A model for prediction of spontaneous preterm birth in asymptomatic women

Prediction of preterm birth in multiparous women using logistic regression and machine learning approaches

To predict preterm birth (PTB) in multiparous women, comparing machine learning approaches with traditional logistic regression. A population-based cohort study was conducted using data from the Ontario Better Outcomes Registry and Network (BORN). The cohort included all multiparous women who delivered a singleton birth at 20-42 weeks' gestation in an Ontario hospital between April 1, 2012 and March 31, 2014. The primary outcome was PTB < 37 weeks, with spontaneous PTB analyzed as a secondary outcome. Stepwise logistic regression and the Boruta machine learning were used to select the important variables during the first and second trimester. For building prediction models, the whole data set were divided for the two independent parts: two-third for training the classifiers (Logistic regression, random forests, decision trees, and artificial neural networks) and one-third for model validation. Then, the training data set were balanced by random over sampling technique. The best hyper parameters were obtained by the tenfold cross validation. The performance of all models was evaluated by sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristics (AUC). The cohort included 145,846 births, of which 8125 (5.57%) were preterm. In first-trimester models, the strongest predictors of PTB were previous PTB, preexisting diabetes, and abnormal pregnancy-associated plasma protein-A. In the testing data set, the highest predictive ability was seen for artificial neural networks, with an area under the receiver operating characteristic curve (AUC) of 68.8% (95% CI 67.6-70.1%). In second-trimester models, addition of infant sex, attendance at first-trimester appointment, medication exposure, and abnormal alpha-fetoprotein concentrations increased the AUC to 72.1% (95% CI 71.1-73.1%) with logistic regression. With the inclusion of the variable complications during pregnancy, the AUC increased to 80.5% (95% CI 79.6-81.5%) using logistic regression. For both overall and spontaneous PTB, during both the first and second trimesters, models yielded negative predictive values of 97%. Overall, machine learning and logistic regression produced similar performance for prediction of PTB. For overall and spontaneous PTB, both first- and second-trimester models provided negative predictive values of ~ 97%, higher than that of fetal fibronectin.

Developing and validating a risk prediction model for preterm birth at Felege Hiwot Comprehensive Specialized Hospital, North-West Ethiopia: a retrospective follow-up study

OBJECTIVE

To develop and validate a risk prediction model for the prediction of preterm birth using maternal characteristics.

DESIGN

This was a retrospective follow-up study. Data were coded and entered into EpiData, V.3.02, and were analysed using R statistical programming language V.4.0.4 for further processing and analysis. Bivariable logistic regression was used to identify the relationship between each predictor and preterm birth. Variables with p≤0.25 from the bivariable analysis were entered into a backward stepwise multivariable logistic regression model, and significant variables (p<0.05) were retained in the multivariable model. Model accuracy and goodness of fit were assessed by computing the area under the receiver operating characteristic curve (discrimination) and calibration plot (calibration), respectively.

SETTING AND PARTICIPANTS

This retrospective study was conducted among 1260 pregnant women who did prenatal care and finally delivered at Felege Hiwot Comprehensive Specialised Hospital, Bahir Dar city, north-west Ethiopia, from 30 January 2019 to 30 January 2021.

RESULTS

Residence, gravidity, haemoglobin <11 mg/dL, early rupture of membranes, antepartum haemorrhage and pregnancy-induced hypertension remained in the final multivariable prediction model. The area under the curve of the model was 0.816 (95% CI 0.779 to 0.856).

CONCLUSION

This study showed the possibility of predicting preterm birth using maternal characteristics during pregnancy. Thus, use of this model could help identify pregnant women at a higher risk of having a preterm birth to be linked to a centre.

Machine learning modeling for preterm birth prediction using health record: A systematic review (Preprint)

Background

Preterm birth (PTB), a common pregnancy complication, is responsible for 35% of the 3.1 million pregnancy-related deaths each year and significantly affects around 15 million children annually worldwide. Conventional approaches to predict PTB lack reliable predictive power, leaving >50% of cases undetected. Recently, machine learning (ML) models have shown potential as an appropriate complementary approach for PTB prediction using health records (HRs).

