Pub Date : 2024-01-09DOI: 10.1101/2024.01.06.24300920
Yaara R Artsi, Vera Sorin, Eli Konen, Benjamin S Glicksberg, Girish Nadkarni, Eyal Klang
Purpose Writing multiple choice questions (MCQs) for the purpose of medical exams is challenging. It requires extensive medical knowledge, time and effort from medical educators. This systematic review focuses on the application of large language models (LLMs) in generating medical MCQs. Methods The authors searched for studies published up to November 2023. Search terms focused on LLMs generated MCQs for medical examinations. MEDLINE was used as a search database. Results Overall, eight studies published between April 2023 and October 2023 were included. Six studies used Chat-GPT 3.5, while two employed GPT 4. Five studies showed that LLMs can produce competent questions valid for medical exams. Three studies used LLMs to write medical questions but did not evaluate the validity of the questions. One study conducted a comparative analysis of different models. One other study compared LLM-generated questions with those written by humans. All studies presented faulty questions that were deemed inappropriate for medical exams. Some questions required additional modifications in order to qualify. Conclusions LLMs can be used to write MCQs for medical examinations. However, their limitations cannot be ignored. Further study in this field is essential and more conclusive evidence is needed. Until then, LLMs may serve as a supplementary tool for writing medical examinations.
{"title":"Large language models for generating medical examinations: systematic review","authors":"Yaara R Artsi, Vera Sorin, Eli Konen, Benjamin S Glicksberg, Girish Nadkarni, Eyal Klang","doi":"10.1101/2024.01.06.24300920","DOIUrl":"https://doi.org/10.1101/2024.01.06.24300920","url":null,"abstract":"Purpose\u0000Writing multiple choice questions (MCQs) for the purpose of medical exams is challenging. It requires extensive medical knowledge, time and effort from medical educators. This systematic review focuses on the application of large language models (LLMs) in generating medical MCQs.\u0000Methods\u0000The authors searched for studies published up to November 2023. Search terms focused on LLMs generated MCQs for medical examinations. MEDLINE was used as a search database.\u0000Results\u0000Overall, eight studies published between April 2023 and October 2023 were included. Six studies used Chat-GPT 3.5, while two employed GPT 4. Five studies showed that LLMs can produce competent questions valid for medical exams. Three studies used LLMs to write medical questions but did not evaluate the validity of the questions. One study conducted a comparative analysis of different models. One other study compared LLM-generated questions with those written by humans. All studies presented faulty questions that were deemed inappropriate for medical exams. Some questions required additional modifications in order to qualify.\u0000Conclusions\u0000LLMs can be used to write MCQs for medical examinations. However, their limitations cannot be ignored. Further study in this field is essential and more conclusive evidence is needed. Until then, LLMs may serve as a supplementary tool for writing medical examinations.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"108 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139408176","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 : 2023-12-21DOI: 10.1101/2023.12.20.23300220
Sophie Clohessy, Theodoros Arvanitis, Umer Rashid, Carly Craddock, Mark Evans, Carla Toro, Mark T. Elliott
Objective: The COVID-19 pandemic accelerated changes to clinical research methodology, with clinical studies being carried out via online/remote means. This mixed-methods study aimed to identify which digital tools are currently used across all stages of clinical research by stakeholders in clinical, health and social care research and investigate their experience using digital tools. Design: Two online surveys followed by semi-structured interviews were conducted. Interviews were audio recorded, transcribed, and analysed thematically. Setting, Participants To explore the digital tools used since the pandemic, survey participants [Researchers and Related Staff (n=41), Research and Development staff (n=25)], needed to have worked on clinical, health or social care research studies over the past two years (2020-2022) in an employing organisation based in the West Midlands region of England (due to funding from a regional clinical research network). Survey participants had the opportunity to participate in an online qualitative interview to explore their experiences of digital tools in greater depth (n=8). Results: Six themes were identified in the qualitative interviews: "Definition of a Digital Tool in Clinical Research"; "Impact of the COVID-19 Pandemic"; "Perceived Benefits/Drawbacks of Digital Tools"; "Selection of a Digital Tool"; "Barriers and Overcoming Barriers" and "Future Digital Tool Use". The context of each theme is discussed, based on the interview results. Conclusions: Findings demonstrate how digital tools are becoming embedded in clinical research, as well as the breadth of tools used across different research stages. The majority of participants viewed the tools positively, noting their ability to enhance research efficiency. Several considerations were highlighted; concerns about digital exclusion; need for collaboration with digital expertise/clinical staff, research on tool effectiveness and recommendations to aid future tool selection. There is a need for the development of resources to help optimise the selection and use of appropriate digital tools for clinical research staff and participants.
