Timothy A Miller, Andrew J McMurry, James Jones, Daniel Gottlieb, Kenneth D Mandl
Objective: To implement an open source, free, and easily deployable high throughput natural language processing module to extract concepts from clinician notes and map them to Fast Healthcare Interoperability Resources (FHIR). Materials and Methods: Using a popular open-source NLP tool (Apache cTAKES), we create FHIR resources that use modifier extensions to represent negation and NLP sourcing, and another extension to represent provenance of extracted concepts. Results: The SMART Text2FHIR Pipeline is an open-source tool, released through standard package managers, and publicly available container images that implement the mappings, enabling ready conversion of clinical text to FHIR. Discussion: With the increased data liquidity because of new interoperability regulations, NLP processes that can output FHIR can enable a common language for transporting structured and unstructured data. This framework can be valuable for critical public health or clinical research use cases. Conclusion: Future work should include mapping more categories of NLP-extracted information into FHIR resources and mappings from additional open-source NLP tools.
{"title":"The SMART Text2FHIR Pipeline.","authors":"Timothy A Miller, Andrew J McMurry, James Jones, Daniel Gottlieb, Kenneth D Mandl","doi":"","DOIUrl":"","url":null,"abstract":"<p><p><b>Objective</b>: To implement an open source, free, and easily deployable high throughput natural language processing module to extract concepts from clinician notes and map them to Fast Healthcare Interoperability Resources (FHIR). <b>Materials and Methods</b>: Using a popular open-source NLP tool (Apache cTAKES), we create FHIR resources that use modifier extensions to represent negation and NLP sourcing, and another extension to represent provenance of extracted concepts. <b>Results</b>: The SMART Text2FHIR Pipeline is an open-source tool, released through standard package managers, and publicly available container images that implement the mappings, enabling ready conversion of clinical text to FHIR. <b>Discussion</b>: With the increased data liquidity because of new interoperability regulations, NLP processes that can output FHIR can enable a common language for transporting structured and unstructured data. This framework can be valuable for critical public health or clinical research use cases. <b>Conclusion</b>: Future work should include mapping more categories of NLP-extracted information into FHIR resources and mappings from additional open-source NLP tools.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785871/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467631","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}
Hongzhi Wang, Amirhossein Sarrami, Joy Tzung-Yu Wu, Lucia Baratto, Arjun Sharma, Ken C L Wong, Shashi Bhushan Singh, Heike E Daldrup-Link, Tanveer Syeda-Mahmood
Lymphoma is one of the most common types of cancer for children (ages 0 to 19). Due to the reduced radiation exposure, PET/MR systems that allow simultaneous PET and MR imaging have become the standard of care for diagnosing cancers and monitoring tumor response to therapy in the pediatric population. In this work, we developed a multimodal deep learning algorithm for automatic pediatric lymphoma detection using PET and MRI. Through innovative designs such as standardized uptake value (SUV) guided tumor candidate generation, location aware classification model learning and weighted multimodal feature fusion, our algorithm can be effectively trained with limited data and achieved superior tumor detection performance over the state-of-the-art in our experiments.
