{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T11:53:48Z","timestamp":1773316428461,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"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":["J Supercomput"],"DOI":"10.1007\/s11227-026-08368-x","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:52:58Z","timestamp":1773251578000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring clinical pathways: a novel BERTopic framework for dynamic analysis using temporal binning and semantic drift"],"prefix":"10.1007","volume":"82","author":[{"given":"Iqra","family":"Mehmood","sequence":"first","affiliation":[]},{"given":"Zoya","family":"Zahra","sequence":"additional","affiliation":[]},{"given":"Ijaz","family":"Hussain","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"issue":"1","key":"8368_CR1","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s12911-022-01756-2","volume":"22","author":"M Manktelow","year":"2022","unstructured":"Manktelow M, Iftikhar A, Bucholc M, McCann M, O\u2019Kane M (2022) Clinical and operational insights from data-driven care pathway mapping: a systematic review. BMC Med Inform Decis Mak 22(1):43. https:\/\/doi.org\/10.1186\/s12911-022-01756-2","journal-title":"BMC Med Inform Decis Mak"},{"key":"8368_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.103994","volume":"127","author":"J Munoz-Gama","year":"2022","unstructured":"Munoz-Gama J, Martin N, Fernandez-Llatas C, Johnson OA, Sep\u00falveda M, Helm E, Galvez-Yanjari V, Rojas E, Martinez-Millana A, Aloini D et al (2022) Process mining for healthcare: characteristics and challenges. J Biomed Inform 127:103994. https:\/\/doi.org\/10.1016\/j.jbi.2022.103994","journal-title":"J Biomed Inform"},{"key":"8368_CR3","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.jbi.2016.04.007","volume":"61","author":"E Rojas","year":"2016","unstructured":"Rojas E, Munoz-Gama J, Sep\u00falveda M, Capurro D (2016) Process mining in healthcare: a literature review. J Biomed Inform 61:224\u2013236. https:\/\/doi.org\/10.1016\/j.jbi.2016.04.007","journal-title":"J Biomed Inform"},{"key":"8368_CR4","unstructured":"Grootendorst M (2022) Bertopic: neural topic modeling with a class-based tf-idf procedure. arxiv: 2203.05794 [cs.CL]"},{"key":"8368_CR5","doi-asserted-by":"publisher","unstructured":"Blei DM, Lafferty JD (2006) Dynamic topic models. In: Proceedings of the 23rd International Conference on Machine Learning. ICML \u201906. Association for Computing Machinery, New York, NY, USA, pp 113\u2013120. https:\/\/doi.org\/10.1145\/1143844.1143859","DOI":"10.1145\/1143844.1143859"},{"issue":"1","key":"8368_CR6","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1038\/s41746-024-01286-3","volume":"7","author":"ST O\u2019Neil","year":"2024","unstructured":"O\u2019Neil ST, Madlock-Brown C, Wilkins KJ, McGrath BM, Davis HE, Assaf GS, Wei H, Zareie P, French ET, Loomba J et al (2024) Finding long-covid: temporal topic modeling of electronic health records from the n3c and recover programs. NPJ Digit Med 7(1):296. https:\/\/doi.org\/10.1038\/s41746-024-01286-3","journal-title":"NPJ Digit Med"},{"key":"8368_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104746","volume":"160","author":"L Muyama","year":"2024","unstructured":"Muyama L, Neuraz A, Coulet A (2024) Machine learning approaches for the discovery of clinical pathways from patient data: a systematic review. J Biomed Inform 160:104746. https:\/\/doi.org\/10.1016\/j.jbi.2024.104746","journal-title":"J Biomed Inform"},{"issue":"3","key":"8368_CR8","doi-asserted-by":"publisher","first-page":"41","DOI":"10.3390\/biotech11030041","volume":"11","author":"I