首页 > 最新文献

International Journal of Medical Informatics最新文献

英文 中文
Technology for fast-tracking high-risk head and neck cancer referrals: Co-designing with patients 快速跟踪高风险头颈癌转诊的技术:与患者共同设计
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-23 DOI: 10.1016/j.ijmedinf.2024.105641
Chinasa Odo , Abigail Albutt , John Hardman , Joanne Patterson , Lynn Mcvey , Nikki Rousseau , Vinidh Paleri , Rebecca Randell

Background

Head and Neck Cancer (HNC) is the eighth most prevalent global cancer. Timely recognition of symptoms is crucial for reducing mortality rates. The EVolution of a patiEnt-REported symptom-based risk stratification sySTem to redesign the suspected Head and Neck cancer referral pathway (EVEREST-HN) study aims to develop and evaluate a risk stratification tool using patient reported symptoms, which will be populated remotely in the community before the patient is seen by the clinician to hasten HNC diagnosis. EVEREST-HN will design a patient SYmptom iNput Clinical (SYNC) system to gather patient symptom data and calculate a risk score to aid clinicians in identifying high-risk cases. This identification potentially allows for high-risk patients to be seen sooner, thereby improving patient outcomes.

Methods

Three workshop sessions were conducted involving a total of 17 unique participants, with several contributing to multiple sessions: nine in the co-design session, six in the validation session, and nine in the evaluation session. The co-design session employed online collaboration with patients’ representatives. Thematic analysis was used to identify requirements and concerns informing the development of a low-fidelity prototype. The validation session assessed whether the prototype aligned with patient expectations. In the evaluation session, participants interacted with an online prototype and provided further feedback.

Results

During the co-design workshop, participants emphasized the need for a concise and clear SYNC system questionnaire for reporting suspected HNC symptoms. Concerns were raised about questionnaire length, language clarity, and the inclusion of probing questions. Participants suggested concise questions using lay language, incorporating visual aids for topics like alcohol and tobacco use, and making the sexual activity question optional. Recommendations included diverse language options, hard copies for non-English speakers, and phone call options for those uncomfortable with screen-based technology. The validation workshop confirmed that the prototype reflected participants’ ideas. Feedback highlighted the need for call-back features to help those not confident with technology and the need to present symptom questions first before social background questions. Feedback from the evaluation demonstrated a commitment to efficiency, and continuous improvement.

Conclusion

This study aims to develop the SYNC system to enhance efficiency of suspected HNC referrals. The workshops highlighted the importance of end-user inclusiveness in the system development life cycle, with collaboration with stakeholders and repeated feedback, providing crucial insights for ensuring the SYNC system effectively addresses the needs and concerns of patients in the context of HNC diagnosis.
背景头颈癌(HNC)是全球发病率第八高的癌症。及时发现症状对降低死亡率至关重要。重新设计疑似头颈癌转诊路径的患者报告症状风险分层系统的演变(EVEREST-HN)研究旨在利用患者报告的症状开发和评估一种风险分层工具,该工具将在患者接受临床医生诊治之前在社区进行远程输入,以加快 HNC 诊断。EVEREST-HN 将设计一个患者 SYmptom iNput Clinical (SYNC) 系统,收集患者症状数据并计算风险评分,帮助临床医生识别高风险病例。方法共举办了三场研讨会,共有 17 人参加,其中多人参与了多场会议:9 人参与了共同设计会议,6 人参与了验证会议,9 人参与了评估会议。共同设计环节采用了与患者代表在线合作的方式。专题分析用于确定需求和关注点,为开发低保真原型提供信息。验证环节评估了原型是否符合患者的期望。在评估环节,与会者与在线原型进行了互动,并提供了进一步的反馈意见。结果在共同设计研讨会上,与会者强调需要一个简洁明了的 SYNC 系统问卷来报告疑似 HNC 症状。与会者对问卷的长度、语言清晰度以及是否包含探究性问题表示担忧。与会者建议使用通俗易懂的语言简明扼要地回答问题,针对酒精和烟草使用等主题加入直观教具,并将性活动问题作为可选项。建议还包括提供多种语言选择、为非英语使用者提供硬拷贝,以及为那些不习惯使用屏幕技术的人提供电话选项。验证研讨会确认原型反映了参与者的想法。反馈意见强调了回拨功能的必要性,以帮助那些对技术不自信的人,以及在提出社会背景问题之前先提出症状问题的必要性。评估反馈显示了对提高效率和持续改进的承诺。 结论本研究旨在开发 SYNC 系统,以提高疑似 HNC 转诊的效率。研讨会强调了在系统开发生命周期中吸纳最终用户的重要性,与利益相关者的合作和反复反馈为确保 SYNC 系统有效解决 HNC 诊断中患者的需求和关切提供了至关重要的见解。
{"title":"Technology for fast-tracking high-risk head and neck cancer referrals: Co-designing with patients","authors":"Chinasa Odo ,&nbsp;Abigail Albutt ,&nbsp;John Hardman ,&nbsp;Joanne Patterson ,&nbsp;Lynn Mcvey ,&nbsp;Nikki Rousseau ,&nbsp;Vinidh Paleri ,&nbsp;Rebecca Randell","doi":"10.1016/j.ijmedinf.2024.105641","DOIUrl":"10.1016/j.ijmedinf.2024.105641","url":null,"abstract":"<div><h3>Background</h3><div>Head and Neck Cancer (HNC) is the eighth most prevalent global cancer. Timely recognition of symptoms is crucial for reducing mortality rates. The EVolution of a patiEnt-REported symptom-based risk stratification sySTem to redesign the suspected Head and Neck cancer referral pathway (EVEREST-HN) study aims to develop and evaluate a risk stratification tool using patient reported symptoms, which will be populated remotely in the community before the patient is seen by the clinician to hasten HNC diagnosis. EVEREST-HN will design a patient SYmptom iNput Clinical (SYNC) system to gather patient symptom data and calculate a risk score to aid clinicians in identifying high-risk cases. This identification potentially allows for high-risk patients to be seen sooner, thereby improving patient outcomes.</div></div><div><h3>Methods</h3><div>Three workshop sessions were conducted involving a total of 17 unique participants, with several contributing to multiple sessions: nine in the co-design session, six in the validation session, and nine in the evaluation session. The co-design session employed online collaboration with patients’ representatives. Thematic analysis was used to identify requirements and concerns informing the development of a low-fidelity prototype. The validation session assessed whether the prototype aligned with patient expectations. In the evaluation session, participants interacted with an online prototype and provided further feedback.</div></div><div><h3>Results</h3><div>During the co-design workshop, participants emphasized the need for a concise and clear SYNC system questionnaire for reporting suspected HNC symptoms. Concerns were raised about questionnaire length, language clarity, and the inclusion of probing questions. Participants suggested concise questions using lay language, incorporating visual aids for topics like alcohol and tobacco use, and making the sexual activity question optional. Recommendations included diverse language options, hard copies for non-English speakers, and phone call options for those uncomfortable with screen-based technology. The validation workshop confirmed that the prototype reflected participants’ ideas. Feedback highlighted the need for call-back features to help those not confident with technology and the need to present symptom questions first before social background questions. Feedback from the evaluation demonstrated a commitment to efficiency, and continuous improvement.</div></div><div><h3>Conclusion</h3><div>This study aims to develop the SYNC system to enhance efficiency of suspected HNC referrals. The workshops highlighted the importance of end-user inclusiveness in the system development life cycle, with collaboration with stakeholders and repeated feedback, providing crucial insights for ensuring the SYNC system effectively addresses the needs and concerns of patients in the context of HNC diagnosis.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105641"},"PeriodicalIF":3.7,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Corrigendum to “Brain health scores to predict neurological outcomes from electronic health records” [Int. J. Med. Inform. (2023) 105270] 从电子健康记录中预测神经系统结果的脑健康评分"[Int. J. Med. Inform. (2023) 105270]的更正。
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-22 DOI: 10.1016/j.ijmedinf.2024.105633
Marta Fernandes , Haoqi Sun , Zeina Chemali , Shibani S. Mukerji , Lidia M.V.R. Moura , Sahar F. Zafar , Akshata Sonni , Alessandro Biffi , Jonathan Rosand , M. Brandon Westover
{"title":"Corrigendum to “Brain health scores to predict neurological outcomes from electronic health records” [Int. J. Med. Inform. (2023) 105270]","authors":"Marta Fernandes ,&nbsp;Haoqi Sun ,&nbsp;Zeina Chemali ,&nbsp;Shibani S. Mukerji ,&nbsp;Lidia M.V.R. Moura ,&nbsp;Sahar F. Zafar ,&nbsp;Akshata Sonni ,&nbsp;Alessandro Biffi ,&nbsp;Jonathan Rosand ,&nbsp;M. Brandon Westover","doi":"10.1016/j.ijmedinf.2024.105633","DOIUrl":"10.1016/j.ijmedinf.2024.105633","url":null,"abstract":"","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105633"},"PeriodicalIF":3.7,"publicationDate":"2024-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142309155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Development of a Natural Language Processing (NLP) model to automatically extract clinical data from electronic health records: results from an Italian comprehensive stroke center 开发自然语言处理 (NLP) 模型,自动提取电子健康记录中的临床数据:意大利综合中风中心的研究结果
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-19 DOI: 10.1016/j.ijmedinf.2024.105626
Davide Badalotti , Akanksha Agrawal , Umberto Pensato , Giovanni Angelotti , Simona Marcheselli

