{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T03:30:05Z","timestamp":1788838205484,"version":"build-2803163510"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T00:00:00Z","timestamp":1656979200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T00:00:00Z","timestamp":1656979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-022-01252-4","type":"journal-article","created":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T09:14:01Z","timestamp":1657012441000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Encoding High-Dimensional Procedure Codes for Healthcare Fraud Detection"],"prefix":"10.1007","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3511-0624","authenticated-orcid":false,"given":"Justin M.","family":"Johnson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,5]]},"reference":[{"issue":"4","key":"1252_CR1","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1136\/svn-2017-000101","volume":"2","author":"F Jiang","year":"2017","unstructured":"Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y, Dong Q, Shen H, Wang Y. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230\u201343.","journal-title":"Stroke Vasc Neurol"},{"issue":"1","key":"1252_CR2","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1111\/cts.12884","volume":"14","author":"KB Johnson","year":"2021","unstructured":"Johnson KB, Wei W-Q, Weeraratne D, Frisse ME, Misulis K, Rhee K, Zhao J, Snowdon JL. Precision medicine, AI, and the future of personalized health care. Clin Transl Sci. 2021;14(1):86\u201393. https:\/\/doi.org\/10.1111\/cts.12884.","journal-title":"Clin Transl Sci"},{"key":"1252_CR3","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-981-13-7166-0_16","volume-title":"Information and communication technology for sustainable development","author":"AM Hafiz","year":"2020","unstructured":"Hafiz AM, Bhat GM. A survey of deep learning techniques for medical diagnosis. In: Tuba M, Akashe S, Joshi A, editors. Information and communication technology for sustainable development. Singapore: Springer; 2020. p. 161\u201370."},{"key":"1252_CR4","doi-asserted-by":"publisher","DOI":"10.1080\/03772063.2019.1649215","author":"PR Jeyaraj","year":"2019","unstructured":"Jeyaraj PR, Nadar ERS. Smart-monitor: patient monitoring system for iot-based healthcare system using deep learning. IETE J Res. 2019. https:\/\/doi.org\/10.1080\/03772063.2019.1649215.","journal-title":"IETE J Res"},{"key":"1252_CR5","doi-asserted-by":"publisher","unstructured":"Mulani J, Heda S, Tumdi K, Patel J, Chhinkaniwala H, Patel J. In: Dash S, Acharya BR, Mittal M, Abraham A, Kelemen A, editors. Deep reinforcement learning based personalized health recommendations. Cham: Springer; 2020. p. 231\u201355. https:\/\/doi.org\/10.1007\/978-3-030-33966-1_12.","DOI":"10.1007\/978-3-030-33966-1_12"},{"issue":"1","key":"1252_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-017-0008-y","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, Liu PJ, Liu X, Marcus J, Sun M, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018;1(1):1\u201310.","journal-title":"NPJ Digit Med"},{"issue":"1","key":"1252_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-018-0045-1","volume":"1","author":"A Sadilek","year":"2018","unstructured":"Sadilek A, Caty S, DiPrete L, Mansour R, Schenk T, Bergtholdt M, Jha A, Ramaswami P, Gabrilovich E. Machine-learned epidemiology: real-time detection of foodborne illness at scale. NPJ Digit Med. 2018;1(1):1\u20137.","journal-title":"NPJ Digit Med"},{"key":"1252_CR8","unstructured":"U.S. Government, U.S. Centers for Medicare & Medicaid Services: The Official U.S. Government Site for Medicare. https:\/\/www.medicare.gov\/. Accessed 01 Oct 2021."},{"key":"1252_CR9","unstructured":"Centers for Medicare & Medicaid Services: Medicare Enrollment Dashboard. https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Dashboard\/Medicare-Enrollment\/Enrollment%20Dashboard.html. Accessed 15 Oct 2020"},{"key":"1252_CR10","unstructured":"Centers For Medicare & Medicaid Services: Trustees Report & Trust Funds. https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/ReportsTrustFunds\/index.html. Accessed 15 Oct 2020"},{"key":"1252_CR11","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1377\/hlthaff.28.5.1351","volume":"28","author":"L Morris","year":"2009","unstructured":"Morris L. Combating fraud in health care: an essential component of any cost containment strategy. Health Aff (Project Hope). 2009;28:1351\u20136. https:\/\/doi.org\/10.1377\/hlthaff.28.5.1351.","journal-title":"Health Aff (Project Hope)"},{"key":"1252_CR12","unstructured":"Medicare Fraud & Abuse: Prevention, Detection, and Reporting. Centers for Medicare & Medicaid Services (2017). https:\/\/www.cms.gov\/Outreach-and-Education\/Medicare-Learning-Network-MLN\/MLNProducts\/Downloads\/Fraud_and_Abuse.pdf. Accessed 15 Oct 2020"},{"key":"1252_CR13","unstructured":"Medicare Provider Utilization and Payment Data. Centers for Medicare & Medicaid Services (2021). https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/index. Accessed 01 Oct 2021"},{"key":"1252_CR14","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2016","unstructured":"Witten IH, Frank E, Hall MA, Pal CJ. Data mining: practical machine learning tools and techniques. 