{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:17:35Z","timestamp":1779383855766,"version":"3.53.1"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["23511100602"],"award-info":[{"award-number":["23511100602"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008838","name":"Shanghai Municipal Commission of Economy and Informatization","doi-asserted-by":"publisher","award":["2024-GZL-RGZN-01013"],"award-info":[{"award-number":["2024-GZL-RGZN-01013"]}],"id":[{"id":"10.13039\/501100008838","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576107"],"award-info":[{"award-number":["62576107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017950","name":"Shanghai Municipal Health Commission","doi-asserted-by":"publisher","award":["2025ZHYL040"],"award-info":[{"award-number":["2025ZHYL040"]}],"id":[{"id":"10.13039\/100017950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113441","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:34:16Z","timestamp":1772696056000},"page":"113441","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["EviMMQA: Multimodal question answering for medical evidence extraction in systematic reviews"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2900-9238","authenticated-orcid":false,"given":"Changkai","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7891-7078","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0155-5046","authenticated-orcid":false,"given":"Yingwen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0440-8516","authenticated-orcid":false,"given":"Wen","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-3998","authenticated-orcid":false,"given":"Ying","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7223","authenticated-orcid":false,"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4747-0574","authenticated-orcid":false,"given":"Rui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-5414","authenticated-orcid":false,"given":"Xiaobo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6964","key":"10.1016\/j.patcog.2026.113441_bib0001","doi-asserted-by":"crossref","first-page":"1286","DOI":"10.1136\/bmj.309.6964.1286","article-title":"Systematic reviews: identifying relevant studies for systematic reviews","volume":"309","author":"Dickersin","year":"1994","journal-title":"BMJ"},{"key":"10.1016\/j.patcog.2026.113441_bib0002","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.jclinepi.2018.11.030","article-title":"Systematic reviews of clinical practice guidelines: a methodological guide","volume":"108","author":"Johnston","year":"2019","journal-title":"J. Clin. Epidemiol."},{"issue":"1","key":"10.1016\/j.patcog.2026.113441_bib0003","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1097\/PRS.0b013e318219c171","article-title":"The levels of evidence and their role in evidence-based medicine","volume":"128","author":"Burns","year":"2011","journal-title":"Plast. Reconstr. Surg."},{"key":"10.1016\/j.patcog.2026.113441_bib0004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/2046-4053-3-74","article-title":"Systematic review automation technologies","volume":"3","author":"Tsafnat","year":"2014","journal-title":"Syst. Rev."},{"key":"10.1016\/j.patcog.2026.113441_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12874-017-0431-4","article-title":"Frequency of data extraction errors and methods to increase data extraction quality: a methodological review","volume":"17","author":"Mathes","year":"2017","journal-title":"BMC Med. Res. Methodol."},{"key":"10.1016\/j.patcog.2026.113441_bib0006","series-title":"BMC Bioinformatics","first-page":"1","article-title":"Automatic classification of sentences to support evidence based medicine","volume":"vol. 12","author":"Kim","year":"2011"},{"key":"10.1016\/j.patcog.2026.113441_bib0007","series-title":"Proceedings of the first Workshop on Information Extraction from Scientific Publications","first-page":"26","article-title":"PICO corpus: a publicly available corpus to support automatic data extraction from biomedical literature","author":"Mutinda","year":"2022"},{"key":"10.1016\/j.patcog.2026.113441_bib0008","series-title":"ECIR 2010, Milton Keynes, UK, March 28\u201331, 2010. Proceedings 32","first-page":"50","article-title":"Improving medical information retrieval with PICO element detection","author":"Boudin","year":"2010"},{"key":"10.1016\/j.patcog.2026.113441_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110930","article-title":"Kyrtos: a methodology for automatic deep analysis of graphic charts with curves in technical documents","volume":"157","author":"Alexiou","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113441_bib0010","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113441_bib0011","unstructured":"J. Bai, S. Bai, S. Yang, et al., Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond, 2023, arXiv: 2308.12966."