{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:29:44Z","timestamp":1756384184876,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031677502"},{"type":"electronic","value":"9783031677519"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-67751-9_6","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T19:02:53Z","timestamp":1722538973000},"page":"66-80","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Human-in-the-Loop Chest X-Ray Diagnosis: Enhancing Large Multimodal Models with\u00a0Eye Fixation Inputs"],"prefix":"10.1007","author":[{"given":"Yunsoo","family":"Kim","sequence":"first","affiliation":[]},{"given":"Jinge","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yusuf","family":"Abdulle","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Honghan","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"6_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"6_CR2","unstructured":"Bae, S., et\u00a0al.: EHRXQA: a multi-modal question answering dataset for electronic health records with chest X-ray images. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"10","key":"6_CR3","doi-asserted-by":"publisher","DOI":"10.2196\/13440","volume":"21","author":"N Bott","year":"2019","unstructured":"Bott, N.: A protocol-driven, bedside digital conversational agent to support nurse teams and mitigate risks of hospitalization in older adults: case control pre-post study. J. Med. Internet Res. 21(10), e13440 (2019)","journal-title":"J. Med. Internet Res."},{"key":"6_CR4","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s13244-016-0534-1","volume":"8","author":"AP Brady","year":"2017","unstructured":"Brady, A.P.: Error and discrepancy in radiology: inevitable or avoidable? Insights Imaging 8, 171\u2013182 (2017)","journal-title":"Insights Imaging"},{"key":"6_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102285","volume":"127","author":"FM Calisto","year":"2022","unstructured":"Calisto, F.M., Santiago, C., Nunes, N., Nascimento, J.C.: Breast screening-AI: evaluating medical intelligent agents for human-AI interactions. Artif. Intell. Med. 127, 102285 (2022)","journal-title":"Artif. Intell. Med."},{"key":"6_CR6","unstructured":"Chen, Z., et\u00a0al.: Meditron-70B: scaling medical pretraining for large language models. arXiv preprint arXiv:2311.16079 (2023)"},{"key":"6_CR7","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: FlashAttention: fast and memory-efficient exact attention with IO-awareness. In: Advances in Neural Information Processing Systems, vol. 35, pp. 16344\u201316359 (2022)"},{"key":"6_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103436","volume":"107","author":"A Feder","year":"2020","unstructured":"Feder, A., Vainstein, D., Rosenfeld, R., Hartman, T., Hassidim, A., Matias, Y.: Active deep learning to detect demographic traits in free-form clinical notes. J. Biomed. Inform. 107, 103436 (2020)","journal-title":"J. Biomed. Inform."},{"key":"6_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109947","volume":"133","author":"Y Gao","year":"2023","unstructured":"Gao, Y., Fu, X., Chen, Y., Guo, C., Wu, J.: Post-pandemic healthcare for covid-19 vaccine: tissue-aware diagnosis of cervical lymphadenopathy via multi-modal ultrasound semantic segmentation. Appl. Soft Comput. 133, 109947 (2023)","journal-title":"Appl. Soft Comput."},{"key":"6_CR10","unstructured":"Groves, E., et al.: Benchmarking and analyzing in-context learning, fine-tuning and supervised learning for biomedical knowledge curation: a focused study on chemical entities of biological interest. arXiv preprint arXiv:2312.12989 (2023)"},{"key":"6_CR11","unstructured":"He, P., Gao, J., Chen, W.: DeBERTaV3: improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543 (2021)"},{"key":"6_CR12","unstructured":"Hsieh, C., Ouyang, C., Nascimento, J.C., Pereira, J., Jorge, J., Moreira, C.: MIMIC-EYE: integrating MIMIC datasets with REFLACX and eye gaze for multimodal deep learning applications (2023)"},{"key":"6_CR13","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"6_CR14","unstructured":"Hyland, S.L., et\u00a0al.: MAIRA-1: a specialised large multimodal model for radiology report generation. arXiv preprint arXiv:2311.13668 (2023)"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Ji, C., et al.: Mammo-Net: integrating gaze supervision and interactive information in multi-view mammogram classification. In: Greenspan, H., et al. (eds.) MICCAI 2023, vol. 14226 pp. 68\u201378. