{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T17:07:13Z","timestamp":1787677633411,"version":"build-2784847793"},"reference-count":51,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"the Second Hospital of Dalian Medical University","award":["2023"],"award-info":[{"award-number":["2023"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62372077"],"award-info":[{"award-number":["No. 62372077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Traditional cystoscopic biopsy-based methods for histological grading of bladder cancer (BC) are invasive, subject to sampling errors, and susceptible to interobserver variability among pathologists. To address these challenges, this study explores a large language model (LLM)-based noninvasive approach to BC grade prediction using long Chinese medical texts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively collected admission records and computed tomography urography (CTU) descriptions from 642 patients pathologically diagnosed with BC. Each paired text was annotated as low grade or high grade according to histopathological results. We developed LLM-BCgrading to leverage HuatuoGPT-7B for Chinese medical long-text representation and integrated a gated multiplicative attention mechanism (GMAM) to selectively emphasize discriminative features. To address class imbalance and clinical risk asymmetry, the model was optimized with a cost-sensitive loss function. Performance was evaluated on a fixed internal test set with additional evaluation on an independent external validation cohort to assess generalizability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The best-performing configuration combined both admission records and CTU descriptions via an attention-based fusion strategy and GMAM, achieving balanced accuracy of 0.757, macro\n                      <jats:italic toggle=\"yes\">F<\/jats:italic>\n                      1 score of 0.749, and macro AUC of 0.740. The ablation results demonstrated that incorporating both texts significantly improved classification performance compared with single-text configurations, and the GMAM consistently outperformed conventional attention mechanisms. Dimensionality experiments identified 256 as the optimal embedding size, balancing computational efficiency and predictive performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our findings demonstrate that LLMs can effectively process Chinese medical long-texts for accurate preoperative prediction of BC grade. Attention-based fusion, cost-sensitive optimization, and interpretability based on Shapley additive explanations further support the robustness and clinical relevance of this LLM-driven framework.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076251393290","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T16:45:06Z","timestamp":1764089106000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["LLM-BCgrading: Large language model-based Chinese medical long text classification for bladder cancer grade prediction"],"prefix":"10.1177","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6397-8079","authenticated-orcid":false,"given":"Xianwei","family":"Pan","sequence":"first","affiliation":[{"name":"Dalian Maritime University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7016-919X","authenticated-orcid":false,"given":"Lijie","family":"Wen","sequence":"additional","affiliation":[{"name":"The Second Affiliated Hospital of Dalian Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2913-4478","authenticated-orcid":false,"given":"Yuhua","family":"Li","sequence":"additional","affiliation":[{"name":"Cardiff University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5843-4675","authenticated-orcid":false,"given":"Yijia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian Maritime University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8663-9870","authenticated-orcid":false,"given":"Mingyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian Maritime University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranon.2024.102269"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.2174\/0109298673283888231217174702"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2005.12.031"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2020.12.002"},{"key":"e_1_3_4_7_2","volume-title":"WHO classification of tumours: urinary and male genital tumours","author":"WHO Classification of Tumours Editorial Board","year":"2022","unstructured":"WHO Classification of Tumours Editorial Board. WHO classification of tumours: urinary and male genital tumours. Lyon, France, IARC; 2022."},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1111\/his.14192"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2024.07.027"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa047"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1093\/clinchem\/hvae156"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2025.01.016"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2020.04.023"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105809"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102275"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-023-01569-5"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103125"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2021.05.006"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1477166"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3104724"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104932"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11090909"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-023-00609-z"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1166245"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.actbio.2022.12.035"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3329025"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127784"},{"key":"e_1_3_4_28_2","first-page":"12798","volume-title":"DKEC: domain knowledge enhanced multi-label classification for diagnosis predictionProceedings of the 2024 conference on empirical methods in natural language processing","author":"Ge X","unstructured":"Ge X, Satpathy A, Williams RD, et al. DKEC: domain knowledge enhanced multi-label classification for diagnosis prediction. In: Proceedings of the 2024 conference on empirical methods in natural language processing, Miami, Florida, USA, 2024. pp.12798\u201312813."},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103098"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109971"},{"key":"e_1_3_4_31_2","first-page":"10","volume-title":"PLM-ICD: automatic ICD coding with pretrained language modelsProceedings of the 4th clinical natural language processing workshop","author":"Huang CW","unstructured":"Huang CW, Tsai SC, Chen YN. PLM-ICD: automatic ICD coding with pretrained language models. In: Proceedings of the 4th clinical natural language processing workshop, Seattle, WA, 2022, pp.10\u201320."