Assessing and Comparing Interpretability Techniques for Artificial Neural Networks Breast Cancer Classification

ABSTRACT Breast cancer is the most common type of cancer among women. Thankfully, early detection and treatment improvements helped decrease the number of deaths. Data Mining techniques have always assisted BC tasks whether it is screening, diagnosis, prognosis, treatment, monitoring, and/or management. Nowadays, the use of Data Mining is witnessing a new era. In fact, the main objective is no longer to replace humans but to enhance their capabilities, which is why Artificial Intelligence is now referred to as Intelligence Augmentation. In this context, interpretability is used to help domain experts learn new patterns and machine learning experts debug their models. This paper aims to investigate three black-boxes interpretation techniques: Feature Importance, Partial Dependence Plot, and LIME when applied to two types of feed-forward Artificial Neural Networks: Multilayer perceptrons, and Radial Basis Function Network, trained on the Wisconsin Original dataset for breast cancer diagnosis. Results showed that local LIME explanations were instance-level interpretations that came in line with the global interpretations of the other two techniques. Global/local interpretability techniques can thus be combined to define the trustworthiness of a black-box model.

[1]  H. M. Baskonus,et al.  Advances in Intelligent Systems and Computing , 2022, Smart Innovation, Systems and Technologies.

[2]  David Ben-Israel,et al.  The impact of machine learning on patient care: A systematic review , 2020, Artif. Intell. Medicine.

[3]  Applications of Artificial Intelligence Techniques in the Petroleum Industry , 2020 .

[4]  Ali Idri,et al.  Reviewing ensemble classification methods in breast cancer , 2019, Comput. Methods Programs Biomed..

[5]  Sherif Sakr,et al.  On the interpretability of machine learning-based model for predicting hypertension , 2019, BMC Medical Informatics and Decision Making.

[6]  Sherin M. Mathews.  Explainable Artificial Intelligence Applications in NLP, Biomedical, and Malware Classification: A Literature Review , 2019, Advances in Intelligent Systems and Computing.

[7]  Alexander Meyer,et al.  External Validation of a "Black-Box" Clinical Predictive Model in Nephrology: Can Interpretability Methods Help Illuminate Performance Differences? , 2019, AIME.

[8]  Mirko Polato,et al.  Boolean kernels for rule based interpretation of support vector machines , 2019, Neurocomputing.

[9]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[10]  Michael Riegler,et al.  Comprehensible reasoning and automated reporting of medical examinations based on deep learning analysis , 2018, MMSys.

[11]  Bin Huang,et al.  Opening the black box of neural networks: methods for interpreting neural network models in clinical applications. , 2018, Annals of translational medicine.

[12]  Sherif Sakr,et al.  Using machine learning on cardiorespiratory fitness data for predicting hypertension: The Henry Ford ExercIse Testing (FIT) Project , 2018, PloS one.

[13]  Victor Alves,et al.  Enhancing interpretability of automatically extracted machine learning features: application to a RBM‐Random Forest system on brain lesion segmentation , 2018, Medical Image Anal..

[14]  Ali Idri,et al.  A systematic map of data analytics in breast cancer , 2018, ACSW.

[15]  Cynthia Rudin,et al.  Model Class Reliance: Variable Importance Measures for any Machine Learning Model Class, from the "Rashomon" Perspective , 2018 .

[16]  Agata Ferretti,et al.  Machine Learning in Medicine , 2018 .

[17]  Christian Biemann,et al.  What do we need to build explainable AI systems for the medical domain? , 2017, ArXiv.

[18]  Chris Russell,et al.  Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR , 2017, ArXiv.

[19]  Piyush Gupta,et al.  MAGIX: Model Agnostic Globally Interpretable Explanations , 2017, ArXiv.

[20]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[21]  An introduction to neural networks for beginners , 2017 .

[22]  Robert Chen,et al.  Machine Learning Model Interpretability for Precision Medicine , 2016, 1610.09045.

[23]  Kamna Solanki,et al.  Analysis of Application of Data Mining Techniques in Healthcare , 2016 .

[24]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[25]  Oluwasanmi Koyejo,et al.  Examples are not enough, learn to criticize! Criticism for Interpretability , 2016, NIPS.

[26]  T. Trikalinos,et al.  Core Needle and Open Surgical Biopsy for Diagnosis of Breast Lesions , 2014 .

[27]  Barbara Hammer,et al.  Neural Smithing – Supervised Learning in Feedforward Artificial Neural Networks , 2001, Pattern Analysis & Applications.

[28]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[29]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[30]  Bor-Wen Cheng,et al.  Diagnosing Breast Masses in Digital Mammography Using Feature Selection and Ensemble Methods , 2012, Journal of Medical Systems.

[31]  Erik Strumbelj,et al.  Explanation and reliability of prediction models: the case of breast cancer recurrence , 2010, Knowledge and Information Systems.

[32]  Bogdan E. Popescu,et al.  PREDICTIVE LEARNING VIA RULE ENSEMBLES , 2008, 0811.1679.

[33]  A. Abran,et al.  Functional Equivalence between Radial Basis Function Neural Networks and Fuzzy Analogy in Software Cost Estimation , 2008, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications.

[34]  Julia Hirschberg,et al.  V-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure , 2007, EMNLP.

[35]  A. Asuncion,et al.  UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences , 2007 .

[36]  Paulo J. G. Lisboa,et al.  Orthogonal search-based rule extraction (OSRE) for trained neural networks: a practical and efficient approach , 2006, IEEE Transactions on Neural Networks.

[37]  Mathias Risse,et al.  Why the count de Borda cannot beat the Marquis de Condorcet , 2005, Soc. Choice Welf..

[38]  Mary K Obenshain.  Application of Data Mining Techniques to Healthcare Data , 2004, Infection Control & Hospital Epidemiology.

[39]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[40]  Taghi M. Khoshgoftaar,et al.  Can neural networks be easily interpreted in software cost estimation? , 2002, 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291).

[41]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[42]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[43]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[44]  Sung Yang Bang,et al.  An Efficient Method to Construct a Radial Basis Function Neural Network Classifier , 1997, Neural Networks.

[45]  Ignacio Requena,et al.  Are artificial neural networks black boxes? , 1997, IEEE Trans. Neural Networks.

[46]  Rudy Setiono,et al.  Extracting rules from pruned networks for breast cancer diagnosis , 1996, Artif. Intell. Medicine.

[47]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[48]  O. Mangasarian,et al.  Multisurface method of pattern separation for medical diagnosis applied to breast cytology. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[49]  Samuel B. Williams,et al.  ASSOCIATION FOR COMPUTING MACHINERY , 2000 .

[50]  N. Metropolis,et al.  The Monte Carlo method. , 1949, Journal of the American Statistical Association.