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

Predicting risk of preterm birth in singleton pregnancies using machine learning algorithms

We aimed to develop, train, and validate machine learning models for predicting preterm birth (<37 weeks' gestation) in singleton pregnancies at different gestational intervals. Models were developed based on complete data from 22,603 singleton pregnancies from a prospective population-based cohort study that was conducted in 51 midwifery clinics and hospitals in Wenzhou City of China between 2014 and 2016. We applied Catboost, Random Forest, Stacked Model, Deep Neural Networks (DNN), and Support Vector Machine (SVM) algorithms, as well as logistic regression, to conduct feature selection and predictive modeling. Feature selection was implemented based on permutation-based feature importance lists derived from the machine learning models including all features, using a balanced training data set. To develop prediction models, the top 10%, 25%, and 50% most important predictive features were selected. Prediction models were developed with the training data set with 5-fold cross-validation for internal validation. Model performance was assessed using area under the receiver operating curve (AUC) values. The CatBoost-based prediction model after 26 weeks' gestation performed best with an AUC value of 0.70 (0.67, 0.73), accuracy of 0.81, sensitivity of 0.47, and specificity of 0.83. Number of antenatal care visits before 24 weeks' gestation, aspartate aminotransferase level at registration, symphysis fundal height, maternal weight, abdominal circumference, and blood pressure emerged as strong predictors after 26 completed weeks. The application of machine learning on pregnancy surveillance data is a promising approach to predict preterm birth and we identified several modifiable antenatal predictors.

Artificial intelligence as a new answer to old challenges in maternal-fetal medicine and obstetrics

BACKGROUND

Following the latest trends in the development of artificial intelligence (AI), the possibility of processing an immense amount of data has created a breakthrough in the medical field. Practitioners can now utilize AI tools to advance diagnostic protocols and improve patient care.

OBJECTIVE

The aim of this article is to present the importance and modalities of AI in maternal-fetal medicine and obstetrics and its usefulness in daily clinical work and decision-making process.

METHODS

A comprehensive literature review was performed by searching PubMed for articles published from inception up until August 2023, including the search terms "artificial intelligence in obstetrics", "maternal-fetal medicine", and "machine learning" combined through Boolean operators. In addition, references lists of identified articles were further reviewed for inclusion.

RESULTS

According to recent research, AI has demonstrated remarkable potential in improving the accuracy and timeliness of diagnoses in maternal-fetal medicine and obstetrics, e.g., advancing perinatal ultrasound technique, monitoring fetal heart rate during labor, or predicting mode of delivery. The combination of AI and obstetric ultrasound can help optimize fetal ultrasound assessment by reducing examination time and improving diagnostic accuracy while reducing physician workload.

CONCLUSION

The integration of AI in maternal-fetal medicine and obstetrics has the potential to significantly improve patient outcomes, enhance healthcare efficiency, and individualized care plans. As technology evolves, AI algorithms are likely to become even more sophisticated. However, the successful implementation of AI in maternal-fetal medicine and obstetrics needs to address challenges related to interpretability and reliability.

Predicting preterm birth using explainable machine learning in a prospective cohort of nulliparous and multiparous pregnant women

Preterm birth (PTB) presents a complex challenge in pregnancy, often leading to significant perinatal and long-term morbidities. "While machine learning (ML) algorithms have shown promise in PTB prediction, the lack of interpretability in existing models hinders their clinical utility. This study aimed to predict PTB in a pregnant population using ML models, identify the key risk factors associated with PTB through the SHapley Additive exPlanations (SHAP) algorithm, and provide comprehensive explanations for these predictions to assist clinicians in providing appropriate care. This study analyzed a dataset of 3509 pregnant women in the United Arab Emirates and selected 35 risk factors associated with PTB based on the existing medical and artificial intelligence literature. Six ML algorithms were tested, wherein the XGBoost model exhibited the best performance, with an area under the operator receiving curves of 0.735 and 0.723 for parous and nulliparous women, respectively. The SHAP feature attribution framework was employed to identify the most significant risk factors linked to PTB. Additionally, individual patient analysis was performed using the SHAP and the local interpretable model-agnostic explanation algorithms (LIME). The overall incidence of PTB was 11.23% (11 and 12.1% in parous and nulliparous women, respectively). The main risk factors associated with PTB in parous women are previous PTB, previous cesarean section, preeclampsia during pregnancy, and maternal age. In nulliparous women, body mass index at delivery, maternal age, and the presence of amniotic infection were the most relevant risk factors. The trained ML prediction model developed in this study holds promise as a valuable screening tool for predicting PTB within this specific population. Furthermore, SHAP and LIME analyses can assist clinicians in understanding the individualized impact of each risk factor on their patients and provide appropriate care to reduce morbidity and mortality related to PTB.

