Prediction of Individual Autism Diagnostic Observation Schedule (ADOS) scores based on neural responses during live eye-to-eye contact
Data files
Sep 13, 2023 version files 311.15 MB
Abstract
Social difficulties are impactful in autism spectrum disorder (ASD), and links between these difficulties and underlying neural processes are active research questions. We present a multivariate classification method for neural data acquired from 36 participants during a live eye-to-eye contact task. Participants were either typically developed (TD) or diagnosed as ASD through gold-standard Autism Diagnostic Observation Schedule (ADOS) evaluation. We hypothesized multivariate classification could discriminate TD vs. ASD based on neural responses. Support vector machine (SVM) classification was able to discriminate between groups during the eye-contact interaction. In addition, it was found that underlying neural patterns contributing to binary classification also predicted measured ADOS scores with high correlation even though ADOS scores were not used for training. The correlation between observed and predicted ADOS scores was 0.72 (p < 0.002) for eye-to-eye contact. These findings suggest neural responses to live eye-to-eye contact are predictive of social symptomatology in ASD.
README: Prediction of Individual Autism Diagnostic Observation Schedule (ADOS) scores based on neural responses during live eye-to-eye contact
Included in the compressed folder ("ASDSVM.zip") are the fNIRS data collected from typically developing and autistic participants engaged in a face-to-face task in which direct eye contact is made on and off for 3-second intervals during a 30-second block design in which 18 seconds are task (face looking alternating with LED looking) and a rest phase (only LED looking) for 12 seconds. The zipped folder also included the 3D localizer information for each participant.
Description of the Data and file structure
The data file includes the following file structures:
There is one folder named ASDSVM. In this folder are all the files needed.
ADOS Scores for each participant are defined in the file ADOS4ASD.txt.
The onset times of each face-to-face interaction are defined in the onset.txt file.
The paradigm was defined as follows
- 0-10 seconds - baseline rest period
- 10-12 seconds - look at faces
- 13-15 seconds - look at LED Light
- 16-18 seconds - look at faces
- 19-21 seconds - look at LED Light
- 22-24 seconds - Look at faces
- 25-28 seconds - Look at LED light
- 29-39 seconds - Look at LED light
This pattern repeats 6 times with onsets at 10, 40, 70, 100, 130 and 160 seconds marking the initial face-looking onset.
For every TD and ASD subject, a series of files exists. These files are pre-pended with TD_SXX or ASD_SXX depending on the Subject Number (XX).
For each subject, there are expected to be a total of 5 files.
As described above, each file is prepended with the SubjectID. Each file name is subsequently named according to the run name or the 3D placement of the optodes on the head.
Runs are defined as either EyeEye (direct face-to-face interaction with live partner) or EyeVideo (Gaze at eyes of prerecorded video of partner). There are expected to be 2 runs per interaction.
In each of these text files the structure is as follows:
The first column is time.
The following columns are increasing channel numbers that contain OxyHb and DeOxyHb values per channel. The channel locations are defined in the xyz file as described below.
The 3D digitized optode locations are in MNI coordinates for the optodes on the subject in the file that has xyz in the filename.
The file is a CSV text file in which each row is a channel number and the channel location is defined as (X, Y, Z)
Sharing/access Information
Links to other publicly accessible locations of the data:
N/A
Was data derived from another source? No
If yes, list source(s): These data were orginally recorded and used in the following publication: https://doi.org/10.1371/journal.pone.0265798 Hirsch J, Zhang X, Noah JA, Dravida S, Naples A, Tiede M, Wolf JM, McPartland JC. Neural correlates of eye contact and social function in autism spectrum disorder. Plos one. 2022 Nov 9;17(11):e0265798.
Methods
Functional near-infrared spectroscopic brain imaging data were collected from a Shimadzu LABNIRS during a face to face interaction task from participants that were categorized as either TD or ASD by a trained clinician.
Univaraite and Multivariate analyses were used to determine classification of participants as TD or ASD using only FNIRS responses.
Typical GLM methods were used for univariate classification.
For multivariate classification, an SVM classifier was used to predict ADOS values for the ASD group and categorize all participants as either TD or ASD.