An objective tool for classification of language deficits in adults

Abstract

Aphasia is a language impairment associated with difficulty in production or comprehension of speech. Post stroke rehabilitation plays a vital role in recovery of these individuals and has been repeatedly suggested that immediate intervention should be initiated as soon as possible after the occurrence of stroke. The results of standardised assessment are often used as a basis for therapy and help in planning treatment goals and individualizing intervention. Variability being a hallmark of aphasic syndromes there is a need of objectivity in routine aphasic evaluation. Selecting domains and controlling parameter that needs to be worked upon for rehabilitation is still challenging for novice therapists. Artificial Neural Networks have been found to be very effective in various fields. The aim of the present study was to build an objective tool that provides assistive objective evaluation along with confidence index on aphasic individuals and possible rehabilitation domains. The study was carried out in two phases i.e. Phase I included the development of the tool using MATLAB software and Phase II of the study testing of the developed tool. As a part of training of ANN, profiles of 49 participants diagnosed with aphasia was loaded onto MATLAB software. Phase II aimed at assessing the efficacy of ANN. Cases diagnosed through subjective assessment was cross verified with the developed tool. Results on Cohen's Kappa evaluation revealed an overall 0.916, indicating a positive agreement between the developed objective tool and traditional subjective evaluation. Hence this tool can help guide novice clinicians in decision making as well as planning appropriate intervention strategies.