淋巴瘤是儿童(0 至 19 岁)最常见的癌症类型之一。由于减少了辐射暴露,可同时进行 PET 和 MR 成像的 PET/MR 系统已成为诊断癌症和监测肿瘤对儿科治疗反应的标准。在这项工作中,我们开发了一种利用 PET 和 MRI 自动检测儿科淋巴瘤的多模态深度学习算法。通过标准化摄取值(SUV)引导的候选肿瘤生成、位置感知分类模型学习和加权多模态特征融合等创新设计,我们的算法可以用有限的数据进行有效训练,并在实验中取得了优于最先进水平的肿瘤检测性能。
{"title":"Multimodal Pediatric Lymphoma Detection using PET and MRI.","authors":"Hongzhi Wang, Amirhossein Sarrami, Joy Tzung-Yu Wu, Lucia Baratto, Arjun Sharma, Ken C L Wong, Shashi Bhushan Singh, Heike E Daldrup-Link, Tanveer Syeda-Mahmood","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Lymphoma is one of the most common types of cancer for children (ages 0 to 19). Due to the reduced radiation exposure, PET/MR systems that allow simultaneous PET and MR imaging have become the standard of care for diagnosing cancers and monitoring tumor response to therapy in the pediatric population. In this work, we developed a multimodal deep learning algorithm for automatic pediatric lymphoma detection using PET and MRI. Through innovative designs such as standardized uptake value (SUV) guided tumor candidate generation, location aware classification model learning and weighted multimodal feature fusion, our algorithm can be effectively trained with limited data and achieved superior tumor detection performance over the state-of-the-art in our experiments.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785920/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467640","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}
Katherine A Brown, Kathleen R Donise, Mary Kathryn Cancilliere, Dilum P Aluthge, Elizabeth S Chen
Individuals diagnosed with autism spectrum disorder (ASD) are at a higher risk for mental health concerns including suicidal thoughts and behaviors (STB). Limited studies have focused on suicidal risk factors that are more prevalent or unique to the population with ASD. This study sought to characterize and classify youth presenting to the psychiatric emergency department (ED) for a chief complaint of STB. The results of this study validated that a high number of patients with ASD present to the ED with STB. There were important differences in clinical characteristics to those with ASD versus those without. Clinical features that showed important impact in predicting high suicide risk in the ASD cases include elements of the mental status exam such as affect, trauma symptoms, abuse history, and auditory hallucinations. Focused attention is needed on these unique differences in ASD cases so that suicide risk level can be appropriately and promptly addressed.
{"title":"Characterizing Autism Spectrum Disorder and Predicting Suicide Risk for Pediatric Psychiatric Emergency Services Encounters.","authors":"Katherine A Brown, Kathleen R Donise, Mary Kathryn Cancilliere, Dilum P Aluthge, Elizabeth S Chen","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Individuals diagnosed with autism spectrum disorder (ASD) are at a higher risk for mental health concerns including suicidal thoughts and behaviors (STB). Limited studies have focused on suicidal risk factors that are more prevalent or unique to the population with ASD. This study sought to characterize and classify youth presenting to the psychiatric emergency department (ED) for a chief complaint of STB. The results of this study validated that a high number of patients with ASD present to the ED with STB. There were important differences in clinical characteristics to those with ASD versus those without. Clinical features that showed important impact in predicting high suicide risk in the ASD cases include elements of the mental status exam such as affect, trauma symptoms, abuse history, and auditory hallucinations. Focused attention is needed on these unique differences in ASD cases so that suicide risk level can be appropriately and promptly addressed.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785882/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467653","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}
Chia-Yuan Chang, Jiayi Yuan, Sirui Ding, Qiaoyu Tan, Kai Zhang, Xiaoqian Jiang, Xia Hu, Na Zou
Clinical trials are indispensable in developing new treatments, but they face obstacles in patient recruitment and retention, hindering the enrollment of necessary participants. To tackle these challenges, deep learning frameworks have been created to match patients to trials. These frameworks calculate the similarity between patients and clinical trial eligibility criteria, considering the discrepancy between inclusion and exclusion criteria. Recent studies have shown that these frameworks outperform earlier approaches. However, deep learning models may raise fairness issues in patient-trial matching when certain sensitive groups of individuals are underrepresented in clinical trials, leading to incomplete or inaccurate data and potential harm. To tackle the issue of fairness, this work proposes a fair patient-trial matching framework by generating a patient-criterion level fairness constraint. The proposed framework considers the inconsistency between the embedding of inclusion and exclusion criteria among patients of different sensitive groups. The experimental results on real-world patient-trial and patient-criterion matching tasks demonstrate that the proposed framework can successfully alleviate the predictions that tend to be biased.