},{"key":"e_1_3_4_32_2","first-page":"3997","volume-title":"Correlation: boosting automatic ICD coding through contextualized code relation learningProceedings of the 2024 Joint international conference on computational linguistics, language resources and evaluation (LREC-COLING)","author":"Luo J","year":"2024","unstructured":"Luo J, Wang X, Wang J, et al. Correlation: boosting automatic ICD coding through contextualized code relation learning. In: Proceedings of the 2024 Joint international conference on computational linguistics, language resources and evaluation (LREC-COLING), Torino, Italia, 2024, pp.3997\u20134007."},{"key":"e_1_3_4_33_2","article-title":"Evaluation of a natural language processing model to identify and characterize patients in the United States with high-risk non-muscle-invasive bladder cancer","volume":"7","author":"Narayan VM","year":"2023","unstructured":"Narayan VM, Siolas D, Meadows ES, et al. Evaluation of a natural language processing model to identify and characterize patients in the United States with high-risk non-muscle-invasive bladder cancer. JCO Clin Cancer Inform 2023; 7: e2300096.","journal-title":"JCO Clin Cancer Inform"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.urology.2017.07.056"},{"key":"e_1_3_4_35_2","article-title":"Context-based identification of muscle invasion status in patients with bladder cancer using natural language processing","volume":"6","author":"Yang R","year":"2022","unstructured":"Yang R, Zhu D, Howard LE, et al. Context-based identification of muscle invasion status in patients with bladder cancer using natural language processing. JCO Clin Cancer Inform 2022; 6: e2100097.","journal-title":"JCO Clin Cancer Inform"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"e_1_3_4_37_2","first-page":"973","volume-title":"The foundations of cost-sensitive learningProceedings of the 17th international joint conference on artificial intelligence (IJCAI)","author":"Elkan C.","unstructured":"Elkan C. The foundations of cost-sensitive learning. In: Proceedings of the 17th international joint conference on artificial intelligence (IJCAI). 2001, pp.973\u2013978."},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.17"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordjournals.pan.a004868"},{"key":"e_1_3_4_40_2","first-page":"2999","volume-title":"Focal loss for dense object detectionProceedings of the IEEE international conference on computer vision (ICCV)","author":"Lin TY","unstructured":"Lin TY, Goyal P, Girshick R, et al. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision (ICCV), Venice, Italy, 2017, pp.2999\u20133007."},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1909"},{"key":"e_1_3_4_42_2","first-page":"4171","volume-title":"Proceedings of NAACL-HLT 2019","author":"Devlin J","year":"2019","unstructured":"Devlin J, Chang MW, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT 2019. Minneapolis, MN. Stroudsburg: Association for Computational Linguistics; 2019, pp.4171\u20134186."},{"key":"e_1_3_4_43_2","unstructured":"Bai J Chen H Chen S et al. Qwen technical report. arXiv preprint arXiv: 2309.16609. 2023. https:\/\/arxiv.org\/abs\/2309.16609."},{"key":"e_1_3_4_44_2","first-page":"4765","volume-title":"Advances in Neural Information Processing Systems (NeurIPS).","author":"Lundberg SM","unstructured":"Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In: Guyon I, Luxburg UV, Bengio S, et al. (eds) Advances in Neural Information Processing Systems (NeurIPS). Vol. 30. New York, NY: Curran Associates, Inc., 2017, pp.4765\u20134774."},{"key":"e_1_3_4_45_2","first-page":"770","volume-title":"Deep residual learning for image recognitionProceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","author":"He K","year":"2016","unstructured":"He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, 2016, pp.770\u2013778."},{"key":"e_1_3_4_46_2","unstructured":"Mikolov T Chen K Corrado G et al. Efficient estimation of word representations in vector space. arXiv https:\/\/arxiv.org\/abs\/1301.3781 (2013 accessed 21 June 2025)."},{"key":"e_1_3_4_47_2","unstructured":"Kaplan J McCandlish S Henighan T et al. Scaling laws for neural language models. arXiv. https:\/\/arxiv.org\/abs\/2001.08361 (2020 accessed 21 June 2025)."},{"key":"e_1_3_4_48_2","first-page":"3265","article-title":"Advanced meta-heuristic algorithm based on particle swarm and Al-Biruni earth radius optimization methods for oral cancer detection","volume":"74","author":"Thippa Reddy G","year":"2023","unstructured":"Thippa Reddy G, Kaluri R, Lakshmanna K, et al. Advanced meta-heuristic algorithm based on particle swarm and Al-Biruni earth radius optimization methods for oral cancer detection. Comput Mater Continua 2023; 74: 3265\u20133281.","journal-title":"Comput Mater Continua"},{"key":"e_1_3_4_49_2","first-page":"291","article-title":"Breast cancer detection based on metaheuristic optimization and machine learning","volume":"75","author":"Yildirim M","year":"2023","unstructured":"Yildirim M, Hameed IA, Oliva D, et al. Breast cancer detection based on metaheuristic optimization and machine learning. Comput Mater Continua 2023; 75: 291\u2013308.","journal-title":"Comput Mater Continua"},{"key":"e_1_3_4_50_2","first-page":"4421","article-title":"Weed detection in precision agriculture using deep learning and metaheuristic optimization","volume":"10","author":"Ullo SL","year":"2022","unstructured":"Ullo SL, Russo M, Peng H, et al. Weed detection in precision agriculture using deep learning and metaheuristic optimization. Mathematics 2022; 10: 4421.","journal-title":"Mathematics"},{"key":"e_1_3_4_51_2","first-page":"41671","article-title":"An intrusion detection system using optimized deep learning model for IoT applications","volume":"11","author":"Ramalingam S","year":"2023","unstructured":"Ramalingam S, Elhoseny M, Suresh A, et al. An intrusion detection system using optimized deep learning model for IoT applications. IEEE Access 2023; 11: 41671\u201341684.","journal-title":"IEEE Access"},{"key":"e_1_3_4_52_2","first-page":"84528","article-title":"Innovative feature selection method based on hybrid sine cosine and dipper throated optimization algorithms","volume":"11","author":"Zaguia A","year":"2023","unstructured":"Zaguia A, Elaziz MA, Dahou A, et al. Innovative feature selection method based on hybrid sine cosine and dipper throated optimization algorithms. IEEE Access 2023; 11: 84528\u201384541.","journal-title":"IEEE Access"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076251393290","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076251393290","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076251393290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:55:06Z","timestamp":1777398906000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076251393290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":51,"alternative-id":["10.1177\/20552076251393290"],"URL":"https:\/\/doi.org\/10.1177\/20552076251393290","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]},"article-number":"20552076251393290"}}