Journal
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
Volume 199, Issue -, Pages -Publisher
ELSEVIER IRELAND LTD
DOI: 10.1016/j.cmpb.2020.105874
Keywords
Artificial intelligence; Deep learning; Transfer learning; Neural networks; Diabetes; Personalized medicine
Categories
Funding
- IDI 2017 project - IDEX Paris-Saclay [ANR-11-IDEX-0003-02]
Ask authors/readers for more resources
The study introduces a multisource adversarial transfer learning framework to enhance knowledge transfer in healthcare by learning a more general feature representation that is similar across different sources of data. By analyzing learned feature representations and utilizing adversarial training, statistical and clinical accuracies can be further improved. Contrary to standard transfer methods, adversarial transfer does not discriminate patients and datasets, leading to a more general feature representation.
Background and objectives: Deep learning has yet to revolutionize general practices in healthcare, despite promising results for some specific tasks. This is partly due to data being in insufficient quantities hurting the training of the models. To address this issue, data from multiple health actors or patients could be combined by capitalizing on their heterogeneity through the use of transfer learning. Methods: To improve the quality of the transfer between multiple sources of data, we propose a multisource adversarial transfer learning framework that enables the learning of a feature representation that is similar across the sources, and thus more general and more easily transferable. We apply this idea to glucose forecasting for diabetic people using a fully convolutional neural network. The evaluation is done by exploring various transfer scenarios with three datasets characterized by their high inter and intra variability. Results: While transferring knowledge is beneficial in general, we show that the statistical and clinical accuracies can be further improved by using of the adversarial training methodology, surpassing the current state-of-the-art results. In particular, it shines when using data from different datasets, or when there is too little data in an intra-dataset situation. To understand the behavior of the models, we analyze the learnt feature representations and propose a new metric in this regard. Contrary to a standard transfer, the adversarial transfer does not discriminate the patients and datasets, helping the learning of a more general feature representation. Conclusion: The adversarial training framework improves the learning of a general feature representation in a multi-source environment, enhancing the knowledge transfer to an unseen target. The proposed method can help improve the efficiency of data shared by different health actors in the training of deep models. (C) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available