{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:37:13Z","timestamp":1765546633264,"version":"3.37.3"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,8,27]],"date-time":"2020-08-27T00:00:00Z","timestamp":1598486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,27]],"date-time":"2020-08-27T00:00:00Z","timestamp":1598486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"CDP LIFE","award":["C7H-ID16-PR4-LIFELIG"],"award-info":[{"award-number":["C7H-ID16-PR4-LIFELIG"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1007\/s00778-020-00625-6","type":"journal-article","created":{"date-parts":[[2020,8,27]],"date-time":"2020-08-27T13:04:10Z","timestamp":1598533450000},"page":"1527-1550","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Cohort analytics: efficiency and applicability"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9405-3386","authenticated-orcid":false,"given":"Behrooz","family":"Omidvar-Tehrani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sihem","family":"Amer-Yahia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laks V. S.","family":"Lakshmanan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,27]]},"reference":[{"key":"625_CR1","doi-asserted-by":"crossref","unstructured":"Munshi, A., Sharma, V., Sharma, S.: Lessons learned from cohort studies, and hospital-based studies and their implications in precision medicine. In: Progress and Challenges in Precision Medicine. Elsevier (2017)","DOI":"10.1016\/B978-0-12-809411-2.00010-6"},{"key":"625_CR2","unstructured":"Welch, S.R., Huff, S.M.: Cohort amplification: an associative classification framework for identification of disease cohorts in the electronic health record. In: Annual Symposium Proceedings. American Medical Informatics Association (2010)"},{"key":"625_CR3","doi-asserted-by":"crossref","unstructured":"Maggi, F.M., Di\u00a0Francescomarino, C., Dumas, M., Ghidini, C.: Predictive monitoring of business processes. In: International Conference on Advanced Information Systems Engineering. Springer, pp. 457\u2013472 (2014)","DOI":"10.1007\/978-3-319-07881-6_31"},{"key":"625_CR4","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.jbi.2017.04.001","volume":"69","author":"T Pham","year":"2017","unstructured":"Pham, T., Tran, T., Phung, D., Venkatesh, S.: Predicting healthcare trajectories from medical records: a deep learning approach. J. Biomed. Inform. 69, 218\u2013229 (2017)","journal-title":"J. Biomed. Inform."},{"key":"625_CR5","doi-asserted-by":"crossref","unstructured":"Fejza, A.., Genev\u00e8s, P., Laya\u00efda, N., Bosson, J.-L.: Scalable and interpretable predictive models for electronic health records. In DSAA, IEEE (2018)","DOI":"10.1109\/DSAA.2018.00045"},{"key":"625_CR6","unstructured":"Heuser, A., Huynh, M., Chang, J.C.: Empirical process-based large sample properties of the area bounded by cohort-weighted Kaplan Meier curves. arXiv preprint arXiv:1701.02424 (2017)"},{"key":"625_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3186727","volume":"51","author":"Y Liu","year":"2018","unstructured":"Liu, Y., Safavi, T., Dighe, A., Danai, K.: Graph summarization methods and applications: a survey. ACM Comput. Surv. 51, 1\u201334 (2018)","journal-title":"ACM Comput. Surv."},{"key":"625_CR8","doi-asserted-by":"crossref","unstructured":"Senderovich, A., Weidlich, M., Gal, A.: Temporal network representation of event logs for improved performance modelling in business processes. In: BPM (2017)","DOI":"10.1007\/978-3-319-65000-5_1"},{"key":"625_CR9","doi-asserted-by":"crossref","unstructured":"Monroe, M., Lan, R., Lee, H., Plaisant, C., Shneiderman, B.: Temporal event sequence simplification. TVCG (2013)","DOI":"10.1109\/TVCG.2013.200"},{"issue":"3","key":"625_CR10","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"SB Needleman","year":"1970","unstructured":"Needleman, S.B., Wunsch, C.D.: A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48(3), 443\u2013453 (1970)","journal-title":"J. Mol. Biol."},{"issue":"12","key":"625_CR11","first-page":"1822","volume":"12","author":"CAL Pahins","year":"2019","unstructured":"Pahins, C.A.L., Omidvar-Tehrani, B., Amer-Yahia, S., Siroux, V., P\u00e9pin, J.L., Borel, J.