Ensemble Learning to Improve the Prediction of Fetal Macrosomia and Large-for-Gestational Age

Machine learning approach for the prediction of macrosomia

Fetal macrosomia is associated with maternal and newborn complications due to incorrect fetal weight estimation or inappropriate choice of delivery models. The early screening and evaluation of macrosomia in the third trimester can improve delivery outcomes and reduce complications. However, traditional clinical and ultrasound examinations face difficulties in obtaining accurate fetal measurements during the third trimester of pregnancy. This study aims to develop a comprehensive predictive model for detecting macrosomia using machine learning (ML) algorithms. The accuracy of macrosomia prediction using logistic regression, k-nearest neighbors, support vector machine, random forest (RF), XGBoost, and LightGBM algorithms was explored. Each approach was trained and validated using data from 3244 pregnant women at a hospital in southern China. The information gain method was employed to identify deterministic features associated with the occurrence of macrosomia. The performance of six ML algorithms based on the recall and area under the curve evaluation metrics were compared. To develop an efficient prediction model, two sets of experiments based on ultrasound examination records within 1-7 days and 8-14 days prior to delivery were conducted. The ensemble model, comprising the RF, XGBoost, and LightGBM algorithms, showed encouraging results. For each experimental group, the proposed ensemble model outperformed other ML approaches and the traditional Hadlock formula. The experimental results indicate that, with the most risk-relevant features, the ML algorithms presented in this study can predict macrosomia and assist obstetricians in selecting more appropriate delivery models.

Development and evaluation of machine learning models for predicting large-for-gestational-age newborns in women exposed to radiation prior to pregnancy

INTRODUCTION

The correlation between radiation exposure before pregnancy and abnormal birth weight has been previously proven. However, for large-for-gestational-age (LGA) babies in women exposed to radiation before becoming pregnant, there is no prediction model yet.

MATERIAL AND METHODS

The data were collected from the National Free Preconception Health Examination Project in China. A sum of 455 neonates (42 SGA births and 423 non-LGA births) were included. A training set (n = 319) and a test set (n = 136) were created from the dataset at random. To develop prediction models for LGA neonates, conventional logistic regression (LR) method and six machine learning methods were used in this study. Recursive feature elimination approach was performed by choosing 10 features which made a big contribution to the prediction models. And the Shapley Additive Explanation model was applied to interpret the most important characteristics that affected forecast outputs.

RESULTS

The random forest (RF) model had the highest average area under the receiver-operating-characteristic curve (AUC) for predicting LGA in the test set (0.843, 95% confidence interval [CI]: 0.714-0.974). Except for the logistic regression model (AUC: 0.603, 95%CI: 0.440-0.767), other models' AUCs displayed well. Thereinto, the RF algorithm's final prediction model using 10 characteristics achieved an average AUC of 0.821 (95% CI: 0.693-0.949).

CONCLUSION

The prediction model based on machine learning might be a promising tool for the prenatal prediction of LGA births in women with radiation exposure before pregnancy.

The State of Machine Learning in Outcomes Prediction of Transsphenoidal Surgery: A Systematic Review

The purpose of this analysis is to assess the use of machine learning (ML) algorithms in the prediction of postoperative outcomes, including complications, recurrence, and death in transsphenoidal surgery. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed all papers that used at least one ML algorithm to predict outcomes after transsphenoidal surgery. We searched Scopus, PubMed, and Web of Science databases for studies published prior to May 12, 2021. We identified 13 studies enrolling 5,048 patients. We extracted the general characteristics of each study; the sensitivity, specificity, area under the curve (AUC) of the ML models developed as well as the features identified as important by the ML models. We identified 12 studies with 5,048 patients that included ML algorithms for adenomas, three with 1807 patients specifically for acromegaly, and five with 2105 patients specifically for Cushing's disease. Nearly all were single-institution studies. The studies used a heterogeneous mix of ML algorithms and features to build predictive models. All papers reported an AUC greater than 0.7, which indicates clinical utility. ML algorithms have the potential to predict postoperative outcomes of transsphenoidal surgery and can improve patient care. Ensemble algorithms and neural networks were often top performers when compared with other ML algorithms. Biochemical and preoperative features were most likely to be selected as important by ML models. Inexplicability remains a challenge, but algorithms such as local interpretable model-agnostic explanation or Shapley value can increase explainability of ML algorithms. Our analysis shows that ML algorithms have the potential to greatly assist surgeons in clinical decision making.

