Predicting academic success of autistic students in higher education.
Theo Bakker, Lydia Krabbendam, Sandjai Bhulai and 2 others
PMID 36602222WHAT IT FOUND
Administrative data like age, secondary school grades, and application timing can predict which autistic students are at risk of dropping out.
The models were more accurate for autistic students than for their peers, but overall predictive power remained low.
Key findings
01The best-performing models for autistic students outperformed the baseline 'best guess' (no information rate) for dropout after 1 and 2 years and for success after 3 years.
02Academic success was more predictable for autistic students than for non-autistic peers, with the accuracy advantage over the baseline increasing from 5.5% in year 1 to 21.4% by year 3.
03Key predictors available before enrollment included age, average secondary education grades, and the number of days between application and the start of the academic year.
STILL TO COME
How it was doneWhat they foundWhat it means for OTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The sample of autistic students was small (101 participants), which limits the generalizability and stability of the predictive models. The study only included students who disclosed their diagnosis and applied for accommodations, potentially excluding those with greater unmet needs or who did not seek support. The models relied solely on pre-enrollment data, ignoring early university performance which might be a stronger predictor. Outliers were removed, meaning the models do not account for extreme cases. The study could not control for unmeasured social or institutional factors that influence academic success.
Declared interests
The authors declared no potential conflicts of interest.
The easy way to misread this
Do not interpret these models as highly accurate or clinically ready for individual decision-making. While they outperformed random guessing for autistic students, the overall predictive power was low, and the small sample size means results should be treated as exploratory rather than definitive.