Quantifying Human Behavior on the Block Design Test Through Automated Multi-Level Analysis of Overhead Video

Abstract

The block design test is a standardized, widely used neuropsychological assessment of visuospatial reasoning that involves a person recreating a series of given designs out of a set of colored blocks. In current testing procedures, an expert neuropsychologist observes a person's accuracy and completion time as well as overall impressions of the person's problem-solving procedures, errors, etc., thus obtaining a holistic though subjective and often qualitative view of the person's cognitive processes. We propose a new framework that combines room sensors and AI techniques to augment the information available to neuropsychologists from block design and similar tabletop assessments. In particular, a ceiling-mounted camera captures an overhead view of the table surface. From this video, we demonstrate how automated classification using machine learning can produce a framelevel description of the state of the block task and the person's actions over the course of each test problem. We also show how a sequence-comparison algorithm can classify one individual's problem-solving strategy relative to a database of simulated strategies, and how these quantitative results can be visualized for use by neuropsychologists.

Multiscopic CPSS for Independent Block-Design Test Based on Hand–Object Interaction Recognition With Visual Attention

“…Compared to other methods, such as BDT with different approaches [15], [28], [56] or the use of virtual reality [31], [32], [58], the multiscopic approach offers several advantages.…”

“…Cha et al introduced a novel framework that combines vision systems and artificial intelligence (A.I.) approaches to enhance the knowledge obtained by neuropsychologists from the BDT and similar tabletop evaluations [15]. They demonstrated how machine learning techniques could automatically categorize and provide a detailed description of the person's activities and the status of the block task throughout each test.…”

“…This research focuses on the cube object used in the block design test (BDT) [14], a widely used neuropsychological assessment for evaluating visuospatial abilities. Traditionally, a neuropsychologist observes a person's accuracy, completion time, and overall problem-solving strategy and errors during the BDT [15]. However, subjective and qualitative assessments from a single perspective may be unreliable, calling for measurements from multiple perspectives.…”