Prediction of Preterm Deliveries from EHG Signals Using Machine Learning

Paul Fergus, Pauline Cheung, Abir Hussain, Dhiya Al-jumeily, Chelsea Dobbins, Shamaila Iram, Zhi Wei (Editor)

Research output: Contribution to journalArticle

51 Citations (Scopus)

Abstract

There has been some improvement in the treatment of preterm infants, which has helped to increase their chance of survival. However, the rate of premature births is still globally increasing. As a result, this group of infants are most at risk of developing severe medical conditions that can affect the respiratory, gastrointestinal, immune, central nervous, auditory and visual systems. In extreme cases, this can also lead to long-term conditions, such as cerebral palsy, mental retardation, learning difficulties, including poor health and growth. In the US alone, the societal and economic cost of preterm births, in 2005, was estimated to be $26.2 billion, per annum. In the UK, this value was close to £2.95 billion, in 2009. Many believe that a better understanding of why preterm births occur, and a strategic focus on prevention, will help to improve the health of children and reduce healthcare costs. At present, most methods of preterm birth prediction are subjective. However, a strong body of evidence suggests the analysis of uterine electrical signals (Electrohysterography), could provide a viable way of diagnosing true labour and predict preterm deliveries. Most Electrohysterography studies focus on true labour detection during the final seven days, before labour. The challenge is to utilise Electrohysterography techniques to predict preterm delivery earlier in the pregnancy. This paper explores this idea further and presents a supervised machine learning approach that classifies term and preterm records, using an open source dataset containing 300 records (38 preterm and 262 term). The synthetic minority oversampling technique is used to oversample the minority preterm class, and cross validation techniques, are used to evaluate the dataset against other similar studies. Our approach shows an improvement on existing studies with 96% sensitivity, 90% specificity, and a 95% area under the curve value with 8% global error using the polynomial classifier.
LanguageEnglish
Article numbere77154
Number of pages16
JournalPLoS One
Volume8
Issue number10
DOIs
Publication statusPublished - 28 Oct 2013
Externally publishedYes

Fingerprint

premature birth
artificial intelligence
Premature Birth
Learning systems
Personnel
labor
prediction
Health
cerebral palsy
health care costs
economic costs
Premature Obstetric Labor
Costs
Classifiers
Cerebral Palsy
methodology
Premature Infants
Polynomials
Intellectual Disability
Health Care Costs

Cite this

Fergus, P., Cheung, P., Hussain, A., Al-jumeily, D., Dobbins, C., Iram, S., & Wei, Z. (Ed.) (2013). Prediction of Preterm Deliveries from EHG Signals Using Machine Learning. PLoS One, 8(10), [e77154]. https://doi.org/10.1371/journal.pone.0077154
Fergus, Paul ; Cheung, Pauline ; Hussain, Abir ; Al-jumeily, Dhiya ; Dobbins, Chelsea ; Iram, Shamaila ; Wei, Zhi (Editor). / Prediction of Preterm Deliveries from EHG Signals Using Machine Learning. In: PLoS One. 2013 ; Vol. 8, No. 10.
@article{5ceedd2997604857a2c71d84f938885d,
title = "Prediction of Preterm Deliveries from EHG Signals Using Machine Learning",
abstract = "There has been some improvement in the treatment of preterm infants, which has helped to increase their chance of survival. However, the rate of premature births is still globally increasing. As a result, this group of infants are most at risk of developing severe medical conditions that can affect the respiratory, gastrointestinal, immune, central nervous, auditory and visual systems. In extreme cases, this can also lead to long-term conditions, such as cerebral palsy, mental retardation, learning difficulties, including poor health and growth. In the US alone, the societal and economic cost of preterm births, in 2005, was estimated to be $26.2 billion, per annum. In the UK, this value was close to £2.95 billion, in 2009. Many believe that a better understanding of why preterm births occur, and a strategic focus on prevention, will help to improve the health of children and reduce healthcare costs. At present, most methods of preterm birth prediction are subjective. However, a strong body of evidence suggests the analysis of uterine electrical signals (Electrohysterography), could provide a viable way of diagnosing true labour and predict preterm deliveries. Most Electrohysterography studies focus on true labour detection during the final seven days, before labour. The challenge is to utilise Electrohysterography techniques to predict preterm delivery earlier in the pregnancy. This paper explores this idea further and presents a supervised machine learning approach that classifies term and preterm records, using an open source dataset containing 300 records (38 preterm and 262 term). The synthetic minority oversampling technique is used to oversample the minority preterm class, and cross validation techniques, are used to evaluate the dataset against other similar studies. Our approach shows an improvement on existing studies with 96{\%} sensitivity, 90{\%} specificity, and a 95{\%} area under the curve value with 8{\%} global error using the polynomial classifier.",
author = "Paul Fergus and Pauline Cheung and Abir Hussain and Dhiya Al-jumeily and Chelsea Dobbins and Shamaila Iram and Zhi Wei",
year = "2013",
month = "10",
day = "28",
doi = "10.1371/journal.pone.0077154",
language = "English",
volume = "8",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