{"title":"Using Digital Tools in Clinical, Health and Social Care Research: A Mixed-Methods Study of UK Stakeholders","authors":"Sophie Clohessy, Theodoros Arvanitis, Umer Rashid, Carly Craddock, Mark Evans, Carla Toro, Mark T. Elliott","doi":"10.1101/2023.12.20.23300220","DOIUrl":"https://doi.org/10.1101/2023.12.20.23300220","url":null,"abstract":"Objective: The COVID-19 pandemic accelerated changes to clinical research methodology, with clinical studies being carried out via online/remote means. This mixed-methods study aimed to identify which digital tools are currently used across all stages of clinical research by stakeholders in clinical, health and social care research and investigate their experience using digital tools. Design: Two online surveys followed by semi-structured interviews were conducted. Interviews were audio recorded, transcribed, and analysed thematically.\u0000Setting, Participants To explore the digital tools used since the pandemic, survey participants [Researchers and Related Staff (n=41), Research and Development staff (n=25)], needed to have worked on clinical, health or social care research studies over the past two years (2020-2022) in an employing organisation based in the West Midlands region of England (due to funding from a regional clinical research network). Survey participants had the opportunity to participate in an online qualitative interview to explore their experiences of digital tools in greater depth (n=8).\u0000Results: Six themes were identified in the qualitative interviews: \"Definition of a Digital Tool in Clinical Research\"; \"Impact of the COVID-19 Pandemic\"; \"Perceived Benefits/Drawbacks of Digital Tools\"; \"Selection of a Digital Tool\"; \"Barriers and Overcoming Barriers\" and \"Future Digital Tool Use\". The context of each theme is discussed, based on the interview results. Conclusions: Findings demonstrate how digital tools are becoming embedded in clinical research, as well as the breadth of tools used across different research stages. The majority of participants viewed the tools positively, noting their ability to enhance research efficiency. Several considerations were highlighted; concerns about digital exclusion; need for collaboration with digital expertise/clinical staff, research on tool effectiveness and recommendations to aid future tool selection. There is a need for the development of resources to help optimise the selection and use of appropriate digital tools for clinical research staff and participants.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"114 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138824068","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 : 2023-12-16DOI: 10.1101/2022.12.19.22283532
Tina A. Solvik, Alexandra M. Schnoes, Thi A. Nguyen, Shannon L. Behrman, Elie Maksoud, Sarah S. Goodwin, Ethan J. Weiss, Arun Padmanabhan, David N. Cornfield
Importance Despite the importance of clinician-scientists in propelling biomedical advances, the proportion of physicians engaged in both hypothesis-driven research and clinical care continues to decline. Recently, multiple institutions have developed programs that promote MD-only physicians pursuing careers in science, but few reports on the impact of these are available.
{"title":"Training the next generation of physician-scientists: a cohort-based program for MD-only residents and fellows","authors":"Tina A. Solvik, Alexandra M. Schnoes, Thi A. Nguyen, Shannon L. Behrman, Elie Maksoud, Sarah S. Goodwin, Ethan J. Weiss, Arun Padmanabhan, David N. Cornfield","doi":"10.1101/2022.12.19.22283532","DOIUrl":"https://doi.org/10.1101/2022.12.19.22283532","url":null,"abstract":"<strong>Importance</strong> Despite the importance of clinician-scientists in propelling biomedical advances, the proportion of physicians engaged in both hypothesis-driven research and clinical care continues to decline. Recently, multiple institutions have developed programs that promote MD-only physicians pursuing careers in science, but few reports on the impact of these are available.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138744719","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 : 2023-12-13DOI: 10.1101/2023.12.05.23297167
Lauren Stokes, Harinder Singh
In the effort to promote academic excellence and provide authentic teaching experiences and training for medical students, the University of California, Irvine, School of Medicine (UCISOM) built a novel peer tutoring program, Collaborative Learning Communities with Medical Students as Teachers (CLC-MSAT). While the role of peer-assisted learning in student success on academic courses is well established, we wanted to assess the impact of our peer-assisted learning program on tutor’s career interest in medical education. Through a mixed-methods analysis of our peer tutors’ experiences, we found >80% were overall satisfied with their positions; >85% learned new skills; >88% felt they were strong teachers; >88% felt they now had a stronger grasp of the medical curriculum. Our findings suggest that the CLC-MSAT program has a positive impact in exposing medical students to teaching experience and training, which may help prepare the next generation of academic clinicians.
