Questioning the definition of Tourette syndrome—evidence from machine learning

Abstract

Tics in Tourette syndrome are often difficult to discern from single spontaneous movements or vocalizations in healthy people. In the present study, videos of patients with Tourette syndrome and healthy controls were taken and independently scored according to the Modified Rush Videotape Rating Scale. We included n = 101 patients with Tourette syndrome (71 males, 30 females, mean age 17.36 years ± 10.46 standard deviation) and n = 109 healthy controls (57 males, 52 females, mean age 17.62 years ± 8.78 standard deviation) in a machine learning-based analysis. The results showed that the severity of motor tics, but not vocal phenomena, is the best predictor to separate and classify patients with Tourette syndrome and healthy controls. This finding questions the validity of current diagnostic criteria for Tourette syndrome requiring the presence of both motor and vocal tics. In addition, the negligible importance of vocalizations has implications for medical practice, because current recommendations for Tourette syndrome probably also apply to the large group with chronic motor tic disorders.

Extra Movements in Healthy People: Challenging the Definition and Diagnostic Practice of Tic Disorders

“…As outlined in the introduction and according to Paulus et al, 10 EMs or EVs were operationally defined as spontaneously occurring non‐goal‐directed movements (or sounds) that in the present context (video recording) are not required or should not occur. Goal‐directed movements, for instance scratching and adjusting sitting (position/clothing/hair/glasses), were not considered EMs.…”

The Role of the Left Inferior Parietal Cortex in Gilles de la Tourette Syndrome—An rTMS Study

“…We calculated the mean values of the two raters when the total score or tic count per minute differed by less than 15%. When these scores differed by more than 15%, relevant video segments were discussed and reviewed to reach a consensus score, and a tic count per minute differed by less than 15% [ 27 ].…”

Automated Motor Tic Detection: A Machine Learning Approach

“…Video seconds without a present motor tic were rated with the intensity rating 0. Vocal tics were not included, because we found in a previous study of our group that on the basis of Rush video recordings, motor tics rather than vocal tics are the best predictor to distinguish between patients with GTS and healthy control subjects 23 . In addition, the analysis of vocal tics would have required sound signal processing, which was not the focus of this study.…”