TY - JOUR AU - Schnetzler, Nicolas AU - Taramarcaz, Victor AU - Herren, Tara AU - Golay, Eric AU - Regard, Simon AU - Mach, François AU - Nasution, Amanta AU - Larribau, Robert AU - Suppan, Melanie AU - Schiffer, Eduardo AU - Suppan, Laurent PY - 2025/4/24 TI - Recruiting Medical, Dental, and Biomedical Students as First Responders in the Immediate Aftermath of the COVID-19 Pandemic: Prospective Follow-Up Study JO - JMIR Med Educ SP - e63018 VL - 11 KW - basic life support KW - out-of-hospital cardiac arrest KW - cardiopulmonary resuscitation KW - e-learning KW - blended learning KW - first responder KW - undergraduate medical education KW - student motivation KW - motivational strategies KW - medical student KW - COVID-19 KW - pandemic KW - life support KW - survival prognosis KW - biomedical students KW - dental students KW - motivational interventions N2 - Background: Basic life support improves survival prognosis after out-of-hospital cardiac arrest, but is too rarely provided before the arrival of professional rescue services. First responder networks have been developed in many regions of the world to decrease the delay between collapse and initiation of resuscitation maneuvers. Their efficiency depends on the number of first responders available and many networks lack potential rescuers. Medical, dental, and biomedical students represent an almost untapped source of potential first responders, and a first study, carried out during the COVID-19 pandemic, led to the recruitment of many of these future professionals even though many restrictions were still in effect. Objective: The objective of this study was to determine the impact of an enhanced strategy on the recruitment of medical, dental, and biomedical students as first responders in the immediate aftermath of the COVID-19 pandemic. Methods: This was a prospective follow-up study, conducted between November 2021 and March 2022 at the University of Geneva Faculty of Medicine, Geneva, Switzerland. A web-based study platform was used to manage consent, registrations, and certificates. A first motivational intervention was held early in the academic year and targeted all first-year medical, dental, and biomedical students. Participants first answered a questionnaire designed to assess their initial basic life support knowledge before following an e-learning module. Those who completed the module were able to register for a face-to-face training session held by senior medical students. A course certificate was awarded to those who completed these sessions, enabling them to register as first responders on the Save a Life first responder network. Since the number of students who had enlisted as first responders 2 months after the motivational intervention was markedly lower than expected, a second, unplanned motivational intervention was held in an attempt to recruit more students. Results: Out of a total of 674 first-year students, 19 (2.5%) students had registered as first responders after the first motivational intervention. This was significantly less than the proportion achieved through the initial study (48/529, 9.1%; P<.001). The second motivational intervention led to the enrollment of 7 more students (26/674, 3.9%), a figure still significantly lower than that of the original study (P<.001). At the end of the study, 76 (11.3%) students had been awarded a certificate of competence. Conclusions: Contrary to expectations, an earlier presentation during the academic year outside the COVID restriction period did not increase the recruitment of medical, dental, and biomedical students as first responders in the immediate aftermath of the COVID-19 pandemic. The reasons underlying this drop in motivation should be explored to enable the design of focused motivational interventions. UR - https://mededu.jmir.org/2025/1/e63018 UR - http://dx.doi.org/10.2196/63018 ID - info:doi/10.2196/63018 ER - TY - JOUR AU - Bieler, Sandra AU - von Düring, Stephan AU - Tagan, Damien AU - Grosgurin, Olivier AU - Fumeaux, Thierry PY - 2025/3/3 TI - Impact of a Point-of-Care Ultrasound Training Program on the Management of Patients With Acute Respiratory or Circulatory Failure by In-Training Emergency Department Residents (IMPULSE): Before-and-After Implementation Study JO - JMIRx Med SP - e53276 VL - 6 KW - point-of-care ultrasonography KW - training program KW - emergency department KW - acute respiratory failure KW - acute circulatory failure N2 - Background: Due to its diagnostic accuracy, point-of-care ultrasound (POCUS) is becoming more frequently used in the emergency department (ED), but the feasibility of its use by in-training residents and the potential clinical impact have not been assessed. Objective: This study aimed to assess the feasibility of implementing a structured POCUS training program for in-training ED residents, as