{"title":"From tutor to future educator: Investigating the role of peer-peer tutoring in shaping careers in medical education","authors":"Lauren Stokes, Harinder Singh","doi":"10.1101/2023.12.05.23297167","DOIUrl":"https://doi.org/10.1101/2023.12.05.23297167","url":null,"abstract":"In the effort to promote academic excellence and provide authentic teaching experiences and training for medical students, the University of California, Irvine, School of Medicine (UCISOM) built a novel peer tutoring program, Collaborative Learning Communities with Medical Students as Teachers (CLC-MSAT). While the role of peer-assisted learning in student success on academic courses is well established, we wanted to assess the impact of our peer-assisted learning program on tutor’s career interest in medical education. Through a mixed-methods analysis of our peer tutors’ experiences, we found >80% were overall satisfied with their positions; >85% learned new skills; >88% felt they were strong teachers; >88% felt they now had a stronger grasp of the medical curriculum. Our findings suggest that the CLC-MSAT program has a positive impact in exposing medical students to teaching experience and training, which may help prepare the next generation of academic clinicians.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"32 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138717284","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 : 2023-12-10DOI: 10.1101/2023.12.09.23299744
Felix Busch, Lena Hoffmann, Daniel Truhn, Esteban Ortiz-Prado, Marcus R. Makowski, Keno K. Bressem, Lisa C. Adams, COMFORT Consortium
Background Artificial intelligence (AI) is anticipated to fundamentally change the educational and professional landscape for the next generation of physicians, but its successful integration depends on the global perspectives of all stakeholders. Previous medical student surveys were limited by small sample sizes or geographic constraints, hindering a global comparison of perceptions. This study aims to explore current medical students’ attitudes towards AI in medical education and the profession on a broad, international scale and to examine regional differences in perspectives.
{"title":"Medical students’ perceptions towards artificial intelligence in education and practice: A multinational, multicenter cross-sectional study","authors":"Felix Busch, Lena Hoffmann, Daniel Truhn, Esteban Ortiz-Prado, Marcus R. Makowski, Keno K. Bressem, Lisa C. Adams, COMFORT Consortium","doi":"10.1101/2023.12.09.23299744","DOIUrl":"https://doi.org/10.1101/2023.12.09.23299744","url":null,"abstract":"<strong>Background</strong> Artificial intelligence (AI) is anticipated to fundamentally change the educational and professional landscape for the next generation of physicians, but its successful integration depends on the global perspectives of all stakeholders. Previous medical student surveys were limited by small sample sizes or geographic constraints, hindering a global comparison of perceptions. This study aims to explore current medical students’ attitudes towards AI in medical education and the profession on a broad, international scale and to examine regional differences in perspectives.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"60 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138574422","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 : 2023-12-08DOI: 10.1101/2023.12.07.23299651
David Hickey, John McFarland
Objectives The proficiency of an accomplished psychiatrist encompasses the development, adaptation, and refinement of a biopsychosocial formulation. A formulation aids clinical decision-making by organizing information and furnishes a documented rationale for decisions. Despite its significance, psychiatric trainees often perceive the formulation as arduous and time-intensive, leading to avoidance. Educational shortcomings are pervasive. Addressing this calls for low-cost, novel solutions. Undergraduate medical education possesses aspiring psychiatrists and provides a platform to develop a foundational understanding of formulation. This study aims to explore the viability of a novel, resource-efficient approach employing a celebrity case narrative to attain a fundamental understanding of the psychiatric formulation while concurrently elucidating activated pedagogical cognitions by using such methodology from the student's perspective. Methods A psychiatric formulation tutorial was conducted across five distinct final-year medical student cohorts during one academic year. A standardized tutorial structure was devised, incorporating interchangeable case studies. Following the tutorial, a post-tutorial survey was administered, followed by interviews that underwent qualitative analysis. Results Seventy-seven participants responded to the survey, expressing favourable views. Twenty students consented to interviews. They were distributed across five sessions with an average of four participants per group. Interviews yielded five key themes: Understanding of formulation, cognitive engagement, emotional salience and ethical considerations with twelve corresponding subthemes. The results suggested viability in using this methodology to teach formulation to foster a basic understanding and elicited a range of pedagogical phenomenon that may have contributed to this understanding. Conclusion This study indicates that integrating a celebrity narrative into psychiatric formulation teaching intervention bears potential for enhancing engagement concurrently mitigating negative attitudes towards the formulation. The approach reveals latent learning outcomes suggesting a profound pedagogical impact. The range of pedagogical process elucidated lays a foundational research base for future instructional design and research.