Early Prediction Model of Macrosomia Using Machine Learning for Clinical Decision Support

The condition of fetal overgrowth, also known as macrosomia, can cause serious health complications for both the mother and the infant. It is crucial to identify high-risk macrosomia-relevant pregnancies and intervene appropriately. Despite this need, there are several gaps in research related to macrosomia, including limited predictive models, insufficient machine learning applications, ineffective interventions, and inadequate understanding of how to integrate machine learning models into clinical decision-making. To address these gaps, we developed a machine learning-based model that uses maternal characteristics and medical history to predict macrosomia. Three different algorithms, namely logistic regression, support vector machine, and random forest, were used to develop the model. Based on the evaluation metrics, the logistic regression algorithm provided the best results among the three. The logistic regression algorithm was chosen as the final algorithm to predict macrosomia. The hyper parameters of the logistic regression model were tuned using cross-validation to achieve the best possible performance. Our results indicate that machine learning-based models have the potential to improve macrosomia prediction and enable appropriate interventions for high-risk pregnancies, leading to better health outcomes for both mother and fetus. By leveraging machine learning algorithms and addressing research gaps related to macrosomia, we can potentially reduce the health risks associated with this condition and make informed decisions about high-risk pregnancies.

Novel Prediction Method Applied to Wound Age Estimation: Developing a Stacking Ensemble Model to Improve Predictive Performance Based on Multi-mRNA

(1) Background: Accurate diagnosis of wound age is crucial for investigating violent cases in forensic practice. However, effective biomarkers and forecast methods are lacking. (2) Methods: Samples were collected from rats divided randomly into control and contusion groups at 0, 4, 8, 12, 16, 20, and 24 h post-injury. The characteristics of concern were nine mRNA expression levels. Internal validation data were used to train different machine learning algorithms, namely random forest (RF), support vector machine (SVM), multilayer perceptron (MLP), gradient boosting (GB), and stochastic gradient descent (SGD), to predict wound age. These models were considered the base learners, which were then applied to developing 26 stacking ensemble models combining two, three, four, or five base learners. The best-performing stacking model and base learner were evaluated through external validation data. (3) Results: The best results were obtained using a stacking model of RF + SVM + MLP (accuracy = 92.85%, area under the receiver operating characteristic curve (AUROC) = 0.93, root-mean-square-error (RMSE) = 1.06 h). The wound age prediction performance of the stacking models was also confirmed for another independent dataset. (4) Conclusions: We illustrate that machine learning techniques, especially ensemble algorithms, have a high potential to be used to predict wound age. According to the results, the strategy can be applied to other types of forensic forecasts.

Towards an explainable clinical decision support system for large-for-gestational-age births

A myriad of maternal and neonatal complications can result from delivery of a large-for-gestational-age (LGA) infant. LGA birth rates have increased in many countries since the late 20th century, partially due to a rise in maternal body mass index, which is associated with LGA risk. The objective of the current study was to develop LGA prediction models for women with overweight and obesity for the purpose of clinical decision support in a clinical setting. Maternal characteristics, serum biomarkers and fetal anatomy scan measurements for 465 pregnant women with overweight and obesity before and at approximately 21 weeks gestation were obtained from the PEARS (Pregnancy Exercise and Nutrition with smart phone application support) study data. Random forest, support vector machine, adaptive boosting and extreme gradient boosting algorithms were applied with synthetic minority over-sampling technique to develop probabilistic prediction models. Two models were developed for use in different settings: a clinical setting for white women (AUC-ROC of 0.75); and a clinical setting for women of all ethnicity and regions (AUC-ROC of 0.57). Maternal age, mid upper arm circumference, white cell count at the first antenatal visit, fetal biometry and gestational age at fetal anatomy scan were found to be important predictors of LGA. Pobal HP deprivation index and fetal biometry centiles, which are population-specific, are also important. Moreover, we explained our models with Local Interpretable Model-agnostic Explanations (LIME) to improve explainability, which was proven effective by case studies. Our explainable models can effectively predict the probability of an LGA birth for women with overweight and obesity, and are anticipated to be useful to support clinical decision-making and for the development of early pregnancy intervention strategies to reduce pregnancy complications related to LGA.