},{"key":"10.1016\/j.patcog.2026.113441_bib0012","unstructured":"F. Li, R. Zhang, H. Zhang, Y. Zhang, B. Li, W. Li, Z. Ma, C. Li, LLaVA-NeXT-interleave: tackling multi-image, video, and 3D in large multimodal models, CoRR(2024). 10.48550\/ARXIV.2407.07895."},{"issue":"2","key":"10.1016\/j.patcog.2026.113441_bib0013","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1007\/s10844-019-00584-7","article-title":"A survey on question answering systems over linked data and documents","volume":"55","author":"Dimitrakis","year":"2020","journal-title":"J. Intell. Inf. Syst."},{"key":"10.1016\/j.patcog.2026.113441_bib0014","doi-asserted-by":"crossref","first-page":"401","DOI":"10.12688\/f1000research.51117.3","article-title":"Data extraction methods for systematic review (semi) automation: Update of a living systematic review","volume":"10","author":"Schmidt","year":"2025","journal-title":"F1000Research"},{"key":"10.1016\/j.patcog.2026.113441_bib0015","series-title":"ACL","first-page":"197","article-title":"A corpus with multi-level annotations of patients, interventions and outcomes to support language processing for medical literature","volume":"2018","author":"Nye","year":"2018"},{"key":"10.1016\/j.patcog.2026.113441_bib0016","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"2200","article-title":"DocVQA: a dataset for VQA on document images","author":"Mathew","year":"2021"},{"key":"10.1016\/j.patcog.2026.113441_bib0017","series-title":"International Conference on Document Analysis and Recognition","first-page":"219","article-title":"Multi-page document visual question answering using self-attention scoring mechanism","author":"Kang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113441_bib0018","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"3897","article-title":"CT2C-QA: multimodal question answering over Chinese text, table and chart","author":"Zhao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113441_bib0019","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"15419","article-title":"M3SciQA: a multi-modal multi-document scientific QA benchmark for evaluating foundation models","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.113441_bib0020","series-title":"Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS)","article-title":"SPIQA: a dataset for multimodal question answering on scientific papers","author":"Pramanick","year":"2024"},{"key":"10.1016\/j.patcog.2026.113441_bib0021","series-title":"Proceedings of EMNLP-IJCNLP 2019","first-page":"2567","article-title":"PubMedQA: a dataset for biomedical research question answering","author":"Jin","year":"2019"},{"key":"10.1016\/j.patcog.2026.113441_bib0022","series-title":"Proceedings of the 31St International Conference on Computational Linguistics","first-page":"1258","article-title":"RoBGuard: enhancing LLMs to assess risk of bias in clinical trial documents","author":"Ji","year":"2025"},{"key":"10.1016\/j.patcog.2026.113441_bib0023","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"5218","article-title":"RJUA-MedDQA: a multimodal benchmark for medical document question answering and clinical reasoning","author":"Jin","year":"2024"},{"issue":"132","key":"10.1016\/j.patcog.2026.113441_bib0024","first-page":"1","article-title":"Extracting PICO sentences from clinical trial reports using supervised distant supervision","volume":"17","author":"Wallace","year":"2016","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"10.1016\/j.patcog.2026.113441_bib0025","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooac107","article-title":"Not so weak PICO: leveraging weak supervision for participants, interventions, and outcomes recognition for systematic review automation","volume":"6","author":"Dhrangadhariya","year":"2023","journal-title":"JAMIA open"},{"key":"10.1016\/j.patcog.2026.113441_bib0026","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","first-page":"1705","article-title":"Sent2Span: span detection for PICO extraction in the biomedical text without span annotations","author":"Liu","year":"2021"},{"issue":"1","key":"10.1016\/j.patcog.2026.113441_bib0027","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1186\/s13643-022-02074-4","article-title":"PICO entity extraction for preclinical animal literature","volume":"11","author":"Wang","year":"2022","journal-title":"Syst. Rev."