Objective

This study aimed to systematically review the literature concerned with PTB prediction using HR data and the ML approach.

Methods

This systematic review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement. A comprehensive search was performed in 7 bibliographic databases until May 15, 2021. The quality of the studies was assessed, and descriptive information, including descriptive characteristics of the data, ML modeling processes, and model performance, was extracted and reported.

Results

A total of 732 papers were screened through title and abstract. Of these 732 studies, 23 (3.1%) were screened by full text, resulting in 13 (1.8%) papers that met the inclusion criteria. The sample size varied from a minimum value of 274 to a maximum of 1,400,000. The time length for which data were extracted varied from 1 to 11 years, and the oldest and newest data were related to 1988 and 2018, respectively. Population, data set, and ML models’ characteristics were assessed, and the performance of the model was often reported based on metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve.

Conclusions

Various ML models used for different HR data indicated potential for PTB prediction. However, evaluation metrics, software and package used, data size and type, selected features, and importantly data management method often remain unjustified, threatening the reliability, performance, and internal or external validity of the model. To understand the usefulness of ML in covering the existing gap, future studies are also suggested to compare it with a conventional method on the same data set.

Clinical risk models for preterm birth less than 28 weeks and less than 32 weeks of gestation using a large retrospective cohort

OBJECTIVE

To develop risk prediction models for singleton preterm birth (PTB) < 28 weeks and <32 weeks.

METHODS

Using a retrospective cohort of 267,226 singleton births in Ontario hospitals, we included variables from the first and second trimester in multivariable logistic regression models to predict overall and spontaneous PTB < 28 weeks and <32 weeks.

RESULTS

During the first trimester, the area under the curve (AUC) for prediction of PTB < 28 weeks for nulliparous and multiparous women was 68.5% (95% CI: 63.5-73.6%) and 73.4% (68.6-78.2%), respectively, while for PTB < 32 weeks it was 68.9% (65.5-72.3%) and 75.5% (72.3-78.7%), respectively. AUCs for second-trimester models were 72.4% (95% CI: 69.7-75.1%) and 78.2% (95% CI: 75.8-80.5%), respectively, in nulliparous and multiparous women. Predicted probabilities were well-calibrated within a wide range around expected base prevalence for the study outcomes.

CONCLUSIONS

Our prediction models generated acceptable AUCs for PTB < 28 weeks and <32 weeks with good calibration during the first and second trimester.

Prediction of preterm birth in nulliparous women using logistic regression and machine learning

OBJECTIVE

To predict preterm birth in nulliparous women using logistic regression and machine learning.

DESIGN

Population-based retrospective cohort.

PARTICIPANTS

Nulliparous women (N = 112,963) with a singleton gestation who gave birth between 20-42 weeks gestation in Ontario hospitals from April 1, 2012 to March 31, 2014.

METHODS

We used data during the first and second trimesters to build logistic regression and machine learning models in a "training" sample to predict overall and spontaneous preterm birth. We assessed model performance using various measures of accuracy including sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) in an independent "validation" sample.

RESULTS

During the first trimester, logistic regression identified 13 variables associated with preterm birth, of which the strongest predictors were diabetes (Type I: adjusted odds ratio (AOR): 4.21; 95% confidence interval (CI): 3.23-5.42; Type II: AOR: 2.68; 95% CI: 2.05-3.46) and abnormal pregnancy-associated plasma protein A concentration (AOR: 2.04; 95% CI: 1.80-2.30). During the first trimester, the maximum AUC was 60% (95% CI: 58-62%) with artificial neural networks in the validation sample. During the second trimester, 17 variables were significantly associated with preterm birth, among which complications during pregnancy had the highest AOR (13.03; 95% CI: 12.21-13.90). During the second trimester, the AUC increased to 65% (95% CI: 63-66%) with artificial neural networks in the validation sample. Including complications during the pregnancy yielded an AUC of 80% (95% CI: 79-81%) with artificial neural networks. All models yielded 94-97% negative predictive values for spontaneous PTB during the first and second trimesters.

