Recently, Kaizen partnered with the Department of Digital Technology at New Zealand's Manukau Institute of Technology to arrive at a better solution to predict Autistic Spectrum Disorder (AD) with the help of state of the art machine learning models using Tensorflow.
The results were nothing short of outstanding.
Autistic Spectrum Disorder (ASD) is a neurodevelopment condition associated with significant healthcare costs, and early diagnosis can significantly reduce these.
Unfortunately, waiting times for an ASD diagnosis are very lengthy and procedures are not cost effective. The economic impact of autism and the increase in the number of ASD cases across the world reveals an urgent need for the development of easily implemented and effective screening methods. Parents and doctors face a difficult dilemma when it comes to detecting and treating autism spectrum disorder (ASD) in children.
The current process of early screening isn’t very accurate because it relies on a questionnaire that parents answer about their child’s behavior (usually at the child’s 18 month checkup).
These questionnaires often produce false positives. In fact, of the children whose parents report early signs of ASD on the questionnaire, Dawson says only 50 percent have that diagnosis confirmed by a licensed ASD clinician. And because there are so few licensed ASD clinicians qualified to follow-up with the many parents who report suspected ASD through the questionnaire, the wait time for children to receive a diagnosis could be well after the child’s third birthday—delaying treatment past the ideal window of time to potentially improve outcomes for children with ASD.
Thanks to Dr. Fadi Fayez Thabtah's initial work and guidance on his data from various client trials, Kaizen's consultants were able to create a machine learning model using Tensorflow that was able to identify autism in children with a 93% accuracy rate.
Furthermore, Kaizen was able to significantly reduce the number of false positives compared to a baseline of questionnaire-only diagnosis, below are the F1-Scores of the final trained model on the test data:
Is your organization interested in utilizing the predictive power of artificial intelligence, but aren't sure how?
Reach out to us and we'd be happy to discuss our work in machine learning and how we've helped many enterprise companies like yours accelerate their business intelligence!
Tags: machine learning, artificial intelligence, ai, tensorflow, predictive insight, business intelligence, healthcare, kaizen technology, cloud computing