ABSTRACT
Radiotherapy treatment for cancer patients involves a complex workflow involving radiation physicists, therapists, dosimetrists, physicians and nurses. Multiple hand-offs between these care team members often lead to errors varying in severity levels. Such errors are logged in incident reports stored in the Radiation Oncology Incident Learning System. Here, we present an automated incident triage and severity determination pipeline that can predict high and low severity incidents. Incident reports are collected from the US Veterans Health Affairs (VHA) and Virginia Commonwealth University (VCU) radiation oncology centers. Natural language processing (NLP) and deep learning (DL) methods, like CNN and BiLSTM, are used to predict severity using the 'Incident Description' information. Other features like 'Incident Type', 'Action taken by reporter' and 'Incident discovered at' are used to infer the best performing model. Random oversampling and minority class oversampling are employed to address large class imbalance ratios in the data.
We observed that CNN performs best on both VHA data (0.83 F1-score) and the combined VCU+VHA data (0.83 F1-score) while CNN with minority sampling performs better on VCU data (0.60 F1-score) using the 'Incident Description' feature. Different feature combinations suggest that the two feature model using 'Incident Description' and 'Action taken by reporter' performs better with CNN on both the VHA (0.84 F1-score) and combined VCU+VHA data (0.81 F1-score). Multiple features were considered for the first time where the two feature model using CNNs emerge as the best suited for automating the radiotherapy incident triage and prioritization process.
- Michael B Barton, Michael Frommer, and Jesmin Shafiq. Role of radiotherapy in cancer control in low-income and middle-income countries. The lancet oncology, 7(7):584--595, 2006.Google Scholar
- Michael B Barton, Susannah Jacob, Jesmin Shafiq, Karen Wong, Stephen R Thompson, Timothy P Hanna, and Geoff P Delaney. Estimating the demand for radiotherapy from the evidence: a review of changes from 2003 to 2012. Radiotherapy and oncology, 112(1):140--144, 2014.Google ScholarCross Ref
- Scott Tyldesley, Geoff Delaney, Farshad Foroudi, Lisa Barbera, Marc Kerba, and William Mackillop. Estimating the need for radiotherapy for patients with prostate, breast, and lung cancers: verification of model estimates of need with radiotherapy utilization data from british columbia. International Journal of Radiation Oncology* Biology* Physics, 79(5):1507--1515, 2011.Google ScholarCross Ref
- Eric C Ford and Stephanie Terezakis. How safe is safe? risk in radiotherapy. International Journal of Radiation Oncology• Biology• Physics, 78(2):321--322, 2010.Google ScholarCross Ref
- Eric C Ford and Suzanne B Evans. Incident learning in radiation oncology: A review. Medical physics, 45, 2018.Google Scholar
- Khajamoinuddin Syed, William Sleeman, Michael Hagan, Jatinder Palta, Rishabh Kapoor, and Preetam Ghosh. Automatic incident triage in radiation oncology incident learning system. In Healthcare, volume 8, page 272. Multidisciplinary Digital Publishing Institute, 2020.Google Scholar
- Jeremy Howard and Sebastian Ruder. Fine-tuned language models for text classification. CoRR, abs/1801.06146, 2018.Google Scholar
- Jeremy Howard and Sebastian Ruder. Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146, 2018.Google Scholar
- Alexis Conneau, Holger Schwenk, Loïc Barrault, and Yann Lecun. Very deep convolutional networks for text classification. arXiv preprint arXiv:1606.01781, 2016.Google Scholar
- Teresa Gonçalves and Paulo Quaresma. The impact of nlp techniques in the multilabel text classification problem. In Intelligent Information Processing and Web Mining, pages 424--428. Springer, 2004.Google ScholarCross Ref
- Samuel Danso, Eric Atwell, and Owen Johnson. A comparative study of machine learning methods for verbal autopsy text classification. arXiv preprint arXiv:1402.4380, 2014.Google Scholar
- Andrés Felipe Torres Cano. Automatic aviation safety reports classification. Master's thesis, University of Twente, 2019.Google Scholar
- Saul D Robinson. Multi-label classification of contributing causal factors in self-reported safety narratives. Safety, 4(3):30, 2018.Google ScholarCross Ref
