July 5, 2019

WSU/PRB researchers lead preterm birth prediction challenge

Researchers of the Wayne State University Perinatal Initiative and the National Institutes of Health’s Perinatology Research Branch at the Wayne State University School of Medicine are leading a revolutionary challenge to develop prediction models for gestational age and preterm birth.

Adi Tarca, Ph.D., associate professor of Obstetrics and Gynecology, and adjunct associate professor of Computer Science at Wayne State University, and Roberto Romero, M.D., D.Med.Sci., chief of the Perinatology Research Branch, program director for Perinatal Research and Obstetrics, Intramural Division of the Eunice Kennedy Shriver National Institute of Child Health and Human Development, and professor of Molecular Obstetrics and Genetics at WSU’s Center of Molecular Medicine and Genetics, are leading to the effort to organize and launch the DREAM Preterm Birth Prediction Challenge with partners from IBM Research, the University of California, San Francisco, the University of Colorado and Stanford University.

“The goal of this challenge is to bring the obstetrics and machine-learning community together to determine the value of maternal whole blood transcriptomics data for gestational dating and determining the risk of preterm birth,” Dr. Tarca said. “We hope that optimal big-data analytics approaches will emerge so that they can be applied to similar research questions in other fields of science. For the obstetrics community, the primary result will be a set of biomarkers that can be pursued in further targeted studies to develop convenient and affordable tests for pregnancy dating, and to identify patients at risk of preterm birth so that they can benefit from closer surveillance and possibly treatment.”

The crowdsourcing initiative invites researchers around the world to use maternal blood transcriptomics data generated at the PRB and WSU to develop prediction models for gestational age and preterm birth. Developing an accurate molecular clock of pregnancy and identifying women at risk of preterm birth could have implications in clinical care.

Since its launch May 4 at the RECOMB 2019 Conference at George Washington University, the DREAM Preterm Birth Prediction Challenge has attracted more than 150 participants, including researchers from top U.S. and international universities. The organizers are optimistic about the results that will be jointly published by organizers and participants.

Drs. Romero and Tarca developed the challenge after receiving top awards in multiple international systems biology challenges, including the IMPROVER Diagnostic Signature Challenge, the Species Translational Challenge and the Systems Toxicology Challenge.

A basic need in pregnancy care is to establish gestational age because inaccurate estimates may lead to unnecessary interventions and sub-optimal patient management. Current approaches to establish gestational age rely on the patient’s recollection of her last menstrual period and/or ultrasound. Ultrasounds can be costly and less accurate if not performed during the first trimester. Development of an inexpensive and accurate molecular clock of pregnancy would benefit patients and health care systems providing treatment.

Participants in the first sub-challenge – the prediction of gestational age -- will be given whole blood gene expression data collected from pregnant women to develop prediction models for the gestational age at blood draw.

Another challenge in obstetrics is the identification and treatment of women at risk of developing the “great obstetrical syndromes.” Of these, preterm birth, defined as giving birth before the completion of 37 weeks of gestation, is the leading cause of newborn deaths and long-term complications, including motor, cognitive and behavioral impairment.

Participants in the second sub-challenge -- prediction of preterm birth -- will be given whole blood gene expression data collected from pregnant women to develop prediction models to determine the risk of preterm birth.

Click here for more details.