scholarly journals Electrohysterogram for ANN-Based Prediction of Imminent Labor in Women with Threatened Preterm Labor Undergoing Tocolytic Therapy

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2681
Author(s):  
J. Mas-Cabo ◽  
G. Prats-Boluda ◽  
J. Garcia-Casado ◽  
J. Alberola-Rubio ◽  
R. Monfort-Ortiz ◽  
...  

Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy and entails high costs for health systems. Currently, no reliable labor proximity prediction techniques are available for clinical use. Regular checks by uterine electrohysterogram (EHG) for predicting preterm labor have been widely studied. The aim of the present study was to assess the feasibility of predicting labor with a 7- and 14-day time horizon in TPL women, who may be under tocolytic treatment, using EHG and/or obstetric data. Based on 140 EHG recordings, artificial neural networks were used to develop prediction models. Non-linear EHG parameters were found to be more reliable than linear for differentiating labor in under and over 7/14 days. Using EHG and obstetric data, the <7- and <14-day labor prediction models achieved an AUC in the test group of 87.1 ± 4.3% and 76.2 ± 5.8%, respectively. These results suggest that EHG can be reliable for predicting imminent labor in TPL women, regardless of the tocolytic therapy stage. This paves the way for the development of diagnostic tools to help obstetricians make better decisions on treatments, hospital stays and admitting TPL women, and can therefore reduce costs and improve maternal and fetal wellbeing.

1995 ◽  
Vol 32 (2) ◽  
pp. 297-304
Author(s):  
Willem A. M. Botes ◽  
J. F. Kapp

Field dilution studies were conducted on three “deep” water marine outfalls located along the South African coast to establish the comparibility of actual achievable initial dilutions against the theoretical predicted values and, where appropriate, to make recommendations regarding the applicability of the different prediction techniques in the design of future outfalls. The physical processes along the 3000 km long coastline of South Africa are diverse, ranging from dynamic sub-tropical waters on the east coast to cold, stratified stagnant conditions on the west coast. Fourteen existing offshore marine outfalls serve medium to large industries and various local authorities (domestic effluent). For this investigation three outfalls were selected to represent the range of outfall types as well as the diversity of the physical conditions of the South African coastline. The predicted dilutions, using various approaches, compared well with the measured dilutions. It was found that the application of more “simple” prediction techniques (using average current velocities and ambient densities) may be more practical, ensuring a conservative approach, in pre-feasibility studies, compared to the more detailed prediction models, which uses accurate field data (stratification and current profiles), when extensive field data is not readily available.


Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2496
Author(s):  
Gema Prats-Boluda ◽  
Julio Pastor-Tronch ◽  
Javier Garcia-Casado ◽  
Rogelio Monfort-Ortíz ◽  
Alfredo Perales Marín ◽  
...  

Preterm birth is the leading cause of death in newborns and the survivors are prone to health complications. Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy. The current methods used in clinical practice to diagnose preterm labor, the Bishop score or cervical length, have high negative predictive values but not positive ones. In this work we analyzed the performance of computationally efficient classification algorithms, based on electrohysterographic recordings (EHG), such as random forest (RF), extreme learning machine (ELM) and K-nearest neighbors (KNN) for imminent labor (<7 days) prediction in women with TPL, using the 50th or 10th–90th percentiles of temporal, spectral and nonlinear EHG parameters with and without obstetric data inputs. Two criteria were assessed for the classifier design: F1-score and sensitivity. RFF1_2 and ELMF1_2 provided the highest F1-score values in the validation dataset, (88.17 ± 8.34% and 90.2 ± 4.43%) with the 50th percentile of EHG and obstetric inputs. ELMF1_2 outperformed RFF1_2 in sensitivity, being similar to those of ELMSens (sensitivity optimization). The 10th–90th percentiles did not provide a significant improvement over the 50th percentile. KNN performance was highly sensitive to the input dataset, with a high generalization capability.


2013 ◽  
Vol 122 (6) ◽  
pp. 1279-1287 ◽  
Author(s):  
Nir Melamed ◽  
Liran Hiersch ◽  
Noam Domniz ◽  
Akiva Maresky ◽  
Ron Bardin ◽  
...  

2014 ◽  
Vol 210 (1) ◽  
pp. S199-S200
Author(s):  
Molly Stout ◽  
Methodius Tuuli ◽  
Lorie Harper ◽  
Alison Cahill ◽  
Anthony Odibo ◽  
...  

2011 ◽  
Vol 29 (3) ◽  
pp. 216-223 ◽  
Author(s):  
Camilla B. Wulff ◽  
Charlotte K. Ekelund ◽  
Morten Hedegaard ◽  
Ann Tabor

Author(s):  
Fatin Shallal Farhan ◽  
Ban Hadi Hameed ◽  
Muna Abdulghani Zghair

Objective: The effectiveness of progesterone in the prevention of threatened preterm labor has been established for many years, but the preferable route, dose, and duration of treatment are until now under the evaluation of researches. The aim of this study was to determine the effect of rectal progesterone on Doppler indices of the uterine arteries in pregnant women with threatened preterm delivery.Methods: A prospective case–control study was conducted at the obstetric ward and the Outpatients Department of Al-Yarmouk Teaching Hospital in Baghdad for the period of 1 year from April 1, 2017, to April 1, 2018. 100 women were enrolled in the study, 50 of them were pregnant women with a diagnosis of preterm labor assigned as a study group and the other 50 were apparently healthy pregnant women of the same gestational age assigned as a control group. Doppler study of uterine arteries was done to all participants, and the results were compared for both groups. The patients with preterm labor received nifedipine tocolysis initially until contractions subsided and Doppler study had been repeated for those women after 1 week of rectal progesterone therapy.Results: The study group had a significantly higher resistance index (RI) than the control group (0.58 vs. 0.52) as p<0.05, in spite of the pulsatility index (PI) being higher for the study group compared to the control group (0.78 vs. 0.77) but this difference was not statistically significant. The RI before the therapy (0.58) was significantly higher than the index after therapy (0.52), and the PI was again significantly higher before therapy (0.78) than after therapy (0.71) as p<0.05. During the follow-up period, 3 (6.5%), 4 (8.7), and 39 (84.8%) patients delivered within 1 week, after 1 week, and at term, respectively.Conclusion: Rectal progesterone can arrest threatened preterm labor, and this effect is possible in part explained by its action on uterine arteries.


1993 ◽  
Vol 27 (2) ◽  
pp. 148-151
Author(s):  
L. E. Murashko ◽  
G. A. Sheveleva

Sign in / Sign up

Export Citation Format

Share Document