Node embedding-based graph autoencoder outlier detection for adverse pregnancy outcomes

Adverse pregnancy outcomes, such as low birth weight (LBW) and preterm birth (PTB), can have serious consequences for both the mother and infant. Early prediction of such outcomes is important for their prevention. Previous studies using traditional machine learning (ML) models for predicting PTB and LBW have encountered two important limitations: extreme class imbalance in medical datasets and the inability to account for complex relational structures between entities. To address these limitations, we propose a node embedding-based graph outlier detection algorithm to predict adverse pregnancy outcomes. We developed a knowledge graph using a well-curated representative dataset of the Emirati population and two node embedding algorithms. The graph autoencoder (GAE) was trained by applying a combination of original risk factors and node embedding features. Samples that were difficult to reconstruct at the output of GAE were identified as outliers considered representing PTB and LBW samples. Our experiments using LBW, PTB, and very PTB datasets demonstrated that incorporating node embedding considerably improved performance, achieving a 12% higher AUC-ROC compared to traditional GAE. Our study demonstrates the effectiveness of node embedding and graph outlier detection in improving the prediction performance of adverse pregnancy outcomes in well-curated population datasets.

Prediction of Preterm Birth among Infants with Orofacial Cleft Defects

OBJECTIVE

To develop risk prediction models for preterm birth among infants with orofacial clefts.

DESIGN

Data from the Texas Birth Defects Registry for infants with orofacial clefts born between 1999-2014 were used to develop preterm birth predictive models. Logistic regression was used to consider maternal and infant characteristics, and internal validation of the final model was performed using bootstrapping methods. The area under the curve (AUC) statistic was generated to assess model performance, and separate predictive models were built and validated for infants with cleft lip and cleft palate alone. Several secondary analyses were conducted among subgroups of interest.

SETTING

State-wide, population-based Registry data.

PATIENTS/PARTICIPANTS

6774 infants with orofacial clefts born in Texas between 1999-2014.

MAIN OUTCOME MEASURE(S)

Preterm birth among infants with orofacial clefts.

RESULTS

The final predictive model performed modestly, with an optimism-corrected AUC of 0.67 among all infants with orofacial clefts. The optimism-corrected models for cleft lip (with or without cleft palate) and cleft palate alone had similar predictive capability, with AUCs of 0.66 and 0.67, respectively. Secondary analyses had similar results, but the model among infants with delivery prior to 32 weeks demonstrated higher optimism-corrected predictive capability (AUC = 0.74).

CONCLUSIONS

This study provides a first step towards predicting preterm birth risk among infants with orofacial clefts. Identifying pregnancies affected by orofacial clefts at the highest risk for preterm birth may lead to new avenues for improving outcomes among these infants.

Risk Scoring Systems for Preterm Birth and Their Performance: A Systematic Review

Introduction: Nowadays, the risk stratification of preterm birth (PTB) and its prediction remain a challenge. Many risk factors associated with PTB have been identified, and risk scoring systems (RSSs) have been developed to face this challenge. The objectives of this systematic review were to identify RSSs for PTB, the variables they consist of, and their performance. Materials and methods: Two databases were searched, and two authors independently performed the screening and eligibility phases. Records studying an RSS, based on specified variables, with an evaluation of the predictive value for PTB, were considered eligible. Reference lists of eligible studies and review articles were also searched. Data from the included studies were extracted. Results: A total of 56 studies were included in this review. The most frequently incorporated variables in the RSS included in this review were maternal age, weight, history of smoking, history of previous PTB, and cervical length. The performance measures varied widely among the studies, with sensitivity ranging between 4.2% and 92.0% and area under the curve (AUC) between 0.59 and 0.95. Conclusions: Despite the recent technological and scientifical evolution with a better understanding of variables related to PTB and the definition of new ultrasonographic parameters and biomarkers associated with PTB, the RSS's ability to predict PTB remains poor in most situations, thus compromising the integration of a single RSS in clinical practice. The development of new RSSs, the identification of new variables associated with PTB, and the elaboration of a large reference dataset might be a step forward to tackle the problem of PTB.

Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries

Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling and multivariate modeling to investigate the biological signatures of these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples from 231 participants were analyzed to generate proteomic, metabolomic, and lipidomic datasets. Machine learning models showed robust performance for the prediction of PTB (AUROC = 0.70), time-to-delivery (r = 0.65), maternal age (r = 0.59), gravidity (r = 0.56), and BMI (r = 0.81). Time-to-delivery biological correlates included fetal-associated proteins (e.g., ALPP, AFP, and PGF) and immune proteins (e.g., PD-L1, CCL28, and LIFR). Maternal age negatively correlated with collagen COL9A1, gravidity with endothelial NOS and inflammatory chemokine CXCL13, and BMI with leptin and structural protein FABP4. These results provide an integrated view of epidemiological factors associated with PTB and identify biological signatures of clinical covariates affecting this disease.

Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications

Introduction

Machine learning (ML) corresponds to a wide variety of methods that use mathematics, statistics and computational science to learn from multiple variables simultaneously. By means of pattern recognition, ML methods are able to find hidden correlations and accomplish accurate predictions regarding different conditions. ML has been successfully used to solve varied problems in different areas of science, such as psychology, economics, biology and chemistry. Therefore, we wondered how far it has penetrated into the field of obstetrics and gynecology.

Aim

To describe the state of art regarding the use of ML in the context of pregnancy diseases and complications.

Methodology

Publications were searched in PubMed, Web of Science and Google Scholar. Seven subjects of interest were considered: gestational diabetes mellitus, preeclampsia, perinatal death, spontaneous abortion, preterm birth, cesarean section, and fetal malformations.

Current state

ML has been widely applied in all the included subjects. Its uses are varied, the most common being the prediction of perinatal disorders. Other ML applications include (but are not restricted to) biomarker discovery, risk estimation, correlation assessment, pharmacological treatment prediction, drug screening, data acquisition and data extraction. Most of the reviewed articles were published in the last five years. The most employed ML methods in the field are non-linear. Except for logistic regression, linear methods are rarely used.

Future challenges

To improve data recording, storage and update in medical and research settings from different realities. To develop more accurate and understandable ML models using data from cutting-edge instruments. To carry out validation and impact analysis studies of currently existing high-accuracy ML models.

Conclusion

The use of ML in pregnancy diseases and complications is quite recent, and has increased over the last few years. The applications are varied and point not only to the diagnosis, but also to the management, treatment, and pathophysiological understanding of perinatal alterations. Facing the challenges that come with working with different types of data, the handling of increasingly large amounts of information, the development of emerging technologies, and the need of translational studies, it is expected that the use of ML continue growing in the field of obstetrics and gynecology.

Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review

INTRODUCTION

There was limited evidence on the quality of reporting and methodological quality of prediction models using machine learning methods in preterm birth. This systematic review aimed to assess the reporting quality and risk of bias of a machine learning-based prediction model in preterm birth.

MATERIAL AND METHODS

We conducted a systematic review, searching the PubMed, Embase, the Cochrane Library, China National Knowledge Infrastructure, China Biology Medicine disk, VIP Database, and WanFang Data from inception to September 27, 2021. Studies that developed (validated) a prediction model using machine learning methods in preterm birth were included. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement and Prediction model Risk of Bias Assessment Tool (PROBAST) to evaluate the reporting quality and the risk of bias of included studies, respectively. Findings were summarized using descriptive statistics and visual plots. The protocol was registered in PROSPERO (no. CRD 42022301623).

RESULTS

Twenty-nine studies met the inclusion criteria, with 24 development-only studies and 5 development-with-validation studies. Overall, TRIPOD adherence per study ranged from 17% to 79%, with a median adherence of 49%. The reporting of title, abstract, blinding of predictors, sample size justification, explanation of model, and model performance were mostly poor, with TRIPOD adherence ranging from 4% to 17%. For all included studies, 79% had a high overall risk of bias, and 21% had an unclear overall risk of bias. The analysis domain was most commonly rated as high risk of bias in included studies, mainly as a result of small effective sample size, selection of predictors based on univariable analysis, and lack of calibration evaluation.

CONCLUSIONS

Reporting and methodological quality of machine learning-based prediction models in preterm birth were poor. It is urgent to improve the design, conduct, and reporting of such studies to boost the application of machine learning-based prediction models in preterm birth in clinical practice.

Maternal preterm birth prediction in the United States: a case-control database study

Background

Preterm birth is serious public health worldwide, and early prediction of preterm birth in pregnant women may provide assistance for timely intervention and reduction of preterm birth. This study aimed to develop a preterm birth prediction model that is readily available and convenient for clinical application.

