A data mining approach using cortical thickness for diagnosis and characterization of essential tremor.

摘要

Essential tremor (ET) is one of the most prevalent movement disorders. Being that it is a commondisorder, its diagnosis is considered routine. However, misdiagnoses may occur regularly. Over thepast decade, several studies have identified brain morphometric changes in ET, but these changesremain poorly understood. Here, we tested the informativeness of measuring cortical thickness forthe purposes of ET diagnosis, applying feature selection and machine learning methods to a studysample of 18 patients with ET and 18 age- and sex-matched healthy control subjects. We found thatcortical thickness features alone distinguished the two, ET from controls, with 81% diagnostic accuracy.More specifically, roughness (i.e., the standard deviation of cortical thickness) of the right inferiorparietal and right fusiform areas was shown to play a key role in ET characterization. Moreover, thesefeatures allowed us to identify subgroups of ET patients as well as healthy subjects at risk for ET. Sincetreatment of tremors is disease specific, accurate and early diagnosis plays an important role in tremormanagement. Supporting the clinical diagnosis with novel computer approaches based on the objectiveevaluation of neuroimage data, like the one presented here, may represent a significant step in thisdirection.