| Neurodevelopmental disorders represent a significant global health challenge due to their widespread prevalence and profound impact on individual lives. The conventional diagnostic process, reliant on behavioral observations and clinical assessments, is often time-intensive and fraught with limitations. This article delves into an approach, utilizing voice and speech analysis for the identification of neurodevelopmental disorders, promising to enhance diagnostic efficiency, reduce costs, and improve patient outcomes. Our research focuses on employing machine learning techniques to create an automated system capable of early disorder detection based on vocal characteristics. We tested multiple classifiers, among which Random Forests and Decision Trees emerged as the most effective, each achieving an accuracy of 82%. This study not only underscores the potential of machine learning in medical diagnostics but also paves the way for more accessible and efficient screening methods for neurodevelopmental disorders |
*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.