Pub Date : 2022-06-01Epub Date: 2022-09-08DOI: 10.1109/ichi54592.2022.00050
Song Wang, Mingquan Lin, Ying Ding, George Shih, Zhiyong Lu, Yifan Peng
Analyzing radiology reports is a time-consuming and error-prone task, which raises the need for an efficient automated radiology report analysis system to alleviate the workloads of radiologists and encourage precise diagnosis. In this work, we present RadText, a high-performance open-source Python radiology text analysis system. RadText offers an easy-to-use text analysis pipeline, including de-identification, section segmentation, sentence split and word tokenization, named entity recognition, parsing, and negation detection. Superior to existing widely used toolkits, RadText features a hybrid text processing schema, supports raw text processing and local processing, which enables higher accuracy, better usability and improved data privacy. RadText adopts BioC as the unified interface, and also standardizes the output into a structured representation that is compatible with Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM), which allows for a more systematic approach to observational research across multiple, disparate data sources. We evaluated RadText on the MIMIC-CXR dataset, with five new disease labels that we annotated for this work. RadText demonstrates highly accurate classification performances, with a 0.91 average precision, 0.94 average recall and 0.92 average F-1 score. We also annotated a test set for the five new disease labels to facilitate future research or applications. We have made our code, documentations, examples and the test set available at https://github.com/bionlplab/radtext.
{"title":"Radiology Text Analysis System (RadText): Architecture and Evaluation.","authors":"Song Wang, Mingquan Lin, Ying Ding, George Shih, Zhiyong Lu, Yifan Peng","doi":"10.1109/ichi54592.2022.00050","DOIUrl":"https://doi.org/10.1109/ichi54592.2022.00050","url":null,"abstract":"<p><p>Analyzing radiology reports is a time-consuming and error-prone task, which raises the need for an efficient automated radiology report analysis system to alleviate the workloads of radiologists and encourage precise diagnosis. In this work, we present RadText, a high-performance open-source Python radiology text analysis system. RadText offers an easy-to-use text analysis pipeline, including de-identification, section segmentation, sentence split and word tokenization, named entity recognition, parsing, and negation detection. Superior to existing widely used toolkits, RadText features a hybrid text processing schema, supports raw text processing and local processing, which enables higher accuracy, better usability and improved data privacy. RadText adopts BioC as the unified interface, and also standardizes the output into a structured representation that is compatible with Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM), which allows for a more systematic approach to observational research across multiple, disparate data sources. We evaluated RadText on the MIMIC-CXR dataset, with five new disease labels that we annotated for this work. RadText demonstrates highly accurate classification performances, with a 0.91 average precision, 0.94 average recall and 0.92 average F-1 score. We also annotated a test set for the five new disease labels to facilitate future research or applications. We have made our code, documentations, examples and the test set available at https://github.com/bionlplab/radtext.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9484781/pdf/nihms-1836549.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"40373631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/ichi54592.2022.00120
Jianping He, Fang Li, Xinyue Hu, Jianfu Li, Yi Nian, Jingqi Wang, Yang Xiang, Qiang Wei, Hua Xu, Cui Tao
Biomedical relation extraction plays a critical role in the construction of high-quality knowledge graphs and databases, which can further support many downstream applications. Pre-trained prompt tuning, as a new paradigm, has shown great potential in many natural language processing (NLP) tasks. Through inserting a piece of text into the original input, prompt converts NLP tasks into masked language problems, which could be better addressed by pre-trained language models (PLMs). In this study, we applied pre-trained prompt tuning to chemical-protein relation extraction using the BioCreative VI CHEMPROT dataset. The experiment results showed that the pre-trained prompt tuning outperformed the baseline approach in chemical-protein interaction classification. We conclude that the prompt tuning can improve the efficiency of the PLMs on chemical-protein relation extraction tasks.
生物医学关系提取在构建高质量的知识图谱和数据库中起着至关重要的作用，可以进一步支持许多下游应用。预训练提示调优作为一种新的模式，在许多自然语言处理(NLP)任务中显示出巨大的潜力。通过在原始输入中插入一段文本，prompt将NLP任务转换为隐藏的语言问题，这些问题可以通过预训练的语言模型(plm)更好地解决。在这项研究中，我们使用BioCreative VI CHEMPROT数据集将预训练的提示调谐应用于化学-蛋白质关系提取。实验结果表明，预先训练的提示调整方法在化学-蛋白质相互作用分类中优于基线方法。我们的结论是，快速调整可以提高PLMs在化学-蛋白质关系提取任务中的效率。
{"title":"Chemical-Protein Relation Extraction with Pre-trained Prompt Tuning.","authors":"Jianping He, Fang Li, Xinyue Hu, Jianfu Li, Yi Nian, Jingqi Wang, Yang Xiang, Qiang Wei, Hua Xu, Cui Tao","doi":"10.1109/ichi54592.2022.00120","DOIUrl":"https://doi.org/10.1109/ichi54592.2022.00120","url":null,"abstract":"<p><p>Biomedical relation extraction plays a critical role in the construction of high-quality knowledge graphs and databases, which can further support many downstream applications. Pre-trained prompt tuning, as a new paradigm, has shown great potential in many natural language processing (NLP) tasks. Through inserting a piece of text into the original input, prompt converts NLP tasks into masked language problems, which could be better addressed by pre-trained language models (PLMs). In this study, we applied pre-trained prompt tuning to chemical-protein relation extraction using the BioCreative VI CHEMPROT dataset. The experiment results showed that the pre-trained prompt tuning outperformed the baseline approach in chemical-protein interaction classification. We conclude that the prompt tuning can improve the efficiency of the PLMs on chemical-protein relation extraction tasks.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10474649/pdf/nihms-1887657.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10514652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01Epub Date: 2022-09-08DOI: 10.1109/ichi54592.2022.00125
Shuang Yang, Xi Yang, Tianchen Lyu, Xing He, Dejana Braithwaite, Hiren J Mehta, Yi Guo, Yonghui Wu, Jiang Bian
This study aims to develop a natural language processing (NLP) tool to extract the pulmonary nodules and nodule characteristics information from free-text clinical narratives. We identified a cohort of 3,080 patients who received low dose computed tomography (LDCT) at the University of Florida health system and collected their clinical narratives including radiology reports in their electronic health records (EHRs). Then, we manually annotated 394 reports as the gold-standard corpus and explored three state-of-the-art transformer-based NLP methods. The best model achieved an F1-score of 0.9279.
