JMIR Publications

ABSTRACT

Background:

Although an increasing number of bedside medical devices have wireless connections, providing feasible and reliable notification, many devices without any connections perform very well in detecting abnormal status and alerting medical staff with various sounds. Staff members, however, can miss these notifications, especially when in distant areas or other private rooms. In contrast, the signal-to-noise ratio (SNR) of alarm systems for medical devices in the neonatal intensive care unit is 0 dB or more. A feasible system for automatic sound identification with high accuracy is needed to prevent alarm sounds from being missed by the staff.

Objective:

The purpose of this study was to design a method for classifying multiple alarm sounds collected with a monaural microphone in a noisy environment.

Methods:

Features of seven alarm sounds were extracted with a Mel filter bank and incorporated into a classifier using convolutional and recurrent neural networks. To estimate its clinical usefulness, the classifier was evaluated with mixtures of up to seven alarm sounds and hospital ward noise.

Results:

At an SNR of 0 dB, the recall performance of the classifier was 0.976 with an F score of 0.945. When foot pump was excluded, the class-wise recall the classifier ranged from 0.990 to 1.000.

Conclusions:

The proposed classifier was found to be highly accurate in detecting alarm sounds. Although the performance of the proposed classifier in a clinical environment can be improved, the classifier could be incorporated into an alarm sound detection system. The classifier, combined with network connectivity, could improve the notification of abnormal status detected by unconnected medical devices.