A Preconception Nomogram to Predict Preterm Delivery

Abstract

Objective Preterm birth is a leading cause of perinatal morbidity and mortality. Prevention strategies rarely focus on preconception care. We sought to create a preconception nomogram that identifies nonpregnant women at highest risk for preterm birth using the Pregnancy Risk Assessment Monitoring System (PRAMS) surveillance data. Methods We used PRAMS data from 2004 to 2009. The odds ratios (ORs) of preterm birth for each preconception variable was estimated and adjusted analyses were conducted. We created a validated nomogram predicting the probability of preterm birth using multivariate logistic regression coefficients. Results 192,208 cases met inclusion criteria. Demographic/maternal health characteristics and associations with preterm birth and ORs are reported. After validation, we identified the following significant predictors of preterm birth: prior history of preterm birth or low birth weight baby, prior spontaneous or elective abortion, maternal diabetes prior to conception, maternal race (e.g., non-Hispanic black), intention to get pregnant prior to conception (i.e., did not want or wanted it sooner), and smoking prior to conception (p < 0.05). Overall, our preconception preterm risk model correctly classified 76.1 % of preterm cases with a negative predictive value (NPV) of 76.7 %. A nomogram using a 0-100 scale illustrates our final preconception model for predicting preterm birth. Conclusion This preconception nomogram can be used by clinicians in multiple settings as a tool to help predict a woman's individual preterm birth risk and to triage high-risk non-pregnant women to preconception care. Future studies are needed to validate the nomogram in a clinical setting.

Nomogram to Early Screen Multiparous Women for Preterm Birth in a Cohort Study

“…Hence, it is probable that the low PTB prediction of the logistic regression model based on the original data was at least partially due to the low prevalence of preterm birth. This model still predicted the majority class of non-PTB women with levels comparable to reported data on preconception PTB modeling [8].…”

“…Although neural networks algorithms have been shown to lead to very high preterm prediction results, it is di cult to develop a simple version that can be used by physicians, especially in developing countries where the gynecologist takes all the decisions. The logistic regression model linear coe cients have been used in nomograms and spreadsheets to deliver prediction tools that can be used by all physicians [8].…”

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

“…The non-LR models significantly outperformed the LR models in preterm delivery (4/5 non-LR models), CS (3/5 non-LR models), pre-eclampsia (1/2 non-LR models), and gestational diabetes (2/3 non-LR models). From those that examined preterm delivery, a prediction model did not include a non-LR high ROB study [115] compared with those from 7 LR studies [32,44,60,63,75,87,96]. This model applied a random forest (differences in logit AUROC 2.51; 95% CI 1.49-3.53).…”

“…All predictors were features extracted from the multichannel EHG obtained at around 22 and 32 weeks of gestation to predict delivery after 39 and 34 to <37 weeks of gestation for term and preterm delivery, respectively. Compared with their counterparts, LR models used predictors consisting of maternal demographics or lifestyle [44,60,75,96,163], medical or obstetric histories [44,75,96,156,163], clinical predictors from obstetrical examinations [44,163], EHG [169], and biomarkers [75]. These were obtained before pregnancy [60,96,156,163], at 11 to 14 weeks of gestation [75], 18 to 34 weeks of gestation [44,163,169], or near events within 1 to 2 weeks [44].…”

“…Compared with their counterparts, LR models used predictors consisting of maternal demographics or lifestyle [44,60,75,96,163], medical or obstetric histories [44,75,96,156,163], clinical predictors from obstetrical examinations [44,163], EHG [169], and biomarkers [75]. These were obtained before pregnancy [60,96,156,163], at 11 to 14 weeks of gestation [75], 18 to 34 weeks of gestation [44,163,169], or near events within 1 to 2 weeks [44]. The LR models were developed to predict preterm delivery at 20 to <37 weeks of gestation [44,75,96,163,169] and any delivery at <37 weeks of gestation (predictors could be taken before pregnancy) [60,156].…”