本研究旨在开发一种自然语言处理（NLP）工具，从自由文本临床叙述中提取肺结节和结节特征信息。我们确定了佛罗里达大学医疗系统中接受低剂量计算机断层扫描（LDCT）的 3080 名患者，并收集了他们的临床叙述，包括电子健康记录（EHR）中的放射学报告。然后，我们人工标注了 394 份报告作为黄金标准语料库，并探索了三种最先进的基于转换器的 NLP 方法。最佳模型的 F1 分数为 0.9279。
{"title":"A Preliminary Study of Extracting Pulmonary Nodules and Nodule Characteristics from Radiology Reports Using Natural Language Processing.","authors":"Shuang Yang, Xi Yang, Tianchen Lyu, Xing He, Dejana Braithwaite, Hiren J Mehta, Yi Guo, Yonghui Wu, Jiang Bian","doi":"10.1109/ichi54592.2022.00125","DOIUrl":"10.1109/ichi54592.2022.00125","url":null,"abstract":"<p><p>This study aims to develop a natural language processing (NLP) tool to extract the pulmonary nodules and nodule characteristics information from free-text clinical narratives. We identified a cohort of 3,080 patients who received low dose computed tomography (LDCT) at the University of Florida health system and collected their clinical narratives including radiology reports in their electronic health records (EHRs). Then, we manually annotated 394 reports as the gold-standard corpus and explored three state-of-the-art transformer-based NLP methods. The best model achieved an F1-score of 0.9279.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9511964/pdf/nihms-1836669.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9655481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-27199-1_6
M. Musaev, I. Khujayarov, M. Ochilov
{"title":"Speech Recognition Technologies Based on Artificial Intelligence Algorithms","authors":"M. Musaev, I. Khujayarov, M. Ochilov","doi":"10.1007/978-3-031-27199-1_6","DOIUrl":"https://doi.org/10.1007/978-3-031-27199-1_6","url":null,"abstract":"","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77351466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-27199-1_43
Aelita Skaržauskienė, M. Maciuliene
{"title":"Co-creating Computer Supported Collective Intelligence in Citizen Science Hubs","authors":"Aelita Skaržauskienė, M. Maciuliene","doi":"10.1007/978-3-031-27199-1_43","DOIUrl":"https://doi.org/10.1007/978-3-031-27199-1_43","url":null,"abstract":"","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79758404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-27199-1_22
A. Singh, Ajit Kumar, Bong Jun Choi
{"title":"Privacy-Preserving Digital Intervention for Mental Health Using Federated Learning","authors":"A. Singh, Ajit Kumar, Bong Jun Choi","doi":"10.1007/978-3-031-27199-1_22","DOIUrl":"https://doi.org/10.1007/978-3-031-27199-1_22","url":null,"abstract":"","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79782557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-27199-1_28
Sonal Jain, D. Mahapatra, Mukesh Saini
{"title":"Real-Time Image Based Plant Phenotyping Using Tiny-YOLOv4","authors":"Sonal Jain, D. Mahapatra, Mukesh Saini","doi":"10.1007/978-3-031-27199-1_28","DOIUrl":"https://doi.org/10.1007/978-3-031-27199-1_28","url":null,"abstract":"","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85226542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-27199-1_30
Liang Tang, P. Ferronato, Masooda N. Bashir
{"title":"Do Users' Values Influence Trust in Automation?","authors":"Liang Tang, P. Ferronato, Masooda N. Bashir","doi":"10.1007/978-3-031-27199-1_30","DOIUrl":"https://doi.org/10.1007/978-3-031-27199-1_30","url":null,"abstract":"","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90744906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-27199-1_15
Vani, Sumit Singh, Puja Burman, Anmol Jain, U. Tiwary
{"title":"GWD: Graded Word Drop Model for When Type Questions for Hindi QA","authors":"Vani, Sumit Singh, Puja Burman, Anmol Jain, U. Tiwary","doi":"10.1007/978-3-031-27199-1_15","DOIUrl":"https://doi.org/10.1007/978-3-031-27199-1_15","url":null,"abstract":"","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90329035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-27199-1_25
Seongyun Ku, Sunghwan Kim, Minji You, M. D. Whitaker
{"title":"Building the Groundwork for a Natural Search, to Make Accurate and Trustworthy Filtered Searches: The Case of a New Educational Platform with a Global Heat Map to Geolocate Innovations in Renewable Energy","authors":"Seongyun Ku, Sunghwan Kim, Minji You, M. D. Whitaker","doi":"10.1007/978-3-031-27199-1_25","DOIUrl":"https://doi.org/10.1007/978-3-031-27199-1_25","url":null,"abstract":"","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73485715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号