Introduction

Data collection often relies on time-consuming manual inputs, with a vast amount of information embedded in unstructured texts such as patients’ medical records and clinical notes. Our study aims to develop a pipeline that combines active learning (AL) and NLP techniques to enhance data extraction in an acute ischemic stroke cohort.

Materials and methods

Consecutive acute ischemic stroke patients who received reperfusion therapies at IRCCS Humanitas Research Hospital were included. The Italian NLP Bidirectional Encoder Representations from Transformers (BERT) model was trained with AL to automatically extract clinical variables from electronic health text. Simulated active learning performances were evaluated on a set of labels representing patients’ comorbidities, comparing Bayesian Uncertainty Sampling by Disagreement (BALD) and random text selection. Prognostic models predicting patients’ functional outcomes using Gradient Boosting were trained on manually labelled and semi-automatically extracted data and their performance was compared.

Results

The active learning process initially showed null performance until around 20% of texts were labelled, possibly due to root layers freezing in the BERT model, yet overall, active learning improves model learning efficiency across most comorbidities. Prognostic modelling showed no significant difference in performance between models trained on manually labelled versus semi-automatically extracted data, indicating effective prediction capabilities in both settings.

Conclusions

We developed an efficient language model to automate the extraction of clinical data from Italian unstructured health texts in a cohort of ischemic stroke patients. In a preliminary analysis, we demonstrated its potential applicability for enhancing prediction model accuracy.
导言数据收集通常依赖于耗时的人工输入,大量信息蕴含在患者病历和临床笔记等非结构化文本中。我们的研究旨在开发一种结合了主动学习(AL)和 NLP 技术的管道,以增强急性缺血性中风队列中的数据提取能力。使用AL对意大利NLP双向编码器变换器表征(BERT)模型进行了训练,以便从电子健康文本中自动提取临床变量。通过比较贝叶斯不确定性分歧采样(BALD)和随机文本选择,对一组代表患者合并症的标签进行了模拟主动学习性能评估。结果可能是由于 BERT 模型中的根层冻结,主动学习过程最初显示出无效性能,直到约 20% 的文本被标记,但总体而言,主动学习提高了大多数合并症的模型学习效率。预后建模结果表明,人工标注数据与半自动提取数据所训练的模型在性能上没有明显差异,这表明在这两种情况下都能有效地进行预测。在初步分析中,我们证明了该模型在提高预测模型准确性方面的潜在适用性。
{"title":"Development of a Natural Language Processing (NLP) model to automatically extract clinical data from electronic health records: results from an Italian comprehensive stroke center","authors":"Davide Badalotti ,&nbsp;Akanksha Agrawal ,&nbsp;Umberto Pensato ,&nbsp;Giovanni Angelotti ,&nbsp;Simona Marcheselli","doi":"10.1016/j.ijmedinf.2024.105626","DOIUrl":"10.1016/j.ijmedinf.2024.105626","url":null,"abstract":"<div><h3>Introduction</h3><div>Data collection often relies on time-consuming manual inputs, with a vast amount of information embedded in unstructured texts such as patients’ medical records and clinical notes. Our study aims to develop a pipeline that combines active learning (AL) and NLP techniques to enhance data extraction in an acute ischemic stroke cohort.</div></div><div><h3>Materials and methods</h3><div>Consecutive acute ischemic stroke patients who received reperfusion therapies at IRCCS Humanitas Research Hospital were included. The Italian NLP Bidirectional Encoder Representations from Transformers (BERT) model was trained with AL to automatically extract clinical variables from electronic health text. Simulated active learning performances were evaluated on a set of labels representing patients’ comorbidities, comparing Bayesian Uncertainty Sampling by Disagreement (BALD) and random text selection. Prognostic models predicting patients’ functional outcomes using Gradient Boosting were trained on manually labelled and semi-automatically extracted data and their performance was compared.</div></div><div><h3>Results</h3><div>The active learning process initially showed null performance until around 20% of texts were labelled, possibly due to root layers freezing in the BERT model, yet overall, active learning improves model learning efficiency across most comorbidities. Prognostic modelling showed no significant difference in performance between models trained on manually labelled versus semi-automatically extracted data, indicating effective prediction capabilities in both settings.</div></div><div><h3>Conclusions</h3><div>We developed an efficient language model to automate the extraction of clinical data from Italian unstructured health texts in a cohort of ischemic stroke patients. In a preliminary analysis, we demonstrated its potential applicability for enhancing prediction model accuracy.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105626"},"PeriodicalIF":3.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1386505624002892/pdfft?md5=ae5845eca9c8a78d1bf6334b838f5be4&pid=1-s2.0-S1386505624002892-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142310979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Improving the quality of nursing care through standardized nursing languages: Call to action across European countries 通过标准化护理语言提高护理质量:呼吁欧洲各国采取行动
