A combination of an autism questionnaire and online tests of emotion recognition, perception, and mental skills distinguished autistic from non-autistic adults with 92% accuracy, according to a new study published in the journal Translational Psychiatry. Led jointly by Erik Van der Burg and Robert M. Jertberg of Vrije Universiteit Amsterdam and the Amsterdam Public Health Research Institute, the team analyzed information from 552 Dutch adults, including 332 women, with an average age of about 38 years old. The sample included 286 adults who reported a formal autism diagnosis and 266 without. Participants completed online tasks assessing emotion recognition, sensory integration, attention, memory, and mental flexibility. The researchers extracted 54 measurements and used machine learning to classify participants. Using the online tasks alone, the model reached 81.8% accuracy in the full sample, but accuracy was 74% in an age and gender matched sample of 250 participants. A standard 28-item autism questionnaire alone reached a maximum accuracy of 83.2% in that matched group. Combining the questionnaire scores with task performance produced the strongest result with 92% accuracy, and the combined model correctly identified 88% of autistic participants.