Abstract
We developed a deep learning approach for accurate prediction of PCA patients one year earlier with minimal features from electronic health records. The area under the receiver operating curve for prediction of PCA was 0.94. Moreover, the sensitivity and specificity of CNN were 0.87 and 0.88, respectively.
Original language | English |
---|---|
Pages (from-to) | 1241-1242 |
Number of pages | 2 |
Journal | Studies in Health Technology and Informatics |
Volume | 270 |
DOIs | |
Publication status | Published - Jun 16 2020 |
Keywords
- Convolutional neural network
- Deep learning
- Electronic health record
- Prostate cancer
ASJC Scopus subject areas
- Biomedical Engineering
- Health Informatics
- Health Information Management