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-19 DOI: 10.1016/j.ijmedinf.2024.105627
Fabiana Cristina Dos Santos , Fabio D’Agostino , Mikko Härkönen , Renate Nantschev , Bente Christensen , Maria Müller-Staub , Kim De Groot

Background

Standardized Nursing Languages (SNLs) have enabled nursing assessments and care to be better documented and visible in electronic health records (EHRs). However, its implementation is challenging and heterogeneous across clinical settings. This study aimed to demonstrate the challenges experienced by members of a European nursing organization, ACENDIO, in implementing SNLs in documentation systems across countries and offer recommendations about its use.

Material and methods

The study was executed in two phases. First, an online survey was distributed among ACENDIO members. Second, members participated in two expert panels. Discussions were recorded, and thematic analysis was performed to formulate challenges and recommendations on the use of SNLs.

Results

The findings highlight that nurses across Europe are faced with several issues with current documentation systems in clinical settings, limited education on SNLs, and challenges in research on SNLs. Nurses, managers, vendors, educators and researchers should work closely together to face the challenges in the implementation of SNLs in electronic documentation systems.

Conclusion

To fully utilize the beneficial effects of the use of SNLs, the call to action is to develop comprehensive collaborations of nursing practice, education, and research.

背景标准化护理语言(SNL)使护理评估和护理在电子健康记录(EHR)中得到更好的记录和显示。然而,在不同的临床环境中,SNL 的实施具有挑战性和差异性。本研究旨在展示欧洲护理组织 ACENDIO 的成员在不同国家的文档系统中实施 SNL 所遇到的挑战,并就其使用提出建议。首先,向 ACENDIO 成员分发了一份在线调查。其次,成员参加了两个专家小组。结果研究结果表明,整个欧洲的护士都面临着以下几个问题:目前临床环境中的记录系统、SNL 教育有限以及 SNL 研究方面的挑战。护士、管理人员、供应商、教育工作者和研究人员应密切合作,共同面对在电子文档系统中实施 SNL 所面临的挑战。
{"title":"Improving the quality of nursing care through standardized nursing languages: Call to action across European countries","authors":"Fabiana Cristina Dos Santos ,&nbsp;Fabio D’Agostino ,&nbsp;Mikko Härkönen ,&nbsp;Renate Nantschev ,&nbsp;Bente Christensen ,&nbsp;Maria Müller-Staub ,&nbsp;Kim De Groot","doi":"10.1016/j.ijmedinf.2024.105627","DOIUrl":"10.1016/j.ijmedinf.2024.105627","url":null,"abstract":"<div><h3>Background</h3><p>Standardized Nursing Languages (SNLs) have enabled nursing assessments and care to be better documented and visible in electronic health records (EHRs). However, its implementation is challenging and heterogeneous across clinical settings. This study aimed to demonstrate the challenges experienced by members of a European nursing organization, ACENDIO, in implementing SNLs in documentation systems across countries and offer recommendations about its use.</p></div><div><h3>Material and methods</h3><p>The study was executed in two phases. First, an online survey was distributed among ACENDIO members. Second, members participated in two expert panels. Discussions were recorded, and thematic analysis was performed to formulate challenges and recommendations on the use of SNLs.</p></div><div><h3>Results</h3><p>The findings highlight that nurses across Europe are faced with several issues with current documentation systems in clinical settings, limited education on SNLs, and challenges in research on SNLs. Nurses, managers, vendors, educators and researchers should work closely together to face the challenges in the implementation of SNLs in electronic documentation systems.</p></div><div><h3>Conclusion</h3><p>To fully utilize the beneficial effects of the use of SNLs, the call to action is to develop comprehensive collaborations of nursing practice, education, and research.</p></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105627"},"PeriodicalIF":3.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142270316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Implementing big data analytics in practice – A response to “Factors impacting the adoption of big data in healthcare: A systematic literature review” 在实践中实施大数据分析--回应 "影响医疗保健领域采用大数据的因素:系统性文献综述"
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-19 DOI: 10.1016/j.ijmedinf.2024.105637
Richard M. Wood
{"title":"Implementing big data analytics in practice – A response to “Factors impacting the adoption of big data in healthcare: A systematic literature review”","authors":"Richard M. Wood","doi":"10.1016/j.ijmedinf.2024.105637","DOIUrl":"10.1016/j.ijmedinf.2024.105637","url":null,"abstract":"","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105637"},"PeriodicalIF":3.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142310976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Flipping healthcare by including the patient perspective in integrated care pathway design: A scoping review 在综合护理路径设计中纳入患者视角,实现医疗保健的翻转:范围审查
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-19 DOI: 10.1016/j.ijmedinf.2024.105623
Sonja Cassidy , Øivind Skeidsvoll Solvang , Conceição Granja , Terje Solvoll

