Predicting academic success of autistic students in higher education.

Researchers studied 101 autistic university students to predict who would succeed academically. They found success could be predicted better for autistic students than other students. Different factors mattered at different stages: study choice concerns in first year, participation in prep programs for second year, and high school grades for graduation. Universities can use this information to identify students who need extra support early.

This study developed predictive models to identify factors associated with academic success among 101 autistic bachelor students, comparing them to students with other health conditions (n=2,465) and without health conditions (n=25,077). Using machine learning approaches with historical student data, researchers found that academic success was predictable for autistic students, with predictions being more precise than for non-autistic students. Key predictors varied by academic stage: aptitude and study choice concerns for first-year success, pre-education participation and early study delays for second-year outcomes, and high school academic performance for three-year degree completion. The findings suggest universities can use administrative data as early warning systems to develop targeted support interventions.

Universities can implement early warning systems using administrative data to identify autistic students at risk of academic difficulties. Tailored interventions should focus on study choice guidance in first year, pre-education programs, and addressing early study delays. High school performance should inform transition planning and support intensity.

Single study with relatively small sample of autistic students (n=101). Study type not specified in metadata, limiting assessment of methodological rigor. Predictive accuracy metrics not provided in abstract. Generalizability across different university systems unclear.

Autistic youths increasingly enter universities. We know from existing research that autistic students are at risk of dropping out or studying delays. Using machine learning and historical information of students, researchers can predict the academic success of bachelor students. However, we know little about what kind of information can predict whether autistic students will succeed in their studies and how accurate these predictions will be.In this research, we developed predictive models for the academic success of 101 autistic bachelor students.

We compared these models to 2,465 students with other health conditions and 25,077 students without health conditions. The research showed that the academic success of autistic students was predictable. Moreover, these predictions were more precise than predictions of the success of students without autism.For the success of the first bachelor year, concerns with aptitude and study choice were the most important predictors. Participation in pre-education and delays at the beginning of autistic students' studies were the most influential predictors for second-year success and delays in the second and final year of their bachelor's program.

In addition, academic performance in high school was the strongest predictor for degree completion in 3 years.These insights can enable universities to develop tailored support for autistic students. Using early warning signals from administrative data, institutions can lower dropout risk and increase degree completion for autistic students.