The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Comparison of feature importance measures as explanations for classification models
Open accessAbstract
Explainable artificial intelligence is an emerging research direction helping the user or developer of machine learning models understand why models behave the way they do. The most popular explanation technique is feature importance. However, there are several different approaches how feature importances are being measured, most notably global and local. In this study we compare different feature importance measures using both linear (logistic regression with L1 penalization) and non-linear (random forest) methods and local interpretable model-agnostic explanations on top of them. These methods are applied to two datasets from the medical domain, the openly available breast cancer data from the UCI Archive and a recently collected running injury data. Our results show that the most important features differ depending on the technique. We argue that a combination of several explanation techniques could provide more reliable and trustworthy results. In particular, local explanations should be used in the most critical cases such as false negatives.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
An introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Statistical Analysis With Missing Data
Lahiff, M., Little, R. J. A., & Rubin, D. B. (1989) · Journal of the American Statistical Association · doi:10.2307/2289883 · Cited by 17,265
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
Kohavi, R. (1995) · Zenodo · doi:10.5281/zenodo.19712698 · Cited by 10,909
The use of the area under the ROC curve in the evaluation of machine learning algorithms
Bradley, A. P. (1997) · Pattern Recognition · doi:10.1016/s0031-3203(96)00142-2 · Cited by 7,217
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788
A review of feature selection techniques in bioinformatics
Saeys, Y., Inza, I., & Larrañaga, P. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm344 · Cited by 5,244
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340
Missing Value Estimation Methods for DNA Microarrays
Troyanskaya, O., Cantor, M., Sherlock, G., Brown, P., Hastie, T., Tibshirani, R., Botstein, D., & Altman, R. B. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.6.520 · Cited by 4,230
Gene selection and classification of microarray data using random forest
Díaz-Uriarte, R., & Alvarez de Andrés, S. (2006) · BMC Bioinformatics · doi:10.1186/1471-2105-7-3 · Cited by 2,929
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524
Explaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507 · cited 1×
“Several XAI review papers were published in recent years [17, 18, 24, 36].”
BackgroundStatistical Analysis with Missing Data
Bo., N., Little, R. J. A., & Rubin, D. B. (1988) · Population (French Edition) · doi:10.2307/1533221 · Cited by 2,095
Can machine-learning improve cardiovascular risk prediction using routine clinical data?
Weng, S. F., Reps, J., Kai, J., Garibaldi, J. M., & Qureshi, N. (2017) · PLOS ONE · doi:10.1371/journal.pone.0174944 · Cited by 1,346
Statistical modeling: The two cultures
Breiman, L. (2001) · Cited by 1,314
Fisher, A., Rudin, C., & Dominici, F. (2018) · arXiv · doi:10.48550/arxiv.1801.01489 · Cited by 1,165
Interpretable Machine Learning
Molnar, C. (2020) · Cited by 1,104
Cross-validation pitfalls when selecting and assessing regression and classification models
Krstajic, D., Buturovic, L. J., Leahy, D. E., & Thomas, S. (2014) · Journal of Cheminformatics · doi:10.1186/1758-2946-6-10 · Cited by 1,090
Unmasking Clever Hans predictors and assessing what machines really learn
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., & Müller, K.-R. (2019) · Nature Communications · doi:10.1038/s41467-019-08987-4 · Cited by 1,047
Boulesteix, A., Janitza, S., Kruppa, J., & König, I. R. (2012) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1072 · Cited by 924
Nonlinear Multivariate Analysis.
