Cecilia Panigutti
ABSTRACT
Several recent advancements in Machine Learning involve blackbox models: algorithms that do not provide human-understandable explanations in support of their decisions. This limitation hampers the fairness, accountability and transparency of these models; the field of eXplainable Artificial Intelligence (XAI) tries to solve this problem providing human-understandable explanations for black-box models. However, healthcare datasets (and the related learning tasks) often present peculiar features, such as sequential data, multi-label predictions, and links to structured background knowledge. In this paper, we introduce Doctor XAI, a model-agnostic explainability technique able to deal with multi-labeled, sequential, ontology-linked data. We focus on explaining Doctor AI, a multilabel classifier which takes as input the clinical history of a patient in order to predict the next visit. Furthermore, we show how exploiting the temporal dimension in the data and the domain knowledge encoded in the medical ontology improves the quality of the mined explanations.
- Ahmad Fayez S Althobaiti. 2017. Comparison of Ontology-Based Semantic-Similarity Measures in the Biomedical Text. Journal of Computer and Communications 5, 02 (2017), 17.Google Scholar
Cross Ref
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).Google Scholar
- Tian Bai, Shanshan Zhang, Brian L Egleston, and Slobodan Vucetic. 2018. Interpretable representation learning for healthcare via capturing disease progression through time. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 43--51.Google ScholarDigital Library
- Donald J. Berndt and James Clifford. 1994. Using Dynamic Time Warping to Find Patterns in Time Series. In Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining (AAAIWS'94). AAAI Press, 359--370. http://dl.acm.org/citation.cfm?id=3000850.3000887Google ScholarDigital Library
- Olivier Bodenreider. 2004. The unified medical language system (UMLS): integrating biomedical terminology. Nucleic acids research 32, suppl_1 (2004).Google Scholar
- Gino Brunner, Yang Liu, Damián Pascual, Oliver Richter, and Roger Wattenhofer. 2019. On the Validity of Self-Attention as Explanation in Transformer Models. arXiv preprint arXiv:1908.04211 (2019).Google Scholar
- Rich Caruana, Yin Lou, Johannes Gehrke, Paul Koch, Marc Sturm, and Noemie Elhadad. 2015. Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 1721--1730.Google ScholarDigital Library
- Zhengping Che, David Kale, Wenzhe Li, Mohammad Taha Bahadori, and Yan Liu. 2015. Deep computational phenotyping. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM.Google ScholarDigital Library
- Edward Choi, Mohammad Taha Bahadori, Andy Schuetz, Walter F Stewart, and Jimeng Sun. 2016. Doctor ai: Predicting clinical events via recurrent neural networks. In Machine Learning for Healthcare Conference. 301--318.Google Scholar
- Edward Choi, Mohammad Taha Bahadori, Le Song, Walter F Stewart, and Jimeng Sun. 2017. GRAM: graph-based attention model for healthcare representation learning. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 787--795.Google ScholarDigital Library
- Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart. 2016. Retain: An interpretable predictive model for healthcare using reverse time attention mechanism. In Advances in Neural Information Processing Systems. 3504--3512.Google Scholar
- Edward Choi, Andy Schuetz, Walter F Stewart, and Jimeng Sun. 2016. Medical concept representation learning from electronic health records and its application on heart failure prediction. arXiv preprint arXiv:1602.03686 (2016).Google Scholar
- Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017).Google Scholar
- Wenjuan Fan, Jingnan Liu, Shuwan Zhu, and Panos M Pardalos. 2018. Investigating the impacting factors for the healthcare professionals to adopt artificial intelligence-based medical diagnosis support system (AIMDSS). Annals of Operations Research (2018), 1--26.Google Scholar
- Samuel G Finlayson, John D Bowers, Joichi Ito, Jonathan L Zittrain, Andrew L Beam, and Isaac S Kohane. 2019. Adversarial attacks on medical machine learning. Science 363, 6433 (2019), 1287--1289.Google Scholar
- Dominic Girardi, Sandra Wartner, Gerhard Halmerbauer, Margit Ehrenmüller, Hilda Kosorus, and Stephan Dreiseitl. 2016. Using concept hierarchies to improve calculation of patient similarity. Journal of biomedical informatics 63 (2016).Google Scholar
- Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Dino Pedreschi, Franco Turini, and Fosca Giannotti. 2018. Local Rule-Based Explanations of Black Box Decision Systems. arXiv preprint arXiv:1805.10820 (2018).Google Scholar
- Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Dino Pedreschi, and Fosca Giannotti. 2018. A Survey Of Methods For Explaining Black Box Models. ACM CSUR 51, 5, Article 93 (Aug. 2018), 42 pages.Google Scholar
- Riccardo Guidotti, Giulio Rossetti, Luca Pappalardo, Fosca Giannotti, and Dino Pedreschi. 2017. Market basket prediction using user-centric temporal annotated recurring sequences. In 2017 IEEE International Conference on Data Mining (ICDM). IEEE, 895--900.Google ScholarCross Ref
- M Hutson. 2018. AI researchers allege that machine learning is alchemy. Science 360, 6388 (2018), 861.Google Scholar
- Abhyuday N Jagannatha and Hong Yu. 2016. Bidirectional RNN for medical event detection in electronic health records. In Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting, Vol. 2016. NIH Public Access, 473.Google ScholarCross Ref
- Sarthak Jain and Byron C Wallace. 2019. Attention is not explanation. arXiv preprint arXiv:1902.10186 (2019).Google Scholar
- Zheng Jia, Xudong Lu, Huilong Duan, and Haomin Li. 2019. Using the distance between sets of hierarchical taxonomic clinical concepts to measure patient similarity. BMC Medical Informatics and Decision Making 19, 1 (2019), 91. Google ScholarCross Ref