Scarpino","year":"2022","unstructured":"Scarpino I, Zucco C, Vallelunga R, Luzza F, Cannataro M (2022) Investigating topic modeling techniques to extract meaningful insights in Italian long covid narration. BioTech (Basel) 11(3):41. https:\/\/doi.org\/10.3390\/biotech11030041","journal-title":"BioTech (Basel)"},{"key":"8368_CR9","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.jbi.2013.09.003","volume":"47","author":"Z Huang","year":"2014","unstructured":"Huang Z, Dong W, Ji L, Gan C, Lu X, Duan H (2014) Discovery of clinical pathway patterns from event logs using probabilistic topic models. J Biomed Inform 47:39\u201357. https:\/\/doi.org\/10.1016\/j.jbi.2013.09.003","journal-title":"J Biomed Inform"},{"key":"8368_CR10","doi-asserted-by":"publisher","unstructured":"Wang Y, Wang M, Chen Y, Tao S, Guo J, Su C, Zhang M, Yang H (2022) Capture human disagreement distributions by calibrated networks for natural language inference, pp. 1524\u20131535. https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.120","DOI":"10.18653\/v1\/2022.findings-acl.120"},{"key":"8368_CR11","doi-asserted-by":"publisher","unstructured":"Martinis MC, Zucco C, Amodeo A, Facente V, Greco F, Cannataro M (2024) Evolution of medical reports over time: an analysis using dynamic topic modeling, pp. 6921\u20136928. https:\/\/doi.org\/10.1109\/BIBM62325.2024.10821802","DOI":"10.1109\/BIBM62325.2024.10821802"},{"issue":"1","key":"8368_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/20476965.2019.1652547","volume":"10","author":"E Aspland","year":"2021","unstructured":"Aspland E, Gartner D, Harper P (2021) Clinical pathway modelling: a literature review. Health Syst 10(1):1\u201323. https:\/\/doi.org\/10.1080\/20476965.2019.1652547","journal-title":"Health Syst"},{"key":"8368_CR13","doi-asserted-by":"publisher","unstructured":"Mersha MA, Gemeda yigezu M, Kalita J, (2024) Semantic-driven topic modeling using transformer-based embeddings and clustering algorithms. Procedia Comput Sci 244:121\u2013132. https:\/\/doi.org\/10.1016\/j.procs.2024.10.185","DOI":"10.1016\/j.procs.2024.10.185"},{"key":"8368_CR14","doi-asserted-by":"publisher","unstructured":"Zhang D, Lee WS (2006) Extracting key-substring-group features for text classification. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD \u201906. Association for Computing Machinery, New York, NY, USA, pp. 474\u2013483. https:\/\/doi.org\/10.1145\/1150402.1150455","DOI":"10.1145\/1150402.1150455"},{"issue":"12","key":"8368_CR15","doi-asserted-by":"publisher","first-page":"40102","DOI":"10.2196\/40102","volume":"10","author":"C Meaney","year":"2022","unstructured":"Meaney C, Escobar M, Stukel TA, Austin PC, Jaakkimainen L (2022) Comparison of methods for estimating temporal topic models from primary care clinical text data: retrospective closed cohort study. JMIR Med Inform 10(12):40102. https:\/\/doi.org\/10.2196\/40102","journal-title":"JMIR Med Inform"},{"key":"8368_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.103995","volume":"127","author":"E De Roock","year":"2022","unstructured":"De Roock E, Martin N (2022) Process mining in healthcare - an updated perspective on the state of the art. J Biomed Inform 127:103995. https:\/\/doi.org\/10.1016\/j.jbi.2022.103995","journal-title":"J Biomed Inform"},{"key":"8368_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122435","volume":"239","author":"G Park","year":"2024","unstructured":"Park G, Cho M, Lee J (2024) Leveraging machine learning for automatic topic discovery and forecasting of process mining research: a literature review. Expert Syst Appl 239:122435. https:\/\/doi.org\/10.1016\/j.eswa.2023.122435","journal-title":"Expert