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43990-2_7","DOI":"10.1007\/978-3-031-43990-2_7"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Kweon, S., et\u00a0al.: Publicly shareable clinical large language model built on synthetic clinical notes. arXiv preprint arXiv:2309.00237 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.305"},{"key":"6_CR17","unstructured":"Lee, S., Youn, J., Kim, M., Yoon, S.H.: CXR-LLAVA: multimodal large language model for interpreting chest X-ray images. arXiv preprint arXiv:2310.18341 (2023)"},{"key":"6_CR18","unstructured":"Li, C., et al.: LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: A comprehensive study of GPT-4V\u2019s multimodal capabilities in medical imaging. medRxiv, pp. 2023\u201311 (2023)","DOI":"10.1101\/2023.11.03.23298067"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Liu, F., Shareghi, E., Meng, Z., Basaldella, M., Collier, N.: Self-alignment pretraining for biomedical entity representations. arXiv preprint arXiv:2010.11784 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.334"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"6_CR22","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Ma, C., et al.: Eye-gaze-guided vision transformer for rectifying shortcut learning. IEEE Trans. Med. Imaging (2023)","DOI":"10.1109\/TMI.2023.3287572"},{"issue":"suppl 4","key":"6_CR24","first-page":"768","volume":"33","author":"V Markoti\u0107","year":"2021","unstructured":"Markoti\u0107, V., Poju\u017eina, T., Radan\u010devi\u0107, D., Miljko, M., Pokraj\u010di\u0107, V.: The radiologist workload increase; where is the limit? Mini review and case study. Psychiatr. Danub. 33(suppl 4), 768\u2013770 (2021)","journal-title":"Psychiatr. Danub."},{"key":"6_CR25","unstructured":"OpenAI: ChatGPT (2023). https:\/\/chat.openai.com\/chat"},{"key":"6_CR26","unstructured":"OpenAI: GPT-4 (2023). https:\/\/www.openai.com\/gpt-4"},{"key":"6_CR27","doi-asserted-by":"publisher","unstructured":"Patel, B.N., et al.: Human\u2013machine partnership with artificial intelligence for chest radiograph diagnosis. npj Digit. Med. 2(1), 111 (2019). https:\/\/doi.org\/10.1038\/s41746-019-0189-7","DOI":"10.1038\/s41746-019-0189-7"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"issue":"1","key":"6_CR29","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s41746-024-01010-1","volume":"7","author":"T Savage","year":"2024","unstructured":"Savage, T., Nayak, A., Gallo, R., Rangan, E., Chen, J.H.: Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine. npj Digit. Med. 7(1), 20 (2024)","journal-title":"npj Digit. Med."},{"key":"6_CR30","unstructured":"Singhal, K., et\u00a0al.: Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617 (2023)"},{"key":"6_CR31","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"6_CR32","unstructured":"Toma, A., Lawler, P.R., Ba, J., Krishnan, R.G., Rubin, B.B., Wang, B.: Clinical camel: an open-source expert-level medical language model with dialogue-based knowledge encoding. arXiv preprint arXiv:2305.12031 (2023)"},{"key":"6_CR33","unstructured":"Tu, T., et\u00a0al.: Towards generalist biomedical AI. arXiv preprint arXiv:2307.14334 (2023)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Ushio, A., Camacho-Collados, J.: T-NER: an all-round python library for transformer-based named entity recognition. arXiv preprint arXiv:2209.12616 (2022)","DOI":"10.18653\/v1\/2021.eacl-demos.7"},{"key":"6_CR35","unstructured":"Wang, Z.J., Choi, D., Xu, S., Yang, D.: Putting humans in the natural language processing loop: a survey. arXiv preprint arXiv:2103.04044 (2021)"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Wei, C.H., et al.: Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task. Database 2016 (2016)","DOI":"10.1093\/database\/baw032"},{"key":"6_CR37","unstructured":"Wu, J., et al.: Exploring multimodal large language models for radiology report error-checking. arXiv preprint arXiv:2312.13103 (2023)"},{"key":"6_CR38","unstructured":"Wu, J., Kim, Y., Wu, H.: Hallucination benchmark in medical visual question answering. arXiv preprint arXiv:2401.05827 (2024)"}],"container-title":["Lecture Notes in Computer Science","Trustworthy Artificial Intelligence for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-67751-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:11:20Z","timestamp":1732551080000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-67751-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031677502","9783031677519"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-67751-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TAI4H","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Trustworthy Artificial Intelligence for Healthcare","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tml4h2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}