ARTIFICIAL INTELLIGENCE–ASSISTED EARLY AUTISM SCREENING: INTEGRATING M-CHAT-R/F WITH DIGITAL BEHAVIORAL MARKERS
Keywords:
Keywords: autism; artificial intelligence; M-CHAT-R/F; early screening; digital biomarkers; clinical validationAbstract
Autism-specific screening can reduce delays in recognition, but accuracy and access vary across settings. M-CHAT-R/F is a validated two-stage parent-report tool for ages 16–30 months; it estimates likelihood and does not establish diagnosis. AI can combine questionnaire responses with video, gaze, speech, or movement features, potentially improving triage while introducing risks of bias, privacy loss, and dataset shift [1–5].
References
1. Hyman SL, Levy SE, Myers SM. Identification, evaluation, and management of children with autism spectrum disorder. Pediatrics. 2020;145:e20193447. doi:10.1542/peds.2019-3447.
2. Zwaigenbaum L, Bauman ML, Fein D, et al. Early screening of autism spectrum disorder: recommendations for practice and research. Pediatrics. 2015;136(Suppl 1):S41–S59. doi:10.1542/peds.2014-3667D.
3. Robins DL, Casagrande K, Barton M, et al. Validation of the Modified Checklist for Autism in Toddlers, Revised with Follow-up (M-CHAT-R/F). Pediatrics. 2014;133:37–45. doi:10.1542/peds.2013-1813.
4. Wieckowski AT, Williams LN, Rando J, Lyall K, Robins DL. Sensitivity and specificity of the Modified Checklist for Autism in Toddlers (original and revised): a systematic review and meta-analysis. JAMA Pediatr. 2023;177:373–383. doi:10.1001/jamapediatrics.2022.5975.
5. Schjølberg S, Shic F, Volkmar FR, et al. What are we optimizing for in autism screening? Examination of algorithmic changes in the M-CHAT. Autism Res. 2022;15:296–304. doi:10.1002/aur.2643.
6. Tariq Q, Daniels J, Schwartz JN, et al. Mobile detection of autism through machine learning on home video: a development and prospective validation study. PLoS Med. 2018;15:e1002705. doi:10.1371/journal.pmed.1002705.
7. Abbas H, Garberson F, Glover E, Wall DP. Machine learning approach for early detection of autism by combining questionnaire and home video screening. J Am Med Inform Assoc. 2018;25:1000–1007. doi:10.1093/jamia/ocy039.
8. Jones W, Klaiman C, Richardson S, et al. Eye-tracking-based measurement of social visual engagement compared with expert clinical diagnosis of autism. JAMA. 2023;330:854–865. doi:10.1001/jama.2023.13295.
9. Keehn B, Kinnear M, Shic F, et al. Eye-tracking biomarkers and autism diagnosis in primary care. JAMA Netw Open. 2024;7:e2411190. doi:10.1001/jamanetworkopen.2024.11190.
10. Moon SJ, Hwang J, Kana R, Torous J, Kim JW. Accuracy of machine learning algorithms for the diagnosis of autism spectrum disorder: systematic review and meta-analysis of brain magnetic resonance imaging studies. Psychiatry Investig. 2019;16:129–140. doi:10.30773/pi.2018.11.12.1.
11. Solek P, Kaszyński J, Słowik A, et al. The role of artificial intelligence for early diagnostic tools of autism spectrum disorder: a systematic review. J Clin Med. 2025;14:1792. doi:10.3390/jcm14061792.
12. National Institute for Health and Care Excellence. Autism spectrum disorder in under 19s: recognition, referral and diagnosis (CG128). London: NICE; updated 2017.