Syst Appl"},{"key":"8368_CR18","unstructured":"McInnes L, Healy J, Melville J (2020) Umap: Uniform manifold approximation and projection for dimension reduction. arxiv: 1802.03426 [stat.ML]"},{"issue":"1","key":"8368_CR19","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s10916-024-02049-z","volume":"48","author":"M Hosseini","year":"2024","unstructured":"Hosseini M, Hosseini M, Javidan R (2024) Leveraging large language models for clinical abbreviation disambiguation. J Med Syst 48(1):27. https:\/\/doi.org\/10.1007\/s10916-024-02049-z","journal-title":"J Med Syst"},{"key":"8368_CR20","doi-asserted-by":"publisher","unstructured":"Campello RJGB, Moulavi D, Sander J (2013) Density-based clustering based on hierarchical density estimates. In: Pei J, Tseng VS, Cao L, Motoda H, Xu G (eds) Advances in knowledge discovery and data mining. Springer, Berlin, Heidelberg, pp. 160\u2013172. https:\/\/doi.org\/10.1007\/978-3-642-37456-2_14","DOI":"10.1007\/978-3-642-37456-2_14"},{"key":"8368_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100044","volume":"6","author":"E Chagnon","year":"2023","unstructured":"Chagnon E, Pandolfi R, Donatelli J, Ushizima D (2023) Benchmarking topic models on scientific articles using Berteley. Nat Lang Process J 6:100044. https:\/\/doi.org\/10.1016\/j.nlp.2023.100044","journal-title":"Nat Lang Process J"},{"key":"8368_CR22","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare14020282","author":"I Mehmood","year":"2026","unstructured":"Mehmood I, Zahra Z, Iqbal S, Qahmash A, Hussain I (2026) A systematic review of topic modeling techniques for electronic health records. Healthcare. https:\/\/doi.org\/10.3390\/healthcare14020282","journal-title":"Healthcare"},{"issue":"suppl 1","key":"8368_CR23","doi-asserted-by":"publisher","first-page":"5228","DOI":"10.1073\/pnas.0307752101","volume":"101","author":"TL Griffiths","year":"2004","unstructured":"Griffiths TL, Steyvers M (2004) Finding scientific topics. Proc Natl Acad Sci 101(suppl 1):5228\u20135235. https:\/\/doi.org\/10.1073\/pnas.0307752101","journal-title":"Proc Natl Acad Sci"},{"issue":"1","key":"8368_CR24","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s12911-024-02418-1","volume":"24","author":"W Li","year":"2024","unstructured":"Li W, Min X, Ye P, Xie W, Zhao D (2024) Temporal topic model for clinical pathway mining from electronic medical records. BMC Med Inform Decis Mak 24(1):20. https:\/\/doi.org\/10.1186\/s12911-024-02418-1","journal-title":"BMC Med Inform Decis Mak"},{"key":"8368_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119921","volume":"656","author":"Y Liu","year":"2024","unstructured":"Liu Y, Zhang Y-A, Zeng M, Zhao J (2024) A novel distance measure based on dynamic time warping to improve time series classification. Inf Sci 656:119921. https:\/\/doi.org\/10.1016\/j.ins.2023.119921","journal-title":"Inf Sci"},{"issue":"13","key":"8368_CR26","doi-asserted-by":"publisher","first-page":"19003","DOI":"10.1007\/s11227-024-06247-x","volume":"80","author":"O Ozyurt","year":"2024","unstructured":"Ozyurt O, \u00d6zk\u00f6se H, Ayaz A (2024) Evaluating the latest trends of industry 4.0 based on lda topic model. J Supercomput 80(13):19003\u201319030. https:\/\/doi.org\/10.1007\/s11227-024-06247-x","journal-title":"J Supercomput"},{"key":"8368_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06659-9","author":"R Gu","year":"2024","unstructured":"Gu R, Lin L (2024) Application of latent Dirichlet allocation and autoencoder to real estate datasets. J Supercomput. https:\/\/doi.org\/10.1007\/s11227-024-06659-9","journal-title":"J