Prediction of autism spectrum disorder diagnosis using nonlinear measures of language-related EEG at 6 and 12 months
- PMID: 34847887
- PMCID: PMC8903497
- DOI: 10.1186/s11689-021-09405-x
Prediction of autism spectrum disorder diagnosis using nonlinear measures of language-related EEG at 6 and 12 months
Abstract
Background: Early identification of autism spectrum disorder (ASD) provides an opportunity for early intervention and improved developmental outcomes. The use of electroencephalography (EEG) in infancy has shown promise in predicting later ASD diagnoses and in identifying neural mechanisms underlying the disorder. Given the high co-morbidity with language impairment, we and others have speculated that infants who are later diagnosed with ASD have altered language learning, including phoneme discrimination. Phoneme learning occurs rapidly in infancy, so altered neural substrates during the first year of life may serve as early, accurate indicators of later autism diagnosis.
Methods: Using EEG data collected at two different ages during a passive phoneme task in infants with high familial risk for ASD, we compared the predictive accuracy of a combination of feature selection and machine learning models at 6 months (during native phoneme learning) and 12 months (after native phoneme learning), and we identified a single model with strong predictive accuracy (100%) for both ages. Samples at both ages were matched in size and diagnoses (n = 14 with later ASD; n = 40 without ASD). Features included a combination of power and nonlinear measures across the 10‑20 montage electrodes and 6 frequency bands. Predictive features at each age were compared both by feature characteristics and EEG scalp location. Additional prediction analyses were performed on all EEGs collected at 12 months; this larger sample included 67 HR infants (27 HR-ASD, 40 HR-noASD).
Results: Using a combination of Pearson correlation feature selection and support vector machine classifier, 100% predictive diagnostic accuracy was observed at both 6 and 12 months. Predictive features differed between the models trained on 6- versus 12-month data. At 6 months, predictive features were biased to measures from central electrodes, power measures, and frequencies in the alpha range. At 12 months, predictive features were more distributed between power and nonlinear measures, and biased toward frequencies in the beta range. However, diagnosis prediction accuracy substantially decreased in the larger, more behaviorally heterogeneous 12-month sample.
Conclusions: These results demonstrate that speech processing EEG measures can facilitate earlier identification of ASD but emphasize the need for age-specific predictive models with large sample sizes to develop clinically relevant classification algorithms.
Keywords: Autism; EEG; Infant; Language development; Machine learning; Sensitive period.
© 2021. The Author(s).
Conflict of interest statement
The authors declare that they have no competing interests.
Figures
![Fig. 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8903497/bin/11689_2021_9405_Fig1_HTML.gif)
![Fig. 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8903497/bin/11689_2021_9405_Fig2_HTML.gif)
![Fig. 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8903497/bin/11689_2021_9405_Fig3_HTML.gif)
Similar articles
-
Multivariate Neural Connectivity Patterns in Early Infancy Predict Later Autism Symptoms.Biol Psychiatry Cogn Neurosci Neuroimaging. 2021 Jan;6(1):59-69. doi: 10.1016/j.bpsc.2020.06.003. Epub 2020 Jun 13. Biol Psychiatry Cogn Neurosci Neuroimaging. 2021. PMID: 32798139 Free PMC article.
-
Association between spectral electroencephalography power and autism risk and diagnosis in early development.Autism Res. 2021 Jul;14(7):1390-1403. doi: 10.1002/aur.2518. Epub 2021 May 6. Autism Res. 2021. PMID: 33955195 Free PMC article.
-
Neural correlates of face processing associated with development of social communication in 12-month infants with familial risk of autism spectrum disorder.J Neurodev Disord. 2022 Jan 12;14(1):6. doi: 10.1186/s11689-021-09413-x. J Neurodev Disord. 2022. PMID: 35021990 Free PMC article.
-
Machine learning approaches for electroencephalography and magnetoencephalography analyses in autism spectrum disorder: A systematic review.Prog Neuropsychopharmacol Biol Psychiatry. 2023 Apr 20;123:110705. doi: 10.1016/j.pnpbp.2022.110705. Epub 2022 Dec 24. Prog Neuropsychopharmacol Biol Psychiatry. 2023. PMID: 36574922 Review.
-
Machine learning in autistic spectrum disorder behavioral research: A review and ways forward.Inform Health Soc Care. 2019 Sep;44(3):278-297. doi: 10.1080/17538157.2017.1399132. Epub 2018 Feb 13. Inform Health Soc Care. 2019. PMID: 29436887 Review.
Cited by
-
Reflections on the past two decades of Mind, Brain, and Education.Mind Brain Educ. 2024 Feb;18(1):6-16. doi: 10.1111/mbe.12407. Epub 2024 Mar 2. Mind Brain Educ. 2024. PMID: 38745857 No abstract available.
-
Implicit Grammatical Gender Representation in Italian Children with Autism without Intellectual/Language Disorder.Children (Basel). 2023 Oct 26;10(11):1737. doi: 10.3390/children10111737. Children (Basel). 2023. PMID: 38002828 Free PMC article.
-
Neural correlates and predictors of speech and language development in infants at elevated likelihood for autism: a systematic review.Front Hum Neurosci. 2023 Aug 17;17:1211676. doi: 10.3389/fnhum.2023.1211676. eCollection 2023. Front Hum Neurosci. 2023. PMID: 37662636 Free PMC article.
-
Socioeconomic and demographic risk factors of autism spectrum disorder among children and adolescents in Bangladesh: Evidence from a cross-sectional study in 2022.PLoS One. 2023 Aug 4;18(8):e0289220. doi: 10.1371/journal.pone.0289220. eCollection 2023. PLoS One. 2023. PMID: 37540667 Free PMC article.
-
A biomarker discovery framework for childhood anxiety.Front Psychiatry. 2023 Jul 17;14:1158569. doi: 10.3389/fpsyt.2023.1158569. eCollection 2023. Front Psychiatry. 2023. PMID: 37533889 Free PMC article.
References
-
- American Psychiatric Association . Diagnostic and Statistical Manual of Mental Disorders. 5 2013.
-
- United States Autism and developmental disabilities monitoring network surveillance year 2008 principal investigators. MMWR Surveill Summ. 2012;61:1–19. - PubMed
-
- Cohen H, Amerine-Dickens M, Smith T. Early intensive behavioral treatment: replication of the UCLA model in a community setting. J Dev Behav Pediatr. 2006;27. 10.1097/00004703-200604002-00013. - PubMed