{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T10:34:16Z","timestamp":1787567656953,"version":"build-2736575974"},"reference-count":37,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003593","name":"National Council for Scientific and Technological Development","doi-asserted-by":"publisher","award":["444552\/2024-3"],"award-info":[{"award-number":["444552\/2024-3"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"award":["444552\/2024-3"],"award-info":[{"award-number":["444552\/2024-3"]}],"id":[{"id":"https:\/\/ror.org\/03swz6y49","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: Free-text veterinary pathology diagnoses contain essential information for cancer registration but are difficult to convert into standardized ontology-based codes because of linguistic variability, contextual modifiers, and large ontology search spaces. This study evaluated a hybrid lexical\u2013semantic architecture for the automated assignment of Vet-ICD-O-Canine-1 morphology codes. Methods: A retrospective single-registry benchmark included 211 diagnoses from the S\u00e3o Paulo Animal Cancer Registry. Of these, 190 contained sufficient morphological information for expert-reviewed reference coding, whereas 21 generic or insufficiently specified descriptions were retained as an exploratory challenge subset. Fuzzy lexical matching retrieved Top-10, Top-20, or Top-30 candidates from the complete 971-entry morphology ontology, followed by semantic selection using Claude Haiku 4.5 and structured JSON output. Performance and computational efficiency were compared to direct full-ontology inference. Results: Among the evaluated fuzzy metrics, token_set_ratio achieved the highest Top-30 reference-code retrieval rate of 89.5%. End-to-end exact-match agreement increased from 73.7% with Top-10 to 79.5% with Top-20 and 85.8% with Top-30 (95% CI, 80.1\u201390.0%). Top-30 generated non-null codes for 93.2% of the 190 evaluable diagnoses and achieved a conditional exact-match agreement of 92.1%. By contrast, the direct full-ontology baseline achieved 71.2% conditional exact-match agreement (42\/59) among non-null predictions and 22.1% end-to-end exact-match agreement (42\/190) when incorrect predictions, null outputs, and technical failures were considered non-concordant outcomes. Compared to direct full-ontology inference, Top-30 reduced input-token consumption by 92.4%, total token consumption by 92.2%, and inference cost by 91.3%, while avoiding the 118 API rate-limit failures observed with the direct baseline. Among the 21 insufficiently specified diagnoses, Top-30 returned null codes in 38.1% and non-null codes in 61.9%. Conclusions: Ontology-guided candidate reduction improved coding agreement, computational efficiency, and operational robustness within this retrospective single-registry benchmark. However, the reported performance estimates require confirmation in larger independent datasets, and an upstream data-sufficiency or abstention mechanism is needed before prospective operational deployment.<\/jats:p>","DOI":"10.3390\/cancers18172728","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:20:02Z","timestamp":1787563202000},"page":"2728","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Lexical\u2013Semantic AI Architecture for Automated Cancer Registry Coding for the Vet-ICD-O-Canine-1 System from Free-Text Veterinary Pathology Reports"],"prefix":"10.3390","volume":"18","author":[{"given":"Vit\u00f3ria Souza de Oliveira","family":"Nascimento","sequence":"first","affiliation":[{"name":"Laboratory of Experimental and Comparative Oncology, Department of Pathology, School of Veterinary Medicine and Animal Science, University of S\u00e3o Paulo, S\u00e3o Paulo 05508-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcello Vannucci","family":"Tedardi","sequence":"additional","affiliation":[{"name":"Laboratory of Experimental and Comparative Oncology, Department of Pathology, School of Veterinary Medicine and Animal Science, University of S\u00e3o Paulo, S\u00e3o Paulo 05508-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6744-9660","authenticated-orcid":false,"given":"Guilherme da Silva","family":"Rog\u00e9rio","sequence":"additional","affiliation":[{"name":"Laboratory of Experimental and Comparative Oncology, Department of Pathology, School of Veterinary Medicine and Animal Science, University of S\u00e3o Paulo, S\u00e3o Paulo 05508-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0870-6281","authenticated-orcid":false,"given":"Katia Cristina","family":"Pinello","sequence":"additional","affiliation":[{"name":"EPIUnit ITR, Institute of Public Health of the University Porto, University of Porto (ISPUP), 4050-600 Porto, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7031-6711","authenticated-orcid":false,"given":"Maria L\u00facia Zaidan","family":"Dagli","sequence":"additional","affiliation":[{"name":"Laboratory of Experimental and Comparative Oncology, Department of Pathology, School of Veterinary Medicine and Animal Science, University of S\u00e3o Paulo, S\u00e3o Paulo 05508-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1007\/s10462-025-11316-5","article-title":"A survey of NLP methods for oncology in the past decade with a focus on cancer registry applications","volume":"58","author":"Hands","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e2400110","DOI":"10.1200\/CCI.24.00110","article-title":"Classifying tumor reportability status from unstructured electronic pathology reports using language models in a population-based cancer registry setting","volume":"8","author":"Gondara","year":"2024","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jbi.2017.07.012","article-title":"Natural language processing systems for capturing and standardizing unstructured clinical information: A systematic review","volume":"73","author":"Kreimeyer","year":"2017","journal-title":"J. Biomed. Inform."