Background

Despite the recognized benefits of integrating patient perspectives into healthcare design and clinical decision support, theoretical approaches and standardized methods are lacking. Various strategies, such as developing pathways, have evolved to address these challenges. Previous research emphasized the need for a framework for care pathways that includes theoretical principles, extensive user involvement, and data from electronic health records to bridge the gap between different fields and disciplines. Standardizing the representation of the patient perspective could facilitate its sharing across healthcare organizations and domains and its integration into journal systems, shifting the balance of power from the provider to the patient.

Objectives

This study aims to 1) Identify research approaches taken to develop patient-centred, integrated, care pathways supported by electronic health records 2) Propose a socio-technical framework for designing patient-centred care pathways across multiple healthcare levels that integrates the voice of the patient with the knowledge of the care provider and technological perspectives.

Methods

This study conducted a scoping review following the Joanna Briggs Institute guidelines and PRISMA-ScR protocol. The databases PubMed, Scopus, Web of Science, ProQuest, IEEE, and Google Scholar were searched using a key term search strategy including variations of patient-centred, integrated care, pathway, framework and model to identify relevant studies. Eligible articles included peer-reviewed literature documenting methodologies for mapping patient-centred, integrated care pathways in healthcare service design.

Results

This review summarizes the application of care pathway modelling practices across various areas of healthcare innovation. The search resulted in 410 studies, with 16 articles included after the full review and grey literature search.

Conclusions

Our research illustrated incorporating patient perspectives into modelling care pathways and healthcare service design. Regardless of the medical domain, our methodology proposes an approach for modelling patient-centred, integrated care pathways across the care continuum, including using electronic health records to support the pathways.
背景尽管将患者视角纳入医疗设计和临床决策支持的益处已得到公认,但仍缺乏理论方法和标准化方法。为了应对这些挑战,人们逐渐发展出了各种策略,例如制定路径。以往的研究强调,护理路径需要一个包含理论原则、广泛用户参与和电子健康记录数据的框架,以弥合不同领域和学科之间的差距。将患者视角的表述标准化可以促进医疗机构和领域之间的共享,并将其整合到期刊系统中,从而将权力的天平从提供者转向患者。本研究旨在:1)确定在电子健康记录支持下开发以患者为中心的综合护理路径的研究方法;2)提出一个社会技术框架,用于在多个医疗保健层面设计以患者为中心的护理路径,该框架将患者的声音与医疗服务提供者的知识和技术视角相结合。采用关键词搜索策略,包括以患者为中心、综合护理、路径、框架和模式的变体,在 PubMed、Scopus、Web of Science、ProQuest、IEEE 和 Google Scholar 等数据库中进行搜索,以确定相关研究。符合条件的文章包括同行评审文献,这些文献记录了在医疗服务设计中绘制以患者为中心的综合护理路径的方法。搜索结果包括 410 项研究,其中有 16 篇文章是在全面综述和灰色文献检索后收录的。结论我们的研究表明,在医疗路径建模和医疗服务设计中融入了患者视角。无论在哪个医疗领域,我们的方法都提出了一种在整个护理过程中模拟以患者为中心的综合护理路径的方法,包括使用电子健康记录来支持护理路径。
{"title":"Flipping healthcare by including the patient perspective in integrated care pathway design: A scoping review","authors":"Sonja Cassidy ,&nbsp;Øivind Skeidsvoll Solvang ,&nbsp;Conceição Granja ,&nbsp;Terje Solvoll","doi":"10.1016/j.ijmedinf.2024.105623","DOIUrl":"10.1016/j.ijmedinf.2024.105623","url":null,"abstract":"<div><h3>Background</h3><div>Despite the recognized benefits of integrating patient perspectives into healthcare design and clinical decision support, theoretical approaches and standardized methods are lacking. Various strategies, such as developing pathways, have evolved to address these challenges. Previous research emphasized the need for a framework for care pathways that includes theoretical principles, extensive user involvement, and data from electronic health records to bridge the gap between different fields and disciplines. Standardizing the representation of the patient perspective could facilitate its sharing across healthcare organizations and domains and its integration into journal systems, shifting the balance of power from the provider to the patient.</div></div><div><h3>Objectives</h3><div>This study aims to 1) Identify research approaches taken to develop patient-centred, integrated, care pathways supported by electronic health records 2) Propose a socio-technical framework for designing patient-centred care pathways across multiple healthcare levels that integrates the voice of the patient with the knowledge of the care provider and technological perspectives.</div></div><div><h3>Methods</h3><div>This study conducted a scoping review following the Joanna Briggs Institute guidelines and PRISMA-ScR protocol. The databases PubMed, Scopus, Web of Science, ProQuest, IEEE, and Google Scholar were searched using a key term search strategy including variations of <em>patient-centred</em>, <em>integrated care</em>, <em>pathway</em>, <em>framework</em> and <em>model</em> to identify relevant studies. Eligible articles included peer-reviewed literature documenting methodologies for mapping patient-centred, integrated care pathways in healthcare service design.</div></div><div><h3>Results</h3><div>This review summarizes the application of care pathway modelling practices across various areas of healthcare innovation. The search resulted in 410 studies, with 16 articles included after the full review and grey literature search.</div></div><div><h3>Conclusions</h3><div>Our research illustrated incorporating patient perspectives into modelling care pathways and healthcare service design. Regardless of the medical domain, our methodology proposes an approach for modelling patient-centred, integrated care pathways across the care continuum, including using electronic health records to support the pathways.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105623"},"PeriodicalIF":3.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1386505624002867/pdfft?md5=4c20d690db4377f89e3ac9535c390e6b&pid=1-s2.0-S1386505624002867-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142310978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Predicting prolonged length of stay following revision total knee arthroplasty: A national database analysis using machine learning models 预测翻修全膝关节置换术后住院时间的延长:使用机器学习模型的国家数据库分析
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-18 DOI: 10.1016/j.ijmedinf.2024.105634
Ashish Mittal, Anirudh Buddhiraju, Murad Abdullah Subih, Tony Lin-Wei Chen, Michelle Shimizu, Henry Hojoon Seo, Mohammadamin Rezazadehsaatlou, Pengwei Xiao, Young-Min Kwon

