Intelligent system based on data mining techniques for prediction of preterm birth for women with cervical cerclage

Preterm birth, defined as a delivery before 37 weeks' gestation, continues to affect 8-15% of all pregnancies and is associated with significant neonatal morbidity and mortality. Effective prediction of timing of delivery among women identified to be at significant risk for preterm birth would allow proper implementation of prophylactic therapeutic interventions. This paper aims first to develop a model that acts as a decision support system for pregnant women at high risk of delivering prematurely before having cervical cerclage. The model will predict whether the pregnancy will continue beyond 26 weeks' gestation and the potential value of adding the cerclage in prolonging the pregnancy. The second aim is to develop a model that predicts the timing of spontaneous delivery in this high risk cohort after cerclage. The model will help treating physicians to define the chronology of management in relation to the risk of preterm birth, reducing the neonatal complications associated with it. Data from 274 pregnancies managed with cervical cerclage were included. 29 of the procedures involved multiple pregnancies. To build the first model, a data balancing technique called SMOTE was applied to overcome the problem of highly imbalanced class distribution in the dataset. After that, four classification models, namely Decision Tree, Random Forest, K-Nearest Neighbors (K-NN), and Neural Network (NN) were used to build the prediction model. The results showed that Random Forest classifier gave the best results in terms of G-mean and sensitivity with values of 0.96 and 1.00, respectively. These results were achieved at an oversampling ratio of 200%. For the second prediction model, five classification models were used to predict the time of spontaneous delivery; linear regression, Gaussian process, Random Forest, K-star, and LWL classifier. The Random Forest classifier performed best, with 0.752 correlation value. In conclusion, computational models can be developed to predict the need for cerclage and the gestation of delivery after this procedure. These models have moderate/high sensitivity for clinical application.

[1]  C. Parker,et al.  Predictive Accuracy of Serial Transvaginal Cervical Lengths and Quantitative Vaginal Fetal Fibronectin Levels for Spontaneous Preterm Birth Among Nulliparous Women , 2017, JAMA.

[2]  N. Fox,et al.  The association between obstetrical history and preterm birth in women with uterine anomalies , 2018, The journal of maternal-fetal & neonatal medicine : the official journal of the European Association of Perinatal Medicine, the Federation of Asia and Oceania Perinatal Societies, the International Society of Perinatal Obstetricians.

[3]  Wei Luo,et al.  Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data , 2016, 1607.08310.

[4]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[5]  Anita Raja,et al.  Predicting Preterm Birth Is Not Elusive: Machine Learning Paves the Way to Individual Wellness , 2014, AAAI Spring Symposia.

[6]  Bernhard Pfahringer,et al.  Locally Weighted Naive Bayes , 2002, UAI.

[7]  Linda K. Goodwin,et al.  Data mining for preterm birth prediction , 2000, SAC '00.

[8]  B. Vohr,et al.  Changing definitions of long-term follow-up: Should "long term" be even longer? , 2016, Seminars in perinatology.

[9]  Hannah E Knight,et al.  Challenges in defining and classifying the preterm birth syndrome. , 2012, American journal of obstetrics and gynecology.

[10]  E. Gratacós,et al.  Follow-Up of Asymptomatic High-Risk Patients with Normal Cervical Length to Predict Recurrence of Preterm Birth , 2017, Fetal Diagnosis and Therapy.

[11]  R. Romero,et al.  Do serial measurements of cervical length improve the prediction of preterm birth in asymptomatic women with twin gestations? , 2016, American journal of obstetrics and gynecology.

[12]  M. Mansournia,et al.  Cross‐sectional study of associations between prior spontaneous abortions and preterm delivery , 2018, International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics.

[13]  S. Dutta,et al.  Routine second trimester cervical length screening in low risk women identified women at risk of a ‘very’ preterm birth but did not reduce the preterm birth rate: a randomised study from India , 2018, Journal of obstetrics and gynaecology : the journal of the Institute of Obstetrics and Gynaecology.

[14]  Neil Marlow,et al.  Preterm birth–associated neurodevelopmental impairment estimates at regional and global levels for 2010 , 2013, Pediatric Research.

[15]  E. Miller,et al.  The association between cervical excisional procedures, midtrimester cervical length, and preterm birth. , 2014, American journal of obstetrics and gynecology.

[16]  S. Tomšič,et al.  Cold-knife conisation and large loop excision of transformation zone significantly increase the risk for spontaneous preterm birth: a population-based cohort study. , 2016, European journal of obstetrics, gynecology, and reproductive biology.

[17]  Jose Villar,et al.  The preterm birth syndrome: issues to consider in creating a classification system. , 2012, American journal of obstetrics and gynecology.