-C., Comba, J.: COVIZ: a system for visual formation and exploration of patient cohorts. PVLDB 12(12), 1822\u20131825 (2019)","journal-title":"PVLDB"},{"key":"625_CR12","first-page":"573","volume":"147","author":"E Von Elm","year":"2007","unstructured":"Von Elm, E., Altman, D.G., Egger, M., et al.: The strengthening the reporting of observational studies in epidemiology (strobe) statement: guidelines for reporting observational studies. PLoS Med. 147, 573\u2013577 (2007)","journal-title":"PLoS Med."},{"issue":"11","key":"625_CR13","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.14778\/2350229.2350259","volume":"5","author":"A Hall","year":"2012","unstructured":"Hall, A., Bachmann, O., B\u00fcssow, R., G\u0103nceanu, S., Nunkesser, M.: Processing a trillion cells per mouse click. Proc. VLDB Endow. 5(11), 1436\u20131446 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"625_CR14","doi-asserted-by":"crossref","unstructured":"Omidvar-Tehrani, B., Amer-Yahia, S., Lakshmanan, L.V.S.: Cohort representation and exploration. In: DSAA. IEEE (2018)","DOI":"10.1109\/DSAA.2018.00027"},{"issue":"1","key":"625_CR15","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1287\/14-SSY153","volume":"5","author":"M Armony","year":"2015","unstructured":"Armony, M., Israelit, S., Mandelbaum, A., Marmor, Y.N., Tseytlin, Y., Yom-Tov, G.B.: On patient flow in hospitals: a data-based queueing-science perspective. Stoch. Syst. 5(1), 146\u2013194 (2015)","journal-title":"Stoch. Syst."},{"key":"625_CR16","unstructured":"Jenkins, K.: Comorbidity patterns with female incontinence distinguish subtypes. MedPage Today J. (2018)"},{"key":"625_CR17","unstructured":"Woodfield, J.: Gestational diabetes associated with early signs of kidney damage. The Global Diabetes Community (2018)"},{"key":"625_CR18","first-page":"1","volume":"18","author":"T Collins","year":"2018","unstructured":"Collins, T.: For your patients-REM sleep behavior disorder: REM disorder is highly predictive of neurodegenerative disease, study shows. Neurol. Today 18, 1\u201322 (2018)","journal-title":"Neurol. Today"},{"issue":"4","key":"625_CR19","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1089\/cmb.1994.1.337","volume":"1","author":"L Wang","year":"1994","unstructured":"Wang, L., Jiang, T.: On the complexity of multiple sequence alignment. J. Comput. Biol. 1(4), 337\u2013348 (1994)","journal-title":"J. Comput. Biol."},{"issue":"10","key":"625_CR20","doi-asserted-by":"publisher","first-page":"5416","DOI":"10.3390\/e16105416","volume":"16","author":"Z Chen","year":"2014","unstructured":"Chen, Z., Dehmer, M., Shi, Y.: A note on distance-based graph entropies. Entropy 16(10), 5416\u20135427 (2014)","journal-title":"Entropy"},{"issue":"3","key":"625_CR21","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1007\/s004530010050","volume":"29","author":"U Feige","year":"2001","unstructured":"Feige, U., Peleg, D., Kortsarz, G.: The dense k-subgraph problem. Algorithmica 29(3), 410\u2013421 (2001)","journal-title":"Algorithmica"},{"issue":"282","key":"625_CR22","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","volume":"53","author":"EL Kaplan","year":"1958","unstructured":"Kaplan, E.L., Meier, P.: Nonparametric estimation from incomplete observations. J. Am. Stat. Assoc. 53(282), 457\u2013481 (1958)","journal-title":"J. Am. Stat. Assoc."},{"key":"625_CR23","doi-asserted-by":"publisher","first-page":"2219","DOI":"10.1373\/clinchem.2005.053850","volume":"51","author":"M Gollery","year":"2005","unstructured":"Gollery, M.: Bioinformatics: sequence and genome analysis. Clin. Chem. 51, 2219 (2005)","journal-title":"Clin. Chem."},{"key":"625_CR24","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1093\/bib\/bbq015","volume":"11","author":"H Li","year":"2010","unstructured":"Li, H., Homer, N.: A survey of sequence alignment algorithms for next-generation sequencing. Brief. Bioinform. 11, 473\u2013483 (2010)","journal-title":"Brief. Bioinform."},{"key":"625_CR25","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"T Smith","year":"1981","unstructured":"Smith, T., Waterman, M.: Identification of common molecular subsequences. Mol. Biol. 147, 195\u2013197 (1981)","journal-title":"Mol. Biol."