Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder
Early diagnosis of autism spectrum disorder (ASD) is crucial for providing appropriate treatments and parental guidance from an early age. Yet, ASD diagnosis is a lengthy process, in part due to the lack of reliable biomarkers. We recently applied RNA-sequencing of peripheral blood samples from 73 A...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/24/3/2082 |
| _version_ | 1797624480272482304 |
|---|---|
| author | Irena Voinsky Oleg Y. Fridland Adi Aran Richard E. Frye David Gurwitz |
| author_facet | Irena Voinsky Oleg Y. Fridland Adi Aran Richard E. Frye David Gurwitz |
| author_sort | Irena Voinsky |
| collection | DOAJ |
| description | Early diagnosis of autism spectrum disorder (ASD) is crucial for providing appropriate treatments and parental guidance from an early age. Yet, ASD diagnosis is a lengthy process, in part due to the lack of reliable biomarkers. We recently applied RNA-sequencing of peripheral blood samples from 73 American and Israeli children with ASD and 26 neurotypically developing (NT) children to identify 10 genes with dysregulated blood expression levels in children with ASD. Machine learning (ML) analyzes data by computerized analytical model building and may be applied to building diagnostic tools based on the optimization of large datasets. Here, we present several ML-generated models, based on RNA expression datasets collected during our recently published RNA-seq study, as tentative tools for ASD diagnosis. Using the random forest classifier, two of our proposed models yield an accuracy of 82% in distinguishing children with ASD and NT children. Our proof-of-concept study requires refinement and independent validation by studies with far larger cohorts of children with ASD and NT children and should thus be perceived as starting point for building more accurate ML-based tools. Eventually, such tools may potentially provide an unbiased means to support the early diagnosis of ASD. |
| first_indexed | 2024-03-11T09:42:56Z |
| format | Article |
| id | doaj.art-8868ab9a198249a6a5de762568a17334 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-11T09:42:56Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-8868ab9a198249a6a5de762568a173342023-11-16T16:52:02ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672023-01-01243208210.3390/ijms24032082Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum DisorderIrena Voinsky0Oleg Y. Fridland1Adi Aran2Richard E. Frye3David Gurwitz4Department of Human Molecular Genetics and Biochemistry, Faculty of Medicine, Tel Aviv University, Tel Aviv 69978, IsraelIndependent Researcher, Tel Aviv 69978, IsraelShaare Zedek Medical Center, Jerusalem 91031, IsraelAutism Discovery and Treatment Foundation, Phoenix, AZ 85050, USADepartment of Human Molecular Genetics and Biochemistry, Faculty of Medicine, Tel Aviv University, Tel Aviv 69978, IsraelEarly diagnosis of autism spectrum disorder (ASD) is crucial for providing appropriate treatments and parental guidance from an early age. Yet, ASD diagnosis is a lengthy process, in part due to the lack of reliable biomarkers. We recently applied RNA-sequencing of peripheral blood samples from 73 American and Israeli children with ASD and 26 neurotypically developing (NT) children to identify 10 genes with dysregulated blood expression levels in children with ASD. Machine learning (ML) analyzes data by computerized analytical model building and may be applied to building diagnostic tools based on the optimization of large datasets. Here, we present several ML-generated models, based on RNA expression datasets collected during our recently published RNA-seq study, as tentative tools for ASD diagnosis. Using the random forest classifier, two of our proposed models yield an accuracy of 82% in distinguishing children with ASD and NT children. Our proof-of-concept study requires refinement and independent validation by studies with far larger cohorts of children with ASD and NT children and should thus be perceived as starting point for building more accurate ML-based tools. Eventually, such tools may potentially provide an unbiased means to support the early diagnosis of ASD.https://www.mdpi.com/1422-0067/24/3/2082machine learningRNA biomarkersblood RNA-sequencingautism spectrum disorder (ASD) |
| spellingShingle | Irena Voinsky Oleg Y. Fridland Adi Aran Richard E. Frye David Gurwitz Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder International Journal of Molecular Sciences machine learning RNA biomarkers blood RNA-sequencing autism spectrum disorder (ASD) |
| title | Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder |
| title_full | Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder |
| title_fullStr | Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder |
| title_full_unstemmed | Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder |
| title_short | Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder |
| title_sort | machine learning based blood rna signature for diagnosis of autism spectrum disorder |
| topic | machine learning RNA biomarkers blood RNA-sequencing autism spectrum disorder (ASD) |
| url | https://www.mdpi.com/1422-0067/24/3/2082 |
| work_keys_str_mv | AT irenavoinsky machinelearningbasedbloodrnasignaturefordiagnosisofautismspectrumdisorder AT olegyfridland machinelearningbasedbloodrnasignaturefordiagnosisofautismspectrumdisorder AT adiaran machinelearningbasedbloodrnasignaturefordiagnosisofautismspectrumdisorder AT richardefrye machinelearningbasedbloodrnasignaturefordiagnosisofautismspectrumdisorder AT davidgurwitz machinelearningbasedbloodrnasignaturefordiagnosisofautismspectrumdisorder |