trail Making Test (dTMT) data collected from (N = 54) older adult participants as feature sets, we use machine learning techniques to analyze the utility of the dTMT and evaluate the insights provided by the digital features. RESULTS: Predicted TMT scores correlate well with clinical digital test scores (r = 0.98) and paper time to completion scores (r = 0.65). Predicted TICS exhibited a small correlation with clinically derived TICS scores (r = 0.12 Part A, r = 0.10 Part B). Predicted FAB scores exhibited a small correlation with clinically derived FAB scores (r = 0.13 Part A, r = 0.29 for Part B). Digitally derived features were also used to predict diagnosis (AUC of 0.65). CONCLUSION: Our findings indicate that the dTMT is capable of measuring the same aspects of cognition as the paper-based TMT. Furthermore, the dTMT's additional data may be able to help monitor other cognitive processes not captured by the paper-based TMT alone.
Entities:
Keywords:
Computerized cognitive assessment; Trail Making Test; design and validation; machine learning; mobile application
Authors: T Moylan; K Das; A Gibb; A Hill; A Kane; C Lee; D Toye; K Wolstencroft; M Fail; D J Stott Journal: Int J Geriatr Psychiatry Date: 2004-10 Impact factor: 3.485
Authors: Russell M Bauer; Grant L Iverson; Alison N Cernich; Laurence M Binder; Ronald M Ruff; Richard I Naugle Journal: Clin Neuropsychol Date: 2012-03-07 Impact factor: 3.535
Authors: Hans Wouters; Aeilko H Zwinderman; Willem A van Gool; Ben Schmand; Robert Lindeboom Journal: Int J Methods Psychiatr Res Date: 2009-06 Impact factor: 4.035
Authors: Robert M Brouillette; Heather Foil; Stephanie Fontenot; Anthony Correro; Ray Allen; Corby K Martin; Annadora J Bruce-Keller; Jeffrey N Keller Journal: PLoS One Date: 2013-06-11 Impact factor: 3.240
Authors: Samantha E John; Sarah A Evans; Bona Kim; Petek Ozgul; David W Loring; Monica Parker; James J Lah; Allan I Levey; Felicia C Goldstein Journal: Neuropsychol Dev Cogn B Aging Neuropsychol Cogn Date: 2021-08-12
Authors: Mengtian Du; Stacy L Andersen; Stephanie Cosentino; Robert M Boudreau; Thomas T Perls; Paola Sebastiani Journal: Alzheimers Dement (Amst) Date: 2022-03-08
Authors: Zhongmin Lin; Fred Tam; Nathan W Churchill; Fa-Hsuan Lin; Bradley J MacIntosh; Tom A Schweizer; Simon J Graham Journal: Front Hum Neurosci Date: 2021-07-01 Impact factor: 3.169