CONCLUSION

Although artificial neural networks provided slightly higher AUC than logistic regression, prediction of preterm birth in the first trimester remained elusive. However, including data from the second trimester improved prediction to a moderate level by both logistic regression and machine learning approaches.

Prediction of preterm birth based on machine learning using bacterial risk score in cervicovaginal fluid

PROBLEM

Preterm birth (PTB) is a major cause of increased morbidity and mortality in newborns. The main cause of spontaneous PTB (sPTB) is the activation of an inflammatory response as a result of ascending genital tract infection. Despite various studies on the effects of the vaginal microbiome on PTB, a practical method for its clinical application has yet to be developed.

METHOD OF STUDY

In this case-control study, 94 Korean pregnant women with PTB (n = 38) and term birth (TB; n = 56) were enrolled. Their cervicovaginal fluid (CVF) was sampled, and a total of 10 bacteria were analyzed using multiplex quantitative real-time PCR (qPCR). The PTB and TB groups were compared, and a PTB prediction model was created using bacterial risk scores using machine learning techniques (decision tree and support vector machine). The predictive performance of the model was validated using random subsampling.

RESULTS

Bacterial risk scoring model showed significant differences (P < 0.001). The PTB risk was low when the Lactobacillus iners ratio was 0.812 or more. In groups with a ratio under 0.812, moderate and high risk was classified as a U. parvum ratio of 4.6 × 10^-3 . The sensitivity and specificity of the PTB prediction model using bacteria risk score were 71% and 59%, respectively, and 77% and 67%, respectively, when white blood cell (WBC) data were included.

CONCLUSION

Using machine learning, the bacterial risk score in CVF can be used to predict PTB.

First Trimester Protein Biomarkers for Risk of Spontaneous Preterm Birth: Identifying a Critical Need for More Rigorous Approaches to Biomarker Identification and Validation

BACKGROUND

Spontaneous preterm birth is the leading cause of perinatal morbidity and mortality worldwide and continues to present a major clinical dilemma. We previously reported that a number of protein species were dysregulated in maternal serum collected at 11-13+6 weeks' gestation from pregnancies that continued to labour spontaneously and deliver preterm.

OBJECTIVES AND METHODS

In this study, we aimed to validate changes seen in 4 candidate protein species: alpha-1-antitrypsin, vitamin D-binding protein (VDBP), alpha-1beta-glycoprotein and apolipoprotein A-1 in a larger cohort of women using a western blot approach.

RESULTS

Serum levels of all 4 proteins were reduced in women who laboured spontaneously and delivered preterm. This reduction was significant for VDBP (p = 0.04), which has been shown to be involved in a plethora of essential biological functions, including actin scavenging, fatty acid transport, macrophage activation and chemotaxis.

CONCLUSIONS

The decrease in select proteoforms of VDBP may result in an imbalance in the optimal intrauterine environment for the developing foetus as well as to a successful uncomplicated pregnancy. Thus, certain (phosphorylated) species of VDBP may be of value in developing a targeted approach to the early prediction of spontaneous preterm labour. Importantly, this study raises the importance of a focus on proteoforms and the need for any biomarker validation process to most effectively take these into account rather than the more widespread practice of simply focussing on the primary amino acid sequence of a protein.

New model for predicting preterm delivery during the second trimester of pregnancy

In this study, a new model for predicting preterm delivery (PD) was proposed. The primary model was constructed using ten selected variables, as previously defined in seventeen different studies. The ability of the model to predict PD was evaluated using the combined measurement from these variables. Therefore, a prospective investigation was performed by enrolling 130 pregnant patients whose gestational ages varied from 17⁺⁰ to 28⁺⁶ weeks. The patients underwent epidemiological surveys and ultrasonographic measurements of their cervixes, and cervicovaginal fluid and serum were collected during a routine speculum examination performed by the managing gynecologist. The results showed eight significant variables were included in the present analysis, and combination of the positive variables indicated an increased probability of PD in pregnant patients. The accuracy for predicting PD were as follows: one positive – 42.9%; two positives – 75.0%; three positives – 81.8% and four positives – 100.0%. In particular, the combination of ≥2× positives had the best predictive value, with a relatively high sensitivity (82.6%), specificity (88.1%) and accuracy rate (79.2%), and was considered the cut-off point for predicting PD. In conclusion, the new model provides a useful reference for evaluating the risk of PD in clinical cases.

