Prediction of newborn’s body mass index using nationwide multicenter ultrasound data: a machine-learning study

Korean Society of Ultrasound in Obstetrics and Gynecology Research Group

Research output: Contribution to journalArticlepeer-review

11 Scopus citations


Background: This study introduced machine learning approaches to predict newborn’s body mass index (BMI) based on ultrasound measures and maternal/delivery information. Methods: Data came from 3159 obstetric patients and their newborns enrolled in a multi-center retrospective study. Variable importance, the effect of a variable on model performance, was used for identifying major predictors of newborn’s BMI among ultrasound measures and maternal/delivery information. The ultrasound measures included biparietal diameter (BPD), abdominal circumference (AC) and estimated fetal weight (EFW) taken three times during the week 21 - week 35 of gestational age and once in the week 36 or later. Results: Based on variable importance from the random forest, major predictors of newborn’s BMI were the first AC and EFW in the week 36 or later, gestational age at delivery, the first AC during the week 21 - the week 35, maternal BMI at delivery, maternal weight at delivery and the first BPD in the week 36 or later. For predicting newborn’s BMI, linear regression (2.0744) and the random forest (2.1610) were better than artificial neural networks with one, two and three hidden layers (150.7100, 154.7198 and 152.5843, respectively) in the mean squared error. Conclusions: This is the first machine-learning study with 64 clinical and sonographic markers for the prediction of newborns’ BMI. The week 36 or later is the most effective period for taking the ultrasound measures and AC and EFW are the best predictors of newborn’s BMI alongside gestational age at delivery and maternal BMI at delivery.

Original languageEnglish
Article number172
JournalBMC Pregnancy and Childbirth
Issue number1
StatePublished - Dec 2021

Bibliographical note

Funding Information:
We appreciate the following researchers and hospitals participated in this study: Korea University Anam Hospital (AKH, KHY, and LKS), Kangwon National University Hospital (NSH, LSJ, and KSO), Konkuk University Hospital (HHS), Ewha Womans University Hospital (PMH), Catholic University of Korea Seoul St. Mary’s Hospital (KHS), Catholic University of Korea Eunpyeong St. Mary’s Hospital (KJY), CHA Gangnam Medical Center (KMY), Kyung Hee University Hospital at Gangdong (SHJ), Hallym University Kangdong Sacred Heart Hospital (MJS), Gangneung Asan Hospital (JDH), Kangbuk Samsung Hospital (SJH), Konyang University Hospital (KTY), Kyungpook National University Hospital (SWJ), Gyeongsang National University Hospital (PJK), Keimyung University Dongsan Medical Center (BJG), Korea University Guro Hospital (CGJ), Hanyang University Guri Hospital (BHY), National Health Insurance Service Ilsan Hospital (KEH), Gachon University Gil Hospital (KSY), Dankook University Hospital (KYD), Daegu Catholic University Medical Center (HSY), Hallym University Dongtan Sacred Heart Hospital (KKS), Pusan National University Hospital (KSC), Inje University Busan Paik Hospital (KYN), Catholic University of Korea Bucheon St. Mary’s Hospital (SKJ and SJE), CHA Bundang Medical Center (LJY), Sungkyunkwan University Samsung Medical Center (OSY), Inje University Sanggye Paik Hospital (SYS), Seoul National University Hospital (LSM), Seoul National University Boramae Medical Center (KBJ), Soon Chun Hyang University Hospital (CGY), Ulsan University Asan Medical Center (WHS and LMY), Yonsei Univeristy Sinchon Severance Hospital (KYH), Pusan National University Yangsan Hospital (LDH), Ulsan University Hospital (LSJ), Inha University Hospital (CSR), Dongguk University Ilsan hospital (PHS), Inje University Ilsan Paik Hospital (KHS), Chonnam National University Hospital (KYH and KJW), Jeonbuk National University Hospital (JYJ and LDH), Jeonju Presbyterian Medical Center (KKJ), Jeju National University Hospital (KHS), Chosun University Hospital (CSJ and CJH), Chung-Ang University Hospital (KGJ), Soon Chun Hyang University Cheonan Hospital (KYS), Chungnam National University Hospital (LMA), Hallym University Kangnam Sacred Heart Hospital (SJE), Hanyang University Hospital (HJK).

Publisher Copyright:
© 2021, The Author(s).


  • Abdominal circumference
  • Body mass index
  • Estimated fetal weight
  • Newborn


Dive into the research topics of 'Prediction of newborn’s body mass index using nationwide multicenter ultrasound data: a machine-learning study'. Together they form a unique fingerprint.

Cite this