Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression

David Chen; Steve Rust; En Ju D. Lin; Simon Lin; Leslie Nelson; Lindsay Alfano; Linda P. Lowes

doi:10.1145/3233547.3233572

Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression

David Chen, Steve Rust, En Ju D. Lin, Simon Lin, Leslie Nelson, Lindsay Alfano, Linda P. Lowes

Physical Therapy

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

2 Scopus citations

Abstract

Spinal muscular atrophy (SMA) is a common muscle disease that can lead to high rate of infant mortality. It is important to be able to quickly and accurately diagnose SMAs as well as track disease progression throughout the treatment process. This study introduced a framework for deriving movement features from motion tracking data, and applied a regularized regression method to predict the gold standard clinical measures for SMA, the CHOP INTEND Extremities Scores (CIES). Our results showed the CIES could be predicted with good accuracy using derived motion features and Elastic Net regression. An RMSE of 8.5 points on CIES was achieved in both cross-validation and prediction on the held-out set. A high ROC-AUC of 0.91 was achieved for discriminating SMA infants from Controls on both session and subject levels. It was concluded that motion tracking devices could potentially be used as a low-cost yet effective method to assess and monitor infants with SMA.

Original language	English (US)
Title of host publication	ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
Publisher	Association for Computing Machinery, Inc
Pages	474-481
Number of pages	8
ISBN (Electronic)	9781450357944
DOIs	https://doi.org/10.1145/3233547.3233572
State	Published - Aug 15 2018
Event	9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018 - Washington, United States Duration: Aug 29 2018 → Sep 1 2018

Publication series

Name	ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

Other

Other	9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018
Country/Territory	United States
City	Washington
Period	8/29/18 → 9/1/18

Keywords

Elastic net
Kinect
Motion tracking
Regularized regression
Spinal muscular atrophy

ASJC Scopus subject areas

Computer Science Applications
Software
Health Informatics
Biomedical Engineering

Access to Document

10.1145/3233547.3233572

Cite this

Chen, D., Rust, S., Lin, E. J. D., Lin, S., Nelson, L., Alfano, L., & Lowes, L. P. (2018). Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression. In ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 474-481). (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics). Association for Computing Machinery, Inc. https://doi.org/10.1145/3233547.3233572

Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression. / Chen, David; Rust, Steve; Lin, En Ju D. et al.
ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2018. p. 474-481 (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics).

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

Chen, D, Rust, S, Lin, EJD, Lin, S, Nelson, L, Alfano, L & Lowes, LP 2018, Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression. in ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, Association for Computing Machinery, Inc, pp. 474-481, 9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018, Washington, United States, 8/29/18. https://doi.org/10.1145/3233547.3233572

Chen D, Rust S, Lin EJD, Lin S, Nelson L, Alfano L et al. Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression. In ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc. 2018. p. 474-481. (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics). doi: 10.1145/3233547.3233572

Chen, David ; Rust, Steve ; Lin, En Ju D. et al. / Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression. ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2018. pp. 474-481 (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics).

@inproceedings{320f0facd1c3425586e7e7df788e7024,

title = "Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression",

abstract = "Spinal muscular atrophy (SMA) is a common muscle disease that can lead to high rate of infant mortality. It is important to be able to quickly and accurately diagnose SMAs as well as track disease progression throughout the treatment process. This study introduced a framework for deriving movement features from motion tracking data, and applied a regularized regression method to predict the gold standard clinical measures for SMA, the CHOP INTEND Extremities Scores (CIES). Our results showed the CIES could be predicted with good accuracy using derived motion features and Elastic Net regression. An RMSE of 8.5 points on CIES was achieved in both cross-validation and prediction on the held-out set. A high ROC-AUC of 0.91 was achieved for discriminating SMA infants from Controls on both session and subject levels. It was concluded that motion tracking devices could potentially be used as a low-cost yet effective method to assess and monitor infants with SMA.",

keywords = "Elastic net, Kinect, Motion tracking, Regularized regression, Spinal muscular atrophy",

author = "David Chen and Steve Rust and Lin, {En Ju D.} and Simon Lin and Leslie Nelson and Lindsay Alfano and Lowes, {Linda P.}",

note = "Publisher Copyright: {\textcopyright} 2018 ACM.; 9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018 ; Conference date: 29-08-2018 Through 01-09-2018",

year = "2018",

month = aug,

day = "15",

doi = "10.1145/3233547.3233572",

language = "English (US)",

series = "ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",

publisher = "Association for Computing Machinery, Inc",

pages = "474--481",

booktitle = "ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",

}

TY - GEN

T1 - Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression

AU - Chen, David

AU - Rust, Steve

AU - Lin, En Ju D.

AU - Lin, Simon

AU - Nelson, Leslie

AU - Alfano, Lindsay

AU - Lowes, Linda P.

PY - 2018/8/15

Y1 - 2018/8/15

N2 - Spinal muscular atrophy (SMA) is a common muscle disease that can lead to high rate of infant mortality. It is important to be able to quickly and accurately diagnose SMAs as well as track disease progression throughout the treatment process. This study introduced a framework for deriving movement features from motion tracking data, and applied a regularized regression method to predict the gold standard clinical measures for SMA, the CHOP INTEND Extremities Scores (CIES). Our results showed the CIES could be predicted with good accuracy using derived motion features and Elastic Net regression. An RMSE of 8.5 points on CIES was achieved in both cross-validation and prediction on the held-out set. A high ROC-AUC of 0.91 was achieved for discriminating SMA infants from Controls on both session and subject levels. It was concluded that motion tracking devices could potentially be used as a low-cost yet effective method to assess and monitor infants with SMA.

AB - Spinal muscular atrophy (SMA) is a common muscle disease that can lead to high rate of infant mortality. It is important to be able to quickly and accurately diagnose SMAs as well as track disease progression throughout the treatment process. This study introduced a framework for deriving movement features from motion tracking data, and applied a regularized regression method to predict the gold standard clinical measures for SMA, the CHOP INTEND Extremities Scores (CIES). Our results showed the CIES could be predicted with good accuracy using derived motion features and Elastic Net regression. An RMSE of 8.5 points on CIES was achieved in both cross-validation and prediction on the held-out set. A high ROC-AUC of 0.91 was achieved for discriminating SMA infants from Controls on both session and subject levels. It was concluded that motion tracking devices could potentially be used as a low-cost yet effective method to assess and monitor infants with SMA.

KW - Elastic net

KW - Kinect

KW - Motion tracking

KW - Regularized regression

KW - Spinal muscular atrophy

UR - http://www.scopus.com/inward/record.url?scp=85056110818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056110818&partnerID=8YFLogxK

U2 - 10.1145/3233547.3233572

DO - 10.1145/3233547.3233572

M3 - Conference contribution

AN - SCOPUS:85056110818

T3 - ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

SP - 474

EP - 481

BT - ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

PB - Association for Computing Machinery, Inc

T2 - 9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018

Y2 - 29 August 2018 through 1 September 2018

ER -

Prediction of Clinical Outcomes of Spinal Muscular Atrophy Using Motion Tracking Data and Elastic Net Regression

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this