{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T07:06:14Z","timestamp":1789542374543,"version":"build-2803163510"},"reference-count":40,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n The clinical progression of chronic gastritis involves intricate temporal dependencies, which makes it difficult to capture both the dynamic trajectory of the disease and the underlying relationships among medical events using conventional methods.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to dynamically predict chronic gastritis diagnosis. We propose RL4TKGR, a reinforcement learning\u2013based temporal knowledge graph (TKG) reasoning model, to predict a chronic gastritis diagnosis.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n RL4TKGR incorporates a reinforcement learning policy network that uses a dual-path encoding module to model historical and nonhistorical diagnostic information separately. RL4TKGR further integrates a dual-channel reward function with a dynamic weight allocation mechanism, which adaptively balances the two information sources. This design addresses the strategic bias problem and enables interpretable reasoning. The chronic gastritis temporal knowledge graph (CG-TKG) was constructed from chronic gastritis diagnosis and treatment records of 17,906 patients comprising 38,360 visits from March 2009 to October 2022.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Experiments on the self-constructed CG-TKG resulted in RL4TKGR achieving the highest mean reciprocal rank (MRR) on CG-TKG-4 (51.66, SD 0.76), CG-TKG-8 (53.18, SD 0.79), and CG-TKG-12 (56.95, SD 0.84). After adding recent TKG reasoning baselines, adaptive path-memory network (DaeMon) achieved the strongest baseline MRR for all 3 subsets, with MRR values of 43.26 (SD 0.95), 51.76 (SD 1.12), and 54.87 (SD 1.17), respectively. Compared with DaeMon, the overall paired\n t<\/jats:italic>\n tests across MRR and Hits@1\/3\/10 yielded \ud835\udc43<.001 for all 3 subsets. Ablation experiments and case analyses further supported the contribution of the historical modeling components and the practical utility of the model for predicting disease subtypes and therapeutic medications.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study improves chronic gastritis diagnosis and treatment prediction by integrating a history-aware dual-path policy network with a dynamic event balance factor in reinforcement learning\u2013based TKG reasoning.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/83544","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:05:06Z","timestamp":1786640706000},"page":"e83544-e83544","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning\u2013Based Temporal Knowledge Graph Reasoning for Predicting Chronic Gastritis Diagnosis and Treatment: Development and Validation Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0932-0361","authenticated-orcid":false,"given":"Xiaolong","family":"Qu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7247-8348","authenticated-orcid":false,"given":"Zhou","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4303-2477","authenticated-orcid":false,"given":"Yuhang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0956-4184","authenticated-orcid":false,"given":"Haiyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2720-3603","authenticated-orcid":false,"given":"Lei","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7409-6656","authenticated-orcid":false,"given":"Dongmei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8184-6186","authenticated-orcid":false,"given":"Guanli","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0909-5475","authenticated-orcid":false,"given":"Runshun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-1906","authenticated-orcid":false,"given":"Xiaoping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"issue":"9","key":"R1","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.1136\/gutjnl-2018-318126","article-title":"British Society of Gastroenterology guidelines on the diagnosis and management of patients at risk of gastric