{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:59:52Z","timestamp":1778169592195,"version":"3.51.4"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3402066","type":"journal-article","created":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T17:31:51Z","timestamp":1715880711000},"page":"69710-69727","source":"Crossref","is-referenced-by-count":15,"title":["Language Models for Hierarchical Classification of Radiology Reports With Attention Mechanisms, BERT, and GPT-4"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9843-7854","authenticated-orcid":false,"given":"Matteo","family":"Olivato","sequence":"first","affiliation":[{"name":"Department of Information Engineering, University of Brescia, Brescia, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5055-6812","authenticated-orcid":false,"given":"Luca","family":"Putelli","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Brescia, Brescia, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9713-6630","authenticated-orcid":false,"given":"Nicola","family":"Arici","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Brescia, Brescia, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-6386","authenticated-orcid":false,"given":"Alfonso","family":"Emilio Gerevini","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Brescia, Brescia, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7175-6804","authenticated-orcid":false,"given":"Alberto","family":"Lavelli","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7785-9492","authenticated-orcid":false,"given":"Ivan","family":"Serina","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Brescia, Brescia, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3296260"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.09.179"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77211-6_36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/fi15020079"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2767063"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.05.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.47672\/ejt.1473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/AIC57670.2023.10263979"},{"key":"ref9","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. Adv. Neural Inf. Process. Syst., 27th Annu. Conf. Neural Inf. Process. Syst.","author":"Mikolov"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3388218.3388229"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICA50127.2020.9182390"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.14445\/22315381\/IJETT-V48P253"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35166-3_32"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1100"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref20","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv:2206.07682"},{"key":"ref21","article-title":"Large language models are human-level prompt engineers","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Zhou"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"ref23","article-title":"A prompt pattern catalog to enhance prompt engineering with ChatGPT","author":"White","year":"2023","journal-title":"arXiv:2302.11382"},{"key":"ref24","article-title":"The parrot dilemma: Human-labeled vs. LLM-augmented data in classification tasks","author":"M\u00f8ller","year":"2023","journal-title":"arXiv:2304.13861"},{"key":"ref25","article-title":"Gpt-4: A review on advancements and opportunities in natural language processing","author":"Baktash","year":"2023","journal-title":"arXiv:2305.03195"},{"key":"ref26","article-title":"Capabilities of GPT-4 on medical challenge problems","author":"Nori","year":"2023","journal-title":"arXiv:2303.13375"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.08.045"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77211-6_42"},{"key":"ref29","first-page":"16","article-title":"On the behaviour of BERT\u2019s attention for the classification of medical reports","volume-title":"Proc. CEUR Workshop","volume":"3277","author":"Putelli"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2021200113"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1053\/j.sult.2022.02.007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-021-01533-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2023.1184919"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s12028-022-01513-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210258"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220055"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1177\/21925682211026910"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2023.100512"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03172-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1021\/acs.est.3c01818"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4335905"},{"key":"ref43","article-title":"Evaluating large language models for radiology natural language processing","author":"Liu","year":"2023","journal-title":"arXiv:2307.13693"},{"key":"ref44","article-title":"PaLM 2 technical report","volume-title":"arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref45","article-title":"The TextPro tool suite","volume-title":"Proc. Int. Conf. Lang. Resour. Eval. (LREC)","author":"Pianta"},{"issue":"1","key":"ref46","first-page":"981","article-title":"Conditional random field with high-order dependencies for sequence labeling and segmentation","volume":"15","author":"Nguyen","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53817-4_4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1211"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref51","article-title":"Feed-forward networks with attention can solve some long-term memory problems","author":"Raffel","year":"2015","journal-title":"arXiv:1512.08756"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1086"},{"key":"ref53","volume-title":"GPT-4 System Card","year":"2023"},{"key":"ref54","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27181-6_32"},{"key":"ref56","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref57","article-title":"GPT-3: Generative pre-trained transformer 3","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref58","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI Blog"},{"key":"ref59","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"arXiv:1905.14165"},{"key":"ref60","article-title":"GPT-2: A 1.5B parameter language model","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref61","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104431"},{"key":"ref63","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent (ICLR)","author":"Loshchilov"},{"key":"ref64","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023","journal-title":"arXiv:2305.10601"},{"key":"ref65","article-title":"Large language model guided tree-of-thought","author":"Long","year":"2023","journal-title":"arXiv:2305.08291"},{"key":"ref66","article-title":"Query-dependent prompt evaluation and optimization with offline inverse RL","author":"Sun","year":"2023","journal-title":"arXiv:2309.06553"},{"key":"ref67","volume-title":"Keras","author":"Chollet","year":"2015"},{"key":"ref68","volume-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","author":"Abadi","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref70","article-title":"Clinical document classification using labeled and unlabeled data across hospitals","volume-title":"Proc. Amer. Med. Inform. Assoc. Annu. Symp. (AMIA)","author":"Hassanzadeh"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966408"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-018-0723-6"},{"key":"ref73","article-title":"Multi-task learning applied to biomedical named entity recognition task","volume-title":"Proc. 6th Italian Conf. Comput. Linguistics","volume":"2481","author":"Mehmood"},{"key":"ref74","article-title":"The impact of self-interaction attention on the extraction of drug-drug interactions","volume-title":"Proc. 6th Italian Conf. Comput. Linguistics","volume":"2481","author":"Putelli"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10531266.pdf?arnumber=10531266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T05:14:27Z","timestamp":1725426867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10531266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3402066","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}