{"title":"Perspectives on using a celebrity narrative to teach the psychiatric formulation to final year medical students","authors":"David Hickey, John McFarland","doi":"10.1101/2023.12.07.23299651","DOIUrl":"https://doi.org/10.1101/2023.12.07.23299651","url":null,"abstract":"Objectives\u0000The proficiency of an accomplished psychiatrist encompasses the development, adaptation, and refinement of a biopsychosocial formulation. A formulation aids clinical decision-making by organizing information and furnishes a documented rationale for decisions. Despite its significance, psychiatric trainees often perceive the formulation as arduous and time-intensive, leading to avoidance. Educational shortcomings are pervasive. Addressing this calls for low-cost, novel solutions. Undergraduate medical education possesses aspiring psychiatrists and provides a platform to develop a foundational understanding of formulation. This study aims to explore the viability of a novel, resource-efficient approach employing a celebrity case narrative to attain a fundamental understanding of the psychiatric formulation while concurrently elucidating activated pedagogical cognitions by using such methodology from the student's perspective.\u0000Methods\u0000A psychiatric formulation tutorial was conducted across five distinct final-year medical student cohorts during one academic year. A standardized tutorial structure was devised, incorporating interchangeable case studies. Following the tutorial, a post-tutorial survey was administered, followed by interviews that underwent qualitative analysis. Results\u0000Seventy-seven participants responded to the survey, expressing favourable views. Twenty students consented to interviews. They were distributed across five sessions with an average of four participants per group. Interviews yielded five key themes: Understanding of formulation, cognitive engagement, emotional salience and ethical considerations with twelve corresponding subthemes. The results suggested viability in using this methodology to teach formulation to foster a basic understanding and elicited a range of pedagogical phenomenon that may have contributed to this understanding.\u0000Conclusion\u0000This study indicates that integrating a celebrity narrative into psychiatric formulation teaching intervention bears potential for enhancing engagement concurrently mitigating negative attitudes towards the formulation. The approach reveals latent learning outcomes suggesting a profound pedagogical impact. The range of pedagogical process elucidated lays a foundational research base for future instructional design and research.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138562940","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 : 2023-12-06DOI: 10.1101/2023.12.05.23299419
Matthew Myers Griffith, Emma Field, Angela Song-En Huang, Tomoe Shimada, Munkhzul Battsend, Tambri Housen, Barbara Pamphilon, Martyn D. Kirk
Introduction. COVID-19 underscored the importance of field epidemiology training programs (FETP) as countries struggled with overwhelming demands. Experts are calling for more field epidemiologists with better training. Since 1951 FETP have been building public health capacities across the globe, yet explorations of learning in these programs are lacking. This qualitative study will 1) describe approaches to training field epidemiologists in FETP; 2) describe strategies for learning field epidemiology among FETP trainees; and 3) explain the principles and practices aligning training approaches with learning strategies in FETP. Methods and analysis. The research design, implementation, and interpretation are collaborative efforts with FETP trainers. Data collection will include interviews with FETP trainers and trainees and participant observations of FETP training and learning events in four FETP in the Western Pacific Region. Data analysis will occur in three phases: I) we will use the constant comparison method of Charmaz's grounded theory during open coding to identify and prioritise categories and properties in the data; II) during focused coding, we will use constant comparison and Polkinghorne's analysis of narratives, comparing stories of prioritized categories, to fill out properties of those categories; III) we will use Polkinghorne's narrative analysis to construct narratives that reflect domains of interest, identifying correspondence among Carr and Kemmis's practices, understandings, and situations to explain principles and processes of learning in FETP. Ethics and dissemination. We have obtained the required ethics approvals to conduct this research at The Australian National University (2021/771) and Taiwan's Ministry of Health and Welfare (112206). Data will not be available publicly, but anonymised findings will be shared with FETP for collaborative interpretation. Ultimately, findings and interpretations will appear in peer reviewed journals and conferences.
