Using AI and predictive analytics in a hybrid neural network called the Neonatal Artificial Intelligence Morality Score (NAIMS), scientists at Australia’s James Cook University (JCU) believe they have made a breakthrough when it comes to keeping premature babies alive.
With NAIMS, scientists use simple demographics and trends in heart and respiratory rate to determine mortality risk.
According to JCU engineering lecturer Stephanie Baker, who led this pilot study as part of her PhD work, complications from premature births are the leading cause of death in children under five, and over 50 percent of neonatal deaths occur in premature infants.
“Preterm birth rates are increasing almost everywhere. In neonatal intensive care units, assessment of mortality risk assists in making difficult decisions regarding which treatments should be used and if and when treatments are working effectively," said Baker in a press release.
In order to determine a plan of care, premature babies are often given a score by their doctors to project the risk they face, but according to Baker, “there are several limitations of this system. Generating the score requires complex manual measurements, extensive laboratory results, and the listing of maternal characteristics and existing conditions.”
While an alternative method could be to measure variables that do not change, such as birthweight, doctors are then unable to reassess the baby’s risk as time progresses not determine how the baby is responding to treatment.
“An ideal scheme would be one that uses fundamental demographics and routinely measured vital signs to provide continuous assessment. This would allow for assessment of changing risk without placing unreasonable additional burden on healthcare staff," Baker explained.
As for NAIMS, Baker said that “using data generated over a 12 hour period, NAIMS showed strong performance in predicting an infant's risk of mortality within 3, 7, or 14 days. This is the first work we're aware of that uses only easy-to-record demographics and respiratory rate and heart rate data to produce an accurate prediction of immediate mortality risk.”
Moreover, said Baker, the technique was fast and did not require invasive procedures or knowledge of medical history.
"Due to the simplicity and high performance of our proposed scheme, NAIMS could easily be continuously and automatically recalculated, enabling analysis of a baby's responsiveness to treatment and other health trends," she said.
The next step is to partner with local hospitals to gather more data and to continue testing.
"Additionally, we aim to conduct research into the prediction of other outcomes in neo-natal intensive care, such as the onset of sepsis and patient length of stay," Baker said.
Photo by SDI Productions/Getty Images