{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T14:23:30Z","timestamp":1771338210754,"version":"3.50.1"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2024,6,8]],"date-time":"2024-06-08T00:00:00Z","timestamp":1717804800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,8]],"date-time":"2024-06-08T00:00:00Z","timestamp":1717804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Instituto Polit\u00e9cnico de Coimbra"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Med Biol Eng Comput"],"published-print":{"date-parts":[[2024,11]]},"abstract":"<jats:sec>\n                <jats:title>Abstract<\/jats:title>\n                <jats:p>The common black box nature of machine learning models is an obstacle to their application in health care context. Their widespread application is limited by a significant \u201clack of trust.\u201d So, the main goal of this work is the development of an evaluation approach that can assess, simultaneously, trust and performance. Trust assessment is based on (i) model robustness (stability assessment), (ii) confidence (95% CI of geometric mean), and (iii) interpretability (comparison of respective features ranking with clinical evidence). Performance is assessed through geometric mean. For validation, in patients\u2019 stratification in cardiovascular risk assessment, a Portuguese dataset (<jats:italic>N<\/jats:italic>=1544) was applied. Five different models were compared: (i) GRACE score, the most common risk assessment tool in Portugal for patients with acute coronary syndrome; (ii) logistic regression; (iii) Na\u00efve Bayes; (iv) decision trees; and (v) rule-based approach, previously developed by this team. The obtained results confirm that the simultaneous assessment of trust and performance can be successfully implemented. The rule-based approach seems to have potential for clinical application. It provides a high level of trust in the respective operation while outperformed the GRACE model\u2019s performance, enhancing the required physicians\u2019 acceptance. This may increase the possibility to effectively aid the clinical decision.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Graphical abstract<\/jats:title>\n                \n              <\/jats:sec>","DOI":"10.1007\/s11517-024-03145-5","type":"journal-article","created":{"date-parts":[[2024,6,8]],"date-time":"2024-06-08T00:01:44Z","timestamp":1717804904000},"page":"3397-3410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Machine learning models\u2019 assessment: trust and performance"],"prefix":"10.1007","volume":"62","author":[{"given":"S.","family":"Sousa","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1021-1173","authenticated-orcid":false,"given":"S.","family":"Paredes","sequence":"additional","affiliation":[]},{"given":"T.","family":"Rocha","sequence":"additional","affiliation":[]},{"given":"J.","family":"Henriques","sequence":"additional","affiliation":[]},{"given":"J.","family":"Sousa","sequence":"additional","affiliation":[]},{"given":"L.","family":"Gon\u00e7alves","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,8]]},"reference":[{"key":"3145_CR1","unstructured":"Margot E. Kaminski (2019) The right to explanation, Explained, 34 Berkeley Tech. L.J. 189.\u00a0\u00a0https:\/\/scholar.law.colorado.edu\/faculty-articles\/1227"},{"key":"3145_CR2","doi-asserted-by":"publisher","unstructured":"Linardatos P et. al. (2020) Explainable AI: a review of machine learning interpretability methods. Entropy 23, 1. https:\/\/doi.org\/10.3390\/e23010018","DOI":"10.3390\/e23010018"},{"issue":"32","key":"3145_CR3","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1108\/INTR-05-2020-0300","volume":"3","author":"B Abedin","year":"2022","unstructured":"Abedin B et al (2022) Managing the tension between opposing effects of explainability of artificial intelligence: a contingency theory perspective. Internet Research 3(32):425\u2013453. https:\/\/doi.org\/10.1108\/INTR-05-2020-0300","journal-title":"Internet Research"},{"key":"3145_CR4","doi-asserted-by":"publisher","first-page":"203203","DOI":"10.1109\/ACCESS.2020.3036322","volume":"8","author":"A Mashrur","year":"2020","unstructured":"Mashrur A et al (2020) Machine learning for financial risk management: a survey. IEEE Access 8:203203\u2013203223. https:\/\/doi.org\/10.1109\/ACCESS.2020.3036322","journal-title":"IEEE Access"},{"key":"3145_CR5","doi-asserted-by":"publisher","first-page":"102113","DOI":"10.1016\/j.artmed.2021.102113","volume":"7","author":"F Valente","year":"2021","unstructured":"Valente F, Henriques J, Paredes S et al (2021) A new approach for interpretability and reliability in clinical risk prediction: acute coronary syndrome scenario. Artif Intell Med 7:102113. https:\/\/doi.org\/10.1016\/j.artmed.2021.102113","journal-title":"Artif Intell Med"},{"key":"3145_CR6","unstructured":"WHO (2022) Cardiovascular diseases (CVDs). https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds). accessed July 2023."},{"key":"3145_CR7","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1093\/eurheartj\/ehi187","volume":"26","author":"P Ara\u00fajo","year":"2005","unstructured":"Ara\u00fajo P et al (2005) TIMI, PURSUIT, and GRACE risk scores: sustained prognostic value and interaction with revascularization in NSTE-ACS. Eur Heart J 26:865\u2013872. https:\/\/doi.org\/10.1093\/eurheartj\/ehi187","journal-title":"Eur Heart J"},{"issue":"8","key":"3145_CR8","doi-asserted-by":"publisher","first-page":"832","DOI":"10.3390\/electronics8080832","volume":"8","author":"DV Carvalho","year":"2019","unstructured":"Carvalho DV et al (2019) Machine learning interpretability: a survey on methods and metrics. Electronics 8(8):832. https:\/\/doi.org\/10.3390\/electronics8080832","journal-title":"Electronics"},{"key":"3145_CR9","doi-asserted-by":"publisher","unstructured":"Carrington A, Fieguth P, Chen H (2018) Measures of model interpretability for model selection. In: 2nd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CDMAKE), Aug 2018, Hamburg, Germany, pp 329\u2013349. https:\/\/doi.org\/10.1007\/978-3-319-99740-7_24","DOI":"10.1007\/978-3-319-99740-7_24"},{"key":"3145_CR10","doi-asserted-by":"publisher","first-page":"107482","DOI":"10.1016\/j.cmpb.2023.107482","volume":"233","author":"C Charlton","year":"2023","unstructured":"Charlton C et al (2023) Development of prediction models for one-year brain tumour survival using machine learning: a comparison of accuracy and interpretability. Comput Methods Programs Biomed 233:107482. