A Comparative Study of Two Rule-Based Explanation Methods for Diabetic Retinopathy Risk Assessment
Source abstract
Abstract
Understanding the reasons behind the decisions of complex intelligent systems is crucial in many domains, especially in healthcare. Local explanation models analyse a decision on a single instance, by using the responses of the system to the points in its neighbourhood to build a surrogate model. This work makes a comparative analysis of the local explanations provided by two rule-based explanation methods on RETIPROGRAM, a system based on a fuzzy random forest that analyses the health record of a diabetic person to assess his/her degree of risk of developing diabetic retinopathy. The analysed explanation methods are C-LORE-F (a variant of LORE that builds a decision tree) and DRSA (a method based on rough sets that builds a set of rules). The explored methods gave good results in several metrics, although there is room for improvement in the generation of counterfactual examples.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Rough Sets and Fuzzy Logic · Data Mining Algorithms and Applications · Imbalanced Data Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
ITAKA Research Group, Department of Computer Science and Mathematics, Universitat Rovira i Virgili, 43007 Tarragona, Spain
Institute of Computing Science, Poznań University of Technology, 60-965 Poznań, Poland
References (35)
Show source-provided references
1. Aguiree, F., Brown, A., Cho, N.H., Dahlquist, G., Dodd, S., Dunning, T., Hirst, M., Hwang, C., Magliano, D., and Patterson, C. (2013). IDF Diabetes Atlas, International Diabetes Federation.
2. Global estimates of the prevalence of diabetes for 2010 and 203010.1016/j.diabres.2009.10.007 ↗
3. Nair, A.T., Muthuvel, K., and Haritha, K. (2022). Effectual Evaluation on Diabetic Retinopathy. Information and Communication Technology for Competitive Strategies (ICTCS 2020), Springer.10.1007/978-981-16-0739-4_53 ↗
4. Prevalence of diabetic retinopathy and its relationship with glomerular filtration rate and other risk factors in patients with type 2 diabetes mellitus in Spain. DM2 HOPE study
5. A clinical decision support system for diabetic retinopathy screening: Creating a clinical support application10.1089/tmj.2017.0282 ↗
6. Saleh, E., Valls, A., Moreno, A., Romero-Aroca, P., Torra, V., and Bustince, H. (2018). Learning fuzzy measures for aggregation in fuzzy rule-based models. International Conference on Modeling Decisions for Artificial Intelligence, Springer.10.1007/978-3-030-00202-2_10 ↗
7. Validation of a diagnostic support system for diabetic retinopathy based on clinical parameters10.1167/tvst.10.3.17 ↗
8. A Survey on the Explainability of Supervised Machine Learning10.1613/jair.1.12228 ↗
9. An efficient explanation of individual classifications using game theory
10. Krause, J., Perer, A., and Ng, K. (2016, January 7–12). Interacting with predictions: Visual inspection of black-box machine learning models. Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, San Jose, CA, USA.10.1145/2858036.2858529 ↗
11. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13–17). Why Should I Trust You?: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939778 ↗
12. Maaroof, N., Moreno, A., Valls, A., and Jabreel, M. (2020). Guided-LORE: Improving LORE with a Focused Search of Neighbours. International Workshop on the Foundations of Trustworthy AI Integrating Learning, Optimization and Reasoning, Springer.10.1007/978-3-030-73959-1_4 ↗
13. Maaroof, N., Moreno, A., Jabreel, M., and Valls, A. (2021). Contextualized LORE for Fuzzy Attributes. Artificial Intelligence Research and Development, IOS Press.10.3233/FAIA210164 ↗
14. A Fuzzy Random Forest Approach for the Detection of Diabetic Retinopathy on Electronic Health Record Data
15. Rough sets theory for multicriteria decision analysis10.1016/S0377-2217(00)00167-3 ↗
16. A survey of methods for explaining black box models10.1145/3236009 ↗
17. Molnar, C. (2020). Interpretable Machine Learning, Lulu.com.
18. Anchors: High-Precision Model-Agnostic Explanations
19. A unified approach to interpreting model predictions
20. Explaining data-driven document classifications10.25300/MISQ/2014/38.1.04 ↗
21. Guidotti, R., Monreale, A., Ruggieri, S., Pedreschi, D., Turini, F., and Giannotti, F. (2018). Local rule-based explanations of black box decision systems. arXiv.
22. Mothilal, R.K., Sharma, A., and Tan, C. (2020, January 27–30). Explaining machine learning classifiers through diverse counterfactual explanations. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, Barcelona, Spain.10.1145/3351095.3372850 ↗
23. Russell, C. (2019, January 19–31). Efficient search for diverse coherent explanations. Proceedings of the Conference on Fairness, Accountability, and Transparency, Atlanta, GA, USA.10.1145/3287560.3287569 ↗
24. Rulematrix: Visualizing and understanding classifiers with rules10.1109/TVCG.2018.2864812 ↗
25. Explainable Matrix—Visualization for Global and Local Interpretability of Random Forest Classification Ensembles10.1109/TVCG.2020.3030354 ↗
26. Improved heterogeneous distance functions10.1613/jair.346 ↗
27. Ruggieri, S. (2004, January 15–17). YaDT: Yet another Decision Tree Builder. Proceedings of the 16th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2004), Boca Raton, FL, USA.
28. Pawlak, Z. (1991). Rough Sets: Theoretical Aspects of Reasoning about Data, Springer Science & Business Media.10.1007/978-94-011-3534-4 ↗
29. Słowiński, R., Greco, S., and Matarazzo, B. (2015). Rough set methodology for decision aiding. Springer Handbook of Computational Intelligence, Springer.10.1007/978-3-662-43505-2_22 ↗
30. Sequential covering rule induction algorithm for variable consistency rough set approaches10.1016/j.ins.2010.10.030 ↗
31. Induction of Ordinal Classification Rules from Incomplete Data10.1007/978-3-642-32115-3_6 ↗
32. Saleh, E., Maaroof, N., and Jabreel, M. (2020). The deployment of a decision support system for the diagnosis of Diabetic Retinopathy into a Catalan medical center. Proceedings of the 6th URV Doctoral Workshop in Computer Science and Mathematics, Universitat Rovira i Virgili.
33. A Clinical Decision Support System (CDSS) for diabetic retinopathy screening. Creating a clinical support application
34. Russell, S., and Norvig, P. (2020). Artificial Intelligence: A Modern Approach, Pearson. [4th ed.].
35. Sani, H.M., Lei, C., and Neagu, D. (2018). Computational complexity analysis of decision tree algorithms. International Conference on Innovative Techniques and Applications of Artificial Intelligence, Springer.10.1007/978-3-030-04191-5_17 ↗