Methods

Data used in this case-control study were extracted from the National Vital Statistics System (NVSS) database between 2018 and 2019. Univariate and multivariate logistic regression analyses were utilized to find factors associated with preterm birth. Odds ratio (OR) and 95% confidence interval (CI) were used as effect measures. The area under the curve (AUC), accuracy, sensitivity, and specificity were utilized as model performance evaluation metrics.

Results

Data from 3,006,989 pregnant women in 2019 and 3,039,922 pregnant women in 2018 were used for the model establishment and external validation, respectively. Of these 3,006,989 pregnant women, 324,700 (10.8%) had a preterm birth. Higher education level of pregnant women [bachelor (OR = 0.82; 95%CI, 0.81–0.84); master or above (OR = 0.82; 95%CI, 0.81–0.83)], pre-pregnancy overweight (OR = 0.96; 95%CI, 0.95–0.98) and obesity (OR = 0.94; 95%CI, 0.93–0.96), and prenatal care (OR = 0.48; 95%CI, 0.47–0.50) were associated with a reduced risk of preterm birth, while age ≥ 35 years (OR = 1.27; 95%CI, 1.26–1.29), black race (OR = 1.26; 95%CI, 1.23–1.29), pre-pregnancy underweight (OR = 1.26; 95%CI, 1.22–1.30), pregnancy smoking (OR = 1.27; 95%CI, 1.24–1.30), pre-pregnancy diabetes (OR = 2.08; 95%CI, 1.99–2.16), pre-pregnancy hypertension (OR = 2.22; 95%CI, 2.16–2.29), previous preterm birth (OR = 2.95; 95%CI, 2.88–3.01), and plurality (OR = 12.99; 95%CI, 12.73–13.24) were related to an increased risk of preterm birth. The AUC and accuracy of the prediction model in the testing set were 0.688 (95%CI, 0.686–0.689) and 0.762 (95%CI, 0.762–0.763), respectively. In addition, a nomogram based on information on pregnant women and their spouses was established to predict the risk of preterm birth in pregnant women.

Conclusions

The nomogram for predicting the risk of preterm birth in pregnant women had a good performance and the relevant predictors are readily available clinically, which may provide a simple tool for the prediction of preterm birth.

Development and Validation of a Novel Pre-Pregnancy Score Predictive of Preterm Birth in Nulliparous Women Using Data from Italian Healthcare Utilization Databases

Background: Preterm birth is a major worldwide public health concern, being the leading cause of infant mortality. Understanding of risk factors remains limited, and early identification of women at high risk of preterm birth is an open challenge. Objective: The aim of the study was to develop and validate a novel pre-pregnancy score for preterm delivery in nulliparous women using information from Italian healthcare utilization databases. Study Design: Twenty-six variables independently able to predict preterm delivery were selected, using a LASSO logistic regression, from a large number of features collected in the 4 years prior to conception, related to clinical history and socio-demographic characteristics of 126,839 nulliparous women from Lombardy region who gave birth between 2012 and 2017. A weight proportional to the coefficient estimated by the model was assigned to each of the selected variables, which contributed to the Preterm Birth Score. Discrimination and calibration of the Preterm Birth Score were assessed using an internal validation set (i.e., other 54,359 deliveries from Lombardy) and two external validation sets (i.e., 14,703 and 62,131 deliveries from Marche and Sicily, respectively). Results: The occurrence of preterm delivery increased with increasing the Preterm Birth Score value in all regions in the study. Almost ideal calibration plots were obtained for the internal validation set and Marche, while expected and observed probabilities differed slightly in Sicily for high Preterm Birth Score values. The area under the receiver operating characteristic curve was 60%, 61% and 56% for the internal validation set, Marche and Sicily, respectively. Conclusions: Despite the limited discriminatory power, the Preterm Birth Score is able to stratify women according to their risk of preterm birth, allowing the early identification of mothers who are more likely to have a preterm delivery.

Prediction and prevention of preterm birth in pregnant women living with HIV on antiretroviral therapy

INTRODUCTION

The rate of spontaneous preterm-birth among pregnant women living with HIV on antiretroviral therapy (ART) is 3- to 4-fold higher when compared to HIV-negative women. The pathophysiology of preterm-birth related to HIV or ART remains unknown, especially as women living with HIV are often excluded from preterm birth studies.

