Classification of intrauterine growth restriction at 34-38 weeks gestation with machine learning models

Use of Artificial Intelligence in Recognition of Fetal Open Neural Tube Defect on Prenatal Ultrasound

To compare the axial cranial ultrasound images of normal and open neural tube defect (NTD) fetuses using a deep learning (DL) model and to assess its predictive accuracy in identifying open NTD.It was a prospective case-control study. Axial trans-thalamic fetal ultrasound images of participants with open fetal NTD and normal controls between 14 and 28 weeks of gestation were taken after consent. The images were divided into training, testing, and validation datasets randomly in the ratio of 70:15:15. The images were further processed and classified using DL convolutional neural network (CNN) transfer learning (TL) models. The TL models were trained for 50 epochs. The data was analyzed in terms of Cohen kappa score, accuracy score, area under receiver operating curve (AUROC) score, F1 score validity, sensitivity, and specificity of the test.A total of 59 cases and 116 controls were fully followed. Efficient net B0, Visual Geometry Group (VGG), and Inception V3 TL models were used. Both Efficient net B0 and VGG16 models gave similar high training and validation accuracy (100 and 95.83%, respectively). Using inception V3, the training and validation accuracy was 98.28 and 95.83%, respectively. The sensitivity and specificity of Efficient NetB0 was 100 and 89%, respectively, and was the best.The analysis of the changes in axial images of the fetal cranium using the DL model, Efficient Net B0 proved to be an effective model to be used in clinical application for the identification of open NTD. · Open spina bifida is often missed due to the nonrecognition of the lemon sign on ultrasound.. · Image classification using DL identified open spina bifida with excellent accuracy.. · The research is clinically relevant in low- and middle-income countries..

AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios

BACKGROUND

Fetal growth restriction (FGR) is a leading risk factor for stillbirth, yet the diagnosis of FGR confers considerable prognostic uncertainty, as most infants with FGR do not experience any morbidity. Our objective was to use data from a large, deeply phenotyped observational obstetric cohort to develop a probabilistic graphical model (PGM), a type of "explainable artificial intelligence (AI)", as a potential framework to better understand how interrelated variables contribute to perinatal morbidity risk in FGR.

METHODS

Using data from 9,558 pregnancies delivered at ≥ 20 weeks with available outcome data, we derived and validated a PGM using randomly selected sub-cohorts of 80% (n = 7645) and 20% (n = 1,912), respectively, to discriminate cases of FGR resulting in composite perinatal morbidity from those that did not. We also sought to identify context-specific risk relationships among inter-related variables in FGR. Performance was assessed as area under the receiver-operating characteristics curve (AUC).

RESULTS

Feature selection identified the 16 most informative variables, which yielded a PGM with good overall performance in the validation cohort (AUC 0.83, 95% CI 0.79-0.87), including among "N of 1" unique scenarios (AUC 0.81, 0.72-0.90). Using the PGM, we identified FGR scenarios with a risk of perinatal morbidity no different from that of the cohort background (e.g. female fetus, estimated fetal weight (EFW) 3-9th percentile, no preexisting diabetes, no progesterone use; RR 0.9, 95% CI 0.7-1.1) alongside others that conferred a nearly 10-fold higher risk (female fetus, EFW 3-9th percentile, maternal preexisting diabetes, progesterone use; RR 9.8, 7.5-11.6). This led to the recognition of a PGM-identified latent interaction of fetal sex with preexisting diabetes, wherein the typical protective effect of female fetal sex was reversed in the presence of maternal diabetes.

CONCLUSIONS

PGMs are able to capture and quantify context-specific risk relationships in FGR and identify latent variable interactions that are associated with large differences in risk. FGR scenarios that are separated by nearly 10-fold perinatal morbidity risk would be managed similarly under current FGR clinical guidelines, highlighting the need for more precise approaches to risk estimation in FGR.

Prediction of adverse neonatal adaptation in fetuses with severe fetal growth restriction after 34 weeks of gestation

OBJECTIVE

To establish a predictive model for adverse immediate neonatal adaptation (INA) in fetuses with suspected severe fetal growth restriction (FGR) after 34 gestational weeks (GW).

METHODS

We conducted a retrospective observational study at the University Hospitals of Strasbourg between 2000 and 2020, including 1,220 women with a singleton pregnancy and suspicion of severe FGR who delivered from 34 GW. The primary outcome (composite) was INA defined as Apgar 5-minute score <7, arterial pH <7.10, immediate transfer to pediatrics, or the need for resuscitation at birth. We developed and tested a logistic regression predictive model.