Background

As the number of revision total knee arthroplasty (TKA) continues to rise, close attention has been paid to factors influencing postoperative length of stay (LOS). The aim of this study is to develop generalizable machine learning (ML) algorithms to predict extended LOS following revision TKA using data from a national database.

Methods

23,656 patients undergoing revision TKA between 2013 and 2020 were identified using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. Patients with missing data and those undergoing re-revision or conversion from unicompartmental knee arthroplasty were excluded. Four ML algorithms were applied and evaluated based on their (1) ability to distinguish between at-risk and not-at-risk patients, (2) accuracy, (3) calibration, and (4) clinical utility.

Results

All four ML predictive algorithms demonstrated good accuracy, calibration, clinical utility, and discrimination, with all models achieving a similar area under the curve (AUC) (AUCLR=AUCRF=AUCHGB=0.75, AUCANN=0.74). The most important predictors of prolonged LOS were found to be operative time, preoperative diagnosis of sepsis, and body mass index (BMI).

Conclusions

ML models developed in this study demonstrated good performance in predicting extended LOS in patients undergoing revision TKA. Our findings highlight the importance of utilizing nationally representative patient data for model development. Prolonged operative time, preoperative sepsis, BMI, and elevated preoperative serum creatinine and BUN were noted to be significant predictors of prolonged LOS. Knowledge of these associations may aid with patient-specific preoperative planning, discharge planning, patient counseling, and cost containment with revision TKA.

背景随着翻修全膝关节置换术(TKA)的数量不断增加,影响术后住院时间(LOS)的因素受到了密切关注。本研究旨在利用国家数据库中的数据,开发可推广的机器学习(ML)算法,以预测翻修TKA术后延长的住院时间。方法 利用美国外科学院国家外科质量改进计划(ACS-NSQIP)数据库,确定了2013年至2020年间接受翻修TKA术的23656名患者。数据缺失的患者和接受翻修或从单髁膝关节置换术转换而来的患者被排除在外。结果所有四种ML预测算法都表现出了良好的准确性、校准性、临床实用性和区分度,所有模型都达到了相似的曲线下面积(AUC)(AUCLR=AUCRF=AUCHGB=0.75,AUCANN=0.74)。本研究开发的ML模型在预测翻修TKA患者延长LOS方面表现良好。我们的研究结果凸显了利用具有全国代表性的患者数据来开发模型的重要性。我们注意到,手术时间延长、术前败血症、体重指数、术前血清肌酐和血清尿素氮升高是延长 LOS 的重要预测因素。了解这些关联有助于为患者制定术前计划、出院计划、患者咨询以及翻修 TKA 的成本控制。
{"title":"Predicting prolonged length of stay following revision total knee arthroplasty: A national database analysis using machine learning models","authors":"Ashish Mittal,&nbsp;Anirudh Buddhiraju,&nbsp;Murad Abdullah Subih,&nbsp;Tony Lin-Wei Chen,&nbsp;Michelle Shimizu,&nbsp;Henry Hojoon Seo,&nbsp;Mohammadamin Rezazadehsaatlou,&nbsp;Pengwei Xiao,&nbsp;Young-Min Kwon","doi":"10.1016/j.ijmedinf.2024.105634","DOIUrl":"10.1016/j.ijmedinf.2024.105634","url":null,"abstract":"<div><h3>Background</h3><p>As the number of revision total knee arthroplasty (TKA) continues to rise, close attention has been paid to factors influencing postoperative length of stay (LOS). The aim of this study is to develop generalizable machine learning (ML) algorithms to predict extended LOS following revision TKA using data from a national database.</p></div><div><h3>Methods</h3><p>23,656 patients undergoing revision TKA between 2013 and 2020 were identified using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. Patients with missing data and those undergoing re-revision or conversion from unicompartmental knee arthroplasty were excluded. Four ML algorithms were applied and evaluated based on their (1) ability to distinguish between at-risk and not-at-risk patients, (2) accuracy, (3) calibration, and (4) clinical utility.</p></div><div><h3>Results</h3><p>All four ML predictive algorithms demonstrated good accuracy, calibration, clinical utility, and discrimination, with all models achieving a similar area under the curve (AUC) (AUC<sub>LR</sub>=AUC<sub>RF</sub>=AUC<sub>HGB</sub>=0.75, AUC<sub>ANN</sub>=0.74). The most important predictors of prolonged LOS were found to be operative time, preoperative diagnosis of sepsis, and body mass index (BMI).</p></div><div><h3>Conclusions</h3><p>ML models developed in this study demonstrated good performance in predicting extended LOS in patients undergoing revision TKA. Our findings highlight the importance of utilizing nationally representative patient data for model development. Prolonged operative time, preoperative sepsis, BMI, and elevated preoperative serum creatinine and BUN were noted to be significant predictors of prolonged LOS. Knowledge of these associations may aid with patient-specific preoperative planning, discharge planning, patient counseling, and cost containment with revision TKA.</p></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105634"},"PeriodicalIF":3.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142270993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Digital tools to support informed decision making among screening invitees in a vulnerable position for population-based cancer screening: A scoping review 支持处于弱势的筛查受邀者做出知情决策的数字化工具:范围审查
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-18 DOI: 10.1016/j.ijmedinf.2024.105625
Corine Oldhoff-Nuijsink , Marloes E. Derksen , Thomas Engelsma , Linda W.P. Peute , Mirjam P. Fransen

Background

Individuals in a vulnerable position are generally less inclined to participate in population-based cancer screening. Digital tools, such as educational videos, narratives or decision aids, show promise in reaching and informing these invitees by tailoring information needs based on their preferences. This review aims to provide an overview of design features and reported outcomes of digital tools intended to support informed decision making among screening invitees in a vulnerable position.