Prognostic models in obstetrics: available, but far from applicable

Health care provision is increasingly focused on the prediction of patients' individual risk for developing a particular health outcome in planning further tests and treatments. There has been a steady increase in the development and publication of prognostic models for various maternal and fetal outcomes in obstetrics. We undertook a systematic review to give an overview of the current status of available prognostic models in obstetrics in the context of their potential advantages and the process of developing and validating models. Important aspects to consider when assessing a prognostic model are discussed and recommendations on how to proceed on this within the obstetric domain are given. We searched MEDLINE (up to July 2012) for articles developing prognostic models in obstetrics. We identified 177 papers that reported the development of 263 prognostic models for 40 different outcomes. The most frequently predicted outcomes were preeclampsia (n = 69), preterm delivery (n = 63), mode of delivery (n = 22), gestational hypertension (n = 11), and small-for-gestational-age infants (n = 10). The performance of newer models was generally not better than that of older models predicting the same outcome. The most important measures of predictive accuracy (ie, a model's discrimination and calibration) were often (82.9%, 218/263) not both assessed. Very few developed models were validated in data other than the development data (8.7%, 23/263). Only two-thirds of the papers (62.4%, 164/263) presented the model such that validation in other populations was possible, and the clinical applicability was discussed in only 11.0% (29/263). The impact of developed models on clinical practice was unknown. We identified a large number of prognostic models in obstetrics, but there is relatively little evidence about their performance, impact, and usefulness in clinical practice so that at this point, clinical implementation cannot be recommended. New efforts should be directed toward evaluating the performance and impact of the existing models.

A description of the methods of the Nulliparous Pregnancy Outcomes Study: monitoring mothers-to-be (nuMoM2b)

OBJECTIVE

The primary aim of the "Nulliparous Pregnancy Outcomes Study: monitoring mothers-to-be" is to determine maternal characteristics, which include genetic, physiologic response to pregnancy, and environmental factors that predict adverse pregnancy outcomes.

STUDY DESIGN

Nulliparous women in the first trimester of pregnancy were recruited into an observational cohort study. Participants were seen at 3 study visits during pregnancy and again at delivery. We collected data from in-clinic interviews, take-home surveys, clinical measurements, ultrasound studies, and chart abstractions. Maternal biospecimens (serum, plasma, urine, cervicovaginal fluid) at antepartum study visits and delivery specimens (placenta, umbilical cord, cord blood) were collected, processed, and stored. The primary outcome of the study was defined as pregnancy ending at <37+0 weeks' gestation. Key study hypotheses involve adverse pregnancy outcomes of spontaneous preterm birth, preeclampsia, and fetal growth restriction.

RESULTS

We recruited 10,037 women to the study. Basic characteristics of the cohort at screening are reported.

CONCLUSION

The "Nulliparous Pregnancy Outcomes Study: monitoring mothers-to-be" cohort study methods and procedures can help investigators when they plan future projects.

Comparison of Perinatal Outcome of Preterm Births Starting in Primary Care versus Secondary Care in Netherlands: A Retrospective Analysis of Nationwide Collected Data