A predictive model of macrosomic birth based upon real-world clinical data from pregnant women

BACKGROUND

Fetal macrosomia is associated with an increased risk of several maternal and newborn complications. Antenatal predication of fetal macrosomia remains challenging. We aimed to develop a nomogram model for the prediction of macrosomia using real-world clinical data to improve the sensitivity and specificity of macrosomia prediction.

METHODS

In the present study, we performed a retrospective, observational study based on 13,403 medical records of pregnant women who delivered singleton infants at a tertiary hospital in Shanghai from 1 January 2018 through 31 December 2019. We split the original dataset into a training set (n = 9382) and a validation set (n = 4021) at a 7:3 ratio to generate and validate our model. The candidate variables, including maternal characteristics, laboratory tests, and sonographic parameters were compared between the two groups. A univariate and multivariate logistic regression was carried out to explore the independent risk factors for macrosomia in pregnant women. Thus, the regression model was adopted to establish a nomogram to predict the risk of macrosomia. Nomogram performance was determined by discrimination and calibration metrics. All the statistical analysis was analyzed using R software.

RESULTS

We compared the differences between the macrosomic and non-macrosomic groups within the training set and found 16 independent risk factors for macrosomia (P < 0.05), including biparietal diameter (BPD), head circumference (HC), femur length (FL), amniotic fluid index (AFI) at the last prenatal examination, pre-pregnancy body mass index (BMI), and triglycerides (TG). Values for the areas under the curve (AUC) for the nomogram model were 0.917 (95% CI, 0.908-0.927) and 0.910 (95% CI, 0.894-0.927) in the training set and validation set, respectively. The internal and external validation of the nomogram demonstrated favorable calibration as well as discriminatory capability of the model.

CONCLUSIONS

Our model has precise discrimination and calibration capabilities, which can help clinical healthcare staff accurately predict macrosomia in pregnant women.

Interpretable machine learning to identify important predictors of birth weight: A prospective cohort study

BACKGROUND

Predicting birth weight and identifying its risk factors are clinically important. This study aims to use interpretable machine learning to predict birth weight and identity important predictors.

METHODS

This prospective cohort study was conducted in Tongzhou Maternal and Child Health Care Hospital of Beijing, China, recruiting pregnant women between June 2018 and February 2019. We used 24 features to predict infant birth weight, including gestational age, mother's age, parity, history of macrosomia delivery, pre-pregnancy body mass index (BMI), height, father's BMI, lifestyle (diet, physical activity, smoking), and biomarker (fasting glucose and lipids) features. Study outcome was birth weight of infant. We used 8 supervised learning models including 4 individual [linear regression, ridge regression, lasso regression, support vector machines regression (SVR)], and 4 ensemble estimators (random forest, AdaBoost, gradient boosted trees, and voting ensemble for regression) to predict birth weight. Model accuracy was measured by root mean squared error (RMSE) of 10-fold cross validation on the training set and RMSE of prediction on the test set. We used permutation importance algorithm to understand the prediction from the models and what affected them.

RESULT

This study included 4,754 mother-child dyads. RMSEs were lower in voting ensemble for regression, linear regression, and SVR than random forest, AdaBoost, and gradient boosted tree. The 5 most important predictors for infant birth weight were gestational age, fetal sex, preterm birth, mother's height, and pre-pregnancy BMI. After adding ultrasound-measured indicators of fetal growth into predictors, mother's height and pre-pregnancy BMI remained the most important predictors in predicting the outcome.

CONCLUSION

Mother's height and pre-pregnancy BMI were identified as important predictors for infant birth weight. Interpretable machine learning is a promising tool in the prediction of birth weight.

Higher Alkylresorcinol Concentrations, a Consequence of Whole-Grain Intake, are Inversely Associated with Gestational Diabetes Mellitus in Iceland

BACKGROUND

A diet rich in whole grains may provide benefits for pregnant women due to whole grains' high nutritional value and dietary fiber content.

OBJECTIVES

To study the associations of whole-grain consumption, as well as the plasma alkylresorcinol concentration, a whole-grain consumption biomarker, in early pregnancy with gestational diabetes mellitus (GDM) diagnoses.

METHODS

Subjects were women from the prospective study Pregnant Women in Iceland II (PREWICE II; n = 853) who attended their ultrasound appointment in gestational weeks 11-14 during the period from October 2017 to March 2018. During that visit, whole-grain consumption was estimated using a diet screening questionnaire, and blood samples were collected for analysis of plasma alkylresorcinols (ARs). Information on GDM diagnoses was later extracted from medical records. Multivariate log-binomial regression was used to evaluate the association of dietary whole-grain and AR concentrations with GDM.

