{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:04:50Z","timestamp":1784642690672,"version":"3.55.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032191045","type":"print"},{"value":"9783032191052","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-19105-2_25","type":"book-chapter","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:09:34Z","timestamp":1778364574000},"page":"351-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing Publicly Available Tabular Health Datasets for\u00a0Responsible Machine Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9708-1123","authenticated-orcid":false,"given":"Mariana","family":"Oliveira","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos","family":"Soares","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, M.: Maternal health risk (2020). https:\/\/doi.org\/10.24432\/C5DP5D","DOI":"10.24432\/C5DP5D"},{"issue":"111","key":"25_CR2","first-page":"1","volume":"21","author":"E Alcoba\u00e7a","year":"2020","unstructured":"Alcoba\u00e7a, E., Siqueira, F., Rivolli, A., Garcia, L.P., Oliva, J.T., De Carvalho, A.C.: MFE: towards reproducible meta-feature extraction. J. Mach. Learn. Res. 21(111), 1\u20135 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Balamuta, J.J., Truong, P.: Ucimlrepo: explore UCI ML repository datasets (2024)","DOI":"10.32614\/CRAN.package.ucimlrepo"},{"key":"25_CR4","unstructured":"Barandas, M.: Input validation. https:\/\/pymdma.readthedocs.io\/en\/v0.1.9\/tabular\/input_val\/"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Barella, V.H., Garcia, L.P.F., de Souto, M.C.P., Lorena, A.C., de Carvalho, A.C.P.L.F.: Assessing the data complexity of imbalanced datasets. Inf. Sci. 553, 83\u2013109 (2021)","DOI":"10.1016\/j.ins.2020.12.006"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Batini, C., Scannapieco, M.: Data and Information Quality: Dimensions, Principles and Techniques. Data-Centric Systems and Applications (2016)","DOI":"10.1007\/978-3-319-24106-7"},{"issue":"4","key":"25_CR7","doi-asserted-by":"publisher","first-page":"2095","DOI":"10.1007\/s00405-023-08299-w","volume":"281","author":"S Borzooei","year":"2024","unstructured":"Borzooei, S., Briganti, G., Golparian, M., Lechien, J.R., Tarokhian, A.: Machine learning for risk stratification of thyroid cancer patients. Eur. Arch. Oto-Rhino-Laryngol. 281(4), 2095\u20132104 (2024)","journal-title":"Eur. Arch. Oto-Rhino-Laryngol."},{"key":"25_CR8","doi-asserted-by":"publisher","unstructured":"CDC: Diabetes Health Indicators (2017). https:\/\/doi.org\/10.24432\/C53919","DOI":"10.24432\/C53919"},{"key":"25_CR9","doi-asserted-by":"publisher","unstructured":"Chicco, D., Jurman, G.: heart failure clinical records (2020). https:\/\/doi.org\/10.24432\/C5Z89R","DOI":"10.24432\/C5Z89R"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Chinta, S.V., et al.: AI-driven healthcare: a review on ensuring fairness and mitigating bias. PLOS Digit. Health 4(5), e0000864 (2025)","DOI":"10.1371\/journal.pdig.0000864"},{"key":"25_CR11","doi-asserted-by":"publisher","first-page":"850611","DOI":"10.3389\/fdata.2022.850611","volume":"5","author":"L Ehrlinger","year":"2022","unstructured":"Ehrlinger, L., W\u00f6\u00df, W.: A survey of data quality measurement and monitoring tools. Front. Big Data 5, 850611 (2022)","journal-title":"Front. Big Data"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Fa\u00e7oco, I.S., et al.: pyMDMA: multimodal data metrics for auditing real and synthetic datasets. SoftwareX 31, 102256 (2025)","DOI":"10.1016\/j.softx.2025.102256"},{"key":"25_CR13","doi-asserted-by":"publisher","unstructured":"Fa\u00e7oco, I.S., Matias, P., Rebelo, J.: