Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results

Sultan Mohammad Manjur; Md Billal Hossain; Paul A. Constable; Dorothy A. Thompson; Fernando Marmolejo-Ramos; Irene O. Lee; David H. Skuse; Hugo F. Posada-Quintero

doi:10.1109/EMBC48229.2022.9871173

Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results

Sultan Mohammad Manjur, Md Billal Hossain, Paul A. Constable, Dorothy A. Thompson, Fernando Marmolejo-Ramos, Irene O. Lee, David H. Skuse, Hugo F. Posada-Quintero

College of Nursing and Health Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

21 Citations (Scopus)

Abstract

Autism spectrum disorder (ASD) is a neurodevelopmental condition that impacts language, communication and social interactions. The current diagnostic process for ASD is based upon a detailed multidisciplinary assessment. Currently no clinical biomarker exists to help in the diagnosis and monitoring of this condition that has a prevalence of approximately 1%. The electroretinogram (ERG), is a clinical test that records the electrical response of the retina to light. The ERG is a promising way to study different neurodevelopmental and neurodegenerative disorders, including ASD. In this study, we have proposed a machine learning based method to detect ASD from control subjects using the ERG waveform. We collected ERG signals from 47 control (CO) and 96 ASD individuals. We analyzed ERG signals both in the time and the spectral domain to gain insight into the statistically significant discriminating features between CO and ASD individuals. We evaluated the machine learning (ML) models using a subject independent cross validation-based approach. Time-domain features were able to detect ASD with a maximum 65% accuracy. The classification accuracy of our best ML model using time-domain and spectral features was 86%, with 98% sensitivity. Our preliminary results indicate that spectral analysis of ERG provides helpful information for the classification of ASD.

Original language	English
Title of host publication	44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society
Publisher	Institute of Electrical and Electronics Engineers
Pages	3435-3438
Number of pages	4
Volume	2022
ISBN (Electronic)	9781728127828
DOIs	https://doi.org/10.1109/EMBC48229.2022.9871173
Publication status	Published - 8 Sept 2022
Event	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Biomedical Engineering transforming the provision of healthcare: promoting wellness through personalized & predictable provision at the point of care - Glasgow, United Kingdom Duration: 11 Jul 2022 → 15 Jul 2022 Conference number: 44th https://embc.embs.org/2022/ (Conference website)

Publication series

Name	Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Publisher	Institute of Electrical and Electronics Engineers
Volume	2022
ISSN (Print)	2375-7477
ISSN (Electronic)	2694-0604

Conference

Conference	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Abbreviated title	EMBS 2022
Country/Territory	United Kingdom
City	Glasgow
Period	11/07/22 → 15/07/22
Other	This conference is themed, “Biomedical Engineering transforming the provision of healthcare: promoting wellness through personalized & predictable provision at the point of care”. The scientific tracks will cover the standard topics of the EMBS technical committees with an additional topic, consistent with the conference theme. Alongside the scientific sessions, there will be an exhibition comprising biomedical engineering companies, publishers, SMEs, start-ups, funded biomedical research, and Biomedical Engineering programs, Institutes, and Universities. The conference will provide networking opportunities for engineers, clinicians, scientists, and entrepreneurs, as well as for students and young professionals. The conference program consists of mini-symposia, workshops, invited sessions, oral and e-poster sessions, sessions for students and young professionals, and sessions for clinicians and entrepreneurs. Glasgow and Scotland, within which it sits, have been the center of innovation for scientific, medical and technical research for centuries – for example, John Macintyre established the world’s first hospital radiology department at Glasgow Royal Infirmary in 1896, and obstetric ultrasound was launched at the Queen Mother’s Hospital, Glasgow in the late 1950s. Many more technical and medical innovations are linked to Scotland and the wider UK – the seat of many scientific discoveries over many centuries.
Internet address	https://embc.embs.org/2022/ (Conference website)

Keywords

Autism
Sensitivity
Biological system modeling
Machine learning
Retina
Feature extraction
Time-domain analysis

