Machine learning analysis of the relationships between traumatic childbirth experience with positive and negative fertility motivations in Iran in a community-based sample.

BACKGROUND

Psychologically traumatic childbirth leads to short and long-term negative impacts on a woman's health and impacts future reproductive decisions. Considering the importance of fertility growth and strengthening positive fertility motivations in …, this community-based study was conducted to investigate the relationship between traumatic childbirth history and positive and negative fertility motivations.

METHODS

The present cross-sectional study was conducted on 900 women of reproductive age. Sampling lasted from March 21 to September 23, 2023, using multi-stage and convenient sampling from health-treatment centers in …. History of pregnancy and childbirth, DSM-A criterion, and Miller's questionnaire were used to collect data. For data analysis, Python software was used for machine learning and elastic net analysis was conducted in a nested cross-validation framework.

RESULTS

Of the 900 women participating in this study, 387 reported a history of traumatic birth and 513 reported no history of traumatic birth. The positive and negative fertility motivations have a significant relationship with the previous history of traumatic childbirth. Elastic network modeling predicts using RMSE, MAE and R-squared that religious beliefs, married duration, and women's education have the greatest increasing effect on positive fertility motivation. Drug addiction, traumatic childbirth, and abortion history have the greatest effect on increasing negative fertility motivation.

CONCLUSIONS

Positive and negative fertility motivations are significantly affected by the history of traumatic childbirth. Therefore, in countries that want to grow their population, preventing traumatic childbirth and providing counseling interventions should be placed in the priorities of maternal care.