\n
![](\"https:\/\/media.springernature.com\/full\/springer-static\/image\/art%3A10.1038%2Fs42256-019-0138-9\/MediaObjects\/42256_2019_138_Fig1_HTML.png\")
<\/p>\n [ad_1]
\n<\/p>\n
The state of data science & maching learning. Kaggle<\/i> https:\/\/www.kaggle.com\/surveys\/2017<\/a> (2017).<\/p>\n<\/li>\n Friedman, J., Hastie, T. & Tibshirani, R. The Elements of Statistical Learning<\/i> Vol. 1 (Springer Series in Statistics, Springer, 2001).<\/p>\n<\/li>\n Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst.<\/i> 30<\/b>, 4768\u20134777 (2017).<\/p>\n<\/li>\n Saabas, A. treeinterpreter python package. GitHub<\/i> https:\/\/github.com\/andosa\/treeinterpreter<\/a> (2019).<\/p>\n<\/li>\n Ribeiro, M. T., Singh, S. & Guestrin, C. Why should i trust you?: Explaining the predictions of any classifier. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining<\/i> 1135\u20131144 (ACM, 2016).<\/p>\n<\/li>\n Datta, A., Sen, S. & Zick, Y. Algorithmic transparency via quantitative input influence: theory and experiments with learning systems. In Proc. 2016 IEEE Symposium on Security and Privacy (SP)<\/i>, 598\u2013617 (IEEE, 2016).<\/p>\n<\/li>\n \u0160trumbelj, E. & Kononenko, I. Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst.<\/i> 41<\/b>, 647\u2013665 (2014).<\/p>\n<\/li>\n Baehrens, D. et al. How to explain individual classification decisions. J. Mach. Learn. Res.<\/i> 11<\/b>, 1803\u20131831 (2010).<\/p>\n<\/li>\n Shapley, L. S. A value for n<\/i>-person games. Contrib. Theor. Games<\/i> 2<\/b>, 307\u2013317 (1953).<\/p>\n<\/li>\n Sundararajan, M. & Najmi, A. The many Shapley values for model explanation. Preprint at https:\/\/arxiv.org\/abs\/1908.08474<\/a> (2019).<\/p>\n<\/li>\n Janzing, D., Minorics, L. & Bl\u00f6baum, P. Feature relevance quantification in explainable AI: a causality problem. Preprint at https:\/\/arxiv.org\/abs\/1910.13413<\/a> (2019).<\/p>\n<\/li>\n Matsui, Y. & Matsui, T. NP-completeness for calculating power indices of weighted majority games. Theor. Comput. Sci.<\/i> 263<\/b>, 305\u2013310 (2001).<\/p>\n<\/li>\n Fujimoto, K., Kojadinovic, I. & Marichal, J.-L. Axiomatic characterizations of probabilistic and cardinal-probabilistic interaction indices. Games Econ. Behav.<\/i> 55<\/b>, 72\u201399 (2006).<\/p>\n<\/li>\n Ribeiro, M. T., Singh, S. & Guestrin, C. Anchors: high-precision model-agnostic explanations. In Proc. AAAI Conference on Artificial Intelligence<\/i> (2018).<\/p>\n<\/li>\n Shortliffe, E. H. & Sep\u00falveda, M. J. Clinical decision support in the era of artificial intelligence. JAMA<\/i> 320<\/b>, 2199\u20132200 (2018).<\/p>\n<\/li>\n Lundberg, S. M. et al. Explainable machine learning predictions to help anesthesiologists prevent hypoxemia during surgery. Nat. Biomed. Eng.<\/i> 2<\/b>, 749\u2013760 (2018).<\/p>\n<\/li>\n Cox, C. S. et al. Plan and operation of the NHANES I Epidemiologic Followup Study, 1992. Vital Health Stat.<\/i> 35<\/b>, 1\u2013231 (1997).<\/p>\n<\/li>\n Chen, T. & Guestrin, C. Xgboost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining<\/i> 785\u2013794 (ACM, 2016).<\/p>\n<\/li>\n Haufe, S. et al. On the interpretation of weight vectors of linear models in multivariate neuroimaging. Neuroimage<\/i> 87<\/b>, 96\u2013110 (2014).<\/p>\n<\/li>\n Kim, B. et al. Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In International Conference on Machine Learning<\/i> (ICLR, 2018).<\/p>\n<\/li>\n Yosinski, J., Clune, J., Nguyen, A., Fuchs, T. & Lipson, H. Understanding neural networks through deep visualization. In ICML Deep Learning Workshop<\/i> (ICML, 2015).