Title |
Machine learning without a feature set for detecting bursts in the EEG of preterm infants
|
---|---|
Published in |
Conference proceedings Annual International Conference of the IEEE Engineering in Medicine and Biology Society, July 2019
|
DOI | 10.1109/embc.2019.8856533 |
Pubmed ID | |
Authors |
John M. O’ Toole, Geraldine B. Boylan |
Abstract |
Deep neural networks enable learning directly on the data without the domain knowledge needed to construct a feature set. This approach has been extremely successful in almost all machine learning applications. We propose a new framework that also learns directly from the data, without extracting a feature set. We apply this framework to detecting bursts in the EEG of premature infants. The EEG is recorded within days of birth in a cohort of infants without significant brain injury and born <; 30 weeks of gestation. The method first transforms the time-domain signal to the time-frequency domain and then trains a machine learning method, a gradient boosting machine, on each time-slice of the time-frequency distribution. We control for oversampling the time-frequency distribution with a significant reduction (<; 1%) in memory and computational complexity. The proposed method achieves similar accuracy to an existing multi-feature approach: area under the characteristic curve of 0.98 (with 95% confidence interval of 0.96 to 0.99), with a median sensitivity of 95% and median specificity of 94%. The proposed framework presents an accurate, simple, and computational efficient implementation as an alternative to both the deep learning approach and to the manual generation of a feature set. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 26 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 6 | 23% |
Student > Bachelor | 5 | 19% |
Student > Doctoral Student | 3 | 12% |
Student > Ph. D. Student | 3 | 12% |
Student > Postgraduate | 2 | 8% |
Other | 4 | 15% |
Unknown | 3 | 12% |
Readers by discipline | Count | As % |
---|---|---|
Medicine and Dentistry | 7 | 27% |
Engineering | 6 | 23% |
Psychology | 2 | 8% |
Computer Science | 2 | 8% |
Neuroscience | 2 | 8% |
Other | 1 | 4% |
Unknown | 6 | 23% |