Health insurance claims data can help predict the likelihood of autism in children

Health insurance claims data can help predict the likelihood of autism in children

Health insurance claims could do more than just help pay for health problems; They could help predict them, according to new findings from a Penn State interdisciplinary research team published in BMJ Health & Care Informatics. Researchers developed machine learning models that assess the relationships between hundreds of clinical variables, including doctor visits and health services for seemingly unrelated conditions, to predict the likelihood of autism spectrum disorder in young children.

Insurance claims data, anonymized and widely available in marketing scan datasets, provides comprehensive, longitudinal medical details about the patient. The scientific literature in this area suggests that children with autism spectrum disorder also often experience higher rates of clinical symptoms such as: B. various types of infections, gastrointestinal problems, seizures and behavioral problems. These symptoms are not a cause of autism, but are common in children with autism, especially at a young age. That’s why we were inspired to summarize the medical information to quantify and predict this associated probability.”

Qiushi Chen, corresponding author, assistant professor of industrial and manufacturing engineering, Penn State College of Engineering

The researchers fed the data into machine learning models and trained them to evaluate hundreds of variables to find correlations associated with an increased likelihood of autism spectrum disorder.

“Autism spectrum disorder is a developmental disorder,” said co-author Guodong Liu, associate professor of public health sciences, of psychiatry and behavioral health, and of pediatrics at Penn State College of Medicine. "A doctor needs observations and multiple examinations to make a diagnosis. The process is usually lengthy and many children miss the window for early intervention - the most effective way to improve outcomes."

One of the most commonly used screening tools to identify young children with an increased likelihood of autism spectrum disorder is the Modified Checklist for Autism in Young Children (M-CHAT), which is typically given at routine child visits at 18 and 24 months of age. It consists of 20 questions that focus on behaviors related to eye contact, social interactions, and some physical milestones such as walking. Guardians respond based on their observations, but Chen says development varies so much at this age that the tool may misidentify children. As a result, children are often not formally diagnosed until they are four or five years old, meaning they miss out on potential early interventions for years.

“Our new model, which quantifies the sum of identified risk factors to determine the probability level, is already comparable to, and in some cases even slightly better than, the existing screening tool,” Chen said. “If we combine the model with the screening tool, we have a promising approach for clinicians.”

According to Liu, it would be practically feasible to integrate the model into the screening tool for clinical use.

“A unique strength of this work is that this clinical informatics approach can be easily integrated into the clinical workflow,” Liu said. “The predictive model could be embedded into a hospital's electronic medical record system, used to record patient health, as a clinical decision support tool to flag the high-risk children, allowing both physicians and families to take action earlier.”

This work, funded by the National Institutes of Health, the Penn State Social Science Research Institute and the Penn State College of Engineering, is the basis for a new $460,000 grant to Chen and Whitney Guthrie, clinical psychologist at the Children's Hospital of Philadelphia Center for Autism Research and assistant professor of Department of Psychiatry and Pediatrics at the University of Pennsylvania Perelman School of Medicine at the National Institute of Mental Health.

They are using the new grant to analyze exactly how well the combined hospital records and screening results predict autism diagnoses, and are also exploring other potential screening tools that could better equip doctors to help their patients.

“Not only are many children on the autism spectrum missed with the current tool, but many children identified by our screening tools also have long waiting lists due to our limited diagnostic capacity,” Guthrie said. "Although the M-CHAT detects many children, it also has a very high rate of false positives and false negatives, meaning many autistic children are missed and other children are referred for an autism evaluation when they do not need one. Both." Problems lead to long waits – often many months or even years – for further assessment. The consequences for children that are not addressed by our current screening tools are particularly important, as delayed diagnosis often results in children completely missing the window for early intervention. Pediatricians need better screening tools to accurately identify all children who need autism evaluation as early as possible.”

Part of the problem is the limited number of psychologists, developmental pediatricians and other pediatric development experts who can make a diagnosis of autism spectrum disorder. According to Chen, the solution could lie in industrial engineering.

“The key idea is to improve the way we use resources,” Chen said. “With Dr. Guthrie’s clinical expertise and my group’s modeling skills, we want to develop a tool that primary care physicians without specialized training can use to make confident assessments to diagnose children as early as possible so they can get the care they need as quickly as possible.” possible."

Other contributing authors include first author Yu-Hsin Chen, a doctoral student in industrial and manufacturing engineering who will also write her dissertation on the fellowship; and co-author Lan Kong, professor of public health sciences at Penn State College of Medicine.

Source:

Penn State

Reference:

Chen, YH., et al. (2022) Early detection of autism spectrum disorder in young children through machine learning using medical claims data. BMJ Health and Care Informatics. doi.org/10.1136/bmjhci-2022-100544.

.