Supercomput"},{"issue":"9","key":"8368_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1012417","volume":"20","author":"D Steiert","year":"2024","unstructured":"Steiert D, Wittig C, Banerjee P, Preissner R, Szulcek R (2024) An exploration into cteph medications: combining natural language processing, embedding learning, in vitro models, and real-world evidence for drug repurposing. PLoS Comput Biol 20(9):1\u201320. https:\/\/doi.org\/10.1371\/journal.pcbi.1012417","journal-title":"PLoS Comput Biol"},{"key":"8368_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107754","author":"J Gao","year":"2025","unstructured":"Gao J, Yu H, Cheung Y-M, Cao J, Wong RC-W, Zhang Y (2025) Shaping pre-trained language models for task-specific embedding generation via consistency calibration. Neural Netw. https:\/\/doi.org\/10.1016\/j.neunet.2025.107754","journal-title":"Neural Netw"},{"key":"8368_CR30","doi-asserted-by":"publisher","unstructured":"Gao J, Wu H, Cheung Y-M, Cao J, Yu H, Zhang Y (2025) Mitigating forgetting in adapting pre-trained language models to text processing tasks via consistency alignment. In: Proceedings of the ACM on Web Conference 2025. WWW \u201925. Association for Computing Machinery, New York, NY, USA, pp. 3492\u20133504. https:\/\/doi.org\/10.1145\/3696410.3714687","DOI":"10.1145\/3696410.3714687"},{"key":"8368_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsim.2025.05.001","author":"C Li","year":"2025","unstructured":"Li C, Hu X (2025) Medical artificial intelligence in scholarly and public perspective: Bertopic-based analysis of topic-sentiment collaborative mining. Data Sci Informetrics. https:\/\/doi.org\/10.1016\/j.dsim.2025.05.001","journal-title":"Data Sci Informetrics"},{"key":"8368_CR32","doi-asserted-by":"publisher","DOI":"10.3390\/s24237843","author":"C L\u00e1zaro","year":"2024","unstructured":"L\u00e1zaro C, Angulo C (2024) Using umap for partially synthetic healthcare tabular data generation and validation. Sensors. https:\/\/doi.org\/10.3390\/s24237843","journal-title":"Sensors"},{"key":"8368_CR33","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1146\/annurev-biodatasci-103123-094729","volume":"8","author":"J Kauffman","year":"2025","unstructured":"Kauffman J, Miotto R, Klang E, Costa A, Norgeot B, Zitnik M, Khader S, Wang F, Nadkarni GN, Glicksberg BS (2025) Embedding methods for electronic health record research. Annu Rev Biomed Data Sci 8:563\u2013590. https:\/\/doi.org\/10.1146\/annurev-biodatasci-103123-094729","journal-title":"Annu Rev Biomed Data Sci"},{"issue":"1","key":"8368_CR34","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1017\/S1351324923000049","volume":"30","author":"M Fern\u00e1ndez-Pichel","year":"2024","unstructured":"Fern\u00e1ndez-Pichel M, Prada-Corral M, Losada DE, Pichel JC, Gamallo P (2024) An unsupervised perplexity-based method for boilerplate removal. Nat Lang Eng 30(1):132\u2013149. https:\/\/doi.org\/10.1017\/S1351324923000049","journal-title":"Nat Lang Eng"},{"key":"8368_CR35","doi-asserted-by":"publisher","unstructured":"R\u00f6der M, Both A, Hinneburg A (2015) Exploring the space of topic coherence measures, 399\u2013408. https:\/\/doi.org\/10.1145\/2684822.2685324","DOI":"10.1145\/2684822.2685324"},{"key":"8368_CR36","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53\u201365. https:\/\/doi.org\/10.1016\/0377-0427(87)90125-7","journal-title":"J Comput Appl Math"},{"key":"8368_CR37","doi-asserted-by":"crossref","unstructured":"Syahrial S, Afidh RPF (2024) Fine-tuning topic modelling: a coherence-focused analysis of correlated topic models. Infolitika J Data Sci 2(2):82\u201387. https:\/\/doi.org\/10.60084\/ijds.v2i2.236","DOI":"10.60084\/ijds.v2i2.236"},{"key":"8368_CR38","doi-asserted-by":"publisher","unstructured":"Fang A, Macdonald C, Ounis I, Habel P (2016) Using word embedding to evaluate the coherence of topics from twitter data, pp 1057\u20131060. https:\/\/doi.org\/10.1145\/2911451.2914729","DOI":"10.1145\/2911451.2914729"},{"key":"8368_CR39","doi-asserted-by":"publisher","unstructured":"Choubey PK, Currey A, Mathur P, Dinu G (2021) GFST: Gender-filtered self-training for more accurate gender in translation, pp 1640\u20131654. