Predictive Analytics Spots Autism Spectrum Disorders in Children

Using predictive analytics, University of Chicago researchers have developed a method to determine an eventual diagnosis of autism spectrum disorder (ASD) in young children. The new computational approach gathers data using diagnostic codes from previous doctor’s visits, eliminating the need for blood work or procedures to make a diagnosis.

According to researchers, this method reportedly reduced the number of false-positive ASD diagnoses produced by traditional screening methods by half. ASD can be diagnosed as early as two years old. However, false positives flagged by the initial screens commonly used today can delay confirming a true diagnosis.

With the importance of early intervention and the limited number of trained professionals, tools that can potentially reduce the number of patients required to undergo the lengthy, multistep process to receive an official positive diagnosis can significantly impact patient care.

Typically, questionnaire-based screening tools are used as the first step to identify ASD.

“But, these are prone to inaccuracies that may arise due to things such as a language barrier or culture barrier, and can give rise to inaccurate diagnoses. By only looking at the data as objectively as possible, our approach avoids some of the pitfalls of traditional screening approaches,” said lead author and senior scientist in the Zero Knowledge Discovery (ZeD) Lab, Dymtro Onishchenko said in a press release.

Using only sequences of ICD9 and ICD10 (International Classification of Diseases) diagnostic codes generated from past doctor’s visits, researchers leveraged known comorbidities of ASD to accurately predict an eventual positive diagnosis.

“Using the information already being gathered and being able to harness it for this kind of exploration and clinical use is exciting, and it really has the potential to be a game-changer,” said Peter J. Smith, MD.

The new algorithm determines an autism comorbid risk score (ACoR), which estimates the risk that a child with a given timeline of diagnoses will eventually receive a confirmed ASD diagnosis.

“The research applied advances in medical informatics to over 30 million de-identified diagnostic sequences representing over 15,000 distinct ICD codes, originating from the Truven Health Analytics and University of Chicago Medical Center (UCM) databases. The team separated these profiles into positive (i.e., an official ASD diagnosis) and controls,” the press release stated.

“They then applied algorithms that “learned” patterns representative of ASD-positive cohorts compared to ASD-negative cohorts. This research strategy allowed them to find which disease categories contribute to the ACoR and how much each category contributes.”

When the risk score is calculated for an individual patient, the researchers can quantify how far their specific diagnostic timeline differs from the positive or control group. When the risk score crosses a threshold, a patient can be flagged as potentially needing interventions.

By several standard metrics, ACoR outperformed the typically used questionnaire-based M-CHAT/F screening method as well as other methods that use comorbidity patterns. Additionally, researchers were able to flag patients as at-risk more than one year before their diagnosis. ACoR also performs consistently well among different racial and ethnic groups, according to researchers.

“A lot of what we have done is take the data and processes available in better connected systems and apply them to less well supported healthcare communities. We know for instance that African American individuals are frequently diagnosed later, which has an impact on long term care. This type of technology could overcome some of these structural barriers,” said Smith.

Using predictive analytics, researchers can promote early invention efforts, ensuring the best quality of care for patients.