Predicting Term and Preterm Delivery With Transabdominal Uterine Electromyography

Maner, William L.; Garfield, Robert E.; Maul, Holger; Olson, Gayle; Saade, George R.

doi:10.1097/00006250-200306000-00020

Cited by 59 publications

(128 citation statements)

References 13 publications

Supporting

Mentioning

109

Contrasting

Unclassified

Order By: Relevance

“…The pre-processing technique, used in [18], passed the EHG signal through a Butterworth filter configured to filter 0.8-4 Hz, 0.3-4 Hz, and 0.3-3Hz frequencies. However, [19] found that uterine electrical activity occurred within 1Hz and that the maternal heart-rate (ECG) was always higher than 1Hz. Furthermore, 95% of the patients measured had respiration rates of 0.33 Hz or less.…”

Section: Methodsmentioning

confidence: 99%

“…Each record in the dataset is approximately 30 minutes long, with a sample frequency of 20Hz, and a 16-bit resolution, with an amplitude range ± 2.5mV. The signals were filtered using an analogue three-pole Butterworth filter to obtain the 0.34 to 1Hz band, which contains most of the EHG information [19]. After filtering the dataset, both linear and nonlinear features are extracted to produce our feature set.…”

Section: A Raw Data Collectionmentioning

confidence: 99%

See 1 more Smart Citation

Advance Artificial Neural Network Classification Techniques Using EHG for Detecting Preterm Births

Idowu

Fergus

Hussain

et al. 2014

2014 Eighth International Conference on Complex, Intelligent and Software Intensive Systems

View full text Add to dashboard Cite

-Worldwide the rate of preterm birth is increasing, which presents significant health, developmental and economic problems. Current methods for predicting preterm births at an early stage are inadequate. Yet, there has been increasing evidence that the analysis of uterine electrical signals, from the abdominal surface, could provide an independent and easy way to diagnose true labour and predict preterm delivery. This analysis provides a heavy focus on the use of advanced machine learning techniques and Electrohysterography (EHG) signal processing. Most EHG studies have focused on true labour detection, in the window of around seven days before labour. However, this paper focuses on using such EHG signals to detect preterm births. In achieving this, the study uses an open dataset containing 262 records for women who delivered at term and 38 who delivered prematurely. The synthetic minority oversampling technique is utilized to overcome the issue with imbalanced datasets to produce a dataset containing 262 term records and 262 preterm records. Six different artificial neural networks were used to detect term and preterm records. The results show that the best performing classifier was the LMNC with 96% sensitivity, 92% specificity, 95% AUC and 6% mean error.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: A Raw Data Collectionmentioning

confidence: 99%

Advance Artificial Neural Network Classification Techniques Using EHG for Detecting Preterm Births

Idowu

Fergus

Hussain

et al. 2014

2014 Eighth International Conference on Complex, Intelligent and Software Intensive Systems

View full text Add to dashboard Cite

show abstract

“…[6,7,19,20]. Abdominal uterine EMG assessment is a simple, noninvasive, easy and well accepted method for understanding uterine physiology [3,[6][7][8][9][10][11][12][13].…”

Section: Discussionmentioning

confidence: 99%

“…Nowadays there is an increasing attention in two topics related to screening for PTD; uterine electrical activity evaluated by electromyography (EMG) and cervical shortening assessed by sonographic cervical length (CL) measurement [3][4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

“…The uterine electrical activity has been revisited, particularly after development of a new, noninvasive transabdominal method of evaluation, and improved filtering systems which reduce recording artifacts [3,[7][8][9][10]. When electrical activity involves many myometrial cells in immediate succession it produces action potentials [11,12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Raised electrical uterine activity and shortened cervical length could predict preterm delivery in a low-risk population

Grgić

Matijević

Kuna

2011

Arch Gynecol Obstet

View full text Add to dashboard Cite

Methods: Prospective study of 308 low-risk women. Shortened CL was defined as < 25 mm (< 5th centile), while raised EMG activity was defined as presence of > 20 action potentials in 20 minutes of assessment (> 95th centile). Outcome measures were diagnostic accuracy of both tests for prediction of PTD and early PTD (< 34 weeks).Results: The incidence of PTD was 23/308 (7.4%) while the incidence of early was 9/308 (2.9%). Shortened CL and raised EMG activity are significantly related to PTD (prevalence-weighted likelihood ratio (pwLR) 1.9 (95%CI 1.0-3.5) versus 9.5 (95%CI 2.5-35.7), but not to early PTD (pwLR 0.4 (95%CI 0.2-0.8) versus 0.6 (95%CI 0.3-1.7).Significant predictive value for early PTD was found only if shortened CL was concomitant with raised EMG activity (pwLR 4 (95% CI 1.3-14.3).Conclusion: Shortened CL and raised EMG activity in the second trimester have significant accuracy regarding the prediction of PTD in a low-risk population. However, in order to be useful as a predictor for early PTD, both tests must be positive.

show abstract

Identification of Human Term and Preterm Labor using Artificial Neural Networks on Uterine Electromyography Data

2007

Self Cite

View full text Add to dashboard Cite

show abstract

Predicting Term and Preterm Delivery With Transabdominal Uterine Electromyography

Cited by 59 publications

References 13 publications

Advance Artificial Neural Network Classification Techniques Using EHG for Detecting Preterm Births

Advance Artificial Neural Network Classification Techniques Using EHG for Detecting Preterm Births

Raised electrical uterine activity and shortened cervical length could predict preterm delivery in a low-risk population

Identification of Human Term and Preterm Labor using Artificial Neural Networks on Uterine Electromyography Data

Contact Info

Product

Resources

About