},{"key":"10.1016\/j.patcog.2026.113441_bib0028","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.ymeth.2024.04.005","article-title":"AlpaPICO: extraction of PICO frames from clinical trial documents using LLMs","volume":"226","author":"Ghosh","year":"2024","journal-title":"Methods"},{"key":"10.1016\/j.patcog.2026.113441_bib0029","series-title":"Machine Learning for Healthcare Conference","first-page":"754","article-title":"Jointly extracting interventions, outcomes, and findings from RCT reports with LLMs","author":"Wadhwa","year":"2023"},{"key":"10.1016\/j.patcog.2026.113441_bib0030","series-title":"NeurIPS","article-title":"SPIQA: a dataset for multimodal question answering on scientific papers","author":"Pramanick","year":"2024"},{"key":"10.1016\/j.patcog.2026.113441_bib0031","series-title":"ACL","first-page":"6088","article-title":"VisDoM: multi-document QA with visually rich elements using multimodal retrieval-augmented generation","author":"Suri","year":"2025"},{"key":"10.1016\/j.patcog.2026.113441_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111332","article-title":"Enhancing textual textbook question answering with large language models and retrieval augmented generation","volume":"162","author":"Alawwad","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113441_bib0033","first-page":"1","article-title":"MoE-LLaVA: mixture of experts for large vision-language models","author":"Lin","year":"2026","journal-title":"IEEE Trans. Multimed."},{"issue":"5","key":"10.1016\/j.patcog.2026.113441_bib0034","doi-asserted-by":"crossref","first-page":"3424","DOI":"10.1109\/TPAMI.2025.3532688","article-title":"Uni-MoE: scaling unified multimodal LLMs with mixture of experts","volume":"47","author":"Li","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113441_bib0035","series-title":"International Conference on Machine Learning","first-page":"34209","article-title":"From crowdsourced data to high-quality benchmarks: arena-hard and benchbuilder pipeline","author":"Li","year":"2025"},{"key":"10.1016\/j.patcog.2026.113441_bib0036","unstructured":"H. Touvron, T. Lavril, G. Izacard, et al., LLaMA: open and efficient foundation language models,(2023) arXiv: 2302.13971."},{"key":"10.1016\/j.patcog.2026.113441_bib0037","unstructured":"A. Yang, B. Yang, B. Zhang, et al., Qwen2.5 technical report,(2025) arXiv: 2412.15115."},{"key":"10.1016\/j.patcog.2026.113441_bib0038","unstructured":"Z. Chen, W. Wang, Y. Cao, Y. Liu, Z. Gao, E. Cui, J. Zhu, S. Ye, H. Tian, Z. Liu, et al., Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling,(2024) arXiv: 2412.05271."},{"key":"10.1016\/j.patcog.2026.113441_bib0039","first-page":"42566","article-title":"InternLM-XComposer2-4KHD: a pioneering large vision-language model handling resolutions from 336 pixels to 4K HD","volume":"37","author":"Dong","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113441_bib0040","unstructured":"Q. Ye, H. Xu, G. Xu, et al., mPLUG-Owl: modularization empowers large language models with multimodality, 2024, arXiv: 2304.14178."},{"key":"10.1016\/j.patcog.2026.113441_bib0041","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":"10.1016\/j.patcog.2026.113441_bib0042","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","article-title":"LlamaFactory: unified efficient fine-tuning of 100+ language models","author":"Zheng","year":"2024"},{"key":"10.1016\/j.patcog.2026.113441_bib0043","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. Computat. Linguist."},{"key":"10.1016\/j.patcog.2026.113441_bib0044","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","first-page":"3982","article-title":"Sentence-BERT: sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019"},{"issue":"1","key":"10.1016\/j.patcog.2026.113441_bib0045","first-page":"1","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans. Comput. Healthcare (HEALTH)"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004073?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004073?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:56:45Z","timestamp":1779382605000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004073"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":45,"alternative-id":["S0031320326004073"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113441","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"EviMMQA: Multimodal question answering for medical evidence extraction in systematic reviews","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113441","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113441"}}