Methods

The review was conducted according to the Preferred Reporting Items for Scoping Reviews guidelines. We searched PubMed, Scopus/MEDLINE and Web of Science and included studies when the effectiveness of the digital tool was assessed and focussed on reaching and/or informing screening invitees in a vulnerable position for breast, cervical or colorectal cancer screening. For each included study, the study population, type of digital tool, the development process, reported design features and reported effects were extracted.

Findings

We found 448 articles, and finally 13 were included in this review after reading full text. Study designs included randomised controlled trials (n = 5), pre-post-test design (n = 7) and experimental design (n = 1). Six different types of digital tools were identified: decision aids (n = 6), educational programs (n = 3), narrative video (n = 1), text-messaging intervention (n = 1), animation video (n = 1), and iPad program (n = 1). A population specific design was applied in 12/13 interventions, such as avoiding jargon and using a voice over function. Reported outcomes measures regarding reaching and informing the target population were: knowledge, attitude, screening intention, self-efficacy, susceptibility, feeling informed, values clarity, and screening uptake. All digital tools reported a significant improvement on at least one of the reported outcome measures.

Principal conclusions

The use of digital tools seems to contribute to reach or inform screening invitees in a vulnerable position for cancer screening. However, insufficient evidence was found regarding the development process of the tools and their effects on outcome measures related to reaching and informing the screening invitees in a vulnerable position. Future research may look in to combining multiple digital tools and animated visual information in combination with spoken text to improve reaching and informing screening invitees in a vulnerable position.
背景处于弱势地位的个人一般不太愿意参加基于人群的癌症筛查。教育视频、解说词或决策辅助工具等数字工具可根据受邀者的偏好满足其信息需求,从而有望接触到这些受邀者并为其提供信息。本综述旨在概述旨在为处于弱势地位的筛查受邀者提供知情决策支持的数字工具的设计特点和报告结果。我们对 PubMed、Scopus/MEDLINE 和 Web of Science 进行了检索,并纳入了对数字工具的有效性进行评估的研究,这些数字工具主要用于帮助和/或告知处于弱势地位的筛查受邀者进行乳腺癌、宫颈癌或结直肠癌筛查。对于每项纳入的研究,我们都提取了研究人群、数字工具类型、开发过程、报告的设计特点和报告的效果。研究设计包括随机对照试验(5 篇)、前后测试设计(7 篇)和实验设计(1 篇)。确定了六种不同类型的数字工具:决策辅助工具(n = 6)、教育程序(n = 3)、叙事视频(n = 1)、文本信息干预(n = 1)、动画视频(n = 1)和 iPad 程序(n = 1)。12/13项干预措施采用了针对特定人群的设计,如避免使用行话和语音播报功能。据报告,在接触目标人群并向其提供信息方面的成果衡量标准包括:知识、态度、筛查意向、自我效能、易感性、知情感、价值观清晰度和筛查接受率。主要结论使用数字工具似乎有助于接触处于癌症筛查弱势地位的筛查受邀者或向其提供信息。然而,关于这些工具的开发过程及其对与接触和告知处于弱势地位的筛查受邀者相关的结果指标的影响,目前还没有发现足够的证据。未来的研究可能会将多种数字工具和动画视觉信息与口语文字相结合,以更好地接触和告知处于弱势地位的筛查受邀者。
{"title":"Digital tools to support informed decision making among screening invitees in a vulnerable position for population-based cancer screening: A scoping review","authors":"Corine Oldhoff-Nuijsink ,&nbsp;Marloes E. Derksen ,&nbsp;Thomas Engelsma ,&nbsp;Linda W.P. Peute ,&nbsp;Mirjam P. Fransen","doi":"10.1016/j.ijmedinf.2024.105625","DOIUrl":"10.1016/j.ijmedinf.2024.105625","url":null,"abstract":"<div><h3>Background</h3><div>Individuals in a vulnerable position are generally less inclined to participate in population-based cancer screening. Digital tools, such as educational videos, narratives or decision aids, show promise in reaching and informing these invitees by tailoring information needs based on their preferences. This review aims to provide an overview of design features and reported outcomes of digital tools intended to support informed decision making among screening invitees in a vulnerable position.</div></div><div><h3>Methods</h3><div>The review was conducted according to the Preferred Reporting Items for Scoping Reviews guidelines. We searched PubMed, Scopus/MEDLINE and Web of Science and included studies when the effectiveness of the digital tool was assessed and focussed on reaching and/or informing screening invitees in a vulnerable position for breast, cervical or colorectal cancer screening. For each included study, the study population, type of digital tool, the development process, reported design features and reported effects were extracted.</div></div><div><h3>Findings</h3><div>We found 448 articles, and finally 13 were included in this review after reading full text. Study designs included randomised controlled trials (n = 5), pre-post-test design (n = 7) and experimental design (n = 1). Six different types of digital tools were identified: decision aids (n = 6), educational programs (n = 3), narrative video (n = 1), text-messaging intervention (n = 1), animation video (n = 1), and iPad program (n = 1). A population specific design was applied in 12/13 interventions, such as avoiding jargon and using a voice over function. Reported outcomes measures regarding reaching and informing the target population were: knowledge, attitude, screening intention, self-efficacy, susceptibility, feeling informed, values clarity, and screening uptake. All digital tools reported a significant improvement on at least one of the reported outcome measures.</div></div><div><h3>Principal conclusions</h3><div>The use of digital tools seems to contribute to reach or inform screening invitees in a vulnerable position for cancer screening. However, insufficient evidence was found regarding the development process of the tools and their effects on outcome measures related to reaching and informing the screening invitees in a vulnerable position. Future research may look in to combining multiple digital tools and animated visual information in combination with spoken text to improve reaching and informing screening invitees in a vulnerable position.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105625"},"PeriodicalIF":3.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1386505624002880/pdfft?md5=b9cfdf5ea4abb8c7b33cbe906aafae55&pid=1-s2.0-S1386505624002880-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142310977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Data protection and information security in biomedical research: A sequential explanatory mixed study 生物医学研究中的数据保护和信息安全:顺序解释性混合研究
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-18 DOI: 10.1016/j.ijmedinf.2024.105635
Marialida Farah , Samar Helou , Elie Raad , Elie El Helou