adenocarcinoma","volume":"68","author":"Banks","journal-title":"Gut"},{"issue":"5","key":"R2","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1016\/j.dld.2019.12.146","article-title":"Diagnosing chronic atrophic gastritis by gastroscopy using artificial intelligence","volume":"52","author":"Zhang","journal-title":"Dig Liver Dis"},{"issue":"16","key":"R3","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13164818","article-title":"Artificial intelligence for the automatic diagnosis of gastritis: a systematic review","volume":"13","author":"Turtoi","journal-title":"J Clin Med"},{"issue":"11","key":"R4","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1016\/j.dld.2022.04.025","article-title":"A deep learning method to assist with chronic atrophic gastritis diagnosis using white light images","volume":"54","author":"Luo","journal-title":"Dig Liver Dis"},{"issue":"8","key":"R5","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1016\/j.dld.2024.01.177","article-title":"An artificial intelligence system for chronic atrophic gastritis diagnosis and risk stratification under white light endoscopy","volume":"56","author":"Tao","journal-title":"Dig Liver Dis"},{"issue":"13","key":"R6","doi-asserted-by":"publisher","first-page":"6194","DOI":"10.3390\/app11136194","article-title":"A deep recurrent neural network-based explainable prediction model for progression from atrophic gastritis to gastric cancer","volume":"11","author":"Kim","journal-title":"Applied Sciences"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1158\/1055-9965.EPI-23-1200","article-title":"Risk of gastric adenocarcinoma in a multiethnic population undergoing routine care: an electronic health records cohort study","volume":"33","author":"Huang","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"key":"R8","unstructured":"Jiang T Liu T Ge T et al. Towards time-aware knowledge graph completion. Presented at: 26th International Conference on Computational Linguistics; Dec 11-16, 2016; Osaka, Japan. URL: https:\/\/aclanthology.org\/C16-1.pdf"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.2196\/57678","article-title":"Explainable AI method for tinnitus diagnosis via neighbor-augmented knowledge graph and traditional Chinese medicine: development and validation study","volume":"12","author":"Yin","journal-title":"JMIR Med Inform"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Song F Wang B Tang Y et al. Research of medical aided diagnosis system based on temporal knowledge graph. Presented at: Advanced Data Mining and Applications: 16th International Conference; Nov 12-14, 2020; Foshan, China. [doi: 10.1007\/978-3-030-65390-3_19]","DOI":"10.1007\/978-3-030-65390-3_19"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-024-02866-3","article-title":"Genetic and phenotypic similarity across major psychiatric disorders: a systematic review and quantitative assessment","volume":"14","author":"Bourque","journal-title":"Transl Psychiatry"},{"key":"R12","doi-asserted-by":"crossref","unstructured":"Chen S Wang J . A survey on temporal knowledge graphs-extrapolation and interpolation tasks. Presented at: The International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery; Jul 30 to Aug 1, 2022; Fuzhou, China. [doi: 10.1007\/978-3-031-20738-9_110]","DOI":"10.1007\/978-3-031-20738-9_110"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Jiang T Liu T Ge T et al. Encoding temporal information for time-aware link prediction. Presented at: 2016 Conference on Empirical Methods in Natural Language Processing; Nov 1-4, 2016; Austin, Texas. URL: http:\/\/aclweb.org\/anthology\/D16-1 [doi: 10.18653\/v1\/D16-1260]","DOI":"10.18653\/v1\/D16-1260"},{"key":"R14","unstructured":"Bordes A Usunier N Garcia-Duran A et al. Translating embeddings for modeling multi-relational data. Presented at: NIPS\u201913: 27th International Conference on Neural Information Processing Systems; Dec 5-10, 2013; Lake Tahoe, Nevada. URL: https:\/\/dl.acm.org\/doi\/10.5555\/2999792.2999923"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Dur\u00e1n A Duman\u010di\u0107 S Niepert M . Learning sequence encoders for temporal knowledge