Refining developmental coordination disorder subtyping with multivariate statistical methods

Abstract

BackgroundWith a large number of potentially relevant clinical indicators penalization and ensemble learning methods are thought to provide better predictive performance than usual linear predictors. However, little is known about how they perform in clinical studies where few cases are available. We used Random Forests and Partial Least Squares Discriminant Analysis to select the most salient impairments in Developmental Coordination Disorder (DCD) and assess patients similarity.MethodsWe considered a wide-range testing battery for various neuropsychological and visuo-motor impairments which aimed at characterizing subtypes of DCD in a sample of 63 children. Classifiers were optimized on a training sample, and they were used subsequently to rank the 49 items according to a permuted measure of variable importance. In addition, subtyping consistency was assessed with cluster analysis on the training sample. Clustering fitness and predictive accuracy were evaluated on the validation sample.ResultsBoth classifiers yielded a relevant subset of items impairments that altogether accounted for a sharp discrimination between three DCD subtypes: ideomotor, visual-spatial and constructional, and mixt dyspraxia. The main impairments that were found to characterize the three subtypes were: digital perception, imitations of gestures, digital praxia, lego blocks, visual spatial structuration, visual motor integration, coordination between upper and lower limbs. Classification accuracy was above 90% for all classifiers, and clustering fitness was found to be satisfactory.ConclusionsRandom Forests and Partial Least Squares Discriminant Analysis are useful tools to extract salient features from a large pool of correlated binary predictors, but also provide a way to assess individuals proximities in a reduced factor space. Less than 15 neuro-visual, neuro-psychomotor and neuro-psychological tests might be required to provide a sensitive and specific diagnostic of DCD on this particular sample, and isolated markers might be used to refine our understanding of DCD in future studies.

Untitled

“…In researches on physical education and sports discriminant function is used for classification of pupils by their motivation for sports practicing (Milić, Milavić, & Grgantov, 2014;Cieslicka, Napierala, Stankiewicz, & Iermakov, 2012), by motor functioning (Gert-Jan & Benjamin, 2011;Kozina & Iermakov, 2015), for classification of groups into sportsmen and not sportsmen (Bondarenko, 2011;Lulzim, 2012), for determination of children's physical condition dynamic under influence of special programs (Golenko, Mihuta, & Kuzmin, 2009;du Toit, Pienaar, & Truter, 2011), for final control of children's and adolescents' functional and motor fitness (Vertel & Gradusov, 2011;Ivashchenko et al, 2015c;Khudolii et al, 2015aKhudolii et al, , 2015b. Discriminant analysis is a useful tool for determination of physical condition characteristic features (Lalanne, Falissard, Golse, & Vaivre-Douret, 2012). In discriminant analysis body mass index should be regarded as an important element for studying of physical condition's typology (Ko & You, 2015).…”

Attention deficit hyperactivity disorder and developmental coordination disorder: Two separate disorders or do they share a common etiology.

“…Subtypes have been proposed in the literature including ideomotor, visual-spatial and constructional, and mixed dyspraxia [45,46]. The hypothesis that DCD may not be a uniform disorder has also been discussed [11,46].…”

Executive Difficulties in Developmental Coordination Disorder: Methodological Issues and Future Directions

“…These disorders, such as Attention Deficit-Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD), often have different profiles of EF difficulties [48] and it may be that EF impairments in DCD in some of the studies are related to these overlapping symptoms or diagnoses, rather than motor difficulties that are central to the disorder. Some researchers have suggested that only a subgroup of individuals with DCD have executive function problems [49][50][51] and that these cases may be those with more cooccurring features of other developmental disorders. However, research suggests that even those children with DCD with relatively 'pure' motor difficulties (i.e., no other clinical diagnoses) are impaired across a range of EF tasks [21,42].…”

“…Throughout this review of the literature into EF in DCD, it has become clear that definitional, measurement, diagnostic and contextual issues associated with the study of EF need to be considered fully before we can understand if difficulties in EF are evident across the disorder, or whether these difficulties are confined to a subgroup with a range of other impairments [49][50][51]. Furthermore, it will be important to understand whether there are different constellations of EF impairments in DCD (e.g., some individuals may have problems with executive-loaded working memory and planning, while others are more impaired in inhibition and switching), and if these varying patterns of impairment have a significant effect on overall functioning.…”