Achieving accurate estimates of fetal gestational age and personalised predictions of fetal growth based on data from an international prospective cohort study: a population-based machine learning study

Abstract

Background: Preterm birth is a major global health challenge, the leading cause of death in children under 5 years of age, and a key measure of a population's general health and nutritional status. Current clinical methods of estimating fetal gestational age are often inaccurate. For example, between 20 and 30 weeks of gestation, the width of the 95% prediction interval around the actual gestational age is estimated to be 18-36 days, even when the best ultrasound estimates are used. The aims of this study are to improve estimates of fetal gestational age and provide personalised predictions of future growth.

Methods: Using ultrasound-derived, fetal biometric data, we developed a machine learning approach to accurately estimate gestational age. The accuracy of the method is determined by reference to exactly known facts pertaining to each fetus-specifically, intervals between ultrasound visits-rather than the date of the mother's last menstrual period. The data stem from a sample of healthy, well-nourished participants in a large, multicentre, population-based study, the International Fetal and Newborn Growth Consortium for the 21st Century (INTERGROWTH-21st). The generalisability of the algorithm is shown with data from a different and more heterogeneous population (INTERBIO-21st Fetal Study).

Findings: In the context of two large datasets, we estimated gestational age between 20 and 30 weeks of gestation with 95% confidence to within 3 days, using measurements made in a 10-week window spanning the second and third trimesters. Fetal gestational age can thus be estimated in the 20-30 weeks gestational age window with a prediction interval 3-5 times better than with any previous algorithm. This will enable improved management of individual pregnancies. 6-week forecasts of the growth trajectory for a given fetus are accurate to within 7 days. This will help identify at-risk fetuses more accurately than currently possible. At population level, the higher accuracy is expected to improve fetal growth charts and population health assessments.

Interpretation: Machine learning can circumvent long-standing limitations in determining fetal gestational age and future growth trajectory, without recourse to often inaccurately known information, such as the date of the mother's last menstrual period. Using this algorithm in clinical practice could facilitate the management of individual pregnancies and improve population-level health. Upon publication of this study, the algorithm for gestational age estimates will be provided for research purposes free of charge via a web portal.

Funding: Bill & Melinda Gates Foundation, Office of Science (US Department of Energy), US National Science Foundation, and National Institute for Health Research Oxford Biomedical Research Centre.

Figure 1

Flowchart used to select a subset of the participants in the INTERGROWTH-21st Fetal Growth Longitudinal Study for analysis The procedure closely follows that used by Papageorghiou and colleagues. INTERGROWTH-21st=International Fetal and Newborn Growth Consortium for the 21st Century. AC=abdominal circumference. FL=femur length. HC=head circumference.

Figure 2

Algorithm accuracy in gestational age estimates based on single ultrasound visits or intervals between visits Accuracy of the new algorithm in estimating gestational age from ultrasound measurements of head circumference, abdominal circumference, and femur length. The Fetal Growth Longitudinal Study dataset of the International Fetal and Newborn Growth Consortium for the 21st Century was analysed. The uncertainty is expressed as the half-width of the 95% interval. For the solid red curve, the measure of error is the discrepancy between the algorithm's estimate of the time elapsed between two visits, and the actual time interval between the visits. The solid blue curve pertains to gestational age estimates based on a single set of biometric measurements. The error is the discrepancy between the algorithm's estimate and that obtained from two visits. For comparison, the reported error of a so-called genetic algorithm with the same data (but with mitigating strategies against truncation) by Papageorghiou and colleagues is shown in the dotted blue curve. The performance of the genetic algorithm is typical of the current state of the art. The dotted red curve shows the accuracy of the genetic algorithm when the intervisit interval is used as the measure of error. Using the intervisit interval as the measure of error modestly improves the estimation accuracy of current algorithms. This highlights the need to take fetal growth heterogeneity into account.

Figure 3

Accuracy of gestational age estimates obtained from different populations After training with subgroups of the Fetal Growth Longitudinal Study dataset of the International Fetal and Newborn Growth Consortium for the 21st Century, the algorithm was used to obtain gestational age estimates for members in different subgroups of the same population, as well as a members of a different population (INTERBIO-21st Fetal Study). Estimates obtained from intervisit intervals and single visits are both shown. Over the 20–30 gestational week window, the gestational age estimation uncertainties differ by at most 1 day.

Figure 4

Probability distributions for fetal biometric variables at week 26 of pregnancy. The top row describes distributions compiled with standard estimates of gestational age. The complex, multipeaked character of the distributions are due to noise (uncertainty) in gestational age estimates obtained with standard techniques. The bottom row describes distributions compiled with gestational age estimates from the algorithm presented in this paper. The tighter, single-peaked distributions show the improvement in gestational age estimates, and would facilitate identification of fetal growth abnormalities.