well as the clinical impact of their use of POCUS in the management of patients in the ED. Methods: IMPULSE (Impact of a Point-of Care Ultrasound Examination) is a before-and-after implementation study evaluating the impact of a structured POCUS training program for ED residents on the management of patients admitted with acute respiratory failure (ARF) and/or circulatory failure (ACF) in a Swiss regional hospital. The training curriculum was organized into 3 steps and consisted of a web-based training course; an 8-hour, practical, hands-on session; and 10 supervised POCUS examinations. ED residents who successfully completed the curriculum participated in the postimplementation phase of the study. Outcomes were time to ED diagnosis, rate and time to correct diagnosis in the ED, time to prescribe appropriate treatment, and in-hospital mortality. Standard statistical analyses were performed using chi-square and Mann-Whitney U tests as appropriate, supplemented by Bayesian analysis, with a Bayes factor (BF)>3 considered significant. Results: A total of 69 and 54 patients were included before and after implementation of the training program, respectively. The median time to ED diagnosis was 25 (IQR 15?60) minutes after implementation versus 30 (IQR 10?66) minutes before implementation, a difference that was significant in the Bayesian analysis (BF=9.6). The rate of correct diagnosis was higher after implementation (51/54, 94% vs 36/69, 52%; P<.001), with a significantly shorter time to correct diagnosis after implementation (25, IQR 15?60 min vs 43, IQR 11?70 min; BF=5.0). The median time to prescribe the appropriate therapy was shorter after implementation (47, IQR 25?101 min vs 70, IQR 20?120 min; BF=2.0). Finally, there was a significant difference in hospital mortality (9/69, 13% vs 3/54, 6%; BF=15.7). Conclusions: The IMPULSE study shows that the implementation of a short, structured POCUS training program for ED residents is not only feasible but also has a significant impact on their initial evaluation of patients with ARF and/or ACF, improving diagnostic accuracy, time to correct diagnosis, and rate of prescribing the appropriate therapy and possibly decreasing hospital mortality. These results should be replicated in other settings to provide further evidence that implementation of a short, structured POCUS training curriculum could significantly impact ED management of patients with ARF and/or ACF. UR - https://xmed.jmir.org/2025/1/e53276 UR - http://dx.doi.org/10.2196/53276 ID - info:doi/10.2196/53276 ER - TY - JOUR AU - Sarkar, Korak AU - Bhimarasetty, Vishal AU - Rahim, Abdul AU - Curtis, Colin AU - Hughes, Kimberly PY - 2025/2/21 TI - Assessing the Feasibility and Utility of Patient-Specific 3D Advanced Visualization Modeling in Cerebrovascular Disease: Retrospective Analysis and Prospective Survey Pilot Study JO - JMIR Form Res SP - e51939 VL - 9 KW - cerebrovascular disease KW - advanced visualization KW - 3D modeling KW - cerebrovascular KW - intracerebral arteriovenous malformations KW - artery KW - vein KW - vessel KW - medical extended reality KW - 3D printing KW - medical simulation KW - virtual reality KW - augmented reality KW - usability KW - survey KW - stroke KW - brain KW - cerebral N2 - Background: The prevalence, clinical burden, and health care costs (>US $100 billion) associated with cerebrovascular disease (CVD) will increase significantly as the US population grows and ages over the next 25 years. Existing 2D imaging modalities have inherent limitations in visualizing complex CVD, which may be mitigated with the use of patient-specific 3D advanced visualization (AV) technologies. There remain gaps in knowledge, however, regarding how and with what impact these technologies are being used in CVD. Objective: The aim of this study was to characterize the clinical attributes and reported utility associated with the use of 3D AV modeling in CVDs, specifically intracerebral arteriovenous malformations. Methods: This pilot study employs a combination of retrospective analysis and prospective surveys to describe the utilization and utility of patient-specific AV models at a single high-volume certified comprehensive stroke center. Results: From July 2017 to February 2023, 25 AV models were created for 4 different clinicians. The average patient age was 37.4 years; 44% (11/25) of the patients were African Americans, 52% (13/25) were on public insurance, and 56% (14/25) were associated with a neurovascular procedure. In this study, 18 clinicians with diverse experience responded to AV model surveys, with a 92.2% (166/180) completion rate. There was an average reported utility of 8.0 on a 0-10 scale, with higher scores reflecting increased utility. Compared to 2D viewing, AV models allowed staff to appreciate novel abnormal anatomy, and therefore, they