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107482","journal-title":"Comput Methods Programs Biomed"},{"key":"3145_CR11","unstructured":"Arya V et al. (2021) One explanation does not fit all: a toolkit and taxonomy of AI explainability techniques, Informs. https:\/\/research.ibm.com\/publications\/one-explanation-does-not-fit-all-a-toolkit-and-taxonomy-of-ai-explainability-techniques"},{"key":"3145_CR12","doi-asserted-by":"publisher","unstructured":"Doshi-Velez F, Kim B (2017) Towards a rigorous science of interpretable machine learning. arXiv: Machine Learning. https:\/\/doi.org\/10.48550\/arXiv.1702.08608","DOI":"10.48550\/arXiv.1702.08608"},{"key":"3145_CR13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1900654116","volume-title":"Definitions, methods, and applications in interpretable machine learning","author":"J Murdoch","year":"2019","unstructured":"Murdoch J (2019) Definitions, methods, and applications in interpretable machine learning. Physical Sciences, PNA.\u00a0\u00a0https:\/\/www.pnas.org\/doi\/full\/10.1073\/pnas.1900654116"},{"key":"3145_CR14","doi-asserted-by":"publisher","first-page":"102493","DOI":"10.1016\/j.ijhcs.2020.102493","volume":"144","author":"J Waa","year":"2020","unstructured":"Waa J et al (2020) Interpretable confidence measures for decision support systems. Int J Hum-Comp Stud 144:102493. https:\/\/doi.org\/10.1016\/j.ijhcs.2020.102493","journal-title":"Int J Hum-Comp Stud"},{"key":"3145_CR15","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1613\/jair.1.12228","volume":"70","author":"N Burkart","year":"2021","unstructured":"Burkart N, Huber M (2021) A survey on the explainability of supervised machine learning. J Artif Intell Res 70:245\u2013317","journal-title":"J Artif Intell Res"},{"key":"3145_CR16","doi-asserted-by":"publisher","unstructured":"Molnar C, Casalicchio G, Bischl B (2020) Interpretable machine learning \u2013 a brief history, state-of-the-art and challenges. In: Koprinska I et al (eds) ECML PKDD 2020 Workshops. ECML PKDD 2020. Communications in Computer and Information Science, vol 1323. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-65965-3_28","DOI":"10.1007\/978-3-030-65965-3_28"},{"key":"3145_CR17","doi-asserted-by":"publisher","unstructured":"Ahmad M, Eckert C, Teredesai A (2018) Interpretable machine learning in healthcare, Proceedings of the 2018 ACM international conference on bioinformatics, computational biology, and health informatics. https:\/\/doi.org\/10.1145\/3233547.3233667","DOI":"10.1145\/3233547.3233667"},{"key":"3145_CR18","volume-title":"Advances in Neural Information Processing Systems 30 (NIPS)","author":"S Lundberg","year":"2017","unstructured":"Lundberg S, Lee S (2017) A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems 30 (NIPS)"},{"key":"3145_CR19","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1016\/s0003-4975(02)04683-0","volume":"75","author":"P Anderson","year":"2003","unstructured":"Anderson P et al (2003) Understanding logistic regression analysis in clinical reports: an introduction. Ann Thorac Surg 75:753\u2013757. https:\/\/doi.org\/10.1016\/s0003-4975(02)04683-0","journal-title":"Ann Thorac Surg"},{"issue":"3","key":"3145_CR20","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.cmpb.2010.12.015","volume":"101","author":"S Paredes","year":"2011","unstructured":"Paredes S et al (2011) Long term cardiovascular risk models\u2019 combination. Comput Methods Programs Biomed 101(3):231\u2013242. https:\/\/doi.org\/10.1016\/j.cmpb.2010.12.015","journal-title":"Comput Methods Programs Biomed"},{"key":"3145_CR21","doi-asserted-by":"publisher","first-page":"107347","DOI":"10.1016\/j.cmpb.2023.107347","volume":"230","author":"M Roseiro","year":"2023","unstructured":"Roseiro M, Henriques J, Paredes S et al (2023) An interpretable machine learning approach to estimate the influence of inflammation biomarkers on cardiovascular risk assessment. Comput Methods Programs Biomed 230:107347. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107347","journal-title":"Comput Methods Programs Biomed"},{"key":"3145_CR22","volume-title":"Validation and Updating. ISBN: 978-0-387-77243-1, Statistics for Biology and Health","author":"W Steyerberg","year":"2009","unstructured":"Steyerberg W (2009) Clinical prediction models \u2013 a practical approach to development. In: Validation and Updating. ISBN: 978-0-387-77243-1, Statistics for Biology and Health. Springer"}],"container-title":["Medical &amp; Biological Engineering &amp; Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-024-03145-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11517-024-03145-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-024-03145-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T04:13:27Z","timestamp":1729052007000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11517-024-03145-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,8]]},"references-count":22,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["3145"],"URL":"https:\/\/doi.org\/10.1007\/s11517-024-03145-5","relation":{},"ISSN":["0140-0118","1741-0444"],"issn-type":[{"value":"0140-0118","type":"print"},{"value":"1741-0444","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,8]]},"assertion":[{"value":"25 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}