Summary: Using a machine learning algorithm to analyse health records of individuals with autism, researchers have been able to identify both increased and decreased health risks associated with ASD. The study reports autistic adults have increased risk of developing hypothyroidism, cardiovascular disease and other neurological issues. By contrast, those with ASD are at decreased risk of alcohol abuse, hypertension and metastatic cancers.
Source: University of Wisconsin Madison.
In the 1990s, the prevalence of autism spectrum disorder (ASD) among children rose sharply. These children are now entering adulthood, yet physicians and scientists know very little about the health outcomes they might face. Most studies of health have focused on children and adolescents.
However, new research published this week by scientists at the University of Wisconsin–Madison found that older adults with ASD may be at greater risk than people without the disorder of developing several health problems, including cardiovascular, urinary, respiratory and digestive issues.
“This is one of the few studies to look at health problems in a primarily middle-aged and older population of individuals with ASD,” says lead author, Lauren Bishop-Fitzpatrick. “Knowing what health issues adults with autism are more likely to encounter is critical to provide them with effective care and develop prevention strategies.”
With colleagues, Bishop-Fitzpatrick, assistant professor of social work and a researcher at the UW–Madison Waisman Center, used machine learning – a form of artificial intelligence – to analyze de-identified electronic health records of individuals who had received healthcare from the Marshfield Clinic in central Wisconsin and have since passed away.
They analyzed the health records of 91 individuals with ASD and more than 6,000 individuals without ASD from the same region as comparison. The ratio of patients with and without autism was roughly equal to 1:68, the most recent rate of ASD prevalence in the United States as calculated by the Centers for Disease Control and Prevention.
The researchers found that individuals with ASD had increased risks of developing several health complications, including various cardiovascular issues, hypothyroidism, and other neurological issues. They were at decreased risk of alcohol abuse, hypertension, and of developing metastatic cancers.
Based solely on information from patients’ electronic health records, the researchers were also able to independently predict with 93 percent accuracy whether or not a specific individual had ASD.
“These findings can help us direct healthcare resources and work on prevention efforts more efficiently,” says Bishop-Fitzpatrick. “For example, knowing that adults with ASD may be at higher risk of developing cardiovascular disease, we can start adapting techniques and healthcare measures that are already in place for the general population to best help adults with ASD.”
Learning more about the healthcare issues of adults with ASD could also help extend their lives. A 2016 study in Sweden found that individuals with ASD died at significantly younger ages – nearly 20 years earlier – compared to those without ASD.
The researchers hope their findings will lead to larger, more comprehensive studies that focus on the health issues faced by older individuals with ASD. Bishop-Fitzpatrick also plans to speak to individuals with autism and their families to understand their individual health issues and concerns at the same time that she works to understand these at the population level.
“Our goal is to create strategies and interventions that can help individuals with ASD live longer and healthier lives and to make sure they have the best quality of life for as long as possible,” says Bishop-Fitzpatrick.
Her study co-authors include UW–Madison colleagues Arezoo Movaghar, David Page, Leann Smith DaWalt, Jan Greenberg, and Marsha Mailick,, as well as Murray Brilliant, of Marshfield Clinic.
Funding: This study was supported by grants from the National Institute of Child Health and Human Development (U54 HD090256; T32HD007489), National Human Genome Research Institute (UO1HG8701), and National Center for Advancing Translational Sciences (UL1TR002373; KL2TR002374). The authors also received resources and support from the Marshfield Clinic Research Foundation, the Waisman Center, and the UW Institute for Clinical and Translational Research.
Source: Adityarup “Rup” Chakravorty – University of Wisconsin Madison
Publisher: Organized by NeuroscienceNews.com.
Image Source: NeuroscienceNews.com image is in the public domain.
Original Research: Abstract for “Using machine learning to identify patterns of lifetime health problems in decedents with autism spectrum disorder” by Lauren Bishop‐Fitzpatrick, Arezoo Movaghar, Jan S. Greenberg, David Page, Leann S. DaWalt, Murray H. Brilliant, and Marsha R. Mailick in Autism Research. Published May 2018.
Using machine learning to identify patterns of lifetime health problems in decedents with autism spectrum disorder
Very little is known about the health problems experienced by individuals with autism spectrum disorder (ASD) throughout their life course. We retrospectively analyzed diagnostic codes associated with de‐identified electronic health records using a machine learning algorithm to characterize diagnostic patterns in decedents with ASD and matched decedent community controls. Participants were 91 decedents with ASD and 6,186 sex and birth year matched decedent community controls who had died since 1979, the majority of whom were middle aged or older adults at the time of their death. We analyzed all ICD‐9 codes, V‐codes, and E‐codes available in the electronic health record and Elixhauser comorbidity categories associated with those codes. Diagnostic patterns distinguished decedents with ASD from decedent community controls with 75% sensitivity and 94% specificity solely based on their lifetime ICD‐9 codes, V‐codes, and E‐codes. Decedents with ASD had higher rates of most conditions, including cardiovascular disease, motor problems, ear problems, urinary problems, digestive problems, side effects from long‐term medication use, and nonspecific lab tests and encounters. In contrast, decedents with ASD had lower rates of cancer. Findings suggest distinctive lifetime diagnostic patterns among decedents with ASD and highlight the need for more research on health outcomes across the lifespan as the population of individuals with ASD ages. As a large wave of individuals with ASD diagnosed in the 1990s enters adulthood and middle age, knowledge about lifetime health problems will become increasingly important for care and prevention efforts.