Automated partial premature infant pain profile scoring using big data analytics

Lack of valid and reliable pain assessment in the neonatal population has become a significant challenge in the Neonatal Intensive Care Unit (NICU). In an attempt to forego the manual pain scoring system, this paper presents an initial framework to automate a partial pain score for newborn infants using big data analytics that automates the analysis of high speed physiological data. An ethically approved retrospective clinical research study was performed to calculate Artemis Premature Infant Pain Profile (APIPP) scores from premature infant data collected from the Artemis platform. Using the Premature Infant Pain Profile (PIPP) as the gold standard scale, scoring techniques were automated to create data abstractions from gestational age and the physiological streams of Heart Rate (HR) and Oxygen Saturation (SpO2). These were then brought together to compute an automated partial pain score. APIPP was retrospectively compared with the PIPP which was manually scored by nursing staff at The Hospital for Sick Children, Toronto. Differences within both the scales were evaluated and analysed by creating a data model. Future research will focus on the clinical validation of this work by implementing this work into a clinical decision support system (CDSS) named Artemis.