Reducing False Alarm Rates in Neonatal Intensive Care: A New Machine Learning Approach.

UNLABELLED

In neonatal intensive care units (NICUs), 87.5% of alarms by the monitoring system are false alarms, often caused by the movements of the neonates. Such false alarms are not only stressful for the neonates as well as for their parents and caregivers, but may also lead to longer response times in real critical situations. The aim of this project was to reduce the rates of false alarms by employing machine learning algorithms (MLA), which intelligently analyze data stemming from standard physiological monitoring in combination with cerebral oximetry data (in-house built, OxyPrem).

MATERIALS & METHODS: Four popular MLAs were selected to categorize the alarms as false or real: (i) decision tree (DT), (ii) 5-nearest neighbors (5-NN), (iii) naïve Bayes (NB) and (iv) support vector machine (SVM). We acquired and processed monitoring data (median duration (SD): 54.6 (± 6.9) min) of 14 preterm infants (gestational age: 26 6/7 (± 2 5/7) weeks). A hybrid method of filter and wrapper feature selection generated the candidate subset for training these four MLAs.

RESULTS

A high specificity of >99% was achieved by all four approaches. DT showed the highest sensitivity (87%). The cerebral oximetry data improved the classification accuracy.

DISCUSSION & CONCLUSION: Despite a (as yet) low amount of data for training, the four MLAs achieved an excellent specificity and a promising sensitivity. Presently, the current sensitivity is insufficient since, in the NICU, it is crucial that no real alarms are missed. This will most likely be improved by including more subjects and data in the training of the MLAs, which makes pursuing this approach worthwhile.