{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T05:52:45Z","timestamp":1771480365443,"version":"3.50.1"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:00:00Z","timestamp":1667520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>The Swiss classification of surgical interventions (CHOP) has to be used in daily practice by physicians to classify clinical procedures. Its purpose is to encode the delivered healthcare services for the sake of quality assurance and billing. For encoding a procedure, a code of a maximal of 6-digits has to be selected from the classification system, which is currently realized by a rule-based system composed of encoding experts and a manual search in the CHOP catalog. In this paper, we will investigate the possibility of automatic CHOP code generation based on a short query to enable automatic support of manual classification. The wide and deep hierarchy of CHOP and the differences between text used in queries and catalog descriptions are two apparent obstacles for training and deploying a learning-based algorithm. Because of these challenges, there is a need for an appropriate classification approach. We evaluate different strategies (multi-class non-terminal and per-node classifications) with different configurations so that a flexible modular solution with high accuracy and efficiency can be provided. The results clearly show that the per-node binary classification outperforms the non-terminal multi-class classification with an F1-micro measure between 92.6 and 94%. The hierarchical prediction based on per-node binary classifiers achieved a high exact match by the single code assignment on the 5-fold cross-validation. In conclusion, the hierarchical context from the CHOP encoding can be employed by both classifier training and representation learning. The hierarchical features have all shown improvement in the classification performances under different configurations, respectively: the stacked autoencoder and training examples aggregation using true path rules as well as the unified vocabulary space have largely increased the utility of hierarchical features. Additionally, the threshold adaption through Bayesian aggregation has largely increased the vertical reachability of the per node classification. All the trainable nodes can be triggered after the threshold adaption, while the F1 measures at code levels 3\u20136 have been increased from 6 to 89% after the threshold adaption.<\/jats:p>","DOI":"10.3389\/frai.2022.1000283","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T07:09:57Z","timestamp":1667545797000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Classification of user queries according to a hierarchical medical procedure encoding system using an ensemble classifier"],"prefix":"10.3389","volume":"5","author":[{"given":"Yihan","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kerstin","family":"Denecke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1109\/JBHI.2017.2743824","article-title":"Machine learning approaches on diagnostic term encoding with the icd for clinical documentation","volume":"22","author":"Atutxa","year":"2018","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B2","unstructured":"Operationen- und Prozedurenschl\u00fcssel2022"},{"key":"B3","unstructured":"BFSS.\n          Schweizerische Operationsklassifikation (CHOP)2022"},{"key":"B4","first-page":"11","article-title":"\u201cAutomatic matching of icd-10 codes to diagnoses in discharge letters,\u201d","volume-title":"Proceedings of the Second Workshop on Biomedical Natural Language Processing","author":"Boytcheva","year":"2011"},{"key":"B5","doi-asserted-by":"crossref","first-page":"3105","DOI":"10.18653\/v1\/2020.acl-main.282","article-title":"\u201cHyperCore: hyperbolic and co-graph representation for automatic ICD coding,\u201d","author":"Cao","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.ijmedinf.2018.09.021","article-title":"Towards automated clinical coding","volume":"120","author":"Catling","year":"2018","journal-title":"Int. J. Med. Inform"},{"key":"B7","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Int. Res"},{"key":"B8","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1197\/jamia.M2077","article-title":"Automating the assignment of diagnosis codes to patient encounters using example-based and machine learning techniques","volume":"13","author":"Chute","year":"2006","journal-title":"J. Am. Inform. Assoc"},{"key":"B9","article-title":"\u201cBayesian aggregation for hierarchical genre classification,\u201d","volume-title":"ISMIR","author":"DeCoro","year":"2007"},{"key":"B10","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.artmed.2018.10.001","article-title":"Towards automatic encoding of medical procedures using convolutional neural networks and autoencoders","author":"Deng","year":"2018","journal-title":"Artif. Intell. Med"},{"key":"B11","first-page":"24","article-title":"\u201cOn the selection of negative examples for hierarchical text categorization,\u201d","volume-title":"Proceedings of the 3rd Language Technology Conference","author":"Fagni","year":"2007"},{"key":"B12","doi-asserted-by":"publisher","first-page":"S10","DOI":"10.1186\/1471-2105-9-S3-S10","article-title":"Automatic construction of rule-based icd-9-cm coding systems","volume":"9","author":"Farkas","year":"2008","journal-title":"BMC Bioinform"},{"key":"B13","first-page":"547","article-title":"\u201cAutomatisierte klinische dokumentation aus elektronischen dokumenten (automated clinical documentation from electronic health records),\u201d","volume-title":"Medizinische Informatik, Biometrie und Epidemiologie, GMDS 2010, 55. Jahrestagung der GMDS","author":"Faulstich","year":"2010"},{"key":"B14","first-page":"279","article-title":"\u201cThree approaches to automatic assignment of icd-9-cm codes to