Access to Document

10.1109/EMBC48229.2022.9871173Licence: In Copyright

Cite this

Manjur, S. M., Hossain, M. B., Constable, P. A., Thompson, D. A., Marmolejo-Ramos, F., Lee, I. O., Skuse, D. H., & Posada-Quintero, H. F. (2022). Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results. In 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (Vol. 2022, pp. 3435-3438). (Annual International Conference of the IEEE Engineering in Medicine and Biology Society; Vol. 2022). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC48229.2022.9871173

Manjur, Sultan Mohammad ; Hossain, Md Billal ; Constable, Paul A. et al. / Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning : Preliminary results. 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Vol. 2022 Institute of Electrical and Electronics Engineers, 2022. pp. 3435-3438 (Annual International Conference of the IEEE Engineering in Medicine and Biology Society).

@inproceedings{55b9ebecf4884c64835f3e5499a4d547,

title = "Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results",

abstract = "Autism spectrum disorder (ASD) is a neurodevelopmental condition that impacts language, communication and social interactions. The current diagnostic process for ASD is based upon a detailed multidisciplinary assessment. Currently no clinical biomarker exists to help in the diagnosis and monitoring of this condition that has a prevalence of approximately 1%. The electroretinogram (ERG), is a clinical test that records the electrical response of the retina to light. The ERG is a promising way to study different neurodevelopmental and neurodegenerative disorders, including ASD. In this study, we have proposed a machine learning based method to detect ASD from control subjects using the ERG waveform. We collected ERG signals from 47 control (CO) and 96 ASD individuals. We analyzed ERG signals both in the time and the spectral domain to gain insight into the statistically significant discriminating features between CO and ASD individuals. We evaluated the machine learning (ML) models using a subject independent cross validation-based approach. Time-domain features were able to detect ASD with a maximum 65% accuracy. The classification accuracy of our best ML model using time-domain and spectral features was 86%, with 98% sensitivity. Our preliminary results indicate that spectral analysis of ERG provides helpful information for the classification of ASD.",

keywords = "Autism, Sensitivity, Biological system modeling, Machine learning, Retina, Feature extraction, Time-domain analysis",

author = "Manjur, {Sultan Mohammad} and Hossain, {Md Billal} and Constable, {Paul A.} and Thompson, {Dorothy A.} and Fernando Marmolejo-Ramos and Lee, {Irene O.} and Skuse, {David H.} and Posada-Quintero, {Hugo F.}",

year = "2022",

month = sep,

day = "8",

doi = "10.1109/EMBC48229.2022.9871173",

language = "English",

volume = "2022",

series = "Annual International Conference of the IEEE Engineering in Medicine and Biology Society",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "3435--3438",

booktitle = "44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society",

address = "United States",

note = "44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society : Biomedical Engineering transforming the provision of healthcare: promoting wellness through personalized & predictable provision at the point of care, EMBS 2022 ; Conference date: 11-07-2022 Through 15-07-2022",

url = "https://embc.embs.org/2022/",

}

Manjur, SM, Hossain, MB, Constable, PA, Thompson, DA, Marmolejo-Ramos, F, Lee, IO, Skuse, DH & Posada-Quintero, HF 2022, Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results. in 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. vol. 2022, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 2022, Institute of Electrical and Electronics Engineers, pp. 3435-3438, 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Glasgow, United Kingdom, 11/07/22. https://doi.org/10.1109/EMBC48229.2022.9871173

Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results. / Manjur, Sultan Mohammad; Hossain, Md Billal; Constable, Paul A. et al.
44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Vol. 2022 Institute of Electrical and Electronics Engineers, 2022. p. 3435-3438 (Annual International Conference of the IEEE Engineering in Medicine and Biology Society; Vol. 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning

T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

AU - Manjur, Sultan Mohammad

AU - Hossain, Md Billal

AU - Constable, Paul A.

AU - Thompson, Dorothy A.

AU - Marmolejo-Ramos, Fernando

AU - Lee, Irene O.