- Alistair EW Johnson, Tom J Pollard, Lu Shen, H Lehman Li-wei, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific data 3 (2016), 160035.Google Scholar
- Thomas A Lasko, Joshua C Denny, and Mia A Levy. 2013. Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data. PloS one 8, 6 (2013), e66341.Google ScholarCross Ref
- Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature 521, 7553 (2015), 436.Google Scholar
- Janette Lehmann, Claudia Müller-Birn, David Laniado, Mounia Lalmas, and Andreas Kaltenbrunner. 2014. Reader preferences and behavior on Wikipedia. In Proceedings of the 25th ACM conference on Hypertext and social media. ACM.Google ScholarDigital Library
- Vladimir I Levenshtein. 1966. Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady, Vol. 10. 707--710.Google Scholar
- Znaonui Liang, Gang Zhang, Jimmy Xiangji Huang, and Qmming Vivian Hu. 2014. Deep learning for healthcare decision making with EMRs. In Bioinformatics and Biomedicine (BIBM), 2014 IEEE International Conference on. IEEE, 556--559.Google ScholarCross Ref
- Zachary C Lipton. 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016).Google Scholar
- Zachary C Lipton, David C Kale, Charles Elkan, and Randall Wetzel. 2015. Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677 (2015).Google Scholar
- Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems. 4765--4774.Google Scholar
- Fenglong Ma, Radha Chitta, Jing Zhou, Quanzeng You, Tong Sun, and Jing Gao. 2017. Dipole: Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, 1903--1911.Google ScholarDigital Library
- Gianclaudio Malgieri and Giovanni Comandè. 2017. Why a Right to Legibility of Automated Decision-Making Exists in the General Data Protection Regulation. International Data Privacy Law 7, 4 (2017). Google ScholarCross Ref
- Riccardo Miotto, Li Li, Brian A Kidd, and Joel T Dudley. 2016. Deep patient: An unsupervised representation to predict the future of patients from the electronic health records. Scientific reports 6 (2016).Google Scholar
- Cecilia Panigutti, Riccardo Guidotti, Anna Monreale, and Dino Pedreschi. 2019. Explaining multi-label black-box classifiers for health applications. In International Workshop on Health Intelligence. Springer, 97--110.Google Scholar
- Mihail Popescu and Mohammad Khalilia. 2011. Improving disease prediction using ICD-9 ontological features. In 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011). IEEE, 1805--1809.Google ScholarCross Ref
- Alvin Rajkomar et al. 2018. Scalable and accurate deep learning with electronic health records. npj Digital Medicine 1, 1 (2018), 18.Google Scholar
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, 1135--1144.Google ScholarDigital Library
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Anchors: High-precision model-agnostic explanations. In Thirty-Second AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- Sofia Serrano and Noah A Smith. 2019. Is Attention Interpretable? arXiv preprint arXiv:1906.03731 (2019).Google Scholar
- Benjamin Shickel, Patrick James Tighe, Azra Bihorac, and Parisa Rashidi. 2017. Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE journal of biomedical and health informatics 22, 5 (2017), 1589--1604.Google Scholar
- Barry Smith, Michael Ashburner, Cornelius Rosse, Jonathan Bard, William Bug, Werner Ceusters, Louis J Goldberg, Karen Eilbeck, Amelia Ireland, Christopher J Mungall, et al. 2007. The OBO Foundry: coordinated evolution of ontologies to support biomedical data integration. Nature biotechnology 25, 11 (2007), 1251.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.Google Scholar
- Scott Wisdom, Thomas Powers, James Pitton, and Les Atlas. 2016. Interpretable recurrent neural networks using sequential sparse recovery. arXiv preprint arXiv:1611.07252 (2016).Google Scholar
- Zhibiao Wu and Martha Palmer. 1994. Verbs semantics and lexical selection. In Proceedings of the 32nd annual meeting on Association for Computational Linguistics. Association for Computational Linguistics, 133--138.Google ScholarDigital Library
- Yanbo Xu, Siddharth Biswal, Shriprasad R Deshpande, Kevin O Maher, and Jimeng Sun. 2018. Raim: Recurrent attentive and intensive model of multimodal patient monitoring data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2565--2573.Google ScholarDigital Library
- Pranjul Yadav, Michael Steinbach, Vipin Kumar, and Gyorgy Simon. 2018. Mining electronic health records (EHRs): a survey. ACM Computing Surveys (CSUR) 50, 6 (2018), 85.Google ScholarDigital Library
- Kun-Hsing Yu, Andrew L Beam, and Isaac S Kohane. 2018. Artificial intelligence in healthcare. Nature biomedical engineering 2, 10 (2018), 719.Google Scholar
- Min-Ling Zhang and Zhi-Hua Zhou. 2014. A review on multi-label learning algorithms. IEEE transactions on knowledge and data engineering 26, 8 (2014).Google Scholar
Index Terms
- Doctor XAI: an ontology-based approach to black-box sequential data classification explanations
Recommendations
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI
Highlights- We review concepts related to the explainability of AI methods (XAI).
- We ...
AbstractIn the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in ...
Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence
AbstractArtificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to ...
Highlights- A novel four-axis framework to examine a model for robustness and explainability.
- Formulation of research questions at each axis and its corresponding taxonomy.
- Discussion of different explainability assessment methods.
- A novel ...
Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities
AbstractThe past decade has seen significant progress in artificial intelligence (AI), which has resulted in algorithms being adopted for resolving a variety of problems. However, this success has been met by increasing model complexity and ...
Comments