},{"key":"625_CR26","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/1748-7188-6-25","volume":"6","author":"VO Polyanovsky","year":"2011","unstructured":"Polyanovsky, V.O., Roytberg, M.A., Tumanyan, V.G.: Comparative analysis of the quality of a global algorithm and a local algorithm for alignment of two sequences. Algorithms Mol. Biol. 6, 25 (2011)","journal-title":"Algorithms Mol. Biol."},{"issue":"2","key":"625_CR27","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1002\/prot.21775","volume":"71","author":"NCW Goonesekere","year":"2008","unstructured":"Goonesekere, N.C.W., Lee, B.: Context-specific amino acid substitution matrices and their use in the detection of protein homologs. Proteins Struct. Funct. Bioinf. 71(2), 910\u2013919 (2008)","journal-title":"Proteins Struct. Funct. Bioinf."},{"key":"625_CR28","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1016\/0022-2836(91)90193-A","volume":"219","author":"SF Altschul","year":"1991","unstructured":"Altschul, S.F.: Amino acid substitution matrices from an information theoretic perspective. J. Mol. Biol. 219, 555\u2013565 (1991)","journal-title":"J. Mol. Biol."},{"key":"625_CR29","doi-asserted-by":"crossref","unstructured":"Omidvar-Tehrani, B.: Augmented therapy with online support groups. In: VLDB Workshop on Data Management and Analytics for Medicine and Healthcare (DMAH). Springer (2018)","DOI":"10.1007\/978-3-030-14177-6_9"},{"issue":"1","key":"625_CR30","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1006\/jmbi.2000.4042","volume":"302","author":"C Notredame","year":"2000","unstructured":"Notredame, C., Higgins, D.G., Heringa, J.: T-coffee: a novel method for fast and accurate multiple sequence alignment. J. Mol. Biol. 302(1), 205\u2013217 (2000)","journal-title":"J. Mol. Biol."},{"key":"625_CR31","doi-asserted-by":"crossref","unstructured":"Chatain, T., Carmona, J., Van\u00a0Dongen, B.: Alignment-based trace clustering. In: International Conference on Conceptual Modeling. Springer, pp. 295\u2013308 (2017)","DOI":"10.1007\/978-3-319-69904-2_24"},{"issue":"7","key":"625_CR32","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1093\/nar\/30.7.1575","volume":"30","author":"AJ Enright","year":"2002","unstructured":"Enright, A.J., Van\u00a0Dongen, S., Ouzounis, C.A.: An efficient algorithm for large-scale detection of protein families. Nucleic Acids Res. 30(7), 1575\u20131584 (2002)","journal-title":"Nucleic Acids Res."},{"key":"625_CR33","doi-asserted-by":"crossref","unstructured":"Bhuiyan, M., Mukhopadhyay, S., Al Hasan, M.: Interactive pattern mining on hidden data: a sampling-based solution. In: CIKM. ACM (2012)","DOI":"10.1145\/2396761.2396777"},{"key":"625_CR34","doi-asserted-by":"crossref","unstructured":"Amer-Yahia, S., Kleisarchaki, S., Kolloju, N.K., Lakshmanan, L.V.S., Zamar, R.H.: Exploring rated datasets with rating maps. In: WWW (2017)","DOI":"10.1145\/3038912.3052623"},{"key":"625_CR35","doi-asserted-by":"crossref","unstructured":"Omidvar-Tehrani, B., Amer-Yahia, S., Termier, A.: Interactive user group analysis. In: CIKM (2015)","DOI":"10.1145\/2806416.2806519"},{"issue":"1","key":"625_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.14778\/3015270.3015271","volume":"10(","author":"D Jiang","year":"2016","unstructured":"Jiang, D., Cai, Q., Chen, G., Jagadish, H.V., Ooi, B.C., Tan, K.-L., Tung, A.K.H.: Cohort query processing. Proc. VLDB Endow. 10((1), 1\u201312 (2016)","journal-title":"Proc. VLDB Endow."},{"key":"625_CR37","doi-asserted-by":"crossref","unstructured":"Ge, C., He, X., Ilyas, I.F., Machanavajjhala, A.: Accuracy-aware differentially private data exploration. In: SIGMOD, Apex (2019)","DOI":"10.1145\/3299869.3300092"},{"issue":"1","key":"625_CR38","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/BF01588971","volume":"14","author":"GL Nemhauser","year":"1978","unstructured":"Nemhauser, G.L., Wolsey, L.A., Fisher, M.L.: An analysis of approximations for maximizing submodular set functions\u2014i. Math. Program. 14(1), 265\u2013294 (1978)","journal-title":"Math. Program."