Fraunhoferportugal\/pymdma: patch version 0.1.9. Zenodo (2025). https:\/\/doi.org\/10.5281\/ZENODO.15064792","DOI":"10.5281\/ZENODO.15064792"},{"key":"25_CR14","unstructured":"Fleming, T.R., Harrington, D.P.: Counting Processes and Survival Analysis. Wiley (2013)"},{"key":"25_CR15","unstructured":"Frank, A.: UCI machine learning repository (2010). http:\/\/archive.ics.uci.edu\/ml"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Garcia, L., Lorena, A.: ECoL: complexity measures for supervised problems (2019)","DOI":"10.32614\/CRAN.package.ECoL"},{"issue":"23","key":"25_CR17","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","volume":"101","author":"AL Goldberger","year":"2000","unstructured":"Goldberger, A.L., et al.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215\u2013e220 (2000)","journal-title":"Circulation"},{"issue":"15","key":"25_CR18","doi-asserted-by":"publisher","first-page":"1081","DOI":"10.1056\/NEJM199610103351501","volume":"335","author":"SM Hammer","year":"1996","unstructured":"Hammer, S.M., et al.: A trial comparing nucleoside monotherapy with combination therapy in HIV-infected adults with A critical comparative study of liver patients from USA and INDIA4 cell counts from 200 to 500 per cubic millimeter. N. Engl. J. Med. 335(15), 1081\u20131090 (1996)","journal-title":"N. Engl. J. Med."},{"issue":"3","key":"25_CR19","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/34.990132","volume":"24","author":"TK Ho","year":"2002","unstructured":"Ho, T.K., Basu, M.: Complexity measures of supervised classification problems. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 289\u2013300 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR20","doi-asserted-by":"publisher","unstructured":"Janosi, A., Steinbrunn, W., Pfisterer, M., Detrano, R.: Heart disease (1989). https:\/\/doi.org\/10.24432\/C52P4X","DOI":"10.24432\/C52P4X"},{"key":"25_CR21","unstructured":"Kohli, R., Feurer, M., Eggensperger, K., Bischl, B., Hutter, F.: Towards quantifying the effect of datasets for benchmarking. In: ICLR 2024 Workshop on Data-centric Machine Learning Research (DMLR) (2024)"},{"key":"25_CR22","doi-asserted-by":"publisher","unstructured":"Lichtinghagen, R., Klawonn, F., Hoffmann, G.: HCV data (2020). https:\/\/doi.org\/10.24432\/C5D612","DOI":"10.24432\/C5D612"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Trustworthy AI. ACM Trans. Intell. Syst. Technol. 14(1), 1\u201359 (2023)","DOI":"10.1145\/3546872"},{"key":"25_CR24","doi-asserted-by":"publisher","first-page":"86435","DOI":"10.52202\/079017-2744","volume":"37","author":"R Longjohn","year":"2024","unstructured":"Longjohn, R., Kelly, M., Singh, S., Smyth, P.: Benchmark data repositories for better benchmarking. Adv. Neural. Inf. Process. Syst. 37, 86435\u201386457 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"5","key":"25_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3347711","volume":"52","author":"AC Lorena","year":"2019","unstructured":"Lorena, A.C., Garcia, L.P., Lehmann, J., Souto, M.C., Ho, T.K.: A survey on measuring classification complexity. ACM Comput. Surv. (CSUR) 52(5), 1\u201334 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"25_CR26","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s10994-017-5681-1","volume":"107","author":"AC Lorena","year":"2018","unstructured":"Lorena, A.C., Maciel, A.I., de Miranda, P.B., Costa, I.G., Prud\u00eancio, R.B.: Data complexity meta-features for regression problems. Mach. Learn. 107, 209\u2013246 (2018)","journal-title":"Mach. Learn."