AI, Predictive Analytics Pave Way for Premature Baby Care

Through a Neonatal Artificial Intelligence Morality Score (NAIMS), scientists at James Cook University believe they may have discovered a breakthrough method in keeping premature babies alive. With NAIMS, scientists use AI and predictive analytics that could accurately assess the level of risk individual premature babies face.

JCU engineering lecturer Stephanie Baker led this pilot study as part of her PhD work. According to Baker, complications from premature births are the leading cause of death in children under five. Additionally, 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 indicate and predict the risk they face.

"But 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," Baker said.

The alternative method was to measure variables that do not change, such as birthweight. However, this prevents recalculation of the baby’s risk as time progresses and does not show 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.

The Neonatal Artificial Intelligence Morality Score (NAIMS) is a hybrid neural network that relies on demographics and trends in heart and respiratory rates in order to determine an infant’s mortality risk.

"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,” Baker continued. “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.”

Additionally, Baker explained that 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," said Baker.

The Neonatal Artificial Intelligence Morality Score (NAIMS) was accurate when tested against hospital mortality records of premature infants. Additionally, it was more effective over existing methods; being able to perform risk assessments based on any 12-hour period during the patient’s stay.

Baker 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.