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1148\/radiol.16142770","article-title":"Natural language processing in radiology: A systematic review","volume":"279","author":"Pons","year":"2016","journal-title":"Radiology"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Alshammari, A.H., Oshiro, T., Ungkulpasvich, U., Yamaguchi, J., Morishita, M., Khdair, S.A., Hatakeyama, H., Hirotsu, T., and di Luccio, E. (2025). Advancing veterinary oncology: Next-generation diagnostics for early cancer detection and clinical implementation. Animals, 15.","DOI":"10.3390\/ani15030389"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1016\/j.tvjl.2018.08.008","article-title":"Companion animals in comparative oncology: One Medicine in action","volume":"240","author":"Garden","year":"2018","journal-title":"Vet. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"20140231","DOI":"10.1098\/rstb.2014.0231","article-title":"Comparative oncology: What dogs and other species can teach us about humans with cancer","volume":"370","author":"Schiffman","year":"2015","journal-title":"Philos. Trans. R. Soc. Lond. B Biol. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"25","DOI":"10.4314\/ovj.v8i1.5","article-title":"Comparative oncology: Integrating human and veterinary medicine","volume":"8","author":"Sultan","year":"2018","journal-title":"Open Vet. J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1002\/aac2.12046","article-title":"Increased risk of cancer in dogs and humans: A consequence of recent extension of lifespan beyond evolutionarily determined limitations?","volume":"3","author":"Sarver","year":"2022","journal-title":"Aging Cancer"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"105517","DOI":"10.1016\/j.rvsc.2024.105517","article-title":"Environmental exposure and cancer occurrence in dogs: A critical appraisal of evidence","volume":"184","author":"Owada","year":"2025","journal-title":"Res. Vet. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"105754","DOI":"10.1016\/j.rvsc.2025.105754","article-title":"Beyond the clinic: Unlocking the power of cancer data in companion animals","volume":"193","author":"Palmieri","year":"2025","journal-title":"Res. Vet. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1146\/annurev-biodatasci-102423-111936","article-title":"Bringing the genomic revolution to comparative oncology: Human and dog cancers","volume":"7","author":"Cahill","year":"2024","journal-title":"Annu. Rev. Biomed. Data Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"105673","DOI":"10.1016\/j.rvsc.2025.105673","article-title":"Cancer registration in dogs and cats: A narrative review of history, current status, and standardization efforts","volume":"191","author":"Fonti","year":"2025","journal-title":"Res. Vet. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Pinello, K., Baldassarre, V., Steiger, K., Paciello, O., Pires, I., Laufer-Amorim, R., Oevermann, A., Niza-Ribeiro, J., Aresu, L., and Rous, B. (2022). Vet-ICD-O-Canine-1, a system for coding canine neoplasms based on the human ICD-O-3.2. Cancers, 14.","DOI":"10.3390\/cancers14061529"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1177\/03009858251347529","article-title":"Natural language processing in veterinary pathology: A review","volume":"62","author":"Stimmer","year":"2025","journal-title":"Vet. Pathol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Davies, H., Nenadic, G., Alfattni, G., Arguello Casteleiro, M., Al Moubayed, N., Farrell, S.O., Radford, A.D., and Noble, P.J.M. (2024). Text mining for disease surveillance in veterinary clinical data: Part one, the language of veterinary clinical records and searching for words. Front. Vet. Sci., 11.","DOI":"10.3389\/fvets.2024.1352239"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1038\/s41597-021-01039-x","article-title":"A text-mining based analysis of 100,000 tumours affecting dogs and cats in the United Kingdom","volume":"8","author":"Killick","year":"2021","journal-title":"Sci. Data"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.jcpa.2022.07.009","article-title":"Tumour incidence in dogs in Germany: A retrospective analysis of 109,616 histopathological diagnoses (2014\u20132019)","volume":"198","author":"Grassinger","year":"2022","journal-title":"J. Comp. Pathol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103712","DOI":"10.1016\/j.jbi.2021.103712","article-title":"Automated classification of cancer morphology from Italian pathology reports using natural language processing techniques: A rule-based approach","volume":"116","author":"Hammami","year":"2021","journal-title":"J. Biomed. