[Risk factors for delayed breastfeeding initiation based on decision tree model and logistic regression model]

Area of Science:

• Maternal and Child Health
• Lactation Science
• Public Health

Background:

• Breastfeeding initiation is critical for infant health and maternal-child bonding.
• Delayed initiation can negatively impact exclusive breastfeeding rates and infant well-being.
• Understanding risk factors is essential for developing targeted interventions.

Purpose of the Study:

• To identify key factors contributing to delayed breastfeeding initiation among mothers.
• To compare the predictive accuracy of logistic regression and decision tree models for identifying these factors.

Main Methods:

• A cross-sectional study involving 950 pregnant women and infant feeding practices in Changsha, Hunan.
• Data collected via questionnaires.
• Logistic regression and decision tree models employed to analyze influential factors.

Main Results:

• 37.5% of mothers experienced delayed breastfeeding initiation.
• Cesarean delivery, pre-initiation bottle use, maternal illness, and vomiting during pregnancy were significant risk factors.
• No significant difference was found between the predictive performance of the logistic regression and decision tree models.

Conclusions:

• Cesarean delivery, early use of feeding bottles, and poor maternal health during pregnancy are significant barriers to timely breastfeeding initiation.
• Interventions should focus on supporting mothers through cesarean delivery, discouraging pre-initiation bottle use, and managing maternal health conditions.
• Healthcare providers should empower mothers to initiate breastfeeding promptly and build confidence in exclusive breastfeeding practices.