RESULTS

Adverse INA occurred in 316 deliveries. The model included six features available before labor: parity, gestational age, diabetes, middle cerebral artery Doppler, cerebral-placental inversion, onset of labor. The model could predict individual risk of adverse INA with confidence interval at 95 %. Taking an optimal cutoff threshold of 32 %, performances were: sensitivity 66 %; specificity 83 %; positive and negative predictive values 60 % and 87 % respectively, and area under the curve 78 %.

DISCUSSION

The predictive model showed good performances and a proof of concept that INA could be predicted with pre-labor characteristics, and needs to be investigated further.

Prediction of Intrauterine Growth Restriction and Preeclampsia Using Machine Learning-Based Algorithms: A Prospective Study

(1) Background: Prenatal care providers face a continuous challenge in screening for intrauterine growth restriction (IUGR) and preeclampsia (PE). In this study, we aimed to assess and compare the predictive accuracy of four machine learning algorithms in predicting the occurrence of PE, IUGR, and their associations in a group of singleton pregnancies; (2) Methods: This observational prospective study included 210 singleton pregnancies that underwent first trimester screenings at our institution. We computed the predictive performance of four machine learning-based methods, namely decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), by incorporating clinical and paraclinical data; (3) Results: The RF algorithm showed superior performance for the prediction of PE (accuracy: 96.3%), IUGR (accuracy: 95.9%), and its subtypes (early onset IUGR, accuracy: 96.2%, and late-onset IUGR, accuracy: 95.2%), as well as their association (accuracy: 95.1%). Both SVM and NB similarly predicted IUGR (accuracy: 95.3%), while SVM outperformed NB (accuracy: 95.8 vs. 94.7%) in predicting PE; (4) Conclusions: The integration of machine learning-based algorithms in the first-trimester screening of PE and IUGR could improve the overall detection rate of these disorders, but this hypothesis should be confirmed in larger cohorts of pregnant patients from various geographical areas.

Similarity network fusion to identify phenotypes of small-for-gestational-age fetuses

Fetal growth restriction (FGR) affects 5-10% of pregnancies, is the largest contributor to fetal death, and can have long-term consequences for the child. Implementation of a standard clinical classification system is hampered by the multiphenotypic spectrum of small fetuses with substantial differences in perinatal risks. Machine learning and multiomics data can potentially revolutionize clinical decision-making in FGR by identifying new phenotypes. Herein, we describe a cluster analysis of FGR based on an unbiased machine-learning method. Our results confirm the existence of two subtypes of human FGR with distinct molecular and clinical features based on multiomic analysis. In addition, we demonstrated that clusters generated by machine learning significantly outperform single data subtype analysis and biologically support the current clinical classification in predicting adverse maternal and neonatal outcomes. Our approach can aid in the refinement of clinical classification systems for FGR supported by molecular and clinical signatures.

Prediction Models for Intrauterine Growth Restriction Using Artificial Intelligence and Machine Learning: A Systematic Review and Meta-Analysis

BACKGROUND

IntraUterine Growth Restriction (IUGR) is a global public health concern and has major implications for neonatal health. The early diagnosis of this condition is crucial for obtaining positive outcomes for the newborn. In recent years Artificial intelligence (AI) and machine learning (ML) techniques are being used to identify risk factors and provide early prediction of IUGR. We performed a systematic review (SR) and meta-analysis (MA) aimed to evaluate the use and performance of AI/ML models in detecting fetuses at risk of IUGR.

METHODS

We conducted a systematic review according to the PRISMA checklist. We searched for studies in all the principal medical databases (MEDLINE, EMBASE, CINAHL, Scopus, Web of Science, and Cochrane). To assess the quality of the studies we used the JBI and CASP tools. We performed a meta-analysis of the diagnostic test accuracy, along with the calculation of the pooled principal measures.

RESULTS

We included 20 studies reporting the use of AI/ML models for the prediction of IUGR. Out of these, 10 studies were used for the quantitative meta-analysis. The most common input variable to predict IUGR was the fetal heart rate variability (n = 8, 40%), followed by the biochemical or biological markers (n = 5, 25%), DNA profiling data (n = 2, 10%), Doppler indices (n = 3, 15%), MRI data (n = 1, 5%), and physiological, clinical, or socioeconomic data (n = 1, 5%). Overall, we found that AI/ML techniques could be effective in predicting and identifying fetuses at risk for IUGR during pregnancy with the following pooled overall diagnostic performance: sensitivity = 0.84 (95% CI 0.80-0.88), specificity = 0.87 (95% CI 0.83-0.90), positive predictive value = 0.78 (95% CI 0.68-0.86), negative predictive value = 0.91 (95% CI 0.86-0.94) and diagnostic odds ratio = 30.97 (95% CI 19.34-49.59). In detail, the RF-SVM (Random Forest-Support Vector Machine) model (with 97% accuracy) showed the best results in predicting IUGR from FHR parameters derived from CTG.

