{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T11:40:03Z","timestamp":1750592403509,"version":"3.41.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031958373","type":"print"},{"value":"9783031958380","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-95838-0_29","type":"book-chapter","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T11:14:42Z","timestamp":1750590882000},"page":"293-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CUE-X: A Framework for\u00a0the\u00a0Automatic Evaluation of\u00a0Clinical Usefulness of\u00a0Explanations for\u00a0the\u00a0Multimorbidity Problem"],"prefix":"10.1007","author":[{"given":"Martin","family":"Michalowski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Szymon","family":"Wilk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jenny M.","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Carrier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herna","family":"Viktor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wojtek","family":"Michalowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"29_CR1","unstructured":"Bedi, S., et al.: Testing and evaluation of health care applications of large language models: a systematic review. JAMA (2024)"},{"issue":"1","key":"29_CR2","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41746-022-00699-2","volume":"5","author":"H Chen","year":"2022","unstructured":"Chen, H., Gomez, C., Huang, C.M., Unberath, M.: Explainable medical imaging ai needs human-centered design: guidelines and evidence from a systematic review. NPJ Dig. Med. 5(1), 156 (2022)","journal-title":"NPJ Dig. Med."},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Deka, P., Jurek-Loughrey, A., P, D.: Multiple evidence combination for fact-checking of health-related information. In: Demner-fushman, D., Ananiadou, S., Cohen, K. (eds.) The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pp. 237\u2013247. Association for Computational Linguistics, Toronto (2023)","DOI":"10.18653\/v1\/2023.bionlp-1.20"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"El\u00a0Shawi, R., Sherif, Y., Al-Mallah, M., Sakr, S.: Interpretability in healthcare a comparative study of local machine learning interpretability techniques. In: 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS), pp. 275\u2013280 (2019)","DOI":"10.1109\/CBMS.2019.00065"},{"issue":"7","key":"29_CR5","doi-asserted-by":"publisher","first-page":"4269","DOI":"10.1109\/JBHI.2024.3393719","volume":"28","author":"S Ghanvatkar","year":"2024","unstructured":"Ghanvatkar, S., Rajan, V.: Evaluating explanations from AI algorithms for clinical decision-making: a social science-based approach. IEEE J. Biomed. Health Inf. 28(7), 4269\u20134280 (2024)","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Gu, Y., et al.: Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthcare 3(1) (2021)","DOI":"10.1145\/3458754"},{"key":"29_CR7","unstructured":"Kanithi, P.K., et al.: MEDIC: towards a comprehensive framework for evaluating llms in clinical applications (2024)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Kogan, A., Peleg, M., Tu, S.W., Allon, R., Khaitov, N., Hochberg, I.: Towards a goal-oriented methodology for clinical-guideline-based management recommendations for patients with multimorbidity: gocom and its preliminary evaluation. J. Biomed. Inf. 112 (2020)","DOI":"10.1016\/j.jbi.2020.103587"},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/978-3-031-66535-6_33","volume-title":"Artificial Intelligence in Medicine","author":"M Michalowski","year":"2024","unstructured":"Michalowski, M., et al.: Manually-curated versus llm-generated explanations for complex patient cases: an exploratory study with physicians. In: Finkelstein, J., Moskovitch, R., Parimbelli, E. (eds.) Artificial Intelligence in Medicine, pp. 313\u2013323. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-66535-6_33"},{"key":"29_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104681","volume":"156","author":"M Michalowski","year":"2024","unstructured":"Michalowski, M., Wilk, S., Michalowski, W., Rao, M., Carrier, M.: Provision and evaluation of explanations within an automated planning-based approach to solving the multimorbidity problem. J. Biomed. Inf. 156, 104681 (2024)","journal-title":"J. Biomed. Inf."},{"key":"29_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019)","journal-title":"Artif. Intell."},{"key":"29_CR12","unstructured":"O\u2019Sullivan, D., et al.: Towards a framework for comparing functionalities of multimorbidity clinical decision support: a literature-based feature set and benchmark cases. In: Proceedings of the Annual AMIA Symposium Proceedings, pp. 920\u2014-929 (2021)"},{"issue":"6","key":"29_CR13","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1109\/MIS.2018.2886697","volume":"33","author":"L Piovesan","year":"2018","unstructured":"Piovesan, L., Terenziani, P., Molino, G.: Glare-sscpm: an intelligent system to support the treatment of comorbid patients. IEEE Intell. Syst. 33(6), 37\u201346 (2018)","journal-title":"IEEE Intell. Syst."},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Rao, M., Michalowski, M., Wilk, S., Michalowski, W., Coles, A., Carrier, M.: Towards an AI planning-based pipeline for the management of multimorbid patients. In: Artificial Intelligence in Medicine, pp. 14\u201323 (2022)","DOI":"10.1007\/978-3-031-09342-5_2"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Szymanski, A., Ziems, N., Eicher-Miller, H.A., Li, T.J.J., Jiang, M., Metoyer, R.A.: Limitations of the LLM-as-a-judge approach for evaluating LLM outputs in expert knowledge tasks (2024)","DOI":"10.1145\/3708359.3712091"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Van\u00a0Woensel, W., Abidi, S., Tennankore, K., Worthen, G., Abidi, S.S.R.: Explainable decision support using task network models in notation3: Computerizing lipid management clinical guidelines as interactive task networks. In: Artificial Intelligence in Medicine, pp. 3\u201313 (2022)","DOI":"10.1007\/978-3-031-09342-5_1"},{"key":"29_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104395","volume":"142","author":"W Van Woensel","year":"2023","unstructured":"Van Woensel, W., Tu, S.W., Michalowski, W., et al.: A community-of-practice-based evaluation methodology for knowledge intensive computational methods and its application to multimorbidity decision support. J. Biomed. Inf. 142, 104395 (2023)","journal-title":"J. Biomed. Inf."},{"issue":"5","key":"29_CR18","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.sapharm.2012.05.009","volume":"9","author":"LW Wang","year":"2013","unstructured":"Wang, L.W., Miller, M.J., Schmitt, M.R., Wen, F.K.: Assessing readability formula differences with written health information materials: application, results, and recommendations. Res. Social Adm. Pharm. 9(5), 503\u2013516 (2013)","journal-title":"Res. Social Adm. Pharm."}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-95838-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T11:14:45Z","timestamp":1750590885000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-95838-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031958373","9783031958380"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-95838-0_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIME","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Medicine","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pavia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aime2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aime25.aimedicine.info\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}