An evaluation of cervical maturity for Chinese women with labor induction by machine learning and ultrasound images.
Bishop score
Cervical maturity
Labor time
Machine learning
Ultrasound
Journal
BMC pregnancy and childbirth
ISSN: 1471-2393
Titre abrégé: BMC Pregnancy Childbirth
Pays: England
ID NLM: 100967799
Informations de publication
Date de publication:
18 Oct 2023
18 Oct 2023
Historique:
received:
10
11
2022
accepted:
23
09
2023
medline:
23
10
2023
pubmed:
19
10
2023
entrez:
18
10
2023
Statut:
epublish
Résumé
To evaluate the improvement of evaluation accuracy of cervical maturity for Chinese women with labor induction by adding objective ultrasound data and machine learning models to the existing traditional Bishop method. The machine learning model was trained and tested using 101 sets of data from pregnant women who were examined and had their delivery in Peking University Third Hospital in between December 2019 and January 2021. The inputs of the model included cervical length, Bishop score, angle, age, induced labor time, measurement time (MT), measurement time to induced labor time (MTILT), method of induced labor, and primiparity/multiparity. The output of the model is the predicted time from induced labor to labor. Our experiments analyzed the effectiveness of three machine learning models: XGBoost, CatBoost and RF(Random forest). we consider the root-mean-squared error (RMSE) and the mean absolute error (MAE) as the criterion to evaluate the accuracy of the model. Difference was compared using t-test on RMSE between the machine learning model and the traditional Bishop score. The mean absolute error of the prediction result of Bishop scoring method was 19.45 h, and the RMSE was 24.56 h. The prediction error of machine learning model was lower than the Bishop score method. Among the three machine learning models, the MAE of the model with the best prediction effect was 13.49 h and the RMSE was 16.98 h. After selection of feature the prediction accuracy of the XGBoost and RF was slightly improved. After feature selection and artificially removing the Bishop score, the prediction accuracy of the three models decreased slightly. The best model was XGBoost (p = 0.0017). The p-value of the other two models was < 0.01. In the evaluation of cervical maturity, the results of machine learning method are more objective and significantly accurate compared with the traditional Bishop scoring method. The machine learning method is a better predictor of cervical maturity than the traditional Bishop method.
Sections du résumé
BACKGROUND
BACKGROUND
To evaluate the improvement of evaluation accuracy of cervical maturity for Chinese women with labor induction by adding objective ultrasound data and machine learning models to the existing traditional Bishop method.
METHODS
METHODS
The machine learning model was trained and tested using 101 sets of data from pregnant women who were examined and had their delivery in Peking University Third Hospital in between December 2019 and January 2021. The inputs of the model included cervical length, Bishop score, angle, age, induced labor time, measurement time (MT), measurement time to induced labor time (MTILT), method of induced labor, and primiparity/multiparity. The output of the model is the predicted time from induced labor to labor. Our experiments analyzed the effectiveness of three machine learning models: XGBoost, CatBoost and RF(Random forest). we consider the root-mean-squared error (RMSE) and the mean absolute error (MAE) as the criterion to evaluate the accuracy of the model. Difference was compared using t-test on RMSE between the machine learning model and the traditional Bishop score.
RESULTS
RESULTS
The mean absolute error of the prediction result of Bishop scoring method was 19.45 h, and the RMSE was 24.56 h. The prediction error of machine learning model was lower than the Bishop score method. Among the three machine learning models, the MAE of the model with the best prediction effect was 13.49 h and the RMSE was 16.98 h. After selection of feature the prediction accuracy of the XGBoost and RF was slightly improved. After feature selection and artificially removing the Bishop score, the prediction accuracy of the three models decreased slightly. The best model was XGBoost (p = 0.0017). The p-value of the other two models was < 0.01.
CONCLUSION
CONCLUSIONS
In the evaluation of cervical maturity, the results of machine learning method are more objective and significantly accurate compared with the traditional Bishop scoring method. The machine learning method is a better predictor of cervical maturity than the traditional Bishop method.
Identifiants
pubmed: 37853378
doi: 10.1186/s12884-023-06023-4
pii: 10.1186/s12884-023-06023-4
pmc: PMC10583473
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
737Informations de copyright
© 2023. BioMed Central Ltd., part of Springer Nature.
Références
Clin Obstet Gynecol. 2017 Mar;60(1):58-81
pubmed: 28005595
Obstet Gynecol. 1964 Aug;24:266-8
pubmed: 14199536
Am J Obstet Gynecol. 2013 Mar;208(3):190.e1-7
pubmed: 23246815
Eur J Obstet Gynecol Reprod Biol. 2002 Feb 10;101(1):15-8
pubmed: 11803093
Am J Perinatol. 2013 Sep;30(8):625-30
pubmed: 23283806
Ultraschall Med. 2015 Feb;36(1):59-64
pubmed: 24327472
Obstet Gynecol. 2020 Apr;135(4):935-944
pubmed: 32168227
J Perinat Med. 1980;8(1):27-37
pubmed: 7365668
Obstet Gynecol Clin North Am. 2019 Jun;46(2):367-378
pubmed: 31056137
BJOG. 2016 Jan;123(1):16-22
pubmed: 26507579
Cochrane Database Syst Rev. 2019 Sep 25;9:CD007235
pubmed: 31553800
Stud Health Technol Inform. 2019 Aug 21;264:888-892
pubmed: 31438052
Radiographics. 2017 Mar-Apr;37(2):505-515
pubmed: 28212054
Ultrasound Obstet Gynecol. 2020 Oct;56(4):588-596
pubmed: 31587401
Radiology. 1988 Feb;166(2):321-4
pubmed: 3275976
Lancet. 2007 Oct 20;370(9596):1453-7
pubmed: 18064739
Cochrane Database Syst Rev. 2015 Jun 12;(6):CD010762
pubmed: 26068943
Arch Gynecol Obstet. 2012 Sep;286(3):739-53
pubmed: 22546948
Ann Intern Med. 2015 Jan 6;162(1):55-63
pubmed: 25560714