Modulating population granularity for improved diagnosis of developmental dyspraxia from dynamic drawing analysis

In this paper, we describe a diagnostic tool for automated assessment of developmental dyspraxia among children using Beery's VMI test drawings. Various attributes extracted from the dynamic pen movements are used for this assessment. The test environment is exactly the same as that used in conventional VMI tests, except that the test population is partitioned into several age-bands. The population granularity significantly improved the diagnostic accuracy and also revealed interesting results despite limited data availability.