- Christophe Pimm, Céline Raynal, Nikola Tulechki, Eric Hermann, Grégory Caudy, and Ludovic Tanguy. Natural language processing (nlp) tools for the analysis of incident and accident reports. 2012.Google Scholar
- Tao Chen, Ruifeng Xu, Yulan He, and Xuan Wang. Improving sentiment analysis via sentence type classification using bilstm-crf and cnn. Expert Systems with Applications, 72:221--230, 2017.Google ScholarDigital Library
- Yoon Kim. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1746--1751, Doha, Qatar, October 2014. Association for Computational Linguistics.Google ScholarCross Ref
- Qimin Zhou and Hao Wu. Nlp at iest 2018: Bilstm-attention and lstm-attention via soft voting in emotion classification. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 189--194, 2018.Google ScholarCross Ref
- Yanming Huang, Y Jiang, Touhidul Hasan, Q Jiang, and Chao Li. A topic bilstm model for sentiment classification. In Proceedings of the 2nd International Conference on Innovation in Artificial Intelligence, pages 143--147, 2018.Google ScholarDigital Library
- Shin Ando and Chun Yuan Huang. Deep over-sampling framework for classifying imbalanced data. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 770--785. Springer, 2017.Google ScholarCross Ref
- Qingfeng Wang, Xuehai Zhou, Chao Wang, Zhiqin Liu, Jun Huang, Ying Zhou, Changlong Li, Hang Zhuang, and Jie-Zhi Cheng. Wgan-based synthetic minority over-sampling technique: Improving semantic fine-grained classification for lung nodules in ct images. IEEE Access, 7:18450--18463, 2019.Google ScholarCross Ref
- Ashutosh Adhikari, Achyudh Ram, Raphael Tang, and Jimmy Lin. Docbert: Bert for document classification. arXiv preprint arXiv:1904.08398, 2019.Google Scholar
- Matthew Tang, Priyanka Gandhi, Md Ahsanul Kabir, Christopher Zou, Jordyn Blakey, and Xiao Luo. Progress notes classification and keyword extraction using attention-based deep learning models with bert. arXiv preprint arXiv:1910.05786, 2019.Google Scholar
- EC Ford, L Fong de Los Santos, T Pawlicki, S Sutlief, and P Dunscombe. Consensus recommendations for incident learning database structures in radiation oncology. Medical physics, 39(12):7272--7290, 2012.Google ScholarCross Ref
- Brenda G Clark, Robert J Brown, Jodi L Ploquin, Anneke L Kind, and Laval Grimard. The management of radiation treatment error through incident learning. Radiotherapy and Oncology, 95(3):344--349, 2010.Google ScholarCross Ref
- Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.Google ScholarCross Ref
- Suyash Lakhotia and Xavier Bresson. An experimental comparison of text classification techniques. In 2018 International Conference on Cyberworlds (CW), pages 58--65. IEEE, 2018.Google ScholarCross Ref
- Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735--1780, 1997.Google ScholarDigital Library
- Mateusz Buda, Atsuto Maki, and Maciej A Mazurowski. A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106:249--259, 2018.Google ScholarDigital Library
- Krystyna Napierala and Jerzy Stefanowski. Types of minority class examples and their influence on learning classifiers from imbalanced data. Journal of Intelligent Information Systems, 46(3):563--597, 2016.Google ScholarDigital Library
Index Terms
- Deep neural network models to automate incident triage in the radiation oncology incident learning system
Recommendations
Continuous incident triage for large-scale online service systems
ASE '19: Proceedings of the 34th IEEE/ACM International Conference on Automated Software EngineeringIn recent years, online service systems have become increasingly popular. Incidents of these systems could cause significant economic loss and customer dissatisfaction. Incident triage, which is the process of assigning a new incident to the responsible ...
Efficient customer incident triage via linking with system incidents
ESEC/FSE 2020: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software EngineeringIn cloud service systems, customers will report the service issues they have encountered to cloud service providers. Despite many issues can be handled by the support team, sometimes the customer issues can not be easily solved, thus raising customer ...
Comments