Machine learning improves early prediction of small‐for‐gestational‐age births and reveals nuchal fold thickness as unexpected predictor. (12th February 2021)

• Record Type: Journal Article
• Authors: Saw, Shier Nee; Biswas, Arijit; Mattar, Citra Nurfarah Zaini; Lee, Hwee Kuan; Yap, Choon Hwai
• Is Part Of: Prenatal diagnosis. Volume 41:Number 4(2021)
• Page Start: 505
• Page End: 516
• Publication Date: 2021-02-12
• Subjects: Prenatal diagnosis -- Periodicals; Fetus -- Diseases -- Diagnosis -- Periodicals; Electronic journals; 618.32075
• DOI: 10.1002/pd.5903
• Languages: English
• ISSNs: 0197-3851

Abstract

Abstract: Objective: To investigate the performance of the machine learning (ML) model in predicting small‐for‐gestational‐age (SGA) at birth, using second‐trimester data. Methods: Retrospective data of 347 patients, consisting of maternal demographics and ultrasound parameters collected between the 20th and 25th gestational weeks, were studied. ML models were applied to different combinations of the parameters to predict SGA and severe SGA at birth (defined as 10th and third centile birth weight). Results: Using second‐trimester measurements, ML models achieved an accuracy of 70% and 73% in predicting SGA and severe SGA whereas clinical guidelines had accuracies of 64% and 48%. Uterine PI (Ut PI) was found to be an important predictor, corroborating with existing literature, but surprisingly, so was nuchal fold thickness (NF). Logistic regression showed that Ut PI and NF were significant predictors and statistical comparisons showed that these parameters were significantly different in disease. Further, including NF was found to improve ML model performance, and vice versa. Conclusion: ML could potentially improve the prediction of SGA at birth from second‐trimester measurements, and demonstrated reduced NF to be an important predictor. Early prediction of SGA allows closer clinical monitoring, which provides an opportunity to discover any underlying diseases associated with SGA. Key points: What's already known about this topic? Prenatal SGA detection, which uses Doppler and fetal size measurements, is currently poor What does this study add? We used machine learning (ML) to learn intrinsic data patterns at the second trimester, and showed that the ML predicted SGA at birth significantly better than clinical guidelines could ML modelling unexpectedly revealed that nuchal fold thickness was important in predicting SGA at birth. SGA fetuses could have thin nuchal folds due to low subcutaneous fats