Detection of developmental language disorder in Cypriot Greek children using a neural network algorithm
This work addresses early identification of DLD in a specific child population, potentially enhancing clinical assessment, but it is incremental as it applies an existing neural network method to new data.
The study tackled the problem of detecting developmental language disorder (DLD) in Cypriot Greek children by developing a neural network model trained on perceptual and production data from 30 children, achieving high classification accuracy across metrics like accuracy, precision, recall, F1 score, and ROC/AUC.
Children with developmental language disorder (DLD) encounter difficulties in acquiring various language structures. Early identification and intervention are crucial to prevent negative long-term outcomes impacting the academic, social, and emotional development of children. The study aims to develop an automated method for the identification of DLD using artificial intelligence, specifically a neural network machine learning algorithm. This protocol is applied for the first time in a Cypriot Greek child population with DLD. The neural network model was trained using perceptual and production data elicited from 15 children with DLD and 15 healthy controls in the age range of 7;10 until 10;4. The k-fold technique was used to crossvalidate the algorithm. The performance of the model was evaluated using metrics such as accuracy, precision, recall, F1 score, and ROC/AUC curve to assess its ability to make accurate predictions on a set of unseen data. The results demonstrated high classification values for all metrics, indicating the high accuracy of the neural model in classifying children with DLD. Additionally, the variable importance analysis revealed that the language production skills of children had a more significant impact on the performance of the model compared to perception skills. Machine learning paradigms provide effective discrimination between children with DLD and those with TD, with the potential to enhance clinical assessment and facilitate earlier and more efficient detection of the disorder.