According to the study, ‘Clinical and Dental Predictors of Preterm Birth Using Machine Learning Methods: the MOHEPI Study,’ data from 60 cesarean section deliveries were analysed, including 30 preterm and 30 full-term deliveries. 

While assessing known factors such as pre-pregnancy BMI, maternal age and pre-eclampsia, the researchers also analysed five dental predictors associated with preterm birth, including the Modified Gingival Index (MGI), stage of periodontitis, 

and the Plaque Index (PI).

The top five predictors of preterm birth identified in the study were pre-pregnancy BMI, Modified Gingival Index, pre-eclampsia, DMF index and maternal age. 

Notably, gingival health emerged as the second highest predictor of preterm birth risk and the sixth highest predictor of spontaneous preterm birth, outperforming previously well-known medical risk factors such as preterm birth, chronic hypertension 

and gestational diabetes.

Despite the limitations of this study, such as the small sample size and the non-inclusion of socioeconomic variables, the results show great potential for improving preterm birth prediction models. 

For example, these findings could provide key evidence for the development of guidelines for preterm birth prediction models and early screening and customised preventive interventions based on these risk factors. 

In addition, the identification of maternal dental health indicators as significant predictors of preterm birth further emphasises the importance of routine dental check-ups for pregnant women.