Selective Information Extraction Strategies for Cancer Pathology Reports with Convolutional Neural Networks
To trust model predictions, it is important to ensure new data scored by the model comes from the same population used for model training. If the model is used to score new data different than the model’s training data, then predictions and model performance metrics cannot be trusted. Identifying and excluding these anomalous data points is an important task when using models in the real world. Traditional machine learning algorithms and classifiers don’t have the capability to abstain in this case. Here we propose a data-novelty detection algorithm for the Convolutional Neural Network classifier, yielding a rejection score for each new data point scored. It is a post-modeling procedure which examines the distribution of convolution filters to determine if the prediction should be trusted. We apply this algorithm to an information extraction model for a natural language text corpus. We evaluated the algorithm performance using a primary cancer site classification model applied to cancer pathology reports. Results demonstrate that the algorithm is an effective way to exclude cancer pathology reports from model scoring when they do not contain the expected information necessary to accurately classify the primary cancer type.
KeywordsNovelty detection Uncertainty determination Cancer pathology reports Information extraction Natural language processing Convolutional neural networks
This work has been supported in part by the Joint Design of Advanced Computing Solutions for Cancer (JDACS4C) program established by the U.S. Department of Energy (DOE) and the National Cancer Institute (NCI) of the National Institutes of Health. This work was performed under the auspices of the U.S. Department of Energy by Argonne National Laboratory under Contract DE-AC02-06-CH11357, Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344, Los Alamos National Laboratory under Contract DE-AC5206NA25396, and Oak Ridge National Laboratory under Contract DE-AC05-00OR22725.
The authors wish to thank Valentina Petkov of the Surveillance Research Program from the National Cancer Institute and the SEER registry at Connecticut, Hawaii, Kentucky, New Mexico and Seattle for the pathology reports used in this investigation.
This research used resources of the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S., Department of Energy under Contract No. DE-AC05-00OR22725.
- 1.Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al.: Tensorflow: a system for large-scale machine learning. OSDI 16, 265–283 (2016)Google Scholar
- 2.Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)
- 3.Chollet, F., et al.: Keras (2015). https://github.com/fchollet/keras
- 7.Goroshin, R., Mathieu, M.F., LeCun, Y.: Learning to linearize under uncertainty. In: Advances in Neural Information Processing Systems, pp. 1234–1242 (2015)Google Scholar
- 8.Kavuluru, R., Hands, I., Durbin, E.B., Witt, L.: Automatic extraction of ICD-O-3 primary sites from cancer pathology reports. In: AMIA Summits on Translational Science Proceedings 2013, p. 112 (2013)Google Scholar
- 9.Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
- 10.Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
- 14.Nguyen, A., Moore, J., Lawley, M., Hansen, D., Colquist, S.: Automatic extraction of cancer characteristics from free-text pathology reports for cancer notifications. Stud. Health Technol. Inform. 168, 117–124 (2011)Google Scholar
- 15.Papadopoulos, H.: Inductive conformal prediction: theory and application to neural networks. In: Tools in Artificial Intelligence. InTech (2008)Google Scholar
- 18.Smith, R.C.: Uncertainty Quantification: Theory, Implementation, and Applications, vol. 12. SIAM, Philadelphia (2013)Google Scholar
- 19.American Cancer Society: Cancer facts & figures. The Society (2018)Google Scholar
- 20.Yoon, H.J., Robinson, S., Christian, J.B., Qiu, J.X., Tourassi, G.D.: Filter pruning of convolutional neural networks for text classification: a case study of cancer pathology report comprehension. In: 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), pp. 345–348. IEEE (2018)Google Scholar