{"title":"HOW DO FIELD EPIDEMIOLOGISTS LEARN? A PROTOCOL FOR A QUALITATIVE INQUIRY INTO LEARNING IN FIELD EPIDEMIOLOGY TRAINING PROGRAMS","authors":"Matthew Myers Griffith, Emma Field, Angela Song-En Huang, Tomoe Shimada, Munkhzul Battsend, Tambri Housen, Barbara Pamphilon, Martyn D. Kirk","doi":"10.1101/2023.12.05.23299419","DOIUrl":"https://doi.org/10.1101/2023.12.05.23299419","url":null,"abstract":"Introduction. COVID-19 underscored the importance of field epidemiology training programs (FETP) as countries struggled with overwhelming demands. Experts are calling for more field epidemiologists with better training. Since 1951 FETP have been building public health capacities across the globe, yet explorations of learning in these programs are lacking. This qualitative study will 1) describe approaches to training field epidemiologists in FETP; 2) describe strategies for learning field epidemiology among FETP trainees; and 3) explain the principles and practices aligning training approaches with learning strategies in FETP. Methods and analysis. The research design, implementation, and interpretation are collaborative efforts with FETP trainers. Data collection will include interviews with FETP trainers and trainees and participant observations of FETP training and learning events in four FETP in the Western Pacific Region. Data analysis will occur in three phases: I) we will use the constant comparison method of Charmaz's grounded theory during open coding to identify and prioritise categories and properties in the data; II) during focused coding, we will use constant comparison and Polkinghorne's analysis of narratives, comparing stories of prioritized categories, to fill out properties of those categories; III) we will use Polkinghorne's narrative analysis to construct narratives that reflect domains of interest, identifying correspondence among Carr and Kemmis's practices, understandings, and situations to explain principles and processes of learning in FETP. Ethics and dissemination. We have obtained the required ethics approvals to conduct this research at The Australian National University (2021/771) and Taiwan's Ministry of Health and Welfare (112206). Data will not be available publicly, but anonymised findings will be shared with FETP for collaborative interpretation. Ultimately, findings and interpretations will appear in peer reviewed journals and conferences.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"251 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138553939","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 : 2023-11-19DOI: 10.1101/2023.11.17.23298680
Danastan Tasaouf Mridula, Abu Ahmed Ferdaus, Tanmoy Sarkar Pias
Emotion is an intricate physiological response that plays a crucial role in how we respond and cooperate with others in our daily affairs. Numerous experiments have been evolved to recognize emotion, however still require exploration to intensify the performance. To enhance the performance of effective emotion recognition, this study proposes a subject-dependent robust end-to-end emotion recognition system based on a 1D convolutional neural network (1D-CNN). We evaluate the SJTU1 Emotion EEG Dataset SEED-V with five emotions (happy, sad, neural, fear, and disgust). To begin with, we utilize the Fast Fourier Transform (FFT) to decompose the raw EEG signals into six frequency bands and extract the power spectrum feature from the frequency bands. After that, we combine the extracted power spectrum feature with eye movement and differential entropy (DE) features. Finally, for classification, we apply the combined data to our proposed system. Consequently, it attains 99.80% accuracy which surpasses each prior state-of-the-art system
{"title":"Exploring Emotions in EEG: Deep Learning Approach with Feature Fusion","authors":"Danastan Tasaouf Mridula, Abu Ahmed Ferdaus, Tanmoy Sarkar Pias","doi":"10.1101/2023.11.17.23298680","DOIUrl":"https://doi.org/10.1101/2023.11.17.23298680","url":null,"abstract":"Emotion is an intricate physiological response that\u0000plays a crucial role in how we respond and cooperate with others in our daily affairs. Numerous experiments have been evolved to recognize emotion, however still require exploration to intensify the performance. To enhance the performance of effective emotion recognition, this study proposes a subject-dependent robust end-to-end emotion recognition system based on a 1D convolutional neural network (1D-CNN). We evaluate the SJTU1 Emotion EEG Dataset SEED-V with five emotions (happy, sad, neural, fear, and disgust). To begin with, we utilize the Fast Fourier Transform (FFT) to decompose the raw EEG signals into six frequency bands and extract the power spectrum feature from the frequency bands. After that, we combine the extracted power spectrum feature with eye movement and differential entropy\u0000(DE) features. Finally, for classification, we apply the combined data to our proposed system. Consequently, it attains 99.80% accuracy which surpasses each prior state-of-the-art system","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"171 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138524106","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}
