Skip to main content
SMFM 2024 Pregnancy Meeting Main banner
Final Program


Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Additional registration fee required
Additional registration fee required
Faculty have requested this content not be shared on social media
Faculty have requested this content not be shared on social media
CME Credit Offered
CME Credit Offered
Poster Icons
Foundation Awardee
Foundation Awardee
No Social Media
No Social Media
Back
Q&A

Clinical Obstetrics

Poster Session 3

(916) Nutrition Pattern and Adverse Pregnancy Outcomes in nulliparous individuals: A cluster analysis

Wednesday, February 14, 2024
8:30 AM – 10:00 AM  
Location: Prince George's Exhibit Hall CDE, Lower Atrium Level
Objective: Studies evaluating association between nutrition and pregnancy outcomes did not take into consideration the various aspects of each patient diet or the large amount of variables within each dietary exposure. Our objective was to use unsupervised machine learning models to characterize dietary profiles and determine their associations with pregnancy outcomes.

Study Design:  This was a secondary analysis of the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be. The primary outcome was a composite of preterm birth, stillbirth, eclampsia, preeclampsia, gestational hypertension, and small for gestational age. An unsupervised machine learning algorithm was developed (k-means). A total of 335 clustering variables were considered. The proportion of the primary outcome was examined within each cluster. Multivariable logistic regression was performed to obtain adjusted odds ratios (aOR) with 95% confidence intervals (95%CI), controlling for predefined confounders.

Results:

Of 7074 individuals, there were 2593 (36.7%) in cluster 1, 546 (7.7%) in cluster 2, and 3935 (55.6%) in cluster 3. Cluster 2 was associated with increased odds of adverse pregnancy outcomes (22.4% vs.31.3%; aOR 1.35 [95%CI 1.06-1.71]) and gestational diabetes (3.9% vs.6.0%; aOR 1.86 [95%CI 1.15-3.01]). Cluster 3 was not associated with adverse pregnancy outcomes (22.4% vs. 25.6%; aOR 1.13 [95%CI 0.99-1.29]). Cluster 1 was characterized by higher intake of vitamin E, vitamin A, fruits, vegetables, and green salad. Cluster 2 was characterized by higher intake of trans-fat, polyunsaturated fatty acids, red meat, sugar beverages, and theobromine intake. Cluster 3 was characterized by lower intake of vitamin E, vitamin A, vegetables, fruits, and fat or oil consumption.

Conclusion:

We were able to use machine learning to categorize food intake into clusters, each with its own risk of adverse pregnancy outcome. Food intake pattern that is characterized by higher intake of trans-fat, polyunsaturated fatty acids, red meat, and sugar beverage intake was associated with adverse pregnancy outcomes.