Fergus, P, Cheung, P, Hussain, A, Al-jumeily, D, Dobbins, C, Iram, S & Wei, Z (ed.) 2013, 'Prediction of Preterm Deliveries from EHG Signals Using Machine Learning', PLoS One, vol. 8, no. 10, e77154. https://doi.org/10.1371/journal.pone.0077154

Prediction of Preterm Deliveries from EHG Signals Using Machine Learning. / Fergus, Paul; Cheung, Pauline; Hussain, Abir; Al-jumeily, Dhiya; Dobbins, Chelsea; Iram, Shamaila; Wei, Zhi (Editor).

In: PLoS One, Vol. 8, No. 10, e77154, 28.10.2013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of Preterm Deliveries from EHG Signals Using Machine Learning

AU - Fergus, Paul

AU - Cheung, Pauline

AU - Hussain, Abir

AU - Al-jumeily, Dhiya

AU - Dobbins, Chelsea

AU - Iram, Shamaila

A2 - Wei, Zhi

PY - 2013/10/28

Y1 - 2013/10/28

N2 - There has been some improvement in the treatment of preterm infants, which has helped to increase their chance of survival. However, the rate of premature births is still globally increasing. As a result, this group of infants are most at risk of developing severe medical conditions that can affect the respiratory, gastrointestinal, immune, central nervous, auditory and visual systems. In extreme cases, this can also lead to long-term conditions, such as cerebral palsy, mental retardation, learning difficulties, including poor health and growth. In the US alone, the societal and economic cost of preterm births, in 2005, was estimated to be $26.2 billion, per annum. In the UK, this value was close to £2.95 billion, in 2009. Many believe that a better understanding of why preterm births occur, and a strategic focus on prevention, will help to improve the health of children and reduce healthcare costs. At present, most methods of preterm birth prediction are subjective. However, a strong body of evidence suggests the analysis of uterine electrical signals (Electrohysterography), could provide a viable way of diagnosing true labour and predict preterm deliveries. Most Electrohysterography studies focus on true labour detection during the final seven days, before labour. The challenge is to utilise Electrohysterography techniques to predict preterm delivery earlier in the pregnancy. This paper explores this idea further and presents a supervised machine learning approach that classifies term and preterm records, using an open source dataset containing 300 records (38 preterm and 262 term). The synthetic minority oversampling technique is used to oversample the minority preterm class, and cross validation techniques, are used to evaluate the dataset against other similar studies. Our approach shows an improvement on existing studies with 96% sensitivity, 90% specificity, and a 95% area under the curve value with 8% global error using the polynomial classifier.

AB - There has been some improvement in the treatment of preterm infants, which has helped to increase their chance of survival. However, the rate of premature births is still globally increasing. As a result, this group of infants are most at risk of developing severe medical conditions that can affect the respiratory, gastrointestinal, immune, central nervous, auditory and visual systems. In extreme cases, this can also lead to long-term conditions, such as cerebral palsy, mental retardation, learning difficulties, including poor health and growth. In the US alone, the societal and economic cost of preterm births, in 2005, was estimated to be $26.2 billion, per annum. In the UK, this value was close to £2.95 billion, in 2009. Many believe that a better understanding of why preterm births occur, and a strategic focus on prevention, will help to improve the health of children and reduce healthcare costs. At present, most methods of preterm birth prediction are subjective. However, a strong body of evidence suggests the analysis of uterine electrical signals (Electrohysterography), could provide a viable way of diagnosing true labour and predict preterm deliveries. Most Electrohysterography studies focus on true labour detection during the final seven days, before labour. The challenge is to utilise Electrohysterography techniques to predict preterm delivery earlier in the pregnancy. This paper explores this idea further and presents a supervised machine learning approach that classifies term and preterm records, using an open source dataset containing 300 records (38 preterm and 262 term). The synthetic minority oversampling technique is used to oversample the minority preterm class, and cross validation techniques, are used to evaluate the dataset against other similar studies. Our approach shows an improvement on existing studies with 96% sensitivity, 90% specificity, and a 95% area under the curve value with 8% global error using the polynomial classifier.

UR - http://journals.plos.org/plosone/

U2 - 10.1371/journal.pone.0077154

DO - 10.1371/journal.pone.0077154

M3 - Article

VL - 8

JO - PLoS One

T2 - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 10

M1 - e77154

ER -

Fergus P, Cheung P, Hussain A, Al-jumeily D, Dobbins C, Iram S et al. Prediction of Preterm Deliveries from EHG Signals Using Machine Learning. PLoS One. 2013 Oct 28;8(10). e77154. https://doi.org/10.1371/journal.pone.0077154