biostudies-literatureUnknown15(2)Handzlik D<h4>Introduction</h4>The clock drawing task (CDT) is frequently used to aid in detecting cognitive impairment, but current scoring techniques are time-consuming and miss relevant features, justifying the creation of an automated quantitative scoring approach.<h4>Methods</h4>We used computer vision methods to analyze the stored scanned images (<i>N</i> = 7,109), and an intelligent system was created to examine these files in a study of aging World Trade Center responders. Outcomes were CDT, Montreal Cognitive Assessment (MoCA) score, and incidence of mild cognitive impairment (MCI).<h4>Results</h4>The system accurately distinguished between previously scored CDTs in three CDT scoring categories: contour (accuracy = 92.2%), digits (accuracy = 89.1%), and clock hands (accuracy = 69.1%). The system reliably predicted MoCA score with CDT scores removed. Predictive analyses of the incidence of MCI at follow-up outperformed human-assigned CDT scores.<h4>Discussion</h4>We created an automated scoring method using scanned and stored CDTs that provided additional information that might not be considered in human scoring.Alzheimer's & dementia (Amsterdam, Netherlands)e12441https://www.ebi.ac.uk/biostudies/studies/S-EPMC10201210biostudies-literatureExplainable automated evaluation of the clock drawing task for memory impairment screening.PMC10201210Skiena SLuft BJRichmond LLCarr MAClouston SAPHandzlik DfalseExplainable automated evaluation of the clock drawing task for memory impairment screening.<h4>Introduction</h4>The clock drawing task (CDT) is frequently used to aid in detecting cognitive impairment, but current scoring techniques are time-consuming and miss relevant features, justifying the creation of an automated quantitative scoring approach.<h4>Methods</h4>We used computer vision methods to analyze the stored scanned images (<i>N</i> = 7,109), and an intelligent system was created to examine these files in a study of aging World Trade Center responders. Outcomes were CDT, Montreal Cognitive Assessment (MoCA) score, and incidence of mild cognitive impairment (MCI).<h4>Results</h4>The system accurately distinguished between previously scored CDTs in three CDT scoring categories: contour (accuracy = 92.2%), digits (accuracy = 89.1%), and clock hands (accuracy = 69.1%). The system reliably predicted MoCA score with CDT scores removed. Predictive analyses of the incidence of MCI at follow-up outperformed human-assigned CDT scores.<h4>Discussion</h4>We created an automated scoring method using scanned and stored CDTs that provided additional information that might not be considered in human scoring.2023-01-01T00:00:00Z2023 Apr-Jun2025-04-04T10:27:42.253Z2025-04-04T10:27:42.253ZS-EPMC102012103722333310.1002/dad2.12441