Paisley: Preliminary validation of a novel app-based e-Screener for ASD in children 18-36 months.
Makayla G Honaker, Amy S Weitlauf, Amy R Swanson and 4 others
PMID 37602567WHAT IT FOUND
A new app-based screener helped community providers identify likely autism in toddlers with high accuracy.
Early interventionists and medical providers achieved similar discrimination rates as psychology providers. The tool is designed to support decision-making, not replace formal diagnosis.
Key findings
01The app-based screener demonstrated strong diagnostic accuracy with an area under the curve of 0.89 when compared to clinical diagnosis.
02Early interventionists and medical providers achieved similar discrimination rates (AUC 0.88) as psychology providers (AUC 0.97) when using the tool.
03Raising the scoring cutoff from 11 to 13 significantly improved specificity and positive predictive value to reduce false positives.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
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 study was conducted in a research laboratory with research assistants available to troubleshoot technology, so it is unknown how the app would function in a busy clinic without this support. The sample was clinically referred and had a high prevalence of autism (75%), which may inflate the positive predictive value compared to a general population screening. Providers did not give feedback to families during the study, so the impact on real-time clinical communication was not tested. The study did not document providers' prior familiarity with autism assessment, which could influence how well they use the tool.
Declared interests
Two authors received consultant fees from Adaptive Technology Consulting, a company that sells autism-related technology, prior to the study period. The study was funded by non-U.S. government and NIH extramural grants.
The easy way to misread this
Do not use this app as a standalone diagnostic tool. It is designed to support screening decisions by community providers, not to replace a comprehensive evaluation by a specialist. The high accuracy in this study was found in a clinically referred sample with a high rate of autism, which may not reflect performance in general population screening.