Purpose

Biomedical research is a pillar of every medical student’s career. When collecting data, several regulations are established to ensure the protection of individuals. Most medical students are not compliant with the guidelines, and this is probably due to a lack of knowledge. The aim of our research is to evaluate the knowledge and behavior of medical students regarding these rules, then attempt to explain the results obtained.

Methods

This is a sequential explanatory mixed study including an initial quantitative section followed by an explanatory qualitative section. For the quantitative part, we administered a questionnaire based on the information security regulation and the GDPR to third- and fourth-year medical students. We evaluated their knowledge and behaviors and their correlation. For the qualitative part, we conducted semi-structured interviews with eight students followed by thematic analysis to explain the results.

Results

Most students have a lack of knowledge. A correlation was found between the non-compliant behavior of keeping the laptop unattended in a public place and a low level of knowledge. For the qualitative section, the thematic analysis represents three groups to explain non-compliant behavior: lack of knowledge, work overload, and consideration of the hospital as a safe place.

Conclusion

Data collection and information security rules are rarely followed by medical students. This is mainly due to lack of knowledge, work overload and assuming the hospital as a safe place. Future awareness interventions would be necessary to improve non-compliant behavior and subsequently ensure a more secure environment during medical research.

目的 生物医学研究是每个医科学生职业生涯的支柱。在收集数据时,有几项规定确保对个人的保护。大多数医学生并不遵守这些规定,这可能是由于他们缺乏相关知识。我们的研究目的是评估医学生对这些规定的了解程度和行为,然后尝试解释所获得的结果。方法这是一项顺序解释性混合研究,包括最初的定量部分和随后的定性解释部分。在定量部分,我们向三年级和四年级医学生发放了一份基于信息安全法规和 GDPR 的调查问卷。我们对他们的知识和行为及其相关性进行了评估。在定性分析部分,我们对八名学生进行了半结构式访谈,并对访谈结果进行了主题分析。在公共场所无人看管笔记本电脑的违规行为与知识水平低之间存在相关性。在定性分析部分,主题分析代表了三组解释不合规行为的原因:缺乏知识、工作负担过重以及将医院视为安全场所。医学生很少遵守数据收集和信息安全规则,这主要是由于缺乏知识、工作负担过重以及认为医院是安全的地方。今后有必要采取提高认识的干预措施,以改善不遵守规则的行为,从而确保在医学研究期间有一个更安全的环境。
{"title":"Data protection and information security in biomedical research: A sequential explanatory mixed study","authors":"Marialida Farah ,&nbsp;Samar Helou ,&nbsp;Elie Raad ,&nbsp;Elie El Helou","doi":"10.1016/j.ijmedinf.2024.105635","DOIUrl":"10.1016/j.ijmedinf.2024.105635","url":null,"abstract":"<div><h3>Purpose</h3><p>Biomedical research is a pillar of every medical student’s career. When collecting data, several regulations are established to ensure the protection of individuals. Most medical students are not compliant with the guidelines, and this is probably due to a lack of knowledge. The aim of our research is to evaluate the knowledge and behavior of medical students regarding these rules, then attempt to explain the results obtained.</p></div><div><h3>Methods</h3><p>This is a sequential explanatory mixed study including an initial quantitative section followed by an explanatory qualitative section. For the quantitative part, we administered a questionnaire based on the information security regulation and the GDPR to third- and fourth-year medical students. We evaluated their knowledge and behaviors and their correlation. For the qualitative part, we conducted semi-structured interviews with eight students followed by thematic analysis to explain the results.</p></div><div><h3>Results</h3><p>Most students have a lack of knowledge. A correlation was found between the non-compliant behavior of keeping the laptop unattended in a public place and a low level of knowledge. For the qualitative section, the thematic analysis represents three groups to explain non-compliant behavior: lack of knowledge, work overload, and consideration of the hospital as a safe place.</p></div><div><h3>Conclusion</h3><p>Data collection and information security rules are rarely followed by medical students. This is mainly due to lack of knowledge, work overload and assuming the hospital as a safe place. Future awareness interventions would be necessary to improve non-compliant behavior and subsequently ensure a more secure environment during medical research.</p></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105635"},"PeriodicalIF":3.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142270994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
What physical examinations are observed during an in-person GP consultation? Automatic extraction using a text-based approach 全科医生上门问诊时会观察到哪些体格检查?使用基于文本的方法自动提取
IF 3.7 2区 医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-17 DOI: 10.1016/j.ijmedinf.2024.105632
Moomna Waheed, Hao Xiong, Kate Tong, Annie.Y. Lau

Objectives

Teleconsultation is anticipated to have a long-term role in primary care. However, conducting virtual physical examinations is a well-known limitation. To anticipate unmet needs general practitioners (GPs) and patients may experience during teleconsultation, this study aims to automatically identify physical examinations typically conducted during in-person GP consultation.

