Identifying predictive behavioral markers: A demonstration using automatically reinforced self‐injurious behavior
Two quick behavioral markers tell you if automatically reinforced self-injury will respond to treatment, so you can switch plans early and save weeks.
01Research in Context
What this study did
Hagopian et al. (2018) looked for early red flags that tell us which kids with self-injury will do well in treatment.
They studied kids whose self-injury happens for no outside reward. The team watched small details before therapy started.
The goal was to give clinicians a quick scorecard so they do not waste weeks on the wrong plan.
What they found
Two simple markers gave a clear thumbs-up or thumbs-down about future success.
If a child scored well on these markers, the chosen treatment worked fast and kept working.
How this fits with other research
Fradet et al. (2025) took the same idea to youth detention. They used the first week of aggression data to flag who needs the most staff time.
Kohli et al. (2022) used machine learning to pick ABA goals for kids with autism. Both papers show data can choose the next step better than guess-work.
Cerasuolo et al. (2022) warn that no single predictor is magic. Their review says child traits mix together, so we still need human eyes on the case.
Why it matters
You can run the two-marker check in one short session. If scores are low, pivot early instead of riding out a failed plan for weeks. Pair this quick screen with your clinical eye and you spend less time on dead-end roads and more time on what actually keeps kids safe.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Run the two-marker probe in your next SIB assessment; if scores are low, move to sensory-based or dense-reinforcement options right away.
02At a glance
03Original abstract
Predictive biomarkers (PBioMs) are objective biological measures that predict response to medical treatments for diseases. The current study translates methods used in the field of precision medicine to identify PBioMs to identify parallel predictive behavioral markers (PBMs), defined as objective behavioral measures that predict response to treatment. We demonstrate the utility of this approach by examining the accuracy of two PBMs for automatically reinforced self-injurious behavior (ASIB). Results of the analysis indicated both functioned as good to excellent PBMs. We discuss the compatibility of this approach with applied behavior analysis, describe methods to identify additional PBMs, and posit that variables related to the mechanisms of problem behavior and putative mechanism of treatment action hold the most promise as potential PBMs. We discuss how this technology could guide individualized treatment selection, inform our understanding of problem behavior and mechanisms of treatment action, and help determine the conditional effectiveness of clinical procedures.
Journal of Applied Behavior Analysis, 2018 · doi:10.1002/jaba.477