{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T20:47:06Z","timestamp":1786222026004,"version":"3.56.0"},"reference-count":27,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000274","name":"British Heart Foundation","doi-asserted-by":"publisher","award":["PG\/21\/10619"],"award-info":[{"award-number":["PG\/21\/10619"]}],"id":[{"id":"10.13039\/501100000274","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015509","name":"National Institute for Health Research Collaboration for Leadership in Applied Health Research and Care North West Coast","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015509","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end\u2010users in their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, the way the explainability metrics of these two methods are generated is discussed and a framework for the interpretation of their outputs, highlighting their weaknesses and strengths is proposed. Specifically, their outcomes in terms of model\u2010dependency and in the presence of collinearity among the features, relying on a case study from the biomedical domain (classification of individuals with or without myocardial infarction) are discussed. The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation.<\/jats:p>","DOI":"10.1002\/aisy.202400304","type":"journal-article","created":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T00:40:23Z","timestamp":1719535223000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":734,"title":["A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME"],"prefix":"10.1002","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0871-8282","authenticated-orcid":false,"given":"Ahmed M.","family":"Salih","sequence":"first","affiliation":[{"name":"William Harvey Research Institute NIHR Barts Biomedical Research Centre Queen Mary University of London  London E1 4NS UK"},{"name":"Barts Heart Centre St. Bartholomew's Hospital Barts Health NHS Trust  E1 1BB West Smithfield London UK"},{"name":"Department of Population Health Sciences University of Leicester  Leicester LE1 7RH UK"},{"name":"Department of Computer Science Faculty of Science University of Zakho  Kurdistan Region Zakho 42002 Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zahra","family":"Raisi\u2010Estabragh","sequence":"additional","affiliation":[{"name":"William Harvey Research Institute NIHR Barts Biomedical Research Centre Queen Mary University of London  London E1 4NS UK"},{"name":"Barts Heart Centre St. Bartholomew's Hospital Barts Health NHS Trust  E1 1BB West Smithfield London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilaria Boscolo","family":"Galazzo","sequence":"additional","affiliation":[{"name":"Department of Engineering for Innovation Medicine University of Verona  37129 Verona Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petia","family":"Radeva","sequence":"additional","affiliation":[{"name":"Department of de Matem\u00e0tiques i Inform\u00e0tica University of Barcelona  08007 Barcelona Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steffen E.","family":"Petersen","sequence":"additional","affiliation":[{"name":"William Harvey Research Institute NIHR Barts Biomedical Research Centre Queen Mary University of London  London E1 4NS UK"},{"name":"Barts Heart Centre St. Bartholomew's Hospital Barts Health NHS Trust  E1 1BB West Smithfield London UK"},{"name":"Health Data Research  UK"},{"name":"British Library Alan Turing Institute  96 Euston Rd. London NW1 2DB UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karim","family":"Lekadir","sequence":"additional","affiliation":[{"name":"Department of de Matem\u00e0tiques i Inform\u00e0tica University of Barcelona  08007 Barcelona Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gloria","family":"Menegaz","sequence":"additional","affiliation":[{"name":"Department of Engineering for Innovation Medicine University of Verona  37129 Verona Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,6,27]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.06.047"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.metabol.2017.01.011"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2020.01.095"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2021.100025"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay7120"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.1016032"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101805"},{"key":"e_1_2_8_9_1","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg S. M.","year":"2017"},{"key":"e_1_2_8_10_1","doi-asserted-by":"crossref","unstructured":"M. T.Ribeiro S.Singh C.Guestrin inProc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining USA2016 pp.1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_8_11_1","doi-asserted-by":"crossref","unstructured":"A.Holzinger A.Saranti C.Molnar P.Biecek W.Samek inInt. Workshop on Extending Explainable AI Beyond Deep Models and Classifiers2022 pp.13\u201338.","DOI":"10.1007\/978-3-031-04083-2_2"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2018.09.016"},{"key":"e_1_2_8_13_1","volume-title":"A Guide for Making Black Box Models Explainable","author":"Learning I.","year":"2019"},{"key":"e_1_2_8_14_1","doi-asserted-by":"crossref","unstructured":"C.Molnar G.K\u00f6nig J.Herbinger T.Freiesleben S.Dandl C. A.Scholbeck G.Casalicchio M.Grosse\u2010Wentrup B.Bischl inxxAI\u2010Beyond Explainable AI: Int. Workshop Held in Conjunction with ICML 2020 July 18 2020 Vienna Austria Revised and Extended Papers Springer New York NY2022 pp.39\u201368.","DOI":"10.1007\/978-3-031-04083-2_4"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2019.101039"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2022.103677"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/er.8219"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrmge.2022.01.002"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"D.Slack S.Hilgard E.Jia S.Singh H.Lakkaraju inProc. AAAI\/ACM Conf. AI Ethics and Society New York NY2020 pp.180\u2013186.","DOI":"10.1145\/3375627.3375830"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103502"},{"key":"e_1_2_8_21_1","unstructured":"M.Mase A. B.Owen B.Seiler arXiv preprint arXiv:1911.00467 2019."},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"A.Salih I. B.Galazzo F.Cruciani L.Brusini P.Radeva in2022 IEEE Int. Conf. Image Processing (ICIP) IEEE Piscataway NJ2022 pp.4003\u20134007.","DOI":"10.1109\/ICIP46576.2022.9897253"},{"key":"e_1_2_8_23_1","author":"Salih A.","year":"2024","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0253443"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2020.07.022"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12020237"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"H.Kaur H.Nori S.Jenkins R.Caruana H.Wallach J. W.Vaughan inProc. 2020 CHI Conf. Human Factors in Computing Systems New York NY2020 pp.1\u201314.","DOI":"10.1145\/3313831.3376219"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3187455"}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202400304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:24:12Z","timestamp":1759857852000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202400304"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,27]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1002\/aisy.202400304"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202400304","archive":["Portico"],"relation":{},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"value":"2640-4567","type":"print"},{"value":"2640-4567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,27]]},"assertion":[{"value":"2024-04-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2400304"}}