An efficient convolutional neural network for coronary heart disease prediction

作者：

Highlights：

• Predictor variables determined using LASSO based filtering with majority voting.

• Sub sampling methods implemented to account for high class imbalances.

• Classifier attains higher class-wise accuracies as compared to traditional models.

• Proposed architecture can be used as a transfer learning model for new data.

摘要

•Predictor variables determined using LASSO based filtering with majority voting.•Sub sampling methods implemented to account for high class imbalances.•Classifier attains higher class-wise accuracies as compared to traditional models.•Proposed architecture can be used as a transfer learning model for new data.

论文关键词：Coronary heart disease,Machine learning,LASSO regression,Convolutional neural network,Artificial Intelligence,NHANES

论文评审过程：Received 3 September 2019, Revised 17 March 2020, Accepted 24 March 2020, Available online 21 May 2020, Version of Record 17 June 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113408