graph completion. Presented at: 2018 Conference on Empirical Methods in Natural Language Processing; Oct 31 to Nov 4, 2018; Brussels, Belgium. URL: http:\/\/aclweb.org\/anthology\/D18-1 [doi: 10.18653\/v1\/D18-1516]","DOI":"10.18653\/v1\/D18-1516"},{"key":"R16","unstructured":"Yang B Yih SW He X et al. Embedding entities and relations for learning and inference in knowledge bases. Presented at: International Conference on Learning Representations (ICLR) 2015; May 7-9, 2015; San Diego, California. URL: https:\/\/www.microsoft.com\/en-us\/research\/publication\/embedding-entities-and-relations-for-learning-and-inference-in-knowledge-bases\/"},{"issue":"4","key":"R17","doi-asserted-by":"publisher","first-page":"3988","DOI":"10.1609\/aaai.v34i04.5815","article-title":"Diachronic embedding for temporal knowledge graph completion","volume":"34","author":"Goel","journal-title":"AAAI"},{"key":"R18","unstructured":"Han Z Chen P Ma Y et al. xERTE: explainable reasoning on temporal knowledge graphs for forecasting future links. arXiv. Preprint posted online on December 31, 2020. 10.48550\/arXiv.2012.15537"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Sun H Zhong J Ma Y Han Z He K . TimeTraveler: reinforcement learning for temporal knowledge graph forecasting. Presented at: 2021 Conference on Empirical Methods in Natural Language Processing; Nov 7-11, 2021; Online and Punta Cana, Dominican Republic. URL: https:\/\/aclanthology.org\/2021.emnlp-main [doi: 10.18653\/v1\/2021.emnlp-main.655]","DOI":"10.18653\/v1\/2021.emnlp-main.655"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2023.102292","article-title":"Reinforcement learning with time intervals for temporal knowledge graph reasoning","volume":"120","author":"Liu","journal-title":"Inf Syst"},{"key":"R21","doi-asserted-by":"crossref","unstructured":"Li Z Jin X Li W et al. Temporal knowledge graph reasoning based on evolutional representation learning. Presented at: SIGIR \u201921; Jul 11-15, 2021; Virtual event. URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3404835 [doi: 10.1145\/3404835.3462963]","DOI":"10.1145\/3404835.3462963"},{"key":"R22","doi-asserted-by":"crossref","unstructured":"Li Z Guan S Jin X et al. Complex evolutional pattern learning for temporal knowledge graph reasoning. Presented at: 60th Annual Meeting of the Association for Computational Linguistics; May 22-27, 2022; Dublin, Ireland. arXiv:220307782URL: https:\/\/aclanthology.org\/2022.acl-short [doi: 10.18653\/v1\/2022.acl-short.32]","DOI":"10.18653\/v1\/2022.acl-short.32"},{"key":"R23","unstructured":"Jin W Jiang H Qu M et al. Recurrent event network: global structure inference over temporal knowledge graph. arXiv. Preprint posted online on Oct 6, 2020. URL: https:\/\/arxiv.org\/abs\/1904.05530v3"},{"issue":"4","key":"R24","doi-asserted-by":"publisher","first-page":"4765","DOI":"10.1609\/aaai.v37i4.25601","article-title":"Temporal knowledge graph reasoning with historical contrastive learning","volume":"37","author":"Xu","journal-title":"AAAI"},{"key":"R25","unstructured":"Trivedi R Dai H Wang Y Song L . Know-evolve: deep temporal reasoning for dynamic knowledge graphs. Presented at: 34th International Conference on Machine Learning; Aug 7-9, 2017; Sydney, Australia. URL: https:\/\/proceedings.mlr.press\/v70\/trivedi17a.html"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Han Z Ding Z Ma Y Gu Y Tresp V . Learning neural ordinary equations for forecasting future links on temporal knowledge graphs. Presented at: 2021 Conference on Empirical Methods in Natural Language Processing; Nov 7-11, 2021; Online and Punta Cana, Dominican Republic. URL: https:\/\/aclanthology.org\/2021.emnlp-main [doi: 10.18653\/v1\/2021.emnlp-main.658]","DOI":"10.18653\/v1\/2021.emnlp-main.658"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Li Y Sun S Zhao J . TiRGN: time-guided recurrent graph network with local-global historical patterns for temporal knowledge graph reasoning. Presented at: Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}; Jul 23-29, 2022; Vienna, Austria. URL: https:\/\/www.ijcai.org\/proceedings\/2022 [doi: 