RESULTS

In total, 14.9% of the women adhered to the national food-based dietary guidelines (n = 127), which recommend 2 portions of whole grains daily. GDM was diagnosed in 127 women (14.9%). The frequency of whole-grain consumption was lower in women who were later diagnosed with GDM compared to the women without GDM (median, 5 times/week vs. 6 times/week, respectively; P = 0.02). This difference was reflected in the lower median concentration of total AR in women diagnosed with GDM (163 nmol/L vs. 209 nmol/L, respectively; P < 0.01). The quartile with the highest concentrations of AR had a RR of 0.50 (95% CI: 0.27-0.90) of being diagnosed with GDM, in comparison to the lowest quartile. There was a significant dose response in the GDM risk with higher AR levels.

CONCLUSIONS

We found that a higher consumption of whole grains, reflected both by reported consumption according to the FFQ and AR biomarkers, was associated with a decreased risk of receiving a GDM diagnosis.

Interventricular Septal Thickness as a Diagnostic Marker of Fetal Macrosomia

Serious complications in both mother and newborn arising as a result of fetal macrosomia indicate the need for early diagnosis and prevention. Unfortunately, current predictors, such as fetal biometry, fundal height, and amniotic fluid index, appear to be insufficient. Therefore, we decided to assess the predictive potential of interventricular septal thickness (IVST), as measured at ≥33 weeks of gestation. Two hundred and ninety-nine patients met the inclusion criteria: complete medical history including all necessary measurements—namely, IVST obtained by M-mode echocardiography, fetal biometry, and birth weight. The Statistica 13.1 PL software was used to generate the receiver operating curve. The optimal cut-off point (IVST of 4.7 mm) was selected using the Youden index method. The analysis of fetal biometry abnormalities resulted in 46.6% of macrosomia cases being correctly predicted; however, IVST analysis detected 71.4% of cases. IVST at ≥4.7 mm appears to have a higher sensitivity and negative predictive value (NPV) than routine ultrasound.

Developing a Predictive Model for Depressive Disorders Using Stacking Ensemble and Naive Bayesian Nomogram: Using Samples Representing South Korea

This study provided baseline data for preventing depression in female older adults living alone by understanding the degree of their depressive disorders and factors affecting these depressive disorders by analyzing epidemiological survey data representing South Koreans. To achieve the study objective, this study explored the main risk factors of depressive disorders using the stacking ensemble machine technique. Moreover, this study developed a nomogram that could help primary physicians easily interpret high-risk groups of depressive disorders in primary care settings based on the major predictors derived from machine learning. This study analyzed 582 female older adults (≥60 years old) living alone. The depressive disorder, a target variable, was measured using the Korean version of Patient Health Questionnaire-9. This study developed five single predictive models (GBM, Random Forest, Adaboost, SVM, XGBoost) and six stacking ensemble models (GBM + Bayesian regression, RandomForest + Bayesian regression, Adaboost + Bayesian regression, SVM + Bayesian regression, XGBoost + Bayesian regression, GBM + RandomForest + Adaboost + SVM + XGBoost + Bayesian regression) to predict depressive disorders. The naive Bayesian nomogram confirmed that stress perception, subjective health, n-6 fatty acid, n-3 fatty acid, mean hours of sitting per day, and mean daily sleep hours were six major variables related to the depressive disorders of female older adults living alone. Based on the results of this study, it is required to evaluate the multiple risk factors for depression including various measurable factors such as social support.

Special Issue on Clinical Medicine for Healthcare and Sustainability

Recently, due to the advancement of network technology, big data and artificial intelligence, the healthcare industry has undergone many sector-wide changes. Medical care has not only changed from passive and hospital-centric to preventative and personalized, but also from disease-centric to health-centric. Healthcare systems and basic medical research are becoming more intelligent and being implemented in biomedical engineering. This Special Issue on "Clinical Medicine for Healthcare and Sustainability" selected 30 excellent papers from 160 papers presented in IEEE ECBIOS 2019 on the topic of clinical medicine for healthcare and sustainability. Our purpose is to encourage scientists to propose their experiments and theoretical researches to facilitate the scientific prediction and influential assessment of global change and development.