Introduction. In Netherlands, the obstetric care system is divided into primary and secondary care by risk level of the pregnancy. We assessed the incidence of preterm birth according to level of care and the association between level of care at time of labor onset and delivery and adverse perinatal outcome. Methods. Singleton pregnancies recorded in Netherlands Perinatal Registry between 1999 and 2007, with spontaneous birth between 25(+0) and 36(+6) weeks, were included. Three groups were compared: (1) labor onset and delivery in primary care; (2) labor onset in primary care and delivery in secondary care; (3) labor onset and delivery in secondary care. Multivariable logistic regression analyses were performed to calculate the risk of perinatal mortality and Apgar score ≤4. Results. Of all preterm deliveries, 42% had labor onset and 7.9% had also delivery in primary care. Women with labor onset between 34(+0) and 36(+6) weeks who were referred before delivery to secondary care had the lowest risk of perinatal mortality (aOR 0.49 (0.30-0.79)). Risk of perinatal mortality (aOR 1.65; 95% CI 1.20-2.27) and low Apgar score (aOR 1.95; 95% CI 1.53-2.48) were significantly increased in preterm home delivery. Conclusion. Referral before delivery is associated with improved perinatal outcome in the occurrence of preterm labor onset in primary care.

Quantity and timing of maternal prenatal smoking on neonatal body composition: the Healthy Start study

OBJECTIVE

To examine the dose-dependent and time-specific relationships of prenatal smoking with neonatal body mass, fat mass (FM), fat-free mass (FFM), and FM-to-FFM ratio, as measured by air-displacement plethysmography (PEA POD system).

STUDY DESIGN

We analyzed 916 mother-neonate pairs participating in the longitudinal prebirth cohort Healthy Start study. Maternal prenatal smoking information was collected in early, middle, and late pregnancy by self-report. Neonatal body composition was measured with the PEA POD system after delivery. Multiple general linear regression models were adjusted for maternal and neonatal characteristics.

RESULTS

Each additional pack of cigarettes smoked during pregnancy was associated with significant decreases in neonatal body mass (adjusted mean difference, -2.8 g; 95% CI, -3.9 to -1.8 g; P < .001), FM (-0.7 g; 95% CI, -1.1 to -0.3 g; P < .001), and FFM (-2.1 g; 95% CI, -2.9 to -1.3 g; P < .001). Neonates exposed to prenatal smoking throughout pregnancy had significantly lower body mass (P < .001), FM (P < .001), and FFM (P < .001) compared with those not exposed to smoking. However, neonates of mothers who smoked only before late pregnancy had no significant differences in body mass (P = .47), FM (P = .43), or FFM (P = .59) compared with unexposed offspring.

CONCLUSION

Exposure to prenatal smoking leads to systematic growth restriction. Smoking cessation before late pregnancy may reduce the consequences of exposure to prenatal smoking on body composition. Follow-up of this cohort is needed to determine the influence of catch-up growth on early-life body composition and the risk of childhood obesity.

Predicting risk of spontaneous preterm delivery in women with a singleton pregnancy

BACKGROUND

Prediction of a woman's risk of a spontaneous preterm delivery (PTD) is a core challenge and an unresolved problem in today's obstetric practice. The objective of this study was to develop prediction models for spontaneous PTD (<37 weeks).

METHODS

A population-based register study of women born in Sweden with spontaneous onset of delivery was designed using Swedish Medical Birth Register data for 1992-2008. Predictive variables were identified by multiple logistic regression analysis, and outputs were used to calculate adjusted likelihood ratios in primiparous (n = 199 272) and multiparous (n = 249 580) singleton pregnant women. The predictive ability of each model was validated in a separate test sample for primiparous (n = 190 936) and multiparous (n = 239 203) women, respectively.

RESULTS

For multiparous women, the area under the ROC curve (AUC) of 0.74 [95% confidence interval (CI) 0.73, 0.74] indicated a satisfying performance of the model, while for primiparous women, it was rather poor {AUC: 0.58 [95% CI 0.57, 0.58]}. For both primiparous and multiparous women, the prediction models were quite good for pregnancies with comparatively low risk for spontaneous PTD, whereas more limited to predict pregnancies with ≥30% risk of spontaneous PTD.

CONCLUSIONS

Spontaneous PTD is difficult to predict in multiparous women and nearly impossible in primiparous, by using this statistical method in a large and unselected sample. However, adding clinical data (like cervical length) may in the future further improve its predictive performance.