{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:22:54Z","timestamp":1773868974126,"version":"3.50.1"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.131669","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:53:31Z","timestamp":1772096011000},"page":"131669","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Toward automated regulatory decision-making: AI-assisted medical device risk classification with multimodal transformers and self-training"],"prefix":"10.1016","volume":"318","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0527-636X","authenticated-orcid":false,"given":"Yu","family":"Han","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8863-6772","authenticated-orcid":false,"given":"Aaron","family":"Ceross","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7306-2630","authenticated-orcid":false,"given":"Jeroen H M","family":"Bergmann","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131669_bib0001","series-title":"Advances in neural information processing systems (neurIPS)","article-title":"Flamingo: A visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"10.1016\/j.eswa.2026.131669_bib0002","series-title":"Global regulations of medicinal, pharmaceutical, and food products","first-page":"153","article-title":"Regulations in japan","author":"Ali","year":"2024"},{"issue":"2","key":"10.1016\/j.eswa.2026.131669_bib0003","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.131669_bib0004","series-title":"Proceedings of the GEMS 2011 workshop on geometrical models of natural language semantics","first-page":"22","article-title":"Distributional semantics from text and images","author":"Bruni","year":"2011"},{"key":"10.1016\/j.eswa.2026.131669_bib0005","series-title":"Proceedings of the 14th International conference on theory and practice of electronic governance","first-page":"285","article-title":"A machine learning approach for medical device classification","author":"Ceross","year":"2021"},{"key":"10.1016\/j.eswa.2026.131669_bib0006","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1146\/annurev-biodatasci-092820-114757","article-title":"Ethical machine learning in healthcare","volume":"4","author":"Chen","year":"2021","journal-title":"Annual Review of Biomedical Data Science"},{"key":"10.1016\/j.eswa.2026.131669_bib0007","series-title":"International conference on machine learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.131669_bib0008","series-title":"European conference on computer vision","first-page":"104","article-title":"Uniter: universal image-text representation learning","author":"Chen","year":"2020"},{"issue":"1","key":"10.1016\/j.eswa.2026.131669_bib0009","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1186\/s12911-020-1069-4","article-title":"Sparse multi-output gaussian processes for online medical time series prediction","volume":"20","author":"Cheng","year":"2020","journal-title":"BMC Medical Informatics and Decision Making"},{"issue":"6","key":"10.1016\/j.eswa.2026.131669_bib0010","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","article-title":"Indexing by latent semantic analysis","volume":"41","author":"Deerwester","year":"1990","journal-title":"Journal of the American Society for Information Science"},{"key":"10.1016\/j.eswa.2026.131669_bib0011","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human language technologies","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.eswa.2026.131669_bib0012","unstructured":"Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv: 1702.08608."},{"key":"10.1016\/j.eswa.2026.131669_bib0013","unstructured":"European Commission (2021). Proposal for a regulation laying down harmonised rules on artificial intelligence. Last updated 20 June 2023 https:\/\/digital-strategy.ec.europa.eu\/en\/library\/proposal-regulation-laying-down-harmonised-rules-artificial-intelligence."},{"key":"10.1016\/j.eswa.2026.131669_bib0014","series-title":"Technical Report","article-title":"Clinical decision support software: Guidance for industry and food and drug administration staff","author":"Food","year":"2022"},{"key":"10.1016\/j.eswa.2026.131669_bib0015","series-title":"International conference on machine learning","first-page":"1174","article-title":"Learning to detect sepsis with a multitask gaussian process RNN classifier","author":"Futoma","year":"2017"},{"key":"10.1016\/j.eswa.2026.131669_bib0016","series-title":"Artificial intelligence in healthcare","first-page":"295","article-title":"Ethical and legal challenges of artificial intelligence-driven healthcare","author":"Gerke","year":"2020"},{"issue":"4","key":"10.1016\/j.eswa.2026.131669_bib0017","doi-asserted-by":"crossref","first-page":"235","DOI":"10.3390\/info15040235","article-title":"An overview on the advancements of support vector machine models in healthcare applications: a review","volume":"15","author":"Guido","year":"2024","journal-title":"Information"},{"key":"10.1016\/j.eswa.2026.131669_bib0018","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2024.1415319","article-title":"More than red tape: Exploring complexity in medical device regulatory affairs","volume":"11","author":"Han","year":"2024","journal-title":"Frontiers in Medicine"},{"key":"10.1016\/j.eswa.2026.131669_bib0019","unstructured":"Han, Y., Ceross, A., & Bergmann, J. H. M. (2025). Ai for regulatory affairs: Balancing accuracy, interpretability, and computational cost in medical device classification. arXiv: 2505.18695."