Decoding Maternal Morbidity Data Challenge


A pregnant woman smiles while reclined. NICHD Decoding Maternal Morbidity Data ChallengeIn 2021, NICHD launched the Decoding Maternal Morbidity Data Challenge to help advance research on maternal health and promote healthy pregnancies. The goal of the challenge was to devise new ways of analyzing data from NICHD’s Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-be (nuMoM2b) to identify factors that impact maternal morbidity and severe maternal morbidity so that clinicians can more quickly and accurately identify and treat pregnancy-related conditions and prevent severe illness or death for a pregnant person. Twelve prizes totaling $400,000 were awarded to seven proposals.

Topic Areas

The goal of the challenge is not to replicate prior findings but to focus on new discoveries using the nuMoM2b data. Potential areas for exploration include prescription drug use, diet, the quality of healthcare including health provider, insurance or access to healthcare, risk factors for adverse outcomes, and the intersection of multiple factors.

Because maternal mortality and maternal morbidity adversely impact disadvantaged racial and ethnic minorities at a much higher rate than other groups, additional credit was given to solutions addressing these communities.

Seven prizes of $50,000 were awarded for innovation, and an additional five prizes of $10,000 were awarded for health disparities. The following are winning teams/individuals (in alphabetical order); asterisks denote winners of both prize categories:

Columbia University and Hunter College, New York City
On Predicting and Understanding Preeclampsia: A Machine Learning Approach
Ansaf Salleb-Aouissi, Ph.D., Team Lead (Columbia)
Adam Catto (Hunter)
Andrea Clark-Sevilla (Columbia)
Alisa Leshchenko (Hunter)
Adam Lin (Columbia)
Daniel Mallia (Hunter)
Itsik Pe’er (Columbia)
Anita Raja (Hunter)
Ron Wapner (Columbia)
Qi Yan (Columbia)

Delfina, San Francisco*
Random Forests for Accurate Prediction of the Risk of Hypertensive Disorders of Pregnancy at Term
Ali Ebrahim, Ph.D., Team Lead
Anna Buford
Senan Ebrahim
Adesh Kadambi
Timothy Wen

Emory University, Atlanta*
Social Determinants of Health Phenotype Predicts Unplanned Cesarean Birth in the Path to Maternal Morbidity Among Healthy Participants of the NuMoM2b Study
Nicole Carlson, Ph.D., Team Lead
Elise Erickson

Feng Ya, LLC, Watkinsville, Georgia
A Fair Diagnosis Proposal of Maternal Morbidity with a Demonstrative Example in Predicting Stillbirths
Yaping Li, Team Lead
Yueying Wang
Zhao Wang
Ruochi Zhang

IBM Data Science and AI Elite, San Francisco*
Tracking Changes in Health Metrics Between Visits to Model Adverse Pregnancy Outcomes Among Nulliparous Women
Ainesh Pandey, Team Lead
Demian Gass
Gabriel Gilling
Andre Violante

Johnston and Company, LLC, Salt Lake City*
The Relationship Between Marginalizing Behaviors and Postpartum Complications for Nulliparous Women Receiving an Undesired C-section
Britnee Johnston

University of Washington, Seattle*
Structural Equation Model Identifies Causal Pathways Between Social Determinants of Maternal Health, Biomarkers of Allostatic Load, and Hypertensive Disorders of Pregnancy Among U.S. Racial Groups
Monica Keith, Ph.D., Team Lead
Melanie Martin

More Information

top of pageBACK TO TOP