Search

Existing diagnosis of the autism spectrum disorder (ASD) heavily depends on the informant’s evaluation of the patient’s behavior, which is both time consuming and labor demanding. In order to develop a rapid diagnostic tool with high accuracy, machine learning (ML) approaches have been proposed to explore the feasibility of identifying ASD with a limited number of features extracted from behavioral evaluation, neuroimaging and kinematic data. Though restricted and repetitive behavior (RRB) is one of the cardinal symptoms of ASD, no study has been conducted to investigate whether restricted kinematic features (RKF) could be used to identify ASD. The present study aimed to address this question. Twenty children with high functioning autism and twenty-three children with typical development (TD) were recruited. They were instructed to perform a motor task that required the execution of the utmost variant movement. Entropy and 95% range of the movement amplitude, velocity and acceleration were computed as indices of RKF. Five ML classifiers were trained and tested including support vector machine (SVM), Linear Discriminant Analysis (LDA), Decision tree (DT), Random forest (RF), and K nearest neighbor (KNN). Results showed that the KNN algorithm ( $k = 1$ ) yielded the highest classification accuracy with four kinematic features (accuracy: 88.37%, specificity: 91.3%, sensitivity: 85%, AUC: 0.8815). Our study demonstrated that RKF could help robustly identify ASD. It is inferred that the application of ML on genetic, neuroimaging, psychological and kinematic features might pose a considerable challenge to the current diagnostic criteria of ASD, and might potentially lead to an automated and objective diagnosis of ASD.

The speed and pen-pressure while sketching a spiral are lower among Parkinson’s disease (PD) patients with higher severity of the disease. However, the correlation between these features and the severity level (SL) of PD has been reported to be 0.4. There is a need for identifying parameters with a stronger correlation for considering this for accurate diagnosis of the disease. This study has proposed the use of the Composite Index of Speed and Pen-pressure (CISP) of sketching as a feature for analyzing the severity of PD. A total of 28 control group (CG) and 27 PD patients (total 55 participants) were recruited and assessed for Unified Parkinson’s Disease Rating Scale (UPDRS). They drew guided Archimedean spiral on an A3 sheet. Speed, pen-pressure, and CISP were computed and analyzed to obtain their correlation with severity of the disease. The correlation of speed, pen-pressure, and CISP with the severity of PD was −0.415, −0.584, and −0.641, respectively. Mann–Whitney U test confirmed that CISP was suitable to distinguish between PD and CG, while non-parametric k-sample Kruskal–Wallis test confirmed that it was significantly different for PD SL-1 and PD SL-3. This shows that CISP during spiral sketching may be used to differentiate between CG and PD and between PD SL-1 and PD SL-3 but not SL-2.