CONCLUSIONS

our findings showed that AI/ML could be part of a more accurate and cost-effective screening method for IUGR and be of help in optimizing pregnancy outcomes. However, before the introduction into clinical daily practice, an appropriate algorithmic improvement and refinement is needed, and the importance of quality assessment and uniform diagnostic criteria should be further emphasized.

Recent Advances in Machine Learning Applied to Ultrasound Imaging

Machine learning (ML) methods are pervading an increasing number of fields of application because of their capacity to effectively solve a wide variety of challenging problems. The employment of ML techniques in ultrasound imaging applications started several years ago but the scientific interest in this issue has increased exponentially in the last few years. The present work reviews the most recent (2019 onwards) implementations of machine learning techniques for two of the most popular ultrasound imaging fields, medical diagnostics and non-destructive evaluation. The former, which covers the major part of the review, was analyzed by classifying studies according to the human organ investigated and the methodology (e.g., detection, segmentation, and/or classification) adopted, while for the latter, some solutions to the detection/classification of material defects or particular patterns are reported. Finally, the main merits of machine learning that emerged from the study analysis are summarized and discussed.

Interpreting the role of nuchal fold for fetal growth restriction prediction using machine learning

The objective of the study is to investigate the effect of Nuchal Fold (NF) in predicting Fetal Growth Restriction (FGR) using machine learning (ML), to explain the model's results using model-agnostic interpretable techniques, and to compare the results with clinical guidelines. This study used second-trimester ultrasound biometry and Doppler velocimetry were used to construct six FGR (birthweight < 3rd centile) ML models. Interpretability analysis was conducted using Accumulated Local Effects (ALE) and Shapley Additive Explanations (SHAP). The results were compared with clinical guidelines based on the most optimal model. Support Vector Machine (SVM) exhibited the most consistent performance in FGR prediction. SHAP showed that the top contributors to identify FGR were Abdominal Circumference (AC), NF, Uterine RI (Ut RI), and Uterine PI (Ut PI). ALE showed that the cutoff values of Ut RI, Ut PI, and AC in differentiating FGR from normal were comparable with clinical guidelines (Errors between model and clinical; Ut RI: 15%, Ut PI: 8%, and AC: 11%). The cutoff value for NF to differentiate between healthy and FGR is 5.4 mm, where low NF may indicate FGR. The SVM model is the most stable in FGR prediction. ALE can be a potential tool to identify a cutoff value for novel parameters to differentiate between healthy and FGR.

Accelerations of the Fetal Heart Rate in the Screening for Fetal Growth Restriction at 34-38 Week's Gestation

OBJECTIVES

To use machine learning to determine what information on Doppler velocimetry and maternal and fetal heart rates, collected at 20-24 weeks gestation, correlates best with fetal growth restriction according to the estimated fetal weight at 34-38 weeks.

STUDY DESIGN

Data of 4496 pregnant women, collected prospectively for the Safe Passage Study, from August 2007 to August 2016, were used for the present analysis. Doppler flow velocity of the uterine, umbilical, and middle cerebral arteries and transabdominally recorded maternal and fetal ECGs were collected at 20-24 weeks gestation and fetal biometry collected at 34-38 weeks from which the estimated fetal weight was calculated. Fetal growth restriction was defined as an estimated fetal weight below the 10th centile. Accelerations and decelerations of the fetal and maternal heart rates were quantified as gained or lost beats per hour of recording respectively. Machine learning with receiver operative characteristic curves were then used to determine which model gives the best performance.

RESULTS

The final model performed exceptionally well across all evaluation metrics, particularly so for the Stochastic Gradient Descent method: achieving a 93% average for Classification Accuracy, Recall, Precision and F1-Score to identify the fetus with an estimated weight below the 10th percentile at 34-38 weeks. Ranking determined that the most important standard feature was the umbilical artery pulsatility index. However, the excellent overall accuracy is likely due to the value added by the pre-processed features regarding fetal gained beats and accelerations.

CONCLUSION

Fetal movements, as characterized by gained beats as early as 20-24 weeks gestation, contribute to the value of the flow velocimetry of the umbilical artery at 34-38 weeks in identifying the growth restricted fetus.