radiology reports,\u201d","volume-title":"AMIA\u2026 Annual Symposium Proceedings","author":"Goldstein","year":"2007"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1016\/j.ins.2022.06.091","article-title":"Deconv-transformer (dect): A histopathological image classification model for breast cancer based on color deconvolution and transformer architecture","volume":"608","author":"He","year":"2022","journal-title":"Inf. Sci"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.05.024","article-title":"An empirical evaluation of deep learning for ICD-9 code assignment using MIMIC-III clinical notes","author":"Huang","year":"2018","journal-title":"CoRR"},{"key":"B17","doi-asserted-by":"publisher","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"Mimic-iii, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.3217\/jucs-017-07-1109","article-title":"A comparison of different retrieval strategies working on medical free texts","volume":"17","author":"Kreuzthaler","year":"2011","journal-title":"J. Univer. Comput. Sci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"8315","DOI":"10.1109\/IEMBS.2011.6092050","article-title":"Open-access mimic-ii database for intensive care research","volume":"2011","author":"Lee","year":"2011","journal-title":"Annu. Int. Conf. IEEE Eng. Med. Biol. Soc"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1007\/s40747-020-00261-1","article-title":"Directional correlation coefficient measures for pythagorean fuzzy sets: their applications to medical diagnosis and cluster analysis","volume":"7","author":"Lin","year":"2021","journal-title":"Complex Intell. Syst"},{"key":"B21","first-page":"84","article-title":"\u201cMachine learning and features selection for semi-automatic ICD-9-cm encoding,\u201d","volume-title":"Proceedings of the NAACL HLT 2010 Second Louhi Workshop on Text and Data Mining of Health Documents, Louhi '10","author":"Medori","year":"2010"},{"key":"B22","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1186\/s12859-017-1854-y","article-title":"Prediction of human phenotype ontology terms by means of hierarchical ensemble methods","volume":"18","author":"Notaro","year":"2017","journal-title":"BMC Bioinform"},{"key":"B23","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.ijmedinf.2017.12.007","article-title":"Inferred joint multigram models for medical term normalization according to ICD","volume":"110","author":"P\u00e9rez","year":"2018","journal-title":"I. J. Med. Inform"},{"key":"B24","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1136\/amiajnl-2013-002159","article-title":"Diagnosis code assignment: models and evaluation metrics","volume":"21","author":"Perotte","year":"2013","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"B25","first-page":"291","article-title":"Quantification of histochemical staining by color deconvolution","volume":"23","author":"Ruifrok","year":"2001","journal-title":"Anal. Quant. Cytol. Histol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10618-010-0175-9","article-title":"A survey of hierarchical classification across different application domains","volume":"22","author":"Silla","year":"2011","journal-title":"Data Min. Knowl. Discov"},{"key":"B27","first-page":"4018","article-title":"\u201cGeneralized zero-shot text classification for icd coding,\u201d","author":"Song","year":"2020","journal-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, International Joint Conferences on Artificial Intelligence Organization"},{"key":"B28","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1007\/978-3-642-02326-2_24","article-title":"\u201cTrue path rule hierarchical ensembles,\u201d","volume-title":"Multiple Classifier Systems","author":"Valentini","year":"2009"},{"key":"B29","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1109\/TCBB.2010.38","article-title":"True path rule hierarchical ensembles for genome-wide gene function prediction","volume":"8","author":"Valentini","year":"2011","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"B30","first-page":"6000","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS'17","author":"Vaswani","year":"2017"},{"key":"B31","doi-asserted-by":"crossref","first-page":"2321","DOI":"10.18653\/v1\/P18-1216","article-title":"\u201cJoint embedding of words and labels for text classification,\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Wang","year":"2018"},{"key":"B32","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1055\/s-0038-1635350","article-title":"Automated indexing based on snomed","volume":"24","author":"Wingert","year":"1984","journal-title":"Methods Inf. Med"},{"key":"B33","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/11527862_24","article-title":"\u201cLearning classifiers using hierarchically structured class taxonomies,\u201d","volume-title":"Abstraction, Reformulation and Approximation","author":"Wu","year":"2005"},{"key":"B34","doi-asserted-by":"crossref","first-page":"1074","DOI":"10.1145\/3394486.3403151","article-title":"\u201cCorrelation networks for extreme multi-label text classification,\u201d","volume-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '20","author":"Xun","year":"2020"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11926","article-title":"An unsupervised model with attention autoencoders for question retrieval","author":"Zhang","year":"2018","journal-title":"ArXiv"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1000283\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T07:10:39Z","timestamp":1667545839000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1000283\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,4]]},"references-count":35,"alternative-id":["10.3389\/frai.2022.1000283"],"URL":"https:\/\/doi.org\/10.3389\/frai.2022.1000283","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,4]]},"article-number":"1000283"}}