California based company Cognoa is using machine learning to detect cognitive disorders in children up to 13 months earlier than traditional diagnosis methods. The company’s VP of data science, Halim Abbas, told Which-50 a machine learning approach is ideal for detecting developmental delays.
“Machine learning algorithms can ingest very large numbers of historical patient records, and use them to capture incredibly subtle patterns that might indicate the presence of cognitive disorders.”
“Highly resilient to noise and subjectivity” the process ultimately produces models that can approximate the understanding of what constitutes autism from the many different doctors who contributed to the dataset, Abbas said.
“This allows Machine Learning screeners to succeed when applied at complex assessments like autism spectrum disorder, which can present a wide and highly variant set of behavioural phenotypes.”
The Cognoa method is much more accessible, according to Abbas. Users can perform the screening process to detect disorders at home using their smartphone. Cognoa offers there method to organisations as a HR benefit for employees and their mission is is to “make cognitive developmental screening accessible to every parent at home,” Abbas said.
“Machine learning screeners can run autonomously and at scale, and can be made accessible to parents at home via web and mobile outlets. This makes for affordable, scalable, and easy-to-use screening with immediate results that are potentially as reliable if not more reliable than the traditional clinical methods.”
The high tech approach to detection is in contrast to the traditional methods which Abbas described as “tedious, cumbersome, time consuming, and expensive”.
“Autism screening is currently done using pen and paper methods relying on answering lengthy multiple choice questionnaires and summing up answer codes.”
Improving this technique is potentially huge. According to Abbas, clinical trials showed early intervention programs, as young as 18 months, resulted in “great improvement in cognitive and language abilities and adaptive behaviour and fewer autism symptoms in the long run”.
“Diagnosis within the first few years of life dramatically improves the outlook of children with autism, as it allows for intervention during a critical developmental time window while the child’s brain is still rapidly developing,” Abbas said.
Abbas is a leading data scientist who previously headed major projects at eBay and Teradata. In an profession experiencing a dearth of talent, Abbas had many suitors. But he told Which-50 Cognoa was a more fulfilling prospect.
“While all those fields were fun to tackle and exciting to innovate in, I felt they didn’t fully satisfy my inner calling to apply my skills for the good,” Abbas said.
“At Cognoa I feel that my accomplishments have direct impact on the lives of real parents and children out there, and that what we do touches upon a very personal aspect of people’s well being. After all, there probably isn’t a bigger gift to a parent than peace of mind about their young child.”
Earlier this year Cognoa secured $US 11 million in funding, taking their total funding to $US20.4 million. According to Abbas, Cognoa has already helped 300,000 parents.