Motor and sensory features successfully decode autism spectrum disorder and combine with the original RDoC framework to boost diagnostic classification
Abstract
Sensory processing and motor coordination atypicalities are not commonly identified as primary characteristics of autism spectrum disorder (ASD), nor are they well captured in the NIMH's original Research Domain Criteria (RDoC) framework. Here, motor and sensory features performed similarly to RDoC features in support vector classification of 30 ASD youth against 33 typically developing controls. Combining sensory with RDoC features boosted classification performance, achieving a Matthews Correlation Coefficient (MCC) of 0.949 and balanced accuracy (BAcc) of 0.971 (p = 0.00020, calculated against a permuted null distribution). Sensory features alone successfully classified ASD (MCC = 0.565, BAcc = 0.773, p = 0.0222) against a clinically relevant control group of 26 youth with Developmental Coordination Disorder (DCD) and were in fact required to decode against DCD above chance. These findings highlight the importance of sensory and motor features to the ASD phenotype and their relevance to the RDoC framework.
Additional Information
© The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Received 12 March 2020; Accepted 25 March 2021; Published 09 April 2021. We would like to thank the research participants and their families who make this research possible. We would also like to thank Jonas Kaplan, Morteza Dehghani, and Kingson Man for consulting on machine learning techniques; Sharon Cermak, Marian Williams, and Emily Harnin for assisting with clinical diagnosis; and Mirella Dapretto, Susan Bookheimer, and Ralph Adolphs for discussions related to this topic. We would also like to thank past and present OTD residents in our laboratory—Alyssa Concha, Cristin Zeisler, Priscilla Ring, Ryann MacMurdo, Alexis Nalbach, and Anusha Hossain—as well as our undergraduate research assistants who assisted with data collection and entry. Data availability: The raw data supporting these findings have been deposited on the Open Science Framework (https://doi.org/10.17605/OSF.IO/UENM9). Code availability: The core custom Python code supporting these findings have been deposited on the Open Science Framework (https://doi.org/10.17605/OSF.IO/UENM9). This research was supported by the NIH Award No. R01HD079432. Author Contributions: L.H., A.K. and L.A-Z. conceived of the study and wrote the main manuscript and text. L.H., A.K. and U.K. completed the analyses. L.H. prepared the figures and tables. L.H., E.K., C.B. and A.J. collected the data. All authors reviewed the manuscript. The authors declare no competing interests.Attached Files
Published - s41598-021-87455-w.pdf
Supplemental Material - 41598_2021_87455_MOESM1_ESM.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:124e8690eeef7e7c03def9a023e4205a
|
2.0 MB | Preview Download |
|
md5:61a56feeda8ef58f3adbff8d6d882f5f
|
3.4 MB | Preview Download |
Additional details
- PMCID
- PMC8035204
- Eprint ID
- 108766
- Resolver ID
- CaltechAUTHORS:20210419-183427183
- R01HD079432
- NIH
- Created
-
2021-04-22Created from EPrint's datestamp field
- Updated
-
2021-04-22Created from EPrint's last_modified field