Identification of Infants at High Familiar Risk for Language-Learning Disorders (LLD) by Combining Machine Learning Techniques with EEG-based Brain Network Metrics

The population of children with language-learning disorders (LLD) is heterogeneous with a mixture of language deficits and also sensorimotor deficits linked to dynamic processing of the speech information (Catts et al., 2002). The core of research focused mainly on the hypothesis of whether deficits on auditory spectro-temporal processing can cause phonological impairment that potentially can lead to reading and language disorders (Bishop and Snowling, 2004). To answer the aforementioned questions, neuroscientists performed longitudinal studies of infants at genetic risk using neuroimaging methods and experimental protocols with main scope to understand the effects of auditory information to the development of language skills (Leppanen et al., 2002; Lyytinen et al., 2004).

from Physiology via xlomafota13 on Inoreader http://ift.tt/1Tqf98N
via IFTTT