Sensor analytics for interpretation of EKG signals

作者：

Highlights：

• Describes a predictive analytics example of interpretation of sensor data in healthcare.

• Created multi-label classification model to classify five heart conditions.

• Trained and tested models on more than 6800 hand annotated EKGs.

• The best model achieves a multi-label classification accuracy of 91%.

• Our model could help alert the users about their cardiac states through smartphones.

摘要

•Describes a predictive analytics example of interpretation of sensor data in healthcare.•Created multi-label classification model to classify five heart conditions.•Trained and tested models on more than 6800 hand annotated EKGs.•The best model achieves a multi-label classification accuracy of 91%.•Our model could help alert the users about their cardiac states through smartphones.

论文关键词：Multi-label classification,Machine learning,EKG sensor,Smartphone app,Predictive analytics

论文评审过程：Received 18 February 2018, Revised 30 November 2018, Accepted 29 December 2018, Available online 12 January 2019, Version of Record 25 January 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.12.056