{"title":"Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraint.","authors":"Chia-Yuan Chang, Jiayi Yuan, Sirui Ding, Qiaoyu Tan, Kai Zhang, Xiaoqian Jiang, Xia Hu, Na Zou","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Clinical trials are indispensable in developing new treatments, but they face obstacles in patient recruitment and retention, hindering the enrollment of necessary participants. To tackle these challenges, deep learning frameworks have been created to match patients to trials. These frameworks calculate the similarity between patients and clinical trial eligibility criteria, considering the discrepancy between inclusion and exclusion criteria. Recent studies have shown that these frameworks outperform earlier approaches. However, deep learning models may raise fairness issues in patient-trial matching when certain sensitive groups of individuals are underrepresented in clinical trials, leading to incomplete or inaccurate data and potential harm. To tackle the issue of fairness, this work proposes a fair patient-trial matching framework by generating a patient-criterion level fairness constraint. The proposed framework considers the inconsistency between the embedding of inclusion and exclusion criteria among patients of different sensitive groups. The experimental results on real-world patient-trial and patient-criterion matching tasks demonstrate that the proposed framework can successfully alleviate the predictions that tend to be biased.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139465532","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}
Yongqiu Li, Xing He, Christopher Wheldon, Yonghui Wu, Mattia Prosperi, Elizabeth A Shenkman, Michael S Jaffee, Jingchuan Guo, Fei Wang, Yi Guo, Jiang Bian
Sexual gender minorities, including lesbian, gay, and bisexual (LGB) individuals face unique challenges due to discrimination, stigma, and marginalization, which negatively impact their well-being. Electronic health record (EHR) systems present an opportunity for LGB research, but accurately identifying LGB individuals in EHRs is challenging. Our study developed and validated a rule-based computable phenotype (CP) to identify LGB individuals and their subgroups using both structured data and unstructured clinical narratives from a large integrated health system. Validating against a sample of 537 chart-reviewed patients, our three best performing CP algorithms balancing different performance metrics, each achieved sensitivity of 1.000, PPV of 0.982, and F1-score of 0.875 in identifying LGB individuals, respectively. Applying the three best-performing CPs, our study also found that the LGB population is younger and experiences a disproportionate burden of adverse health outcomes, particularly mental health distress.
{"title":"A Computable Phenotype for the Identification of Sexual and Gender Minorities in Electronic Health Records.","authors":"Yongqiu Li, Xing He, Christopher Wheldon, Yonghui Wu, Mattia Prosperi, Elizabeth A Shenkman, Michael S Jaffee, Jingchuan Guo, Fei Wang, Yi Guo, Jiang Bian","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Sexual gender minorities, including lesbian, gay, and bisexual (LGB) individuals face unique challenges due to discrimination, stigma, and marginalization, which negatively impact their well-being. Electronic health record (EHR) systems present an opportunity for LGB research, but accurately identifying LGB individuals in EHRs is challenging. Our study developed and validated a rule-based computable phenotype (CP) to identify LGB individuals and their subgroups using both structured data and unstructured clinical narratives from a large integrated health system. Validating against a sample of 537 chart-reviewed patients, our three best performing CP algorithms balancing different performance metrics, each achieved sensitivity of 1.000, PPV of 0.982, and F1-score of 0.875 in identifying LGB individuals, respectively. Applying the three best-performing CPs, our study also found that the LGB population is younger and experiences a disproportionate burden of adverse health outcomes, particularly mental health distress.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785915/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467065","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}
Amanda J Moy, Kenrick D Cato, Eugene Y Kim, Jennifer Withall, Sarah C Rossetti
Workflow fragmentation, defined as task switching, may be one proxy to quantify electronic health record (EHR) documentation burden in the emergency department (ED). Few measures have been operationalized to evaluate task switching at scale. Theoretically grounded in the time-based resource-sharing model (TBRSM) which conceives task switching as proportional to the cognitive load experienced, we describe the functional relationship between cognitive load and the time and effort constructs previously applied for measuring documentation burden. We present a computational framework, COMBINE, to evaluate multilevel task switching in the ED using EHR event logs. Based on this framework, we conducted a descriptive analysis on task switching among 63 full-time ED physicians from one ED site using EHR event logs extracted between April-June 2021 (n=2,068,605 events) which were matched to scheduled shifts (n=952). On average, we found a high volume of event-level (185.8±75.3/hr) and within-(6.6±1.7/chart) and between-patient chart (27.5±23.6/hr) switching per shift worked.
