Machine learning algorithms to classify spinal muscular atrophy subtypes
Citation Manager Formats
Make Comment
See Comments

This article requires a subscription to view the full text. If you have a subscription you may use the login form below to view the article. Access to this article can also be purchased.
Abstract
Objectives: The development of better biomarkers for disease assessment remains an ongoing effort across the spectrum of neurologic illnesses. One approach for refining biomarkers is based on the concept of machine learning, in which individual, unrelated biomarkers are simultaneously evaluated. In this cross-sectional study, we assess the possibility of using machine learning, incorporating both quantitative muscle ultrasound (QMU) and electrical impedance myography (EIM) data, for classification of muscles affected by spinal muscular atrophy (SMA).
Methods: Twenty-one normal subjects, 15 subjects with SMA type 2, and 10 subjects with SMA type 3 underwent EIM and QMU measurements of unilateral biceps, wrist extensors, quadriceps, and tibialis anterior. EIM and QMU parameters were then applied in combination using a support vector machine (SVM), a type of machine learning, in an attempt to accurately categorize 165 individual muscles.
Results: For all 3 classification problems, normal vs SMA, normal vs SMA 3, and SMA 2 vs SMA 3, use of SVM provided the greatest accuracy in discrimination, surpassing both EIM and QMU individually. For example, the accuracy, as measured by the receiver operating characteristic area under the curve (ROC-AUC) for the SVM discriminating SMA 2 muscles from SMA 3 muscles was 0.928; in comparison, the ROC-AUCs for EIM and QMU parameters alone were only 0.877 (p < 0.05) and 0.627 (p < 0.05), respectively.
Conclusions: Combining EIM and QMU data categorizes individual SMA-affected muscles with very high accuracy. Further investigation of this approach for classifying and for following the progression of neuromuscular illness is warranted.
GLOSSARY
- AUC=
- area under the curve;
- EIM=
- electrical impedance myography;
- PCA=
- principal component analysis;
- QMU=
- quantitative muscle ultrasound;
- ROC=
- receiver operating characteristic;
- SMA=
- spinal muscular atrophy;
- SVM=
- support vector machine
Footnotes
-
Study funding: Supported by the Spinal Muscular Atrophy Foundation.
- Received November 2, 2011.
- Accepted March 19, 2012.
- Copyright © 2012 by AAN Enterprises, Inc.
AAN Members
We have changed the login procedure to improve access between AAN.com and the Neurology journals. If you are experiencing issues, please log out of AAN.com and clear history and cookies. (For instructions by browser, please click the instruction pages below). After clearing, choose preferred Journal and select login for AAN Members. You will be redirected to a login page where you can log in with your AAN ID number and password. When you are returned to the Journal, your name should appear at the top right of the page.
AAN Non-Member Subscribers
Purchase access
For assistance, please contact:
AAN Members (800) 879-1960 or (612) 928-6000 (International)
Non-AAN Member subscribers (800) 638-3030 or (301) 223-2300 option 3, select 1 (international)
Sign Up
Information on how to subscribe to Neurology and Neurology: Clinical Practice can be found here
Purchase
Individual access to articles is available through the Add to Cart option on the article page. Access for 1 day (from the computer you are currently using) is US$ 39.00. Pay-per-view content is for the use of the payee only, and content may not be further distributed by print or electronic means. The payee may view, download, and/or print the article for his/her personal, scholarly, research, and educational use. Distributing copies (electronic or otherwise) of the article is not allowed.
Letters: Rapid online correspondence
REQUIREMENTS
You must ensure that your Disclosures have been updated within the previous six months. Please go to our Submission Site to add or update your Disclosure information.
Your co-authors must send a completed Publishing Agreement Form to Neurology Staff (not necessary for the lead/corresponding author as the form below will suffice) before you upload your comment.
If you are responding to a comment that was written about an article you originally authored:
You (and co-authors) do not need to fill out forms or check disclosures as author forms are still valid
and apply to letter.
Submission specifications:
- Submissions must be < 200 words with < 5 references. Reference 1 must be the article on which you are commenting.
- Submissions should not have more than 5 authors. (Exception: original author replies can include all original authors of the article)
- Submit only on articles published within 6 months of issue date.
- Do not be redundant. Read any comments already posted on the article prior to submission.
- Submitted comments are subject to editing and editor review prior to posting.
You May Also be Interested in
Dr. David E. Vaillancourt and Dr. Shannon Y. Chiu
► Watch
Related Articles
Topics Discussed
Alert Me
Recommended articles
-
Article
Machine Learning to Predict Delayed Cerebral Ischemia and Outcomes in Subarachnoid HemorrhageJude P.J. Savarraj, Georgene W. Hergenroeder, Liang Zhu et al.Neurology, November 12, 2020 -
Articles
Assessing spinal muscular atrophy with quantitative ultrasoundJim S. Wu, Basil T. Darras, Seward B. Rutkove et al.Neurology, August 09, 2010 -
Article
Machine Learning–Based Automatic Rating for Cardinal Symptoms of Parkinson DiseaseKye Won Park, Eun-Jae Lee, Jun Seong Lee et al.Neurology, February 10, 2021 -
Article
Bulbar muscle MRI changes in patients with SMA with reduced mouth opening and dysphagiaRenske I. Wadman, H. Willemijn van Bruggen, Theo D. Witkamp et al.Neurology, August 13, 2014