Automated detection of repetitive motor behaviors as an outcome measurement in intellectual and developmental disabilities
A $20 wrist accelerometer gives you 80-a large share accurate counts of hand flapping and body rocking without any setup fuss.
01Research in Context
What this study did
The team tested a cheap wrist or torso accelerometer.
They wanted to see if it could spot hand flapping and body rocking.
They used the adults with ID or DD. No custom setup was needed.
The same math worked for every person.
What they found
The device caught rocking and flapping 80-a large share of the time.
It worked without tuning for each client.
That beats pen-and-paper counts and saves staff time.
How this fits with other research
Lotfizadeh et al. (2020) took the same sensor idea further. They used fancier math to spot self-injury in kids with ASD. Their hit rate jumped to 94-a large share.
Maharaj et al. (2020) swapped the sensor for a Kinect camera. They still hit a large share accuracy for repetitive acts.
Ellement et al. (2021) used EMG to catch silent teeth grinding. All three papers show sensors can track hidden or fast behaviors better than eyes alone.
Together, they build a toolkit: accelerometers for flapping, EMG for bruxism, Kinect for whole-body moves.
Why it matters
You can tape a $20 accelerometer on a client’s wrist today. Run the free code and get real-time counts of stereotypy. Use the data to set baselines, track meds, or show parents clear graphs. No extra staff, no guesswork.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Strap an old Fitbit to one client’s wrist, run the open-source script, and compare the auto count to your current tally sheet.
02At a glance
03Original abstract
Repetitive sensory motor behaviors are a direct target for clinical treatment and a potential treatment endpoint for individuals with intellectual or developmental disabilities. By removing the burden associated with video annotation or direct observation, automated detection of stereotypy would allow for longer term monitoring in ecologic settings. We report automated detection of common stereotypical motor movements using commercially available accelerometers affixed to the body and a generalizable detection algorithm. The method achieved a sensitivity of 80% for body rocking and 93% for hand flapping without individualized algorithm training or foreknowledge of subject’s specific movements. This approach is well-suited for implementation in a continuous monitoring system outside of a clinical setting.
Journal of Autism and Developmental Disorders, 2018 · doi:10.1007/s10803-017-3408-6