Home Oral Health Dental factors included in the ‘first attempt’ to predict likelihood of preterm birth

Dental factors included in the ‘first attempt’ to predict likelihood of preterm birth

by adminjay


The study underscores the importance of early screening and the integration of medical and dental care during pregnancy. (iStock)

Researchers from South Korean universities described their model for predicting the risk of preterm birth (PTB) as “significant,” marking the “first attempt” to include dental factors as independent variables in PTB prediction. Their findings were published in Nature on Oct. 21.

“What differentiates our study from previous ones is that we added dental factors in addition to the well-known clinical risk factors, including various clinical backgrounds and obstetric histories,” the researchers stated.

Understanding the risks associated with PTB is key.

According to the World Health Organization (WHO), an estimated 13.4 million babies were born prematurely in 2020, representing more than one in ten births. In 2019, about 900,000 children died due to complications related to PTB, and many survivors face long-term disabilities, including learning difficulties and visual and hearing impairments.

In addition to dental factors such as the modified gingival index (MGI), the machine learning-based predictive model included major predictors of PTB, such as pre-pregnancy body mass index (BMI), maternal age, and preeclampsia. The researchers found that gum health (MGI) ranked second in predicting PTB risk and sixth in predicting spontaneous preterm birth (SPTB), which estimates the likelihood of a baby being born spontaneously before 37 weeks of gestation.

Notably, MGI surpassed well-known medical PTB risk factors, such as maternal age (5th), prior PTB (14th), preeclampsia (3rd), chronic hypertension (15th), and gestational diabetes mellitus (10th).

While the authors acknowledged the “small sample size of the database” and the absence of socio-economic factors like income, they confirmed the model demonstrated “solid performance,” achieving an area under the curve (AUC) of 73% for PTB and 86% for SPTB.

The AUC measures the performance of a prediction model, ranging from 0 to 1. A value of 1.0 indicates perfect prediction, while a value of 0.5 suggests no better than random guessing. Closer to 1 indicates better model performance. An AUC of 0.73 suggests “acceptable” or “good” performance, while an AUC of 0.86 is considered “very good.”

The study emphasizes the need for early screening and the integration of medical and dental care during pregnancy. “Future research should focus on validating these predictors in larger populations and exploring interventions to mitigate these risk factors,” the authors concluded.





Source link

Related Articles