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.123","DOI":"10.18653\/v1\/2021.emnlp-main.123"},{"issue":"1","key":"8368_CR40","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s10916-025-02188-x","volume":"49","author":"C Liu","year":"2025","unstructured":"Liu C, Zhang H, Zheng Z, Liu W, Gu C, Lan Q, Zhang W, Yang J (2025) Chatoct: embedded clinical decision support systems for optical coherence tomography in offline and resource-limited settings. J Med Syst 49(1):59. https:\/\/doi.org\/10.1007\/s10916-025-02188-x","journal-title":"J Med Syst"},{"key":"8368_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107039","volume":"223","author":"N Shi","year":"2021","unstructured":"Shi N, Yu L, Sun L, Wang L, Lin C, Zhang R (2021) Deep heterogeneous network for temporal set prediction. Knowl-Based Syst 223:107039. https:\/\/doi.org\/10.1016\/j.knosys.2021.107039","journal-title":"Knowl-Based Syst"},{"issue":"1","key":"8368_CR42","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-012012","volume":"7","author":"RG Jackson","year":"2017","unstructured":"Jackson RG et al (2017) Natural language processing to extract symptoms of severe mental illness from clinical text: the clinical record interactive search comprehensive data extraction (cris-code) project. BMJ Open 7(1):012012. https:\/\/doi.org\/10.1136\/bmjopen-2016-012012","journal-title":"BMJ Open"},{"issue":"4","key":"8368_CR43","doi-asserted-by":"publisher","first-page":"38799","DOI":"10.2196\/38799","volume":"9","author":"Y Shan","year":"2022","unstructured":"Shan Y et al (2022) Public trust in artificial intelligence applications in mental health care: topic modeling analysis. JMIR Hum Factors 9(4):38799. https:\/\/doi.org\/10.2196\/38799","journal-title":"JMIR Hum Factors"},{"key":"8368_CR44","doi-asserted-by":"publisher","first-page":"63476","DOI":"10.2196\/63476","volume":"26","author":"S-H Ahn","year":"2024","unstructured":"Ahn S-H et al (2024) Discovering time-varying public interest for covid-19 case prediction in south korea using search engine queries: Infodemiology study. J Med Internet Res 26:63476. https:\/\/doi.org\/10.2196\/63476","journal-title":"J Med Internet Res"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08368-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-026-08368-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08368-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:53:01Z","timestamp":1773251581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-026-08368-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":44,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["8368"],"URL":"https:\/\/doi.org\/10.1007\/s11227-026-08368-x","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]},"assertion":[{"value":"23 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human ethics and consent to participate"}},{"value":"We would like to inform you that our study did not require approval from an ethics committee or an Institutional Review Board (IRB) as it does not involve human participants or animal subjects.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical trial number"}}],"article-number":"242"}}