Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests

Nikhit Mago, Shikhar Srivastava, Rudresh D. Shirwaikar, U. Dinesh Acharya, Leslie Edward S. Lewis, M. Shivakumar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Machine Learning has a wide array of applications in the healthcare domain and has been used extensively for analyzing data. Apnea of Prematurity is a breathing disorder commonly observed in preterm infants. This paper compares the usage of Support Vector Machines and Random Forests, which are supervised learning algorithms, to predict Apnea of Prematurity at the end of the first week of the child's birth using data collected during the first three days of neonatal life. This paper also uses an optimization method called Synthesized Minority Oversampling Technique (SMOTE) to resolve the class imbalance problem observed in the data. Principal Component Analysis and one-hot encoding have been implemented for feature extraction and data preprocessing respectively. Among the results obtained, an AUC of 0.72 using the amalgamation of Random Forests and SMOTE is found to be the most accurate model.

Original languageEnglish
Title of host publicationProceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages693-697
Number of pages5
ISBN (Electronic)9781509052554
DOIs
Publication statusPublished - 01-01-2016
Event2nd International Conference on Contemporary Computing and Informatics, IC3I 2016 - Noida, India
Duration: 14-12-201617-12-2016

Conference

Conference2nd International Conference on Contemporary Computing and Informatics, IC3I 2016
CountryIndia
CityNoida
Period14-12-1617-12-16

Fingerprint

Supervised learning
Apnea
Principal component analysis
Learning algorithms
Support vector machines
Learning systems
Feature extraction
Newborn Infant
Principal Component Analysis
Premature Infants
Area Under Curve
Respiration
Learning
Parturition
Delivery of Health Care
Support Vector Machine
Forests
Prediction
Support vector machine
Minorities

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Information Systems and Management
  • Health Informatics
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Cite this

Mago, N., Srivastava, S., Shirwaikar, R. D., Acharya, U. D., Lewis, L. E. S., & Shivakumar, M. (2016). Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests. In Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016 (pp. 693-697). [7918051] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IC3I.2016.7918051
Mago, Nikhit ; Srivastava, Shikhar ; Shirwaikar, Rudresh D. ; Acharya, U. Dinesh ; Lewis, Leslie Edward S. ; Shivakumar, M. / Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests. Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 693-697
@inproceedings{0846b85d3f2e470295384e2794d8f08a,
title = "Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests",
abstract = "Machine Learning has a wide array of applications in the healthcare domain and has been used extensively for analyzing data. Apnea of Prematurity is a breathing disorder commonly observed in preterm infants. This paper compares the usage of Support Vector Machines and Random Forests, which are supervised learning algorithms, to predict Apnea of Prematurity at the end of the first week of the child's birth using data collected during the first three days of neonatal life. This paper also uses an optimization method called Synthesized Minority Oversampling Technique (SMOTE) to resolve the class imbalance problem observed in the data. Principal Component Analysis and one-hot encoding have been implemented for feature extraction and data preprocessing respectively. Among the results obtained, an AUC of 0.72 using the amalgamation of Random Forests and SMOTE is found to be the most accurate model.",
author = "Nikhit Mago and Shikhar Srivastava and Shirwaikar, {Rudresh D.} and Acharya, {U. Dinesh} and Lewis, {Leslie Edward S.} and M. Shivakumar",
year = "2016",
month = "1",
day = "1",
doi = "10.1109/IC3I.2016.7918051",
language = "English",
pages = "693--697",
booktitle = "Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Mago, N, Srivastava, S, Shirwaikar, RD, Acharya, UD, Lewis, LES & Shivakumar, M 2016, Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests. in Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016., 7918051, Institute of Electrical and Electronics Engineers Inc., pp. 693-697, 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016, Noida, India, 14-12-16. https://doi.org/10.1109/IC3I.2016.7918051

Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests. / Mago, Nikhit; Srivastava, Shikhar; Shirwaikar, Rudresh D.; Acharya, U. Dinesh; Lewis, Leslie Edward S.; Shivakumar, M.

Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 693-697 7918051.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests

AU - Mago, Nikhit

AU - Srivastava, Shikhar

AU - Shirwaikar, Rudresh D.

AU - Acharya, U. Dinesh

AU - Lewis, Leslie Edward S.

AU - Shivakumar, M.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Machine Learning has a wide array of applications in the healthcare domain and has been used extensively for analyzing data. Apnea of Prematurity is a breathing disorder commonly observed in preterm infants. This paper compares the usage of Support Vector Machines and Random Forests, which are supervised learning algorithms, to predict Apnea of Prematurity at the end of the first week of the child's birth using data collected during the first three days of neonatal life. This paper also uses an optimization method called Synthesized Minority Oversampling Technique (SMOTE) to resolve the class imbalance problem observed in the data. Principal Component Analysis and one-hot encoding have been implemented for feature extraction and data preprocessing respectively. Among the results obtained, an AUC of 0.72 using the amalgamation of Random Forests and SMOTE is found to be the most accurate model.

AB - Machine Learning has a wide array of applications in the healthcare domain and has been used extensively for analyzing data. Apnea of Prematurity is a breathing disorder commonly observed in preterm infants. This paper compares the usage of Support Vector Machines and Random Forests, which are supervised learning algorithms, to predict Apnea of Prematurity at the end of the first week of the child's birth using data collected during the first three days of neonatal life. This paper also uses an optimization method called Synthesized Minority Oversampling Technique (SMOTE) to resolve the class imbalance problem observed in the data. Principal Component Analysis and one-hot encoding have been implemented for feature extraction and data preprocessing respectively. Among the results obtained, an AUC of 0.72 using the amalgamation of Random Forests and SMOTE is found to be the most accurate model.

UR - http://www.scopus.com/inward/record.url?scp=85020033656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020033656&partnerID=8YFLogxK

U2 - 10.1109/IC3I.2016.7918051

DO - 10.1109/IC3I.2016.7918051

M3 - Conference contribution

SP - 693

EP - 697

BT - Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Mago N, Srivastava S, Shirwaikar RD, Acharya UD, Lewis LES, Shivakumar M. Prediction of Apnea of Prematurity in neonates using Support Vector Machines and Random Forests. In Proceedings of the 2016 2nd International Conference on Contemporary Computing and Informatics, IC3I 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 693-697. 7918051 https://doi.org/10.1109/IC3I.2016.7918051