Material and Methods

This study utilizes 281 GP in-person consultations (de-identified transcripts & video recordings) within UK general practices, where 169 eligible ones were included in this study. We propose an automated text-based approach using regular expressions on keywords in GP-patient consultation dialogue (e.g., “roll up your sleeves”) to identify physical examinations (e.g. blood pressure measurement). This approach involves the construction of conceptual diagrams to visually inspect the relationship between keywords and physical examinations, syntax analysis to identify patterns between keywords and generate regular expressions, and the use of these regular expressions in consultation transcripts to detect potential instances of physical examinations, where matching video frames were subsequently retrieved. The performance of our automated text-based approach is compared to manual classification by 2 independent researchers using 5-fold cross-validation (precision, recall, and F1-score).

Results

Among the 169 eligible GP in-person consultations, 133 (79%) required a physical examination, while the other 33 visits were for psychological reasons. Out of these 133 consultations, a total of 283 physical examinations were observed, with 21 instances conducted behind a curtain. We identified 42 distinct types of physical examinations from these 283 instances, grouped into 10 physical examination categories based on body areas and physical artefacts. The most frequent category of physical examinations is Vital Signs 26.80% (76/283). Overall, blood pressure measurement (also belonging to the Vital Signs category) is the most frequent physical examination at 59.2% (45/76). The comparison between manual classification and the regular expression model demonstrates an average precision of 88.3%, recall of 78.9%, and an F1-score of 83.3% from 5-fold cross-validation, providing significant insights into the frequency and types of physical examinations conducted during in-person GP consultations.

Conclusion

By using regular expressions in consultation dialogues between GPs and patients, we can automatically identify physical examinations in GP consultations with a precision of 88.3%. Findings from this study, i.e. physical examinations during in-person GP consultations, provide insights into areas where GPs and patients may need support during teleconsultation.

目标预计远程会诊将在初级医疗中长期发挥作用。然而,进行虚拟体检是一个众所周知的限制因素。为了预测全科医生(GP)和患者在远程会诊过程中可能遇到的未满足需求,本研究旨在自动识别全科医生面对面会诊过程中通常会进行的身体检查。我们提出了一种基于文本的自动方法,利用全科医生与患者问诊对话中的关键词(如 "卷起袖子")的正则表达式来识别身体检查(如血压测量)。这种方法包括构建概念图以直观地检查关键词与体检之间的关系,进行语法分析以识别关键词之间的模式并生成正则表达式,以及在问诊记录中使用这些正则表达式来检测体检的潜在实例,随后检索匹配的视频帧。两名独立研究人员使用 5 倍交叉验证(精确度、召回率和 F1 分数)将我们基于文本的自动化方法的性能与人工分类进行了比较。在这 133 次问诊中,共观察到 283 次体格检查,其中 21 次是在幕后进行的。我们从这 283 次体格检查中确定了 42 种不同类型的体格检查,并根据身体部位和体征将其分为 10 个体格检查类别。最常见的体检类别是生命体征 26.80%(76/283)。总体而言,血压测量(也属于生命体征类别)是最常见的体格检查,占 59.2%(45/76)。人工分类与正则表达式模型之间的比较显示,5 倍交叉验证的平均精确度为 88.3%,召回率为 78.9%,F1 分数为 83.3%,为了解全科医生当面问诊时进行身体检查的频率和类型提供了重要依据。这项研究的结果,即全科医生面对面咨询中的身体检查,为全科医生和患者在远程咨询中可能需要支持的领域提供了启示。
{"title":"What physical examinations are observed during an in-person GP consultation? Automatic extraction using a text-based approach","authors":"Moomna Waheed,&nbsp;Hao Xiong,&nbsp;Kate Tong,&nbsp;Annie.Y. Lau","doi":"10.1016/j.ijmedinf.2024.105632","DOIUrl":"10.1016/j.ijmedinf.2024.105632","url":null,"abstract":"<div><h3>Objectives</h3><p>Teleconsultation is anticipated to have a long-term role in primary care. However, conducting virtual physical examinations is a well-known limitation. To anticipate unmet needs general practitioners (GPs) and patients may experience during teleconsultation, this study aims to automatically identify physical examinations typically conducted during in-person GP consultation.</p></div><div><h3>Material and Methods</h3><p>This study utilizes 281 GP in-person consultations (de-identified transcripts &amp; video recordings) within UK general practices, where 169 eligible ones were included in this study. We propose an automated text-based approach using regular expressions on keywords in GP-patient consultation dialogue (e.g., “roll up your sleeves”) to identify physical examinations (e.g. blood pressure measurement). This approach involves the construction of conceptual diagrams to visually inspect the relationship between keywords and physical examinations, syntax analysis to identify patterns between keywords and generate regular expressions, and the use of these regular expressions in consultation transcripts to detect potential instances of physical examinations, where matching video frames were subsequently retrieved. The performance of our automated text-based approach is compared to manual classification by 2 independent researchers using 5-fold cross-validation (precision, recall, and F1-score).</p></div><div><h3>Results</h3><p>Among the 169 eligible GP in-person consultations, 133 (79%) required a physical examination, while the other 33 visits were for psychological reasons. Out of these 133 consultations, a total of 283 physical examinations were observed, with 21 instances conducted behind a curtain. We identified 42 distinct types of physical examinations from these 283 instances, grouped into 10 physical examination categories based on body areas and physical artefacts. The most frequent category of physical examinations is Vital Signs 26.80% (76/283). Overall, blood pressure measurement (also belonging to the Vital Signs category) is the most frequent physical examination at 59.2% (45/76). The comparison between manual classification and the regular expression model demonstrates an average precision of 88.3%, recall of 78.9%, and an F1-score of 83.3% from 5-fold cross-validation, providing significant insights into the frequency and types of physical examinations conducted during in-person GP consultations.</p></div><div><h3>Conclusion</h3><p>By using regular expressions in consultation dialogues between GPs and patients, we can automatically identify physical examinations in GP consultations with a precision of 88.3%. Findings from this study, i.e. physical examinations during in-person GP consultations, provide insights into areas where GPs and patients may need support during teleconsultation.</p></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105632"},"PeriodicalIF":3.7,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1386505624002958/pdfft?md5=9a2b86388a3da840370c2dce100122ec&pid=1-s2.0-S1386505624002958-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142270995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
International Journal of Medical Informatics
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1