Background. Medical students’ rate of depression, suicidal ideation, anxiety, and burnout have been shown to be higher than those of the same-age general population. However, longitudinal studies spanning the whole course of medical school are scarce and present contradictory findings. This study aims to analyze the longitudinal evolution of mental health and burnout from the first to the last year of medical school using a wide range of indicators. Moreover, biopsychosocial covariates that can influence this evolution are explored. Method. In an open cohort study design, 3066 annual questionnaires were filled in by 1595 different students from the first to the sixth year of the Lausanne Medical School (Switzerland). Depression symptoms, suicidal ideation, anxiety symptoms, stress, and burnout were measured along with biopsychosocial covariates. The longitudinal evolution of mental health and burnout and the impact of covariates were modelled with linear mixed models. Results. Comparison to a same-aged general population sample shows that medical students reported significantly more depression symptoms and anxiety symptoms. Medical students’ mental health improved during the course of the studies in terms of depression symptoms, suicidal ideation, and stress, although suicidal ideation increased again in the last year and anxiety symptoms remained stable. Conversely, the results regarding burnout globally showed a significant worsening from beginning to end of medical school. The covariates most strongly related to better mental health and less burnout were less emotion-focused coping, more social support, and more satisfaction with health. Conclusion. Both improvement of mental health and worsening of burnout were observed during the course of medical school. This underlines that the beginning and the end of medical school bring specific challenges with the first years’ stressors negatively impacting mental health and the last year’s difficulties negatively impacting burnout.
背景。医学院学生的抑郁、自杀意念、焦虑和倦怠率已被证明高于同龄一般人群。然而，跨越整个医学院课程的纵向研究很少，并且呈现出相互矛盾的结果。本研究旨在利用广泛的指标，分析医学院一年级至最后一年心理健康与倦怠的纵向演变。此外，还探讨了影响这种进化的生物心理社会协变量。在一项开放队列研究设计中，1595名来自瑞士洛桑医学院(Lausanne Medical School)一年级至六年级的学生填写了3066份年度问卷。测量抑郁症状、自杀意念、焦虑症状、压力和倦怠以及生物心理社会协变量。心理健康与职业倦怠的纵向演变及协变量的影响采用线性混合模型进行建模。与同龄的普通人群样本相比，医学生报告的抑郁症状和焦虑症状明显更多。在研究过程中，医学生的心理健康状况在抑郁症状、自杀意念和压力方面有所改善，但自杀意念在去年再次增加，焦虑症状保持稳定。相反，全球范围内关于职业倦怠的结果显示，从医学院开始到结束，情况明显恶化。与更好的心理健康和更少的职业倦怠最密切相关的协变量是较少的情绪集中应对、更多的社会支持和更多的健康满意度。在医学院学习期间，心理健康状况有所改善，职业倦怠状况有所恶化。这强调了医学院的开始和结束会带来具体的挑战，第一年的压力因素会对心理健康产生负面影响，而最后一年的困难会对倦怠产生负面影响。
{"title":"Mental health and burnout during medical school: Longitudinal evolution and covariates","authors":"Valerie Carrard, Sylvie Berney, Céline Bourquin, Setareh Ranjbar, Enrique Castelao, Katja Schlegel, Jacques Gaumes, Pierre-Alexandre Bart, Marianne Schmid Mast, Martin Preisig, Alexandre Berney","doi":"10.1101/2023.11.15.23298610","DOIUrl":"https://doi.org/10.1101/2023.11.15.23298610","url":null,"abstract":"Background. Medical students’ rate of depression, suicidal ideation, anxiety, and burnout have been shown to be higher than those of the same-age general population. However, longitudinal studies spanning the whole course of medical school are scarce and present contradictory findings. This study aims to analyze the longitudinal evolution of mental health and burnout from the first to the last year of medical school using a wide range of indicators. Moreover, biopsychosocial covariates that can influence this evolution are explored.\u0000Method. In an open cohort study design, 3066 annual questionnaires were filled in by 1595 different students from the first to the sixth year of the Lausanne Medical School (Switzerland). Depression symptoms, suicidal ideation, anxiety symptoms, stress, and burnout were measured along with biopsychosocial covariates. The longitudinal evolution of mental health and burnout and the impact of covariates were modelled with linear mixed models.