AU - Skuse, David H.

AU - Posada-Quintero, Hugo F.

N1 - Conference code: 44th

PY - 2022/9/8

Y1 - 2022/9/8

N2 - Autism spectrum disorder (ASD) is a neurodevelopmental condition that impacts language, communication and social interactions. The current diagnostic process for ASD is based upon a detailed multidisciplinary assessment. Currently no clinical biomarker exists to help in the diagnosis and monitoring of this condition that has a prevalence of approximately 1%. The electroretinogram (ERG), is a clinical test that records the electrical response of the retina to light. The ERG is a promising way to study different neurodevelopmental and neurodegenerative disorders, including ASD. In this study, we have proposed a machine learning based method to detect ASD from control subjects using the ERG waveform. We collected ERG signals from 47 control (CO) and 96 ASD individuals. We analyzed ERG signals both in the time and the spectral domain to gain insight into the statistically significant discriminating features between CO and ASD individuals. We evaluated the machine learning (ML) models using a subject independent cross validation-based approach. Time-domain features were able to detect ASD with a maximum 65% accuracy. The classification accuracy of our best ML model using time-domain and spectral features was 86%, with 98% sensitivity. Our preliminary results indicate that spectral analysis of ERG provides helpful information for the classification of ASD.

AB - Autism spectrum disorder (ASD) is a neurodevelopmental condition that impacts language, communication and social interactions. The current diagnostic process for ASD is based upon a detailed multidisciplinary assessment. Currently no clinical biomarker exists to help in the diagnosis and monitoring of this condition that has a prevalence of approximately 1%. The electroretinogram (ERG), is a clinical test that records the electrical response of the retina to light. The ERG is a promising way to study different neurodevelopmental and neurodegenerative disorders, including ASD. In this study, we have proposed a machine learning based method to detect ASD from control subjects using the ERG waveform. We collected ERG signals from 47 control (CO) and 96 ASD individuals. We analyzed ERG signals both in the time and the spectral domain to gain insight into the statistically significant discriminating features between CO and ASD individuals. We evaluated the machine learning (ML) models using a subject independent cross validation-based approach. Time-domain features were able to detect ASD with a maximum 65% accuracy. The classification accuracy of our best ML model using time-domain and spectral features was 86%, with 98% sensitivity. Our preliminary results indicate that spectral analysis of ERG provides helpful information for the classification of ASD.

KW - Autism

KW - Sensitivity

KW - Biological system modeling

KW - Machine learning

KW - Retina

KW - Feature extraction

KW - Time-domain analysis

UR - http://www.scopus.com/inward/record.url?scp=85138127655&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/xpl/conhome/9870821/proceeding

U2 - 10.1109/EMBC48229.2022.9871173

DO - 10.1109/EMBC48229.2022.9871173

M3 - Conference contribution

C2 - 36083945

AN - SCOPUS:85138127655

VL - 2022

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology Society

SP - 3435

EP - 3438

BT - 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society

PB - Institute of Electrical and Electronics Engineers

Y2 - 11 July 2022 through 15 July 2022

ER -

Manjur SM, Hossain MB, Constable PA, Thompson DA, Marmolejo-Ramos F, Lee IO et al. Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results. In 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Vol. 2022. Institute of Electrical and Electronics Engineers. 2022. p. 3435-3438. (Annual International Conference of the IEEE Engineering in Medicine and Biology Society). doi: 10.1109/EMBC48229.2022.9871173

Detecting Autism Spectrum Disorder Using Spectral Analysis of Electroretinogram and Machine Learning: Preliminary results

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Discrete Wavelet Transform Analysis of the Electroretinogram in Autism Spectrum Disorder and Attention Deficit Hyperactivity Disorder

The electroretinogram b-wave amplitude: a differential physiological measure for Attention Deficit Hyperactivity Disorder and Autism Spectrum Disorder

Light-adapted electroretinogram differences in Autism Spectrum Disorder

Cite this