Hill, M. O., & Gifi, A. (1990) · The Journal of Ecology · doi:10.2307/2260960 · Cited by 906
Automated machine learning: Review of the state-of-the-art and opportunities for healthcare
Waring, J., Lindvall, C., & Umeton, R. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101822 · Cited by 834
A review of feature selection methods on synthetic data
Bolón-Canedo, V., Sánchez-Maroño, N., & Alonso-Betanzos, A. (2013) · Knowledge and Information Systems · doi:10.1007/s10115-012-0487-8 · Cited by 830
A review of feature selection methods in medical applications
Remeseiro, B., & Bolon-Canedo, V. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.103375 · Cited by 804
iml: An R package for Interpretable Machine Learning
Molnar, C. (2018) · Journal of Open Source Software · doi:10.21105/joss.00786 · Cited by 718
Vellido, A. (2020) · Neural Computing and Applications · doi:10.1007/s00521-019-04051-w · Cited by 635
Explainable machine learning in deployment
Bhatt, U., Xiang, A., Sharma, S., Weller, A., Taly, A., Jia, Y., Ghosh, J., Puri, R., Moura, J. M. F., & Eckersley, P. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3375624 · Cited by 633
A Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629
Combrisson, E., & Jerbi, K. (2015) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2015.01.010 · Cited by 599
Unmasking Clever Hans predictors and assessing what machines really learn
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., & Müller, K. (2019) · RePEc: Research Papers in Economics · Cited by 580
Bondell, H. D., & Reich, B. J. (2008) · Biometrics · doi:10.1111/j.1541-0420.2007.00843.x · Cited by 465
Visualizing the Feature Importance for Black Box Models
Casalicchio, G., Molnar, C., & Bischl, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-10925-7_40 · Cited by 325
Breast cancer diagnosis using GA feature selection and Rotation Forest
Aličković, E., & Subasi, A. (2017) · Neural Computing and Applications · doi:10.1007/s00521-015-2103-9 · Cited by 306
Hadzhiev, Y., Qureshi, H. K., Wheatley, L., Cooper, L., Jasiulewicz, A., Van Nguyen, H., Wragg, J. W., Poovathumkadavil, D., Conic, S., Bajan, S., et al. (2019) · Nature Communications · doi:10.1038/s41467-019-08487-5 · Cited by 256
Wolberg, W. H., Street, W. N., & Mangasarian, O. L. (1994) · Cancer Letters · doi:10.1016/0304-3835(94)90099-x · Cited by 251
The autofeat Python Library for Automated Feature Engineering and Selection
Horn, F., Pack, R., & Rieger, M. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-43823-4_10 · Cited by 184
The Feature Importance Ranking Measure
Zien, A., Krämer, N., Sonnenburg, S., & Rätsch, G. (2009) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-04174-7_45 · Cited by 171
New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes
Jauhiainen, S., Kauppi, J., Leppänen, M., Pasanen, K., Parkkari, J. P., Vasankari, T. J., Kannus, P., & Äyrämö, S. (2020) · International Journal of Sports Medicine · doi:10.1055/a-1231-5304 · Cited by 130
Self-citationIn AI We Trust? Factors That Influence Trustworthiness of AI-infused Decision-Making ProcessesPreprint
Ashoori, M., & Weisz, J. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02675 · Cited by 122
Gender and Age-Related Differences in Bilateral Lower Extremity Mechanics during Treadmill Running
Phinyomark, A., Hettinga, B. A., Osis, S. T., & Ferber, R. (2014) · PLoS ONE · doi:10.1371/journal.pone.0105246 · Cited by 109
Pohl, M. B., Lloyd, C. H., & Ferber, R. (2010) · Gait & Posture · doi:10.1016/j.gaitpost.2010.07.020 · Cited by 99
Can we automate expert-based journal rankings? Analysis of the Finnish publication indicator
Saarela, M., & Kärkkäinen, T. (2020) · Journal of Informetrics · doi:10.1016/j.joi.2020.101008 · Cited by 46
Self-citationPredicting 30-day all-cause readmissions from hospital inpatient discharge data
Yang, C., Delcher, C., Shenkman, E. A., & Ranka, S. (2016) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom.2016.7749452 · Cited by 40
Predicting hospital associated disability from imbalanced data using supervised learning
Saarela, M., Ryynänen, O., & Äyrämö, S. (2018) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2018.09.004 · Cited by 36
Self-citation
Research works printed but not linked: 3
- Ferber R, Osis ST, Hicks JL, Delp SL (2016) Gait biomechanics in the era of data science. J Biomech 49(16):3759–3761 · doi:10.1016/j.jbiomech.2016.10.033
- Tang J, Alelyani S, Liu H (2014) Feature selection for classification: A review. Data classification: Algorithms and applications p 37
- Wachter S, Mittelstadt B, Russell C (2017) Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harv. JL Tech. 31:841
Cited by
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024) · Cognitive Computation · doi:10.1007/s12559-023-10179-8 · Cited by 2,495
“For some datasets and problems, this approach may provide more accurate and trustworthy explanations than other methods [110, 111].”
Ghasemi, A., Hashtarkhani, S., Schwartz, D. L., & Shaban‐Nejad, A. (2024) · Cancer Innovation · doi:10.1002/cai2.136 · Cited by 193
AI Trust: Can Explainable AI Enhance Warranted Trust?
de Brito Duarte, R., Correia, F., Arriaga, P., & Paiva, A. (2023) · Human Behavior and Emerging Technologies · doi:10.1155/2023/4637678 · Cited by 52
Toward assessment of human voice biomarkers of brain lesions through explainable deep learning
Gutiérrez-Serafín, B., Andreu-Perez, J., Pérez-Espinosa, H., Paulmann, S., & Ding, W. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105457 · Cited by 14
Metadata
- Authors
- Saarela, M., & Jauhiainen, S.
- Venue
- SN Applied Sciences
- Published
- 2021-02
- Volume
- 3
- Issue
- 2
- ISSN
- 2523-3963 (ISSN-L)
- 2523-3971
- OpenAlex
- W3126673261
- Cited by
- 456
- References
- 45
- FWCI
- 21.52
- Type
- journal article
- Language
- en
- Open access
- gold
- Licence
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor, 2 d)
- Funders
- Academy of Finland (311877)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.