Kwang-Sig Lee1, Ho Yeon Kim2, Se Jin Lee3, Sung Ok Kwon4, Sunghun Na5, Han Sung Hwang6, Mi Hye Park7, Ki Hoon Ahn8. 1. AI Center, Korea University College of Medicine, Seoul, South Korea. 2. Department of Obstetrics and Gynecology, Korea University College of Medicine, 73 Goryeodae-ro, Seongbuk-gu, Seoul, 02841, South Korea. 3. Department of Obstetrics and Gynecology, Kangwon National University Hospital, Kangwon National University School of Medicine, Kangwon, Chuncheon, South Korea. 4. Department of Preventive Medicine, Kangwon National University School of Medicine, Kangwon, Chuncheon, South Korea. 5. Department of Obstetrics and Gynecology, Kangwon National University Hospital, Kangwon National University School of Medicine, Kangwon, Chuncheon, South Korea. lahun@kangwon.ac.kr. 6. Department of Obstetrics and Gynecology, Research Institute of Medical Science, Konkuk University School of Medicine, Seoul, South Korea. 7. Department of Obstetrics and Gynecology, Ewha Medical Institute, Ewha Medical Center, Ewha Womans University College of Medicine, Seoul, South Korea. 8. Department of Obstetrics and Gynecology, Korea University College of Medicine, 73 Goryeodae-ro, Seongbuk-gu, Seoul, 02841, South Korea. akh1220@hanmail.net.
Abstract
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.
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.
Entities:
Keywords:
Abdominal circumference; Body mass index; Estimated fetal weight; Newborn
Authors: Jason E Lang; H Timothy Bunnell; Md Jobayer Hossain; Tim Wysocki; John J Lima; Terri H Finkel; Leonard Bacharier; Amanda Dempsey; Lisa Sarzynski; Matthew Test; Christopher B Forrest Journal: Pediatrics Date: 2018-12 Impact factor: 7.124
Authors: Jeong Ha Wie; Se Jin Lee; Sae Kyung Choi; Yun Sung Jo; Han Sung Hwang; Mi Hye Park; Yeon Hee Kim; Jae Eun Shin; Ki Cheol Kil; Su Mi Kim; Bong Suk Choi; Hanul Hong; Hyun-Joo Seol; Hye-Sung Won; Hyun Sun Ko; Sunghun Na Journal: Life (Basel) Date: 2022-04-18
Authors: Hykoush A Asaturyan; Nicolas Basty; Marjola Thanaj; Brandon Whitcher; E Louise Thomas; Jimmy D Bell Journal: PLoS One Date: 2022-09-13 Impact factor: 3.752