被定义为任务切换的工作流程碎片可能是量化急诊科(ED)电子健康记录(EHR)文档负担的一种替代方法。目前很少有可操作的措施来评估大规模的任务切换。基于时间的资源共享模型(TBRSM)认为任务切换与认知负荷成正比,我们以该模型为理论基础,描述了认知负荷与之前用于测量文档负担的时间和精力结构之间的功能关系。我们提出了一个名为 COMBINE 的计算框架,用于利用电子病历事件日志评估 ED 中的多层次任务切换。在此框架基础上,我们利用 2021 年 4 月至 6 月期间提取的 EHR 事件日志(n=2,068,605 个事件),对来自一个急诊室的 63 名全职急诊医生的任务切换情况进行了描述性分析,并与排定的班次(n=952)进行了匹配。我们发现,平均而言,每个轮班的事件级(185.8±75.3/小时)、病历内(6.6±1.7/张)和病历间(27.5±23.6/小时)的切换量都很高。
{"title":"A Computational Framework to Evaluate Emergency Department Clinician Task Switching in the Electronic Health Record Using Event Logs.","authors":"Amanda J Moy, Kenrick D Cato, Eugene Y Kim, Jennifer Withall, Sarah C Rossetti","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Workflow fragmentation, defined as task switching, may be one proxy to quantify electronic health record (EHR) documentation burden in the emergency department (ED). Few measures have been operationalized to evaluate task switching at scale. Theoretically grounded in the time-based resource-sharing model (TBRSM) which conceives task switching as proportional to the cognitive load experienced, we describe the functional relationship between cognitive load and the time and effort constructs previously applied for measuring documentation burden. We present a computational framework, COMBINE, to evaluate multilevel task switching in the ED using EHR event logs. Based on this framework, we conducted a descriptive analysis on task switching among 63 full-time ED physicians from one ED site using EHR event logs extracted between April-June 2021 (n=2,068,605 events) which were matched to scheduled shifts (n=952). On average, we found a high volume of event-level (185.8±75.3/hr) and within-(6.6±1.7/chart) and between-patient chart (27.5±23.6/hr) switching per shift worked.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785917/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467069","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}
Elise L Ruan, Sarah C Rossetti, Hanson Hsu, Eugene Y Kim, Richard C Trepp
Computerized provider order entry (CPOE) systems have been cited as a significant contributor to clinician burden. Vendor-derived measures and data sets have been developed to help with optimization of CPOE systems. We describe how we analyzed vendor-derived Order Friction (OF) EHR log data at our health system and propose a practical approach for optimizing CPOE systems by reducing OF. We also conducted a pre-post intervention study using OF data to evaluate the impact of defaulting the frequency of urine, stool and nasal swab tests and found that all modified orders had significantly fewer changes required per order (p<0.01). Our proposed approach is a six-step process: 1) understand the ordering process, 2) understand OF data elements contextually, 3) explore ordering user-level factors, 4) evaluate order volume and friction from different order sources, 5) optimize order-level design, 6) identify high volume alerts to evaluate for appropriateness.