10.24963\/ijcai.2022\/299]","DOI":"10.24963\/ijcai.2022\/299"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Liu K Zhao F Xu G Wang X Jin H . RETIA: relation-entity twin-interact aggregation for temporal knowledge graph extrapolation. Presented at: 2023 IEEE 39th International Conference on Data Engineering (ICDE); Apr 3-7, 2023; Anaheim, CA. [doi: 10.1109\/ICDE55515.2023.00138]","DOI":"10.1109\/ICDE55515.2023.00138"},{"key":"R29","doi-asserted-by":"crossref","unstructured":"Dong H Ning Z Wang P et al. Adaptive path-memory network for temporal knowledge graph reasoning. Presented at: Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}; Aug 19-25, 2023; Macau, SAR China. URL: https:\/\/www.ijcai.org\/proceedings\/2023 [doi: 10.24963\/ijcai.2023\/232]","DOI":"10.24963\/ijcai.2023\/232"},{"issue":"4","key":"R30","doi-asserted-by":"publisher","first-page":"4120","DOI":"10.1609\/aaai.v36i4.20330","article-title":"TLogic: temporal logical rules for explainable link forecasting on temporal knowledge graphs","volume":"36","author":"Liu","journal-title":"AAAI"},{"issue":"5","key":"R31","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.7507\/1001-5515.202204016","article-title":"A review of knowledge graph applications in the medical field","volume":"40","author":"Wang","journal-title":"Sheng Wu Yi Xue Gong Cheng Xue Za Zhi"},{"key":"R32","unstructured":"Carvalho RM Teixeira AS Pesquita C . Building a temporal knowledge graph for electronic health records. Presented at: DAO-XAI 2024: Workshop on Data meets Applied Ontologies in Explainable AI; Oct 19-20, 2024; Santiago de Compostela, Spain. URL: https:\/\/ceur-ws.org\/Vol-3833\/paper6.pdf"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Geng S Tao B Liang G Fu C Zhang W Niu B . Temporal knowledge graph attention network for online doctor recommendation. Presented at: 2023 8th International Conference on Intelligent Information Processing; Nov 21-22, 2023; Bucharest, Romania. [doi: 10.1145\/3635175.3635224]","DOI":"10.1145\/3635175.3635224"},{"key":"R34","doi-asserted-by":"crossref","unstructured":"Chaturvedi R . Temporal knowledge graph extraction and modeling across multiple documents for health risk prediction. Presented at: WWW \u201924; May 13-17, 2024; Singapore, Singapore. URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3589335 [doi: 10.1145\/3589335.3651256]","DOI":"10.1145\/3589335.3651256"},{"issue":"7","key":"R35","doi-asserted-by":"publisher","first-page":"4238","DOI":"10.1109\/JBHI.2024.3390419","article-title":"Predicting future disorders via temporal knowledge graphs and medical ontologies","volume":"28","author":"Postiglione","journal-title":"IEEE J Biomed Health Inform"},{"key":"R36","doi-asserted-by":"crossref","unstructured":"Lippman SA . Dynamic programming and Markov decision processes. In: The New Palgrave Dictionary of Economics. Palgrave Macmillan; 2018:3158-3164. [doi: 10.1057\/978-1-349-95189-5_80]","DOI":"10.1057\/978-1-349-95189-5_80"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107968","article-title":"Alzheimer\u2019s disease prediction using CAdam optimized reinforcement learning-based deep convolutional neural network model","volume":"108","author":"Chaudhari","journal-title":"Biomed Signal Process Control"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.2196\/63847","article-title":"Optimizing vital signs in patients with traumatic brain injury: reinforcement learning algorithm development and validation","volume":"27","author":"Zhang","journal-title":"J Med Internet Res"},{"issue":"3-4","key":"R39","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","journal-title":"Mach Learn"},{"key":"R40","unstructured":"QuXiaolong0812\/RL4TKGR. GitHub. URL: https:\/\/github.com\/QuXiaolong0812\/RL4TKGR [Accessed 22-08-2026]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:42:31Z","timestamp":1789540951000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e83544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":40,"URL":"https:\/\/doi.org\/10.2196\/83544","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]},"article-number":"v14i9e83544"}}