},{"issue":"4","key":"625_CR39","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/BF02289527","volume":"31","author":"G Sabidussi","year":"1966","unstructured":"Sabidussi, G.: The centrality index of a graph. Psychometrika 31(4), 581\u2013603 (1966)","journal-title":"Psychometrika"},{"issue":"3","key":"625_CR40","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.socnet.2010.03.006","volume":"32","author":"T Opsahl","year":"2010","unstructured":"Opsahl, T., Agneessens, F., Skvoretz, J.: Node centrality in weighted networks: generalizing degree and shortest paths. Soc. Netw. 32(3), 245\u2013251 (2010)","journal-title":"Soc. Netw."},{"key":"625_CR41","unstructured":"Sharma, D., Kapoor, A., Deshpande, A.: On greedy maximization of entropy. In: International Conference on Machine Learning, pp. 1330\u20131338 (2015)"},{"key":"625_CR42","volume-title":"Mathematical Handbook for Scientists and Engineers: Definitions, Theorems, and Formulas for Reference and Review","author":"GA Korn","year":"2000","unstructured":"Korn, G.A., Korn, T.M.: Mathematical Handbook for Scientists and Engineers: Definitions, Theorems, and Formulas for Reference and Review. Courier Corporation, North Chelmsford (2000)"},{"key":"625_CR43","volume-title":"Elements of Information Theory","author":"TM Cover","year":"2012","unstructured":"Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley, Hoboken (2012)"},{"key":"625_CR44","unstructured":"Fekete, J.-D., Primet, R.: Progressive analytics: a computation paradigm for exploratory data analysis. arXiv preprint arXiv:1607.05162 (2016)"},{"issue":"3","key":"625_CR45","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1956.1056815","volume":"2","author":"G Miller","year":"1956","unstructured":"Miller, G.: Human memory and the storage of information. IRE Trans. Inf. Theory 2(3), 129\u2013137 (1956)","journal-title":"IRE Trans. Inf. Theory"},{"key":"625_CR46","doi-asserted-by":"crossref","unstructured":"Rozinat, A., de\u00a0Medeiros, A.K.A., G\u00fcnther, C.W., et\u00a0al.: The need for a process mining evaluation framework in research and practice. In: BPM. Springer, pp. 84\u201389 (2007)","DOI":"10.1007\/978-3-540-78238-4_10"},{"issue":"3","key":"625_CR47","doi-asserted-by":"publisher","first-page":"253","DOI":"10.2147\/ciia.2006.1.3.253","volume":"1","author":"G Sharma","year":"2006","unstructured":"Sharma, G., Goodwin, J.: Effect of aging on respiratory system physiology and immunology. Clin. Interv. Aging 1(3), 253 (2006)","journal-title":"Clin. Interv. Aging"},{"key":"625_CR48","volume-title":"Solved and Unsolved Problems in Number Theory","author":"D Shanks","year":"2001","unstructured":"Shanks, D.: Solved and Unsolved Problems in Number Theory, vol. 297. AMS, Providence (2001)"},{"key":"625_CR49","doi-asserted-by":"crossref","unstructured":"Bonchi, F., Giannotti, F., Lucchese, C., Orlando, S., Perego, R., Trasarti, R.: Conquest: a constraint-based querying system for exploratory pattern discovery. In: ICDE (2006)","DOI":"10.1109\/ICDE.2006.42"},{"key":"625_CR50","doi-asserted-by":"crossref","unstructured":"Yan, N., Li, C., Roy, S.B., Ramegowda, R., Das, G.: Facetedpedia: enabling query-dependent faceted search for Wikipedia. In: CIKM. ACM (2010)","DOI":"10.1145\/1871437.1871767"},{"issue":"12","key":"625_CR51","doi-asserted-by":"publisher","first-page":"1977","DOI":"10.14778\/3137765.3137824","volume":"10","author":"D Mottin","year":"2017","unstructured":"Mottin, D., Lissandrini, M., Velegrakis, Y., Palpanas, T.: New trends on exploratory methods for data analytics. Proc. VLDB Endow. 10(12), 1977\u20131980 (2017)","journal-title":"Proc. VLDB Endow."}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-020-00625-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00778-020-00625-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-020-00625-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T00:18:44Z","timestamp":1630023524000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00778-020-00625-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,27]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["625"],"URL":"https:\/\/doi.org\/10.1007\/s00778-020-00625-6","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"type":"print","value":"1066-8888"},{"type":"electronic","value":"0949-877X"}],"subject":[],"published":{"date-parts":[[2020,8,27]]},"assertion":[{"value":"10 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}