Detection of Dysarthria Severity Levels Using ML Models

A motor speech problem called dysarthria impairs communication and drastically lowers quality of life. It results from damage to the nervous system, often caused by weakened or paralyzed speech muscles. While traditional speech therapy has proven effective in improving communication, this study aims to enhance diagnostic and treatment strategies using machine learning (ML) techniques. By analyzing patient-reported outcomes and clinical assessments, the proposed models seek to predict the severity levels of dysarthria more accurately. The study employs, various advanced Machine learning (ML) algorithms and ML methods are combined with clinical data to improve diagnosis and treatment by examining patient records, medical images, and genetic information. ML models recognize patterns for detecting diseases, predicting risks, and creating personalized treatment strategies, enhancing diagnostic precision, optimizing therapies, and facilitating early interventions for improved patient results. Feature selection and optimization techniques are applied to refine the models and improve predictive accuracy. This work addresses not only the speech deficits associated with dysarthria but also the overall quality of life for affected individuals. By integrating traditional speech therapy with modern technology and focusing on personalized experiences, the study proposes a holistic approach to treatment, paving the way for more personalized and responsive healthcare solutions.