计算机化医嘱输入系统(CPOE)被认为是加重临床医生负担的一个重要因素。为了帮助优化 CPOE 系统,我们开发了源自供应商的测量方法和数据集。我们介绍了如何在我们的医疗系统中分析来自供应商的订单摩擦 (OF) 电子病历日志数据,并提出了通过减少订单摩擦来优化 CPOE 系统的实用方法。我们还使用 OF 数据进行了一项事前事后干预研究,以评估默认尿液、粪便和鼻拭子检测频率的影响,结果发现所有修改后的订单每单所需的更改次数都明显减少(p<0.05)。
{"title":"A Practical Approach to Optimize Computerized Provider Order Entry Systems and Reduce Clinician Burden: Pre-Post Evaluation of Vendor-Derived \"Order Friction\" Data.","authors":"Elise L Ruan, Sarah C Rossetti, Hanson Hsu, Eugene Y Kim, Richard C Trepp","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Computerized provider order entry (CPOE) systems have been cited as a significant contributor to clinician burden. Vendor-derived measures and data sets have been developed to help with optimization of CPOE systems. We describe how we analyzed vendor-derived Order Friction (OF) EHR log data at our health system and propose a practical approach for optimizing CPOE systems by reducing OF. We also conducted a pre-post intervention study using OF data to evaluate the impact of defaulting the frequency of urine, stool and nasal swab tests and found that all modified orders had significantly fewer changes required per order (p<0.01). Our proposed approach is a six-step process: 1) understand the ordering process, 2) understand OF data elements contextually, 3) explore ordering user-level factors, 4) evaluate order volume and friction from different order sources, 5) optimize order-level design, 6) identify high volume alerts to evaluate for appropriateness.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785931/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467137","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}
Gaetano Manzo, Leo Anthony Celi, Yasmeen Shabazz, Rory Mulcahey, Lorenzo Jaime Flores, Dina Demner-Fushman
Caregivers' attitudes impact healthcare quality and disparities. Clinical notes contain highly specialized and ambiguous language that requires extensive domain knowledge to understand, and using negative language does not necessarily imply a negative attitude. This study discusses the challenge of detecting caregivers' attitudes from their clinical notes. To address these challenges, we annotate MIMIC clinical notes and train state-of-the-art language models from the Hugging Face platform. The study focuses on the Neonatal Intensive Care Unit and evaluates models in zero-shot, few-shot, and fully-trained scenarios. Among the chosen models, RoBERTa identifies caregivers' attitudes from clinical notes with an F1-score of 0.75. This approach not only enhances patient satisfaction, but opens up exciting possibilities for detecting and preventing care provider syndromes, such as fatigue, stress, and burnout. The paper concludes by discussing limitations and potential future work.
护理人员的态度会影响医疗质量和差异。临床笔记包含高度专业化和含糊不清的语言,需要广泛的领域知识才能理解,而使用负面语言并不一定意味着态度消极。本研究讨论了从护理人员的临床笔记中检测其态度所面临的挑战。为了应对这些挑战,我们对 MIMIC 临床笔记进行了注释,并从 Hugging Face 平台训练了最先进的语言模型。本研究以新生儿重症监护室为重点,评估了零镜头、少量镜头和完全训练场景下的模型。在所选模型中,RoBERTa 能从临床笔记中识别护理人员的态度,F1 分数为 0.75。这种方法不仅提高了患者满意度,而且为检测和预防护理人员综合症(如疲劳、压力和职业倦怠)提供了令人兴奋的可能性。论文最后讨论了局限性和未来可能开展的工作。
{"title":"Caregivers Attitude Detection From Clinical Notes.","authors":"Gaetano Manzo, Leo Anthony Celi, Yasmeen Shabazz, Rory Mulcahey, Lorenzo Jaime Flores, Dina Demner-Fushman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Caregivers' attitudes impact healthcare quality and disparities. Clinical notes contain highly specialized and ambiguous language that requires extensive domain knowledge to understand, and using negative language does not necessarily imply a negative attitude. This study discusses the challenge of detecting caregivers' attitudes from their clinical notes. To address these challenges, we annotate MIMIC clinical notes and train state-of-the-art language models from the Hugging Face platform. The study focuses on the Neonatal Intensive Care Unit and evaluates models in zero-shot, few-shot, and fully-trained scenarios. Among the chosen models, <i>RoBERTa</i> identifies caregivers' attitudes from clinical notes with an F1-score of 0.75. This approach not only enhances patient satisfaction, but opens up exciting possibilities for detecting and preventing care provider syndromes, such as fatigue, stress, and burnout. The paper concludes by discussing limitations and potential future work.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785866/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467368","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}
This study used social network analysis and trending hashtags on Twitter to identify trends related to health and vaccine equity during the Omicron wave. The analysis was conducted using consumer-friendly platforms/tools such as the Healthcare Hashtag Project and NodeXL. The study found that during the Omicron wave, there was a higher volume of tweets related to the more specific hashtag #VaccineEquity, as compared to the more general topic of #HealthEquity. The study also identified the top influencers for these hashtags and how they changed over time. The study proposes a combination of existing tools and approaches, including ontological surveillance and social network analysis, to develop proactive strategies that respond to public opinion in a timely manner. Social network analysis tools could also be useful for healthcare organizations and providers in training their staff involved in social media management to develop better social media communication strategies.
