Adverse pregnancy outcomes (APOs) such as Preterm Birth and Preeclampsia, are major long-lasting public health problems.
Preterm Birth (PTB) is the leading cause of mortality and long-term disabilities among neonates, with heavy emotional and financial consequences to families and society. Prediction of PTB risk has been an exceedingly challenging problem, in particular for first time mothers (nulliparous women) due to the lack of prior pregnancy history. We are devising longitudinal risk prediction models for PTB that integrate multimodal pregnancy data.
We address three important gaps in current literature as our three project objectives: a focused study of nulliparous women and their risk for PTB; combining genetic factors with other clinical factors to determine risk ; and using longitudinal data and models to optimize scheduling of patient visits, testing and treatment.
We are also interested in Preeclampsia (PE), one of the most serious and life-threatening APOs. PE is a pregnancy hypertensive disorder characterized by poor tissue perfusion in pregnancy. It is a spectrum of diverse clinical presentations ranging from a milder form to a more severe one with neurological, renal, hepatic and coagulation abnormalities causing serious damage to blood vessels.
The seriousness of PE represents a significant impetus to develop robust prediction methods for PE risk, with emphasis on early detection in pregnancy, for ensuring optimal patient outcomes.
For both studies, we focus on a recently released NIH-NICHD dataset called nuMoM2b, which is a prospective cohort study of a racially/ethnically/geographically diverse population of10 ,038 nulliparous women with singleton gestation.
Ansaf Salleb-Aouissi (co-PI)
Anita Raja (co-PI)
Ronald Wapner (co-PI)
Itsik Pe’er (co-PI)
Raiyan R. Khan
 Preeclampsia Predictor with Machine Learning: A Comprehensive and Bias-Free Machine Learning Pipeline, Yun C. Lin, Daniel Mallia, Andrea O. Clark-Sevilla, Adam Catto, Alisa Leshchenko, David M. Haas, Ronald Wapner, Itsik Pe’er, Anita Raja, Ansaf Salleb-AouissimedRxiv 2022.06.08.22276107; doi: https://doi.org/10.1101/2022.06.08.22276107
 Genetic Polymorphisms Associated with Adverse Pregnancy Outcomes in Nulliparas. Rafael F.Guerrero, Raiyan R. Khan, Ronald J.Wapner, Matthew W. Hahn, Anita Raja, Ansaf Salleb-Aouissi, William A. Grobman, Hyagriv Simhan, Robert Silver, Judith H. Chung, Uma M. Reddy, Predrag Radivojac, Itsik Pe’er, David M. Haas. Under review AJOG. March 2022. https://www.medrxiv.org/content/10.1101/2022.02.28.22271641v1
 Data Preparation of the nuMoM2b Dataset. Anton Goretsky, Anastasia Dmitrienko, Irene Tang, Nicolae Lari, Owen Kunhardt, Raiyan Rashid Khan,Cassandra Marcussen, Adam Catto, Daniel Mallia, Alisa Leshchenko, Adam (Yun Chao) Lin, Anita Raja, Ansaf Salleb-Aouissi, Itsik Pe’err, Ronald Wapner, Cynthia Gyamfi-Bannerman August 2021.
 Using Privileged Information to Improve Prediction in Health Data: A Case Study.Jongoh Jeong, Do Hyung Kwon, Min Joon So, Anita Raja, Shivani Ghatge, Nicolae Lari, Ansaf Salleb-Aouissi NeurIPS 2019 Workshop on Information Theory and Machine Learning.  Using Kernel Methods and Model Selection for Prediction of Preterm Birth. Ilia Vovsha, Ansaf Salleb-Aouissi, Anita Raja, Thomas Koch, Alex Rybchuk, Axinia Radeva, Ashwath Rajan, Yiwen Huang, Hatim Diab, Ashish Tomar, Ronald Wapner ; Proceeding of Machine Learning Research; PMLR 56:55-72
 Press: S. Conova, Why Mothers Deliver Early - And How To Stop It. Columbia Medicine Magazine Volume 35 No. 2, 2016. http://www.columbiamedicinemagazine.org/features/fall-2015/why-mothers-deliver-early-–-and-how-stop-it
 Ilia Vovsha, Ashwath Rajan, Ansaf Salleb-Aouissi, Anita Raja , Axinia Radeva, Hatim Diab, Ashish Tomar and Ronald Wapner Predicting preterm birth is not elusive: machine learning paves the way to individual wellness. 2014 Association for the Advancement of Artificial Intelligence (AAAI) Spring Symposium Series.
Related Press Release
1- Our team was one of the winners of the National Institutes of Health Decoding Maternal Morbidity Data Challenge. https://www.nichd.nih.gov/newsroom/news/120721-data-challenge-winners
2 -Talk March 2022: Talk at the NIH NICHD Decoding Maternal Morbidity Data Challenge Winners’ Webinar. https://videocast.nih.gov/watch=45018
3- Press release: https://datascience.columbia.edu/news/2022/columbia-hunter-researchers-win-nih-maternal-morbidity-data-challenge/