Childhood obesity poses a significant public health challenge, with estimates suggesting that rates of obesity among children could reach one-third by 2030. A recent Israeli study published in the International Journal of Obesity introduces an artificial intelligence model that can predict the risk of excess weight in children at age 2 based solely on data collected during pregnancy and delivery. Conducted at the women’s and obstetrics division at Barzilai University Medical Center in Ashkelon, the study highlights the potential for early nutritional interventions to combat a growing epidemic.
Dr. Yaniv Ovadia, head of the Big Data Research Unit at Barzilai Medical Center and one of the study’s leaders, noted that obesity-related mortality was estimated at about five million deaths per year as of 2019. The study aims to shed light on the complex interactions between maternal nutrition, thyroid function, and the risk of childhood obesity. “Overweight and obesity in early life are linked to cardiovascular disease later on and even to premature death,” Ovadia warned.
Dr. Naama Fisch-Shvalb, a senior physician at the Institute of Endocrinology and Diabetes at Schneider Children’s Medical Center, emphasized the challenges of treating obesity once it has developed. “Once obesity is present, it is very difficult to treat because it is persistent,” she stated, advocating for a focus on prevention rather than treatment.
The researchers tested the hypothesis that a combination of biological, nutritional, and anthropometric measures collected during pregnancy could forecast excess weight in children. By analyzing maternal thyroid function, nutritional status, and other physiological characteristics, they aimed to predict offspring weight outcomes by age 2. “Obesity in early childhood is not random but rather the result of a complex interaction of hormonal, metabolic, and environmental factors that begin operating as early as pregnancy,” Ovadia explained.
Israel, like many developed nations, faces mild to moderate iodine deficiency. In a preliminary study conducted in 2017, the research team found that urinary iodine concentrations among pregnant Israeli women were significantly lower than levels recommended by the World Health Organization. The current study sought to determine whether this deficiency, along with pregnancy data, could be linked to excess weight in children during the early years of life.
Following 191 mother-newborn pairs, researchers collected data from women upon their arrival at the hospital. The study examined 87 variables, including maternal height, weight, thyroid function, iodine-rich food consumption, and urinary iodine concentrations. By the age of 2, children’s height and weight were recorded during routine checkups at maternal and child health clinics, with overweight defined as a weight at or above the 85th percentile for age and sex.
The data was analyzed using various artificial intelligence models, and ultimately, the model with the best predictive performance was selected. “We tested several machine-learning classification algorithms and ultimately selected the one that showed the best predictive performance, already at birth, for identifying children who would be overweight at age 2,” said Dr. Abigail Paradise-Vit, a data scientist involved in the study. The model incorporated maternal dietary information, anthropometric measures, and the newborn’s birth weight and head circumference.
By the study’s conclusion, the model accurately identified 74.3 percent of cases in the test group and correctly identified 71 percent of the overweight children at age 2. The most impactful factors included a combination of obstetric, anthropometric, hormonal, and nutritional elements. Specifically, maternal height, the number of previous pregnancies, and newborn head circumference emerged as strong predictors. Nutritionally, a diet rich in iodine and certain dairy products were also significant indicators.
Ovadia noted that lean sea fish, which are high in iodine, may positively influence metabolism during pregnancy, thereby affecting the newborn’s metabolism. Conversely, high-fat foods such as mozzarella and certain frozen treats may indicate an energy surplus that could contribute to fetal growth and fat accumulation, leading to excess weight later in life.
The study does have limitations, including its focus on a single group of pregnant women and the lack of long-term follow-up on the children’s growth trajectories. Dr. Fisch-Shvalb pointed out that the children’s diets were not assessed, which could also influence weight outcomes. Additionally, some data were generated synthetically to balance the study, emphasizing the need for caution in generalizing findings.
Looking ahead, the study underscores a potential new approach in addressing childhood obesity. “This may be one of the study’s most significant contributions,” Ovadia said, suggesting that the findings could help healthcare professionals develop personalized risk profiles for pregnant women, leading to targeted care and individualized dietary recommendations. “It is a tool with real potential because it is supported by artificial intelligence, which may save time and uncertainty in identifying risk,” he added. Effective use of this research could pave the way for proactive measures aimed at preventing excess weight in future generations.
See also
AI Study Reveals Generated Faces Indistinguishable from Real Photos, Erodes Trust in Visual Media
Gen AI Revolutionizes Market Research, Transforming $140B Industry Dynamics
Researchers Unlock Light-Based AI Operations for Significant Energy Efficiency Gains
Tempus AI Reports $334M Earnings Surge, Unveils Lymphoma Research Partnership
Iaroslav Argunov Reveals Big Data Methodology Boosting Construction Profits by Billions
