Fetal heart rate research uses big data to reduce childbirth risks

March 6, 2018 by Alan Scher Zagier, Missouri University of Science and Technology
Dr. Steve Corns, right, and graduate student Vinayaka Nagendra Harikishan Gude Divya Sampath confer on their fetal heart rate research. Credit: Sam O’Keefe/Missouri S&T.

Giving birth to a child can be described as a sacred, spiritual and life-changing experience. It can also be fraught with pain, fear, complications and injury to both child and mother. For Dr. Steve Corns, associate professor of engineering management and systems engineering, the key to removing some of the uncertainty associated with giving birth may lie not with woman or man, but with machine—machine learning, to be precise.

Working in collaboration with researchers from Phelps County Regional Medical Center, Corns and graduate student Vinayaka Nagendra Harikishan Gude Divya Sampath are studying fetal heart rate patterns to develop a computational model to predict the risk of dangerous conditions such as fetal hypoxia and acidosis after a mother has entered labor.

The research is funded through the Ozark Biomedical Initiative, a partnership between PCRMC and Missouri S&T that provides seed money to support biomedical research. The research team, which includes Dr. James Davison, a retired physician in obstetrics and gynecology at PCRMC, is also seeking additional financial support from the National Institutes of Health.

"The goal is to look at the heart rate to try to predict what those conditions are (that cause oxygen deprivation during birth)," Corns says. "And then before we get to the situation where the baby is highly acidotic, go in and do an intervention."

In the U.S., about 700 women die each year as a result of pregnancy or delivery complications, according the Centers for Disease Control and Prevention. Complications affect more than 50,000 women annually, the CDC reports—with the risk of pregnancy-related death among black women three to four times higher than for expectant white mothers.

Despite advances in medical technology, those numbers have increased in recent decades, the CDC notes, from slightly more than 7 deaths per 100,000 live births three decades ago to a high of 17.8 deaths per 100,000 live births in both 2009 and 2011.

As Corns explains, doctors monitoring mothers in the early stages of labor typically rely on cardiotocography, also known as an electronic fetal monitor, to record fetal heartbeat and uterine contractions, usually reviewing the results every 10 to 20 minutes.

But rather than rely on case-by-case observation, the Corns-led research team wants to analyze tens of thousands of discrete data points that could more accurately predict patterns—and pitfalls ─ to arm physicians and nurses with more informed decision-making tools than the current three-tiered classification system for fetal .

"Instead of having those 10-minute windows with a marker, we'd have a computer keep track much further back, and keep track of patterns, and use pattern recognition to not just predict categories, which are a secondhand artifact, but predict what trajectory this baby is on," he says.

The early results are promising. In a research paper presented at the 2017 IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, Missouri S&T researchers found that support vector machines and random forest classifiers, two types of algorithms, demonstrated a 96 percent accuracy rate in predicting outcomes in the three classifications: normal, indeterminate and abnormal.

Experts advise that fetal heart rates falling into the indeterminate category should be closely monitored, with those in the abnormal category requiring further intervention.

Explore further: Is continuous electronic fetal monitoring useful for all women in labor?

More information: Vinayaka Nagendra et al. Evaluation of support vector machines and random forest classifiers in a real-time fetal monitoring system based on cardiotocography data, 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) (2017). DOI: 10.1109/CIBCB.2017.8058546

Related Stories

Is continuous electronic fetal monitoring useful for all women in labor?

December 5, 2017
Electronic fetal monitoring is often used during labour to detect unborn babies at risk of brain damage (neonatal encephalopathy) from a lack of oxygen (hypoxia). In the UK, continuous monitoring is used only for women in ...

New study finds fetal heart rate not a good indicator of a baby's health

October 26, 2011
Physicians preparing to deliver a baby look at fetal heart rate patterns to guide them in deciding whether or not to perform a C- section. But a new study by maternal-fetal medicine specialists at Intermountain Medical Center ...

Multidisciplinary team completes first-ever EXIT to ventricular pacing procedure

February 16, 2018
Researchers at Children's Hospital Colorado (Children's Colorado) have completed the first-ever EXIT (Ex Utero Intrapartum Treatment) to ventricular pacing procedure. The patient, a 36-week fetus, who suffered from complete ...

1 in 4 U.S. stillbirths might be prevented

January 19, 2018
(HealthDay)—About 1 in every 160 pregnancies in the United States ends in stillbirth. Now, a new study suggests many of these tragedies are "potentially" avoidable.

New method for monitoring fetal heartbeat

September 11, 2017
Researchers have developed a technique to accurately isolate fetal heart sounds from background noise in acoustic recordings, allowing them to distinguish between different segments of the fetal heartbeat. This technique ...

ACOG: interventions can be limited during labor, birth

January 30, 2017
(HealthDay)—Women can meet their labor and birth goals with minimal intervention, according to an American College of Obstetricians and Gynecologists Committee Opinion published in the February issue of Obstetrics & Gynecology.

Recommended for you

3-D bioPen: A hydrogel injection to regenerate cartilage

September 25, 2018
Highly specialized cartilage is characteristically avascular and non-neural in composition with low cell numbers in an aliphatic environment. Despite its apparent simplicity, bioengineering regenerative hyaline cartilage ...

Evidence that addictive behaviors have strong links with ancient retroviral infection

September 24, 2018
New research from an international team led by Oxford University's Department of Zoology and the National-Kapodistrian University of Athens, published today in Proceedings of the National Academy of Sciences (PNAS), shows ...

Taking a catnap? Mouse mutation shown to increase need for sleep

September 24, 2018
Sleep is vital for adequate functioning across the animal kingdom, but little is known about the physiological mechanisms that regulate it, or the reasons for natural variation in people's sleep patterns.

Know someone sick? Your own smell might give it away

September 24, 2018
Odors surround us, providing cues about many aspects of personal identity, including health status. Now, research from the Monell Center extends the scope and significance of personal odors as a source of information about ...

New findings on the muscle disease Laing early-onset distal myopathy

September 24, 2018
New avenues are now being opened toward treatment of Laing distal myopathy, a rare disorder that causes atrophy of the muscles in the feet, hands and elsewhere. In a study published in the journal PNAS, researchers have identified ...

Reconstructing healthy liver cells using a nanomaterial-based matrix 

September 24, 2018
NUS pharmaceutical scientists, together with clinicians from the National University Health System (NUHS), have developed a nanomaterial-based hydrogel that encourages amniotic epithelial cells (a type of stem cell) to grow ...


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.