Machine-Learning Algorithm Helps Monitor Movement Patterns in Infants
A recent analysis effort described a machine-learning algorithm that could help clinicians track infants' movement patterns, furthering their understanding of neonatal care delivery.
Source: Getty Images
By - After receiving a grant from the National Science Foundation, a group of researchers from Dell Children’s Medical Center of Central Texas created a machine-learning (ML) algorithm to track the movement patterns of babies in the neonatal intensive care unit (NICU).
Soon after birth, monitoring infants' movement patterns is critical as they can be indicative of medical risks. This is particularly important for those infants born before 37 weeks of gestation. Certain patterns can predict when these infants will experience common events such as apnea or bradycardia, which may indicate long-term neurological health.
The artificial intelligence-supported effort by Dell Children’s Medical Center of Central Texas aimed to monitor babies' movement patterns within the NICU.
“We’re trying to make the case that movement is a vital sign, just like blood pressure, pulse, respiration or temperature,” said David Paydarfar, MD, chair of Dell Med’s Department of Neurology, in a press release. “We know that preterm infants are at risk of many neurological complications later in life, like cerebral palsy, autism spectrum disorder or learning disabilities, and tracking on some of these early events can help us better understand the relationship to those later outcomes more clearly.”
The Dell Med researchers conducted a study to assess the efficacy of an ML algorithm in tracking infants' movement patterns. The research consisted of a review of previously collected data from 100 babies within the NICU. With this data, researchers developed an algorithm to track movement patterns through blood-oxygen saturation levels.
They noted that traditional methods to monitor movement patterns, such as video monitors and accelerometers, often fail or disrupt basic care, but since the collection of blood-oxygen saturation levels is routine, this data can be used instead.
Using the ML algorithm to monitor movement can assist clinicians in predicting adverse events, the researchers noted.
“If I get up and I start running, I breathe more," Paydarfar said. “Well, in preterm infants who have very immature movement patterns, they are more likely to do the opposite. They stop breathing — their heart rate goes down. So we see a direct, paradoxical effect in these bursts of movement, and we can actually use movement to predict when the next apnea is going to be.”
The press release also states that the algorithm could aid the process of creating additional tools and resources, like a smart mattress that vibrates to indicate apnea among infants.
In addition to signaling adverse events, tracking movement patterns using ML could help clinicians determine which infants can go home.
“The holy grail of this would be a clear indicator that something bad is about to happen with a baby, which we could then respond to before it happens,” said John Loyd, MD, associate professor in Dell Med’s Department of Pediatrics and chief of the Division of Neonatology at Dell Children’s Medical Center, in a press release. “But the second thing is also to be able to more clearly identify those who are safe for discharge. With movement, we may be able to more clearly identify infants that are developmentally ready for discharge."
Remote monitoring of patient vital signs is becoming increasingly popular in healthcare.
In February 2022, Community Health Systems (CHS) and Cadence announced they were working in collaboration to improve chronic condition management through remote patient monitoring.
Initially supporting patients with hypertension, heart failure, diabetes, and chronic obstructive pulmonary disease, the partnership aims to expand CHS’ remote care platform to support an increasing number of conditions.