4th ed. San Francisco: Morgan Kaufmann Publishers Inc.; 2016.","edition":"4"},{"key":"1252_CR15","doi-asserted-by":"publisher","unstructured":"Chen L. In: Liu L, \u00d6zsu MT, editors. Curse of dimensionality. Boston: Springer; 2009. p. 545\u2013546. https:\/\/doi.org\/10.1007\/978-0-387-39940-9_133","DOI":"10.1007\/978-0-387-39940-9_133"},{"issue":"1","key":"1252_CR16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s40537-018-0138-3","volume":"5","author":"M Herland","year":"2018","unstructured":"Herland M, Khoshgoftaar TM, Bauder RA. Big data fraud detection using multiple medicare data sources. J Big Data. 2018;5(1):29. https:\/\/doi.org\/10.1186\/s40537-018-0138-3.","journal-title":"J Big Data"},{"key":"1252_CR17","doi-asserted-by":"crossref","unstructured":"Johnson JM, Khoshgoftaar TM. Hcpcs2vec: Healthcare procedure embeddings for medicare fraud prediction. In: 2020 IEEE 6th International Conference on Collaboration and Internet Computing (CIC); 2020.","DOI":"10.1109\/CIC50333.2020.00026"},{"key":"1252_CR18","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu T-Y. Lightgbm: a highly efficient gradient boosting decision tree. In: Proceedings of the 31st international conference on neural information processing systems. NIPS\u201917. Curran Associates Inc., Red Hook, NY, USA; 2017. p. 3149\u20133157."},{"key":"1252_CR19","unstructured":"Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. Catboost: unbiased boosting with categorical features. In: Proceedings of the 32nd international conference on neural information processing systems. NIPS\u201918. Curran Associates Inc., Red Hook, NY, USA; 2018. p. 6639\u20136649."},{"key":"1252_CR20","doi-asserted-by":"crossref","unstructured":"Johnson JM, Khoshgoftaar TM. Encoding techniques for high-cardinality features and ensemble learners. In: 2021 IEEE 22nd international conference on information reuse and integration for data science (IRI); 2021.","DOI":"10.1109\/IRI51335.2021.00055"},{"key":"1252_CR21","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. Xgboost. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"1252_CR22","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep learning. MIT Press; 2016. http:\/\/www.deeplearningbook.org"},{"issue":"2","key":"1252_CR23","doi-asserted-by":"publisher","first-page":"99","DOI":"10.2307\/3001913","volume":"5","author":"JW Tukey","year":"1949","unstructured":"Tukey JW. Comparing individual means in the analysis of variance. Biometrics. 1949;5(2):99\u2013114.","journal-title":"Biometrics"},{"key":"1252_CR24","doi-asserted-by":"publisher","unstructured":"Akbar NA, Sunyoto A, Rudyanto\u00a0Arief M, Caesarendra W. Improvement of decision tree classifier accuracy for healthcare insurance fraud prediction by using extreme gradient boosting algorithm. In: 2020 International conference on informatics, multimedia, cyber and information system (ICIMCIS); 2020. p. 110\u2013114. https:\/\/doi.org\/10.1109\/ICIMCIS51567.2020.9354286","DOI":"10.1109\/ICIMCIS51567.2020.9354286"},{"key":"1252_CR25","unstructured":"Rohit AG. Healthcare provider fraud detection analysis. https:\/\/www.kaggle.com\/rohitrox\/medical-provider-fraud-detection\/data. Accessed 01 Oct 2021."},{"key":"1252_CR26","doi-asserted-by":"publisher","unstructured":"Bauder R, da Rosa R, Khoshgoftaar T. Identifying medicare provider fraud with unsupervised machine learning. In: 2018 IEEE international conference on information reuse and integration (IRI); 2018. p. 285\u2013292. https:\/\/doi.org\/10.1109\/IRI.2018.00051","DOI":"10.1109\/IRI.2018.00051"},{"key":"1252_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.urology.2014.11.054","author":"J Ko","year":"2015","unstructured":"Ko J, Chalfin H, Trock B, Feng Z, Humphreys E, Park S-W, Carter B, Frick KD, Han M. Variability in medicare utilization and payment among urologists. Urology. 2015. https:\/\/doi.org\/10.1016\/j.urology.2014.11.054.","journal-title":"Urology"},{"issue":"1","key":"1252_CR28","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s10729-018-9460-8","volume":"23","author":"M Herland","year":"2020","unstructured":"Herland M, Bauder RA, Khoshgoftaar TM. Approaches for identifying US medicare fraud in provider claims data. Health Care Manag Sci. 2020;23(1):2\u201319. https:\/\/doi.org\/10.1007\/s10729-018-9460-8.","journal-title":"Health Care Manag Sci"},{"key":"1252_CR29","doi-asserted-by":"publisher","unstructured":"Branting LK, Reeder F, Gold J, Champney T. Graph analytics for healthcare fraud risk estimation. In: 2016 IEEE\/ACM international conference on advances in social networks analysis and mining (ASONAM); 2016. p. 845\u2013851. https:\/\/doi.org\/10.1109\/ASONAM.2016.7752336","DOI":"10.1109\/ASONAM.2016.7752336"},{"key":"1252_CR30","doi-asserted-by":"crossref","unstructured":"Chandola V, Sukumar SR, Schryver JC. Knowledge discovery from massive healthcare claims data. In: KDD; 2013.","DOI":"10.1145\/2487575.2488205"},{"key":"1252_CR31","first-page":"41","volume":"2016","author":"Y Choi","year":"2016","unstructured":"Choi Y, Chiu CY-I, Sontag DA. Learning low-dimensional representations of medical concepts. AMIA Summits Transl Sci Proc. 2016;2016:41\u201350.","journal-title":"AMIA Summits Transl Sci Proc"},{"key":"1252_CR32","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.dss.2015.02.007","volume":"72","author":"J Moeyersoms","year":"2015","unstructured":"Moeyersoms J, Martens D. Including high-cardinality attributes in predictive models: a case study in churn prediction in the energy sector. Decis Support Syst. 2015;72:72\u201381. https:\/\/doi.org\/10.1016\/j.dss.2015.02.007.","journal-title":"Decis Support Syst"},{"key":"1252_CR33","doi-asserted-by":"publisher","unstructured":"De\u00a0Vine L, Zuccon G, Koopman B, Sitbon L, Bruza P. Medical semantic similarity with a neural language model. In: Proceedings of the 23rd ACM international conference on conference on information and knowledge management. CIKM\u201914. New York: Association for Computing Machinery; 2014. p. 1819\u20131822. https:\/\/doi.org\/10.1145\/2661829.2661974","DOI":"10.1145\/2661829.2661974"},{"key":"1252_CR34","doi-asserted-by":"crossref","unstructured":"Beam AL, Kompa B, Fried I, Palmer NP, Shi X, Cai T, Kohane IS. Clinical concept embeddings learned from massive sources of medical data; 2018. arXiv:abs\/1804.01486.","DOI":"10.1142\/9789811215636_0027"},{"key":"1252_CR35","unstructured":"Centers For Medicare & Medicaid Services: Medicare Provider Utilization and Payment Data. https:\/\/www.cms.gov\/research-statistics-data-and-systems\/statistics-trends-and-reports\/medicare-provider-charge-data. Accessed 15 Oct 2020."},{"key":"1252_CR36","unstructured":"Office of Inspector General: LEIE Downloadable Databases. https:\/\/oig.hhs.gov\/exclusions\/exclusions_list.asp. Accessed 01 Oct 2021."},{"key":"1252_CR37","unstructured":"Office of Inspector General: Exclusion Authorities. https:\/\/oig.hhs.gov\/exclusions\/authorities.asp. Accessed 15 Oct 2020"},{"key":"1252_CR38","doi-asserted-by":"publisher","unstructured":"Bauder RA, Khoshgoftaar TM. A novel method for fraudulent medicare claims detection from expected payment deviations (application paper). In: 2016 IEEE 17th international conference on information reuse and integration (IRI); 2016. p. 11\u201319. https:\/\/doi.org\/10.1109\/IRI.2016.11","DOI":"10.1109\/IRI.2016.11"},{"issue":"4","key":"1252_CR39","first-page":"7","volume":"175","author":"K Potdar","year":"2017","unstructured":"Potdar K, Pardawala TS, Pai CD. A comparative study of categorical variable encoding techniques for neural network classifiers. Int J Comput Appl. 2017;175(4):7\u20139.","journal-title":"Int J Comput Appl"},{"issue":"284","key":"1252_CR40","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1080\/01621459.1958.10501479","volume":"53","author":"WD Fisher","year":"1958","unstructured":"Fisher WD. On grouping for maximum homogeneity. J Am Stat Assoc. 1958;53(284):789\u201398. https:\/\/doi.org\/10.1080\/01621459.1958.10501479.","journal-title":"J Am Stat Assoc"},{"key":"1252_CR41","unstructured":"Mikolov T, Chen K, Corrado GS, Dean J. Efficient estimation of word representations in vector space; 2013. CoRR arXiv:abs\/1301.3781."},{"issue":"2\u20133","key":"1252_CR42","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1080\/00437956.1954.11659520","volume":"10","author":"ZS Harris","year":"1954","unstructured":"Harris ZS. Distributional structure. Word. 1954;10(2\u20133):146\u201362. https:\/\/doi.org\/10.1080\/00437956.1954.11659520.","journal-title":"Word"},{"key":"1252_CR43","unstructured":"\u0158eh\u016f\u0159ek R, Sojka P. Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks. ELRA, Valletta, Malta; 2010. p. 45\u201350. http:\/\/is.muni.cz\/publication\/884893\/en"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01252-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-022-01252-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01252-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T15:17:23Z","timestamp":1663600643000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-022-01252-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,5]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["1252"],"URL":"https:\/\/doi.org\/10.1007\/s42979-022-01252-4","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,5]]},"assertion":[{"value":"17 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2022","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 that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}],"article-number":"362"}}