would have changed their therapeutic approach in 45% (23/51) of the cases. Conclusions: AV models were used in complex CVDs associated with young, publicly insured individuals requiring resource-intensive interventions. There was strong and diverse clinician engagement with overall report of substantial utility of AV models. Staff clinicians frequently reported novel anatomical and therapeutic insights based on AV models compared to traditional 2D viewing. This study establishes the infrastructure for future larger randomized studies that can be repeated for CVDs or other disease states and incorporate assessments of other AV modalities such as 3D printing and medical extended reality. UR - https://formative.jmir.org/2025/1/e51939 UR - http://dx.doi.org/10.2196/51939 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/51939 ER - TY - JOUR AU - Kitapcioglu, Dilek AU - Aksoy, Emin Mehmet AU - Ozkan, Ekin Arun AU - Usseli, Tuba AU - Cabuk Colak, Dilan AU - Torun, Tugrul PY - 2025/2/14 TI - Enhancing Immersion in Virtual Reality?Based Advanced Life Support Training: Randomized Controlled Trial JO - JMIR Serious Games SP - e68272 VL - 13 KW - artificial intelligence KW - voice recognition KW - serious gaming KW - immersion KW - virtual reality N2 - Background: Serious game?based training modules are pivotal for simulation-based health care training. With advancements in artificial intelligence (AI) and natural language processing, voice command interfaces offer an intuitive alternative to traditional virtual reality (VR) controllers in VR applications. Objective: This study aims to compare AI-supported voice command interfaces and traditional VR controllers in terms of user performance, exam scores, presence, and confidence in advanced cardiac life support (ACLS) training. Methods: A total of 62 volunteer students from Acibadem Mehmet Ali Aydinlar University Vocational School for Anesthesiology, aged 20-22 years, participated in the study. All the participants completed a pretest consisting of 10 multiple-choice questions about ACLS. Following the pretest, participants were randomly divided into 2 groups: the voice command group (n=31) and the VR controller group (n=31). The voice command group members completed the VR-based ACLS serious game in training mode twice, using an AI-supported voice command as the game interface. The VR controller group members also completed the VR-based ACLS serious game in training mode twice, but they used VR controllers as the game interface. The participants completed a survey to assess their level of presence and confidence during gameplay. Following the survey, participants completed the exam module of the VR-based serious gaming module. At the final stage of the study, participants completed a posttest, which had the same content as the pretest. VR-based exam scores of the voice command and VR controller groups were compared using a 2-tailed, independent-samples t test, and linear regression analysis was conducted to examine the effect of presence and confidence rating. Results: Both groups showed an improvement in performance from pretest to posttest, with no significant difference in the magnitude of improvement between the 2 groups (P=.83). When comparing presence ratings, there was no significant difference between the voice command group (mean 5.18, SD 0.83) and VR controller group (mean 5.42, SD 0.75; P=.25). However, when comparing VR-based exam scores, the VR controller group (mean 80.47, SD 13.12) significantly outperformed the voice command group (mean 66.70, SD 21.65; P=.005), despite both groups having similar time allocations for the exam (voice command group: mean 18.59, SD 5.28 minutes and VR controller group: mean 17.3, SD 4.83 minutes). Confidence levels were similar between the groups (voice command group: mean 3.79, SD 0.77 and VR controller group: mean 3.60, SD 0.72), but the voice command group displayed a significant overconfidence bias (voice command group: mean 0.09, SD 0.24 and VR controller group: mean ?0.09, SD 0.18; P=.002). Conclusions: VR-based ACLS training demonstrated effectiveness; however, the use of voice commands did not result in improved performance. Further research should explore ways to optimize AI?s role in education through VR. Trial Registration: ClinicalTrials.gov NCT06458452; https://clinicaltrials.gov/ct2/show/NCT06458452 UR - https://games.jmir.org/2025/1/e68272 UR - http://dx.doi.org/10.2196/68272 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/68272 ER - TY - JOUR AU - Brown, Joan AU - De-Oliveira, Sophia AU - Mitchell, Christopher AU - Cesar, Carmen Rachel AU - Ding, Li AU - Fix, Melissa AU - Stemen, Daniel AU - Yacharn, Krisda AU - Wong, Fum Se AU - Dhillon, Anahat PY - 2025/1/24 TI - Barriers to and Facilitators of Implementing Team-Based Extracorporeal Membrane Oxygenation Simulation