Using machine learning to identify patterns of lifetime health problems in decedents with autism spectrum disorder.
Lifetime health codes can spot autism even after death, revealing more heart, gut, and motor problems but fewer cancers.
01Research in Context
What this study did
The team pulled every ICD code from the health records of 252 people who died with autism.
They fed the codes into a machine-learning model and asked it to spot patterns that separate the autism group from 252 matched controls.
All records covered the person’s whole life, not just one clinic visit.
What they found
The computer correctly flagged a large share of the autism decedents and ruled out a large share of controls.
People with autism had more heart, stomach, muscle, bladder, and drug-side-effect problems.
Surprise: they had lower rates of cancer than the control group.
How this fits with other research
Kou et al. (2019) also used tech—30-second eye-tracking—to separate autistic kids from peers. Both studies hit high accuracy, showing machines can catch autism in very different ways.
Arwert et al. (2020) pooled gait data and found movement markers; Lauren et al. did the same with lifetime health codes. Together they say “look beyond behavior—body and motion data also flag ASD.”
Mhatre et al. (2016) tracked Indian kids for 10 years and saw mostly good outcomes. Lauren’s picture looks darker because it only includes people who died. Same diagnosis, different slice of life, so no true clash—just different windows.
Why it matters
If you do intake for adult clients, ask for a full medical history. Heart, gut, or urinary issues can signal missed autism in older generations. Flagging these patterns early may guide both medical referrals and behavior-plan accommodations like extra bathroom breaks or medication reviews.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Add a quick medical-history checklist for new adult clients—circle heart, stomach, muscle, bladder, or multiple drug reactions and refer for full evaluation if several are present.
02At a glance
03Original abstract
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. Autism Res 2018, 11: 1120-1128. © 2018 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: This study looked at patterns of lifetime health problems to find differences between people with autism who had died and community controls who had died. People with autism had higher rates of most health problems, including cardiovascular, urinary, respiratory, digestive, and motor problems, in their electronic health records. They also had lower rates of cancer. More research is needed to understand these potential health risks as a large number of individuals with autism enter adulthood and middle age.
Autism research : official journal of the International Society for Autism Research, 2018 · doi:10.1002/aur.1960