},{"issue":"1","key":"10.1016\/j.eswa.2026.131669_bib0020","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1038\/s41746-025-01596-0","article-title":"Is regulatory science ready for artificial intelligence?","volume":"8","author":"Hartung","year":"2025","journal-title":"npj Digital Medicine"},{"issue":"19103432","key":"10.1016\/j.eswa.2026.131669_bib0021","article-title":"Beyond medical imaging-a review of multimodal deep learning in radiology","author":"Heiliger","year":"2022","journal-title":"TechRxiv"},{"key":"10.1016\/j.eswa.2026.131669_bib0022","unstructured":"International Organization for Standardization (ISO) \/ International Electrotechnical Commission (IEC) (2021). Information technology - artificial intelligence (AI) - Bias in AI systems and AI-aided decision making (ISO\/IEC TR 24027:2021). Technical report; uploaded 3 July 2024 to OECD AI Tools & Metrics catalogue https:\/\/aistandardshub.org\/ai-standards\/information-technology-artificial-intelligence-ai-bias-in-ai-systems-and-ai-aided-decision-making\/."},{"key":"10.1016\/j.eswa.2026.131669_bib0023","series-title":"International conference on machine learning (ICML)","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume":"vol. 139","author":"Jia","year":"2021"},{"key":"10.1016\/j.eswa.2026.131669_bib0024","series-title":"Proceedings of the 56th Annual meeting of the Association for computational linguistics (volume 1: long papers)","first-page":"2577","article-title":"On the automatic generation of medical imaging reports","author":"Jing","year":"2018"},{"key":"10.1016\/j.eswa.2026.131669_bib0025","series-title":"2006 IET seminar on software for medical devices","first-page":"41","article-title":"Standard IEC 62304-medical device software-software lifecycle processes","author":"Jordan","year":"2006"},{"key":"10.1016\/j.eswa.2026.131669_bib0026","unstructured":"Junyi, S. (2012). Jieba: Chinese text segmentation. https:\/\/github.com\/fxsjy\/jieba, Accessed: 2025-04-30."},{"key":"10.1016\/j.eswa.2026.131669_bib0027","series-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","first-page":"36","article-title":"Learning image embeddings using convolutional neural networks for improved multi-modal semantics","author":"Kiela","year":"2014"},{"key":"10.1016\/j.eswa.2026.131669_bib0028","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv: 1412.6980."},{"key":"10.1016\/j.eswa.2026.131669_bib0029","unstructured":"Kobayashi, S. (2018). Contextual augmentation: Data augmentation by words with paradigmatic relations. arXiv: 1805.06201."},{"key":"10.1016\/j.eswa.2026.131669_bib0030","series-title":"International conference on machine learning (ICML)","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.131669_bib0031","unstructured":"Li, L. H., Yatskar, M., Yin, D., Hsieh, C.-J., & Chang, K.-W. (2019). VisualBERT: A simple and performant baseline for vision and language. arXiv: 1908.03557."},{"issue":"6","key":"10.1016\/j.eswa.2026.131669_bib0032","doi-asserted-by":"crossref","first-page":"3873","DOI":"10.21037\/qims-22-1158","article-title":"Automatic knowledge extraction from chinese electronic medical records and rheumatoid arthritis knowledge graph construction","volume":"13","author":"Liu","year":"2023","journal-title":"Quantitative Imaging in Medicine and Surgery"},{"issue":"1","key":"10.1016\/j.eswa.2026.131669_bib0033","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1109\/JBHI.2022.3217810","article-title":"Multimodal data matters: Language model pre-training over structured and unstructured electronic health records","volume":"27","author":"Liu","year":"2022","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.1016\/j.eswa.2026.131669_bib0034","series-title":"Proceedings of the biocreative III workshop","first-page":"1","article-title":"Overview of biocreative III gene normalization","author":"Lu","year":"2009"},{"key":"10.1016\/j.eswa.2026.131669_bib0035","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"10.1016\/j.eswa.2026.131669_bib0036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3457607","article-title":"A survey on bias and fairness in machine learning","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"issue":"10s","key":"10.1016\/j.eswa.2026.131669_bib0037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3522747","article-title":"A survey on deep learning and explainability for automatic report generation from medical images","volume":"54","author":"Messina","year":"2022","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.1016\/j.eswa.2026.131669_bib0038","unstructured":"National Medical Products Administration (n.d.). Udi database. https:\/\/udi.nmpa.gov.cn\/download.html, Accessed: 2024-09-25."},{"key":"10.1016\/j.eswa.2026.131669_bib0039","series-title":"Icml","first-page":"689","article-title":"Multimodal deep learning","volume":"vol. 11","author":"Ngiam","year":"2011"},{"key":"10.1016\/j.eswa.2026.131669_bib0040","series-title":"Ethics and governance of artificial intelligence for health: Large multi-modal models. WHO guidance","author":"Organization","year":"2024"},{"issue":"3","key":"10.1016\/j.eswa.2026.131669_bib0041","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1177\/1460458217720400","article-title":"Reporting medical device safety incidents to regulatory authorities: An analysis and classification of technology-induced errors","volume":"25","author":"Palojoki","year":"2019","journal-title":"Health Informatics Journal"},{"key":"10.1016\/j.eswa.2026.131669_bib0042","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131669_bib0043","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.131669_bib0044","series-title":"Proceedings of the 38th International conference on machine learning (ICML)","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.131669_bib0045","doi-asserted-by":"crossref","first-page":"273","DOI":"10.4337\/9781802205657.ch16","article-title":"Us regulation of medical artificial intelligence and machine learning (ai\/ml) research and development","author":"Rahimzadeh","year":"2024","journal-title":"Research Handbook on Health, AI and the Law"},{"key":"10.1016\/j.eswa.2026.131669_bib0046","series-title":"Proceedings of the 2019 conference on empirical methods in natural language processing","first-page":"3982","article-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.eswa.2026.131669_bib0047","series-title":"Proceedings of the 22nd ACM SIGKDD International conference on knowledge discovery and data mining","first-page":"1135","article-title":"\u201d Why should i trust you?