AREAS COVERED

This review discusses the currently available evidence on the prediction and prevention of preterm-birth in pregnant women living with HIV. A review of the literature was conducted of primary articles between 2005 and 2021 measuring the association or lack thereof between combination ART and preterm birth, as well as of other predisposing factors to preterm birth in women living with HIV, including cervical length, vaginal microbiome, and cervico-vaginal biomarkers.

EXPERT OPINION

Further research into the effect of ART exposure on preterm-birth risk is critical, and development of preterm-birth predictive tools in this population should be a priority. Vaginal progesterone supplementation deserves further investigation as a therapeutic option to prevent recurrent preterm birth in pregnant women living with HIV. The ProSPAR study, a multicenter randomized controlled trial studying progesterone supplementation in pregnant women on protease inhibitor-based regimens, has been designed but is not yet recruiting patients.

Risk factors for spontaneous preterm birth among healthy nulliparous pregnant women in the Netherlands, a prospective cohort study

Introduction

Spontaneous preterm birth (sPTB) is a major contributor to neonatal morbidity and mortality worldwide. The pathophysiology of sPTB is poorly understood, in particular among nulliparous women without apparent medical or obstetric risk factors. Therefore, we aimed to identify risk factors for sPTB in healthy nulliparous women.

Material and Methods

We performed a prospective cohort study. Recruitment took place from February 2014 to December 2016 in 16 community midwifery centers in the Netherlands. Eligibility criteria were: ≥18 years, no previous pregnancy >16 weeks of gestation, healthy singleton pregnancy, and antenatal booking <24 weeks of gestation. At study inclusion, participants completed a questionnaire, including details on lifestyle, work, and medical history. Cervical length was measured by vaginal ultrasound at the second‐trimester anomaly scan. Detailed information concerning pregnancy and birth was collected via antenatal charts. We calculated the adjusted odds ratio (aOR) and 95% confidence intervals (CI) for various risk factors with correction for socioeconomic status (SES) using logistic regression and Firth's correction.

Results

We included 363 women of whom pregnancy outcomes were available in 349 (96.1%) participants. The cervical length measurement was available for 225 (62.0%) participants. sPTB occurred in 26 women (7.5%). SES was associated with sPTB (OR: 3.7, 95%  CI: 1.6–8.5) in univariate analysis. First or second trimester vaginal bleeding (aOR: 3.6, 95% CI: 1.4–9.0) and urinary tract infection during pregnancy (aOR: 4.9, 95% CI: 1.7–13.9) were associated with sPTB in multivariate analysis.

Conclusions

This prospective cohort confirms established risk factors for sPTB in nulliparous women deemed at low risk of sPTB.

Prediction of low Apgar score at five minutes following labor induction intervention in vaginal deliveries: machine learning approach for imbalanced data at a tertiary hospital in North Tanzania

Background

Prediction of low Apgar score for vaginal deliveries following labor induction intervention is critical for improving neonatal health outcomes. We set out to investigate important attributes and train popular machine learning (ML) algorithms to correctly classify neonates with a low Apgar scores from an imbalanced learning perspective.

Methods

We analyzed 7716 induced vaginal deliveries from the electronic birth registry of the Kilimanjaro Christian Medical Centre (KCMC). 733 (9.5%) of which constituted of low (< 7) Apgar score neonates. The ‘extra-tree classifier’ was used to assess features’ importance. We used Area Under Curve (AUC), recall, precision, F-score, Matthews Correlation Coefficient (MCC), balanced accuracy (BA), bookmaker informedness (BM), and markedness (MK) to evaluate the performance of the selected six (6) machine learning classifiers. To address class imbalances, we examined three widely used resampling techniques: the Synthetic Minority Oversampling Technique (SMOTE) and Random Oversampling Examples (ROS) and Random undersampling techniques (RUS). We applied Decision Curve Analysis (DCA) to evaluate the net benefit of the selected classifiers.

Results

Birth weight, maternal age, and gestational age were found to be important predictors for the low Apgar score following induced vaginal delivery. SMOTE, ROS and and RUS techniques were more effective at improving “recalls” among other metrics in all the models under investigation. A slight improvement was observed in the F1 score, BA, and BM. DCA revealed potential benefits of applying Boosting method for predicting low Apgar scores among the tested models.

Conclusion

There is an opportunity for more algorithms to be tested to come up with theoretical guidance on more effective rebalancing techniques suitable for this particular imbalanced ratio. Future research should prioritize a debate on which performance indicators to look up to when dealing with imbalanced or skewed data.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12884-022-04534-0.