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Davies, H., Nenadic, G., Alfattni, G., Arguello Casteleiro, M., Al Moubayed, N., Farrell, S., Radford, A.D., and Noble, P.J.M. (2024). Text mining for disease surveillance in veterinary clinical data: Part two, training computers to identify features in clinical text. Front. Vet. Sci., 11.","DOI":"10.3389\/fvets.2024.1352726"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1093\/jamia\/ocz153","article-title":"Automatic extraction of cancer registry reportable information from free-text pathology reports using multitask convolutional neural networks","volume":"27","author":"Alawad","year":"2020","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Rios, A., Durbin, E.B., Hands, I., and Kavuluru, R. (2021, January 1\u20134). Assigning ICD-O-3 codes to pathology reports using neural multi-task training with hierarchical regularization. Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (BCB \u201921), Gainesville, FL, USA.","DOI":"10.1145\/3459930.3469541"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e27210","DOI":"10.2196\/27210","article-title":"A question-and-answer system to extract data from free-text oncological pathology reports (CancerBERT Network): Development study","volume":"24","author":"Mitchell","year":"2022","journal-title":"J. Med. Internet Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e2400124","DOI":"10.1200\/CCI.24.00124","article-title":"Developing and validating an automatic support system for tumor coding in pathology reports in Spanish","volume":"9","author":"Villena","year":"2025","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e000759","DOI":"10.1136\/bmjonc-2025-000759","article-title":"Large language models in oncology: A review","volume":"4","author":"Chen","year":"2025","journal-title":"BMJ Oncol."},{"key":"ref_26","first-page":"120","article-title":"VetLLM: Large language model for predicting diagnosis from veterinary notes","volume":"29","author":"Jiang","year":"2024","journal-title":"Pac. Symp. Biocomput."},{"key":"ref_27","first-page":"121","article-title":"Using large language models for efficient cancer registry coding in the real hospital setting: A feasibility study","volume":"30","author":"Wang","year":"2025","journal-title":"Pac. Symp. Biocomput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e2500254","DOI":"10.1200\/CCI-25-00254","article-title":"Automated tumor International Classification of Diseases coding of real-world pathology reports using self-hosted large language models","volume":"10","author":"Arzideh","year":"2026","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"106022","DOI":"10.1016\/j.ijmedinf.2025.106022","article-title":"From text to data: Open-source large language models in extracting cancer related medical attributes from German pathology reports","volume":"203","author":"Bartels","year":"2025","journal-title":"Int. J. Med. Inform."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1162\/tacl_a_00638","article-title":"Lost in the middle: How language models use long contexts","volume":"12","author":"Liu","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_31","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, C., Zhang, M., Mei, Q., and Bendersky, M. (2024, January 12\u201314). Retrieval augmented generation or long-context LLMs? A comprehensive study and hybrid approach. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, Miami, FL, USA.","DOI":"10.18653\/v1\/2024.emnlp-industry.66"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lee, H., and Lim, S. (2026). Hybrid retrieval-augmented generation: Semantic and structural integration for large language model reasoning. Appl. Sci., 16.","DOI":"10.3390\/app16052244"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"ooag017","DOI":"10.1093\/jamiaopen\/ooag017","article-title":"Large language models as medical code selectors: A benchmark using the International Classification of Primary Care","volume":"9","author":"Finger","year":"2026","journal-title":"JAMIA Open"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1111\/vco.12133","article-title":"S\u00e3o Paulo Animal Cancer Registry, the first in Latin America","volume":"13","author":"Tedardi","year":"2015","journal-title":"Vet. Comp. Oncol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1177\/03009858251413572","article-title":"Development and implementation of a data parsing protocol for companion animal cancer data","volume":"63","author":"Palmieri","year":"2026","journal-title":"Vet. Pathol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"100070","DOI":"10.1016\/j.intonc.2026.100070","article-title":"The role of artificial intelligence in cancer epidemiology: Challenges and opportunities","volume":"2","author":"Zhao","year":"2026","journal-title":"Intell. Oncol."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/17\/2728\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:31:36Z","timestamp":1787563896000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/17\/2728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,23]]},"references-count":37,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["cancers18172728"],"URL":"https:\/\/doi.org\/10.3390\/cancers18172728","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,23]]}}}