\u201d; explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"issue":"1","key":"10.1016\/j.eswa.2026.131669_bib0048","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-009-9124-7","article-title":"Ensemble-based classifiers","volume":"33","author":"Rokach","year":"2010","journal-title":"Artificial Intelligence Review"},{"issue":"5","key":"10.1016\/j.eswa.2026.131669_bib0049","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","article-title":"Term-weighting approaches in automatic text retrieval","volume":"24","author":"Salton","year":"1988","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.eswa.2026.131669_bib0050","series-title":"Proceedings of the IEEE International conference on computer vision","first-page":"618","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"10.1016\/j.eswa.2026.131669_bib0051","unstructured":"Sennrich, R., Haddow, B., & Birch, A. (2015). Improving neural machine translation models with monolingual data. arXiv: 1511.06709."},{"issue":"1","key":"10.1016\/j.eswa.2026.131669_bib0052","first-page":"3","article-title":"Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: A randomised clinical trial","volume":"24","author":"Shimabukuro","year":"2017","journal-title":"JAMIA Open"},{"key":"10.1016\/j.eswa.2026.131669_bib0053","unstructured":"Simonetta, A., & Paoletti, M. C. (2024). Iso\/iec standards and design of an artificial intelligence system."},{"key":"10.1016\/j.eswa.2026.131669_bib0054","first-page":"1","article-title":"Regulation 2024\/1689 of the Eur. Parl. & Council of June 13, 2024 (EU artificial intelligence act)","author":"Smuha","year":"2025","journal-title":"International Legal Materials"},{"key":"10.1016\/j.eswa.2026.131669_bib0055","article-title":"Fixmatch: simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"Sohn","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.eswa.2026.131669_bib0056","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":"5100","article-title":"Lxmert: Learning cross-modality encoder representations from transformers","author":"Tan","year":"2019"},{"key":"10.1016\/j.eswa.2026.131669_bib0057","series-title":"International conference on machine learning","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.eswa.2026.131669_bib0058","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"issue":"3","key":"10.1016\/j.eswa.2026.131669_bib0059","first-page":"83","article-title":"Iso 14971-medical device risk management standard","volume":"3","author":"Teferra","year":"2017","journal-title":"International Journal of Latest Research in Engineering and Technology (IJLRET)"},{"key":"10.1016\/j.eswa.2026.131669_bib0060","series-title":"Xiii jornadas de cloud computing, big data & emerging topics (la plata, 24 al 26 de junio de 2025)","article-title":"Ensuring quality in the OECD AI lifecycle through ISO\/IEC standards","author":"Torres","year":"2025"},{"key":"10.1016\/j.eswa.2026.131669_bib0061","series-title":"Advances in neural information processing systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.eswa.2026.131669_bib0062","unstructured":"Wei, J., & Zou, K. (2019). Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv: 1901.11196."},{"key":"10.1016\/j.eswa.2026.131669_bib0063","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"10687","article-title":"Self-training with noisy student improves imagenet classification","author":"Xie","year":"2020"},{"key":"10.1016\/j.eswa.2026.131669_bib0064","series-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"10687","article-title":"Self-training with noisy student improves imagenet classification","author":"Xie","year":"2020"},{"key":"10.1016\/j.eswa.2026.131669_bib0065","unstructured":"Yang, A., Pan, J., Lin, J., Men, R., Zhang, Y., Zhou, J., & Zhou, C. (2022). Chinese CLIP: Contrastive vision-language pretraining in chinese. arXiv: 2211.01335."},{"key":"10.1016\/j.eswa.2026.131669_bib0066","series-title":"33rd annual meeting of the association for computational linguistics","first-page":"189","article-title":"Unsupervised word sense disambiguation rivaling supervised methods","author":"Yarowsky","year":"1995"},{"key":"10.1016\/j.eswa.2026.131669_bib0067","unstructured":"Zhang, Z., Liang, Y., Liu, Y., Zhang, N., Zhang, Y., & Zhu, W. (2021). Textclass: A large-scale chinese medical text classification benchmark. arXiv: 2106.05361."}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426005828?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426005828?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:11:45Z","timestamp":1773843105000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426005828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":67,"alternative-id":["S0957417426005828"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131669","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Toward automated regulatory decision-making: AI-assisted medical device risk classification with multimodal transformers and self-training","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131669","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"131669"}}