[18]  T. Colaizy,et al.  Abortion and the risk of subsequent preterm birth: a systematic review with meta-analyses. , 2009, The Journal of reproductive medicine.

[19]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[20]  G. Saade,et al.  Prediction of Spontaneous Preterm Birth Among Nulliparous Women With a Short Cervix , 2016, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[21]  Richard Guest,et al.  Comparing Machine Learning Classifiers and Linear/Logistic Regression to Explore the Relationship between Hand Dimensions and Demographic Characteristics , 2016, PloS one.

[22]  Joy Lawn,et al.  Born Too Soon: The global epidemiology of 15 million preterm births , 2013, Reproductive Health.

[23]  Ivanka Orozova-Bekkevold,et al.  Maternal vaccination and preterm birth: using data mining as a screening tool , 2007, Pharmacy World & Science.

[24]  P. Sheehan,et al.  Clinical Application of Quantitative Foetal Fibronectin for the Prediction of Preterm Birth in Symptomatic Women , 2017, Gynecologic and Obstetric Investigation.

[25]  Hsiang-Yang Chen,et al.  Exploring the risk factors of preterm birth using data mining , 2011, Expert Syst. Appl..

[26]  A. Rebarber,et al.  Type of congenital uterine anomaly and adverse pregnancy outcomes , 2014, The journal of maternal-fetal & neonatal medicine : the official journal of the European Association of Perinatal Medicine, the Federation of Asia and Oceania Perinatal Societies, the International Society of Perinatal Obstetricians.

[27]  J. Martin,et al.  Births: Final Data for 2015. , 2017, National vital statistics reports : from the Centers for Disease Control and Prevention, National Center for Health Statistics, National Vital Statistics System.

[28]  K. Nicolaides,et al.  Cervical length screening for prevention of preterm birth in singleton pregnancy with threatened preterm labor: systematic review and meta‐analysis of randomized controlled trials using individual patient‐level data , 2017, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[29]  K. Nicolaides,et al.  Shirodkar versus McDonald Cerclage for the Prevention of Preterm Birth in Women with Short Cervical Length , 2006 .

[30]  K. Nicolaides,et al.  Cervical length and obstetric history predict spontaneous preterm birth: development and validation of a model to provide individualized risk assessment , 2008, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[31]  N. Okun,et al.  Emergency Cerclage: Literature Review , 2013, Obstetrical & gynecological survey.

[32]  M. Oncel,et al.  The association of a cervical length of <25 mm in high-risk pregnancies on neonatal morbidity and mortality in preterm infants , 2013, Archives of Gynecology and Obstetrics.

[33]  G. Kulanthaivel,et al.  Data Mining Approach in Preterm Birth Prediction , 2010 .

[34]  C. Oliver‐Williams,et al.  Previous miscarriage and the subsequent risk of preterm birth in Scotland, 1980–2008: a historical cohort study , 2015, BJOG : an international journal of obstetrics and gynaecology.

[35]  W. Callaghan,et al.  Effects of Maternal Age and Age-Specific Preterm Birth Rates on Overall Preterm Birth Rates - United States, 2007 and 2014. , 2016, MMWR. Morbidity and mortality weekly report.

[36]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[37]  Assuring Healthy Outcomes,et al.  Preterm Birth : Causes , Consequences , and Prevention , 2005 .

[38]  Babak Saleh,et al.  Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions , 2013, 2013 IEEE International Conference on Computer Vision.

[39]  V. Berghella,et al.  Cervical length and prediction of preterm delivery , 2007, Current opinion in obstetrics & gynecology.

[40]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[41]  K. Nicolaides,et al.  Large loop excision of transformation zone and cervical length in the prediction of spontaneous preterm delivery , 2012, BJOG : an international journal of obstetrics and gynaecology.

[42]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[43]  M. Ghojazadeh,et al.  Pre- and post-McDonald cerclage cervical length, width and funneling rate and their association with duration of pregnancy. , 2011, Pakistan journal of biological sciences : PJBS.

[44]  John G. Cleary,et al.  K*: An Instance-based Learner Using and Entropic Distance Measure , 1995, ICML.

[45]  Jeff Gilchrist,et al.  Applying Data Preprocessing Methods to Predict Premature Birth , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[46]  J. Beyene,et al.  Vaginal progesterone, oral progesterone, 17‐OHPC, cerclage, and pessary for preventing preterm birth in at‐risk singleton pregnancies: an updated systematic review and network meta‐analysis , 2018, BJOG : an international journal of obstetrics and gynaecology.

[47]  Jamie Perin,et al.  Global, regional, and national causes of under-5 mortality in 2000–15: an updated systematic analysis with implications for the Sustainable Development Goals , 2016, The Lancet.