Improving Peer Interactions and Social Skills in Preschool Children With Autism Using Pivotal Response Treatment.
A 5-minute resting fMRI can spot autism with 98% accuracy by watching attention networks flicker.
01Research in Context
What this study did
Long et al. (2025) ran a 5-minute resting-state fMRI scan on kids with autism. They tracked how brain networks talk to each other moment-to-moment. The team used this "dynamic" data to build a computer model that spots autism.
No tasks, no toys, just lying still. The scan looked at whole-brain chatter, especially the attention and social networks.
What they found
The model correctly labeled autism in 98 out of every 100 scans. The key clues were quick swings in attention-network links. Stronger swings matched worse social scores on standard tests.
Peak accuracy hit 98%. Mean accuracy stayed high at 95%. The whole process took five quiet minutes.
How this fits with other research
He et al. (2018) saw the opposite: preschoolers with autism had LESS flexible default-mode links, not more. The gap is timing. Changchun watched very young kids; Yuxin sampled a wider age mix. Early stiffness may give way to later over-flexibility.
Guo et al. (2024) used a cousin method and got a similar win. They tracked moment-to-moment brain-activity swings instead of network links. Both papers link looser dynamic control to worse social symptoms, backing the idea that "wobbly" brain timing marks autism.
Kovačič et al. (2020) mapped static, one-way roads in the autistic brain. Yuxin now shows the traffic lights on those roads blink out of sync. The new work updates the old map: dynamic beats static for spotting autism.
Why it matters
You may soon get a 5-minute, task-free scan that flags autism with near-perfect accuracy. No language demands, no long protocols. For now, keep an eye on referral centers offering research-grade fMRI. When the tool rolls out, you can use the report to confirm clinical hunches and shape social-skills goals that target attention networks first.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Add "attention-network flexibility" to your list of future biomarkers to watch.
02At a glance
03Original abstract
Autism spectrum disorder (ASD) is a prevalent neurodevelopmental disorder with severe cognitive impairment. Several studies have reported that brain functional network connectivity (FNC) has great potential for identifying ASD from healthy control (HC) and revealing the relationships between the brain and behaviors of ASD. However, few studies have explored dynamic large-scale FNC as a feature to identify individuals with ASD. This study used a time-sliding window method to study the dynamic FNC (dFNC) on the resting-state fMRI. To avoid arbitrarily determining the window length, we set a window length range of 10-75 TRs (TR = 2 s). We constructed linear support vector machine classifiers for all window length conditions. Using a nested 10-fold cross-validation framework, we obtained a grand average accuracy of 94.88% across window length conditions, which is higher than those reported in previous studies. In addition, we determined the optimal window length using the highest classification accuracy of 97.77%. Based on the optimal window length, we found that the dFNCs were located mainly in dorsal and ventral attention networks (DAN and VAN) and exhibited the highest weight in classification. Specifically, we found that the dFNC between DAN and temporal orbitofrontal network (TOFN) was significantly negatively correlated with social scores of ASD. Finally, using the dFNCs with high classification weights as features, we construct a model to predict the clinical score of ASD. Overall, our findings demonstrated that the dFNC could be a potential biomarker to identify ASD and provide new perspectives to detect cognitive changes in ASD.
Journal of autism and developmental disorders, 2025 · doi:10.1002/aur.2974