{"title":"COVID-19 vaccine equity and health equity conversations on Twitter.","authors":"Nishant R Jain, Iris Zachary, Suzanne A Boren","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>This study used social network analysis and trending hashtags on Twitter to identify trends related to health and vaccine equity during the Omicron wave. The analysis was conducted using consumer-friendly platforms/tools such as the Healthcare Hashtag Project and NodeXL. The study found that during the Omicron wave, there was a higher volume of tweets related to the more specific hashtag #VaccineEquity, as compared to the more general topic of #HealthEquity. The study also identified the top influencers for these hashtags and how they changed over time. The study proposes a combination of existing tools and approaches, including ontological surveillance and social network analysis, to develop proactive strategies that respond to public opinion in a timely manner. Social network analysis tools could also be useful for healthcare organizations and providers in training their staff involved in social media management to develop better social media communication strategies.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785937/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467417","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}
Anastasios Lamproudis, Sara Mora, Therese Olsen Svenning, Torbjørn Torsvik, Taridzo Chomutare, Phuong Dinh Ngo, Hercules Dalianis
The lack of relevant annotated datasets represents one key limitation in the application of Natural Language Processing techniques in a broad number of tasks, among them Protected Health Information (PHI) identification in Norwegian clinical text. In this work, the possibility of exploiting resources from Swedish, a very closely related language, to Norwegian is explored. The Swedish dataset is annotated with PHI information. Different processing and text augmentation techniques are evaluated, along with their impact in the final performance of the model. The augmentation techniques, such as injection and generation of both Norwegian and Scandinavian Named Entities into the Swedish training corpus, showed to increase the performance in the de-identification task for both Danish and Norwegian text. This trend was also confirmed by the evaluation of model performance on a sample Norwegian gastro surgical clinical text.
{"title":"De-identifying Norwegian Clinical Text using Resources from Swedish and Danish.","authors":"Anastasios Lamproudis, Sara Mora, Therese Olsen Svenning, Torbjørn Torsvik, Taridzo Chomutare, Phuong Dinh Ngo, Hercules Dalianis","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The lack of relevant annotated datasets represents one key limitation in the application of Natural Language Processing techniques in a broad number of tasks, among them Protected Health Information (PHI) identification in Norwegian clinical text. In this work, the possibility of exploiting resources from Swedish, a very closely related language, to Norwegian is explored. The Swedish dataset is annotated with PHI information. Different processing and text augmentation techniques are evaluated, along with their impact in the final performance of the model. The augmentation techniques, such as injection and generation of both Norwegian and Scandinavian Named Entities into the Swedish training corpus, showed to increase the performance in the de-identification task for both Danish and Norwegian text. This trend was also confirmed by the evaluation of model performance on a sample Norwegian gastro surgical clinical text.</p>","PeriodicalId":72180,"journal":{"name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10785939/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139467431","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}