Machine Learning for Developmental Screening based on Facial Expressions and Health Parameters

Abstract

The screening tools used by developmental therapists to diagnose sensory processing disorders are primarily manual and based on a static questionnaire. These screening sessions are prohibitively expensive for most parents and there are also no clear scoring criteria. Trained and experienced doctors are needed to examine and treat these youngsters. Early detection and treatment are critically required. Researchers and scientists struggled to model a child's sensory processing pattern. Modern technology makes it feasible to automatically record characteristics related to sensory processing, behavioural factors, and reactions to specific stimuli. A novel dataset is created using smartwatch sensor data and their facial expression as a response to stimuli and a simplified questionnaire. Real-time stress-related health metrics are gathered in response to stimuli. Using the suggested dataset, multiple machine learning models are trained, tested, and validated for the diagnosis of visual sensory processing disorders. With the use of these classification models, behavioral therapists will be able to detect visual sensory processing abnormalities and monitor the efficacy of treatment with less time, reduced effort, and few screening sessions. The experimentation of the proposed system is performed on the novel dataset. The performance of machine learning methods is evaluated using f1-score and standard deviation. The experimentation ensued with promising results. The framework is tested on the live dataset. The experimental results show that the proposed system outperforms the manual method of sensory processing disorder diagnosis by obtaining maximum f1-score of 1 and minimum standard deviation of 0 for decision tree and random forest classifier.