<\/p>\n<\/li>\n Bau, D., Zhou, B., Khosla, A., Oliva, A. & Torralba, A. Network dissection: quantifying interpretability of deep visual representations. In Proc. IEEE Conference on Computer Vision and Pattern Recognition<\/i> 6541\u20136549 (IEEE, 2017).<\/p>\n<\/li>\n Leino, K., Sen, S., Datta, A., Fredrikson, M. & Li, L. Influence-directed explanations for deep convolutional networks. In Proc. 2018 IEEE International Test Conference (ITC)<\/i> 1\u20138 (IEEE, 2018).<\/p>\n<\/li>\n Group, S. R. A randomized trial of intensive versus standard blood-pressure control. N. Engl. J. Med.<\/i> 373<\/b>, 2103\u20132116 (2015).<\/p>\n<\/li>\n Mozaffarian, D. et al. Heart disease and stroke statistics-2016 update a report from the American Heart Association. Circulation<\/i> 133<\/b>, e38\u2013e48 (2016).<\/p>\n<\/li>\n Bowe, B., Xie, Y., Xian, H., Li, T. & Al-Aly, Z. Association between monocyte count and risk of incident CKD and progression to ESRD. Clin. J. Am. Soc. Nephrol.<\/i> 12<\/b>, 603\u2013613 (2017).<\/p>\n<\/li>\n Fan, F., Jia, J., Li, J., Huo, Y. & Zhang, Y. White blood cell count predicts the odds of kidney function decline in a Chinese community-based population. BMC Nephrol.<\/i> 18<\/b>, 190 (2017).<\/p>\n<\/li>\n Zinkevich, M. Rules of machine learning: best practices for ML engineering (2017).<\/p>\n<\/li>\n van Rooden, S. M. et al. The identification of Parkinson\u2019s disease subtypes using cluster analysis: a systematic review. Mov. Disord.<\/i> 25<\/b>, 969\u2013978 (2010).<\/p>\n<\/li>\n S\u00f8rlie, T. et al. Repeated observation of breast tumor subtypes in independent gene expression data sets. Proc. Natl Acad. Sci. USA<\/i> 100<\/b>, 8418\u20138423 (2003).<\/p>\n<\/li>\n Lapuschkin, S. et al. Unmasking clever hans predictors and assessing what machines really learn. Nat. Commun.<\/i> 10<\/b>, 1096 (2019).<\/p>\n<\/li>\n Pfungst, O. Clever Hans: (the Horse of Mr. Von Osten.) A Contribution to Experimental Animal and Human Psychology (Holt, Rinehart and Winston, 1911).<\/p>\n<\/li>\n Machine Learning Recommendations for Policymakers<\/i> (IIF, 2019); https:\/\/www.iif.com\/Publications\/ID\/3574\/Machine-Learning-Recommendations-for-Policymakers<\/a>\n<\/p>\n<\/li>\n Deeks, A. The judicial demand for explainable artificial intelligence. (2019).<\/p>\n<\/li>\n Plumb, G., Molitor, D. & Talwalkar, A. S. Model agnostic supervised local explanations. Adv. Neural Inf. Process. Syst.<\/i> 31<\/b>, 2520\u20132529 (2018).<\/p>\n<\/li>\n Young, H. P. Monotonic solutions of cooperative games. Int. J. Game Theor.<\/i> 14<\/b>, 65\u201372 (1985).<\/p>\n<\/li>\n Ancona, M., Ceolini, E., Oztireli, C. & Gross, M. Towards better understanding of gradient-based attribution methods for deep neural networks. In Proc. 6th International Conference on Learning Representations (ICLR 2018)<\/i> (2018).<\/p>\n<\/li>\n Hooker, S., Erhan, D., Kindermans, P.-J. & Kim, B. A benchmark for interpretability methods in deep neural networks. In Conference on<\/i> Neural Information Processing Systems<\/i> (NIPS, 2019).<\/p>\n<\/li>\n Shrikumar, A., Greenside, P., Shcherbina, A. & Kundaje, A. Not just a black box: learning important features through propagating activation differences. Preprint at https:\/\/arxiv.org\/abs\/1605.01713<\/a> (2016).<\/p>\n<\/li>\n Lunetta, K. L., Hayward, L. B., Segal, J. & Van Eerdewegh, P. Screening large-scale association study data: exploiting interactions using random forests. BMC Genet.<\/i> 5<\/b>, 32 (2004).<\/p>\n<\/li>\n Jiang, R., Tang, W., Wu, X. & Fu, W. A random forest approach to the detection of epistatic interactions in case-control studies. BMC Bioinformatics<\/i> 10<\/b>, S65 (2009).<\/p>\n<\/li>\n<\/div>\n