Predicting Language Difficulties in Middle Childhood From Early Developmental Milestones: A Comparison of Traditional Regression and Machine Learning Techniques

Conclusions The current study provides preliminary evidence that machine learning algorithms provide equivalent predictive accuracy to traditional methods. Furthermore, the inclusion of broader developmental skills did not improve predictive capability. Assessment of language at more than 1 time point is necessary to ensure children whose language delays emerge later are identified and supported.Supplemental Materialhttps://doi.org/10.23641/asha.6879719
Source: Journal of Speech, Language, and Hearing Research - Category: Speech-Language Pathology Source Type: research