},{"key":"25_CR27","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.ins.2013.08.059","volume":"261","author":"N Maci\u00e0","year":"2014","unstructured":"Maci\u00e0, N., Bernad\u00f3-Mansilla, E.: Towards UCI+. Inf. Sci. 261, 237\u2013262 (2014)","journal-title":"Inf. Sci."},{"key":"25_CR28","doi-asserted-by":"publisher","unstructured":"Malani, P.N., Kullgren, J., Solway, E.: National poll on healthy aging (NPHA), [USA], April 2017 (2019). https:\/\/doi.org\/10.3886\/ICPSR37305.V1","DOI":"10.3886\/ICPSR37305.V1"},{"key":"25_CR29","doi-asserted-by":"publisher","unstructured":"National Center For Health Statistics (NCHS) At The Centers For Disease Control And Prevention (CDC): National Health and Nutrition Health Survey 2013-2014 (NHANES) Age Prediction Subset (2019).https:\/\/doi.org\/10.24432\/C5BS66","DOI":"10.24432\/C5BS66"},{"key":"25_CR30","doi-asserted-by":"publisher","first-page":"104344","DOI":"10.1016\/j.dib.2019.104344","volume":"25","author":"FM Palechor","year":"2019","unstructured":"Palechor, F.M., De la Hoz Manotas, A.: Dataset for estimation of obesity levels based on eating habits and physical condition in individuals from Colombia, Peru and Mexico. Data Br. 25, 104344 (2019)","journal-title":"Data Br."},{"key":"25_CR31","unstructured":"Quaresmini, C., Primiero, G.: Data quality dimensions for fair AI. In: Proceedings of the 2nd Workshop on Fairness and Bias in AI Co-located with ECAI (2024)"},{"issue":"3","key":"25_CR32","first-page":"506","volume":"9","author":"BV Ramana","year":"2012","unstructured":"Ramana, B.V., Babu, M.S.P., Venkateswarlu, N.B.: A critical comparative study of liver patients from USA and India: an exploratory analysis. IJCSI 9(3), 506 (2012)","journal-title":"IJCSI"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Rivolli, A., Garcia, L.P., Soares, C., Vanschoren, J., De\u00a0Carvalho, A.C.: Meta-features for meta-learning. Knowl.-Based Syst. 240, 108101 (2022)","DOI":"10.1016\/j.knosys.2021.108101"},{"key":"25_CR34","doi-asserted-by":"publisher","first-page":"104824","DOI":"10.1016\/j.cmpb.2018.12.029","volume":"181","author":"R\u00c1 S\u00e1nchez","year":"2019","unstructured":"S\u00e1nchez, R.\u00c1., Iraola, A.B., Unanue, G.E., Carlin, P.: TAQIH, a tool for tabular data quality assessment and improvement in the context of health data. Comput. Methods Programs Biomed. 181, 104824 (2019)","journal-title":"Comput. Methods Programs Biomed."},{"issue":"1","key":"25_CR35","first-page":"781670","volume":"2014","author":"B Strack","year":"2014","unstructured":"Strack, B., et al.: Impact of HbA1c measurement on hospital readmission rates: analysis of 70,000 clinical database patient records. Biomed. Res. Int. 2014(1), 781670 (2014)","journal-title":"Biomed. Res. Int."},{"issue":"22","key":"25_CR36","doi-asserted-by":"publisher","first-page":"14155","DOI":"10.3390\/ijms232214155","volume":"23","author":"E Tasci","year":"2022","unstructured":"Tasci, E., Zhuge, Y., Kaur, H., Camphausen, K., Krauze, A.V.: Hierarchical voting-based feature selection and ensemble learning model scheme for glioma grading with clinical and molecular characteristics. Int. J. Mol. Sci. 23(22), 14155 (2022)","journal-title":"Int. J. Mol. Sci."},{"key":"25_CR37","doi-asserted-by":"publisher","unstructured":"Zwitter, M., Soklic, M.: Breast cancer (1988). https:\/\/doi.org\/10.24432\/C51P4M","DOI":"10.24432\/C51P4M"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-19105-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T13:44:52Z","timestamp":1784641492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-19105-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032191045","9783032191052"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-19105-2_25","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}