\u0000Results. Comparison to a same-aged general population sample shows that medical students reported significantly more depression symptoms and anxiety symptoms. Medical students’ mental health improved during the course of the studies in terms of depression symptoms, suicidal ideation, and stress, although suicidal ideation increased again in the last year and anxiety symptoms remained stable. Conversely, the results regarding burnout globally showed a significant worsening from beginning to end of medical school. The covariates most strongly related to better mental health and less burnout were less emotion-focused coping, more social support, and more satisfaction with health.\u0000Conclusion. Both improvement of mental health and worsening of burnout were observed during the course of medical school. This underlines that the beginning and the end of medical school bring specific challenges with the first years’ stressors negatively impacting mental health and the last year’s difficulties negatively impacting burnout.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"53 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138524092","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 : 2023-11-17DOI: 10.1101/2023.11.16.23298661
Gregory Ow, Adam Rodman, Geoffrey V Stetson
BACKGROUND: Medical education scholarship often lacks a strong theoretical underpinning, with this gap most often affecting early-career researchers and researchers in the Global South. Large language models (LLMs) have shown considerable promise to augment human writing and creativity in a variety of settings. In this study, we describe the development of MedEdMENTOR - an online platform for medical education research with a library of over 250 theories - and the development and evaluation of MedEdMENTOR AI, an LLM containing knowledge from MedEdMENTOR and the first AI mentor for medical education research. METHODS: From a postpositivist paradigm, we evaluated MedEdMENTOR AI by testing it against 6 months of qualitative research published in 24 core medical educational journals. In a blinded fashion, we presented MedEdMENTOR AI with only the phenomenon of the qualitative study, and asked it to recommend 5 theories that could be used to study that phenomenon. RESULTS: For 55% (29 of 53) of studies, MedEdMENTOR AI recommended the actual theoretical constructs chosen in the respective qualitative studies. CONCLUSIONS: Our data is preliminary, but it suggests that MedEdMENTOR AI and other LLMs can be highly effective in guiding medical education scholars towards theories that may be applicable in their research. Further research is needed to assess performance on other tasks in medical education research.
{"title":"MedEdMENTOR AI: Can artificial intelligence help medical education researchers select theoretical constructs?","authors":"Gregory Ow, Adam Rodman, Geoffrey V Stetson","doi":"10.1101/2023.11.16.23298661","DOIUrl":"https://doi.org/10.1101/2023.11.16.23298661","url":null,"abstract":"BACKGROUND: Medical education scholarship often lacks a strong theoretical underpinning, with this gap most often affecting early-career researchers and researchers in the Global South. Large language models (LLMs) have shown considerable promise to augment human writing and creativity in a variety of settings. In this study, we describe the development of MedEdMENTOR - an online platform for medical education research with a library of over 250 theories - and the development and evaluation of MedEdMENTOR AI, an LLM containing knowledge from MedEdMENTOR and the first AI mentor for medical education research. METHODS: From a postpositivist paradigm, we evaluated MedEdMENTOR AI by testing it against 6 months of qualitative research published in 24 core medical educational journals. In a blinded fashion, we presented MedEdMENTOR AI with only the phenomenon of the qualitative study, and asked it to recommend 5 theories that could be used to study that phenomenon. RESULTS: For 55% (29 of 53) of studies, MedEdMENTOR AI recommended the actual theoretical constructs chosen in the respective qualitative studies. CONCLUSIONS: Our data is preliminary, but it suggests that MedEdMENTOR AI and other LLMs can be highly effective in guiding medical education scholars towards theories that may be applicable in their research. Further research is needed to assess performance on other tasks in medical education research.","PeriodicalId":501387,"journal":{"name":"medRxiv - Medical Education","volume":"77 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138524093","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：