Study: Exploratory Analysis JO - JMIR Med Educ SP - e57424 VL - 11 KW - intensive care unit KW - ICU KW - teamwork in the ICU KW - team dynamics KW - collaboration KW - interprofessional collaboration KW - simulation KW - simulation training KW - ECMO KW - extracorporeal membrane oxygenation KW - life support KW - cardiorespiratory dysfunction KW - cardiorespiratory KW - cardiology KW - respiratory KW - heart KW - lungs N2 - Introduction: Extracorporeal membrane oxygenation (ECMO) is a critical tool in the care of severe cardiorespiratory dysfunction. Simulation training for ECMO has become standard practice. Therefore, Keck Medicine of the University of California (USC) holds simulation-training sessions to reinforce and improve providers knowledge. Objective: This study aimed to understand the impact of simulation training approaches on interprofessional collaboration. We believed simulation-based ECMO training would improve interprofessional collaboration through increased communication and enhance teamwork. Methods: This was a single-center, mixed methods study of the Cardiac and Vascular Institute Intensive Care Unit at Keck Medicine of USC conducted from September 2021 to April 2023. Simulation training was offered for 1 hour monthly to the clinical team focused on the collaboration and decision-making needed to evaluate the initiation of ECMO therapy. Electronic surveys were distributed before, after, and 3 months post training. The survey evaluated teamwork and the effectiveness of training, and focus groups were held to understand social environment factors. Additionally, trainee and peer evaluation focus groups were held to understand socioenvironmental factors. Results: In total, 37 trainees attended the training simulation from August 2021 to August 2022. Using 27 records for exploratory factor analysis, the standardized Cronbach ? was 0.717. The survey results descriptively demonstrated a positive shift in teamwork ability. Qualitative themes identified improved confidence and decision-making. Conclusions: The study design was flawed, indicating improvement opportunities for future research on simulation training in the clinical setting. The paper outlines what to avoid when designing and implementing studies that assess an educational intervention in a complex clinical setting. The hypothesis deserves further exploration and is supported by the results of this study. UR - https://mededu.jmir.org/2025/1/e57424 UR - http://dx.doi.org/10.2196/57424 ID - info:doi/10.2196/57424 ER - TY - JOUR AU - Nicolau, Abel AU - Jorge, Inês AU - Vieira-Marques, Pedro AU - Sa-Couto, Carla PY - 2024/12/19 TI - Influence of Training With Corrective Feedback Devices on Cardiopulmonary Resuscitation Skills Acquisition and Retention: Systematic Review and Meta-Analysis JO - JMIR Med Educ SP - e59720 VL - 10 KW - cardiopulmonary resuscitation KW - CPR quality KW - resuscitation training KW - corrective feedback devices KW - skills acquisition KW - skills retention KW - systematic review KW - evidence-based research KW - meta-analysis KW - feedback devices KW - PRISMA N2 - Background: Several studies related to the use of corrective feedback devices in cardiopulmonary resuscitation training, with different populations, training methodologies, and equipment, present distinct results regarding the influence of this technology. Objective: This systematic review and meta-analysis aimed to examine the impact of corrective feedback devices in cardiopulmonary resuscitation skills acquisition and retention for laypeople and health care professionals. Training duration was also studied. Methods: The search was conducted in PubMed, Web of Science, and Scopus from January 2015 to December 2023. Eligible randomized controlled trials compared technology-based training incorporating corrective feedback with standard training. Outcomes of interest were the quality of chest compression?related components. The risk of bias was assessed using the Cochrane tool. A meta-analysis was used to explore the heterogeneity of the selected studies. Results: In total, 20 studies were included. Overall, it was reported that corrective feedback devices used during training had a positive impact on both skills acquisition and retention. Medium to high heterogeneity was observed. Conclusions: This systematic review and meta-analysis suggest that corrective feedback devices enhance skills acquisition and retention over time. Considering the medium to high heterogeneity observed, these findings should be interpreted with caution. More standardized, high-quality studies are needed. Trial Registration: PROSPERO CRD42021240953; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=240953 UR - https://mededu.jmir.org/2024/1/e59720 UR - http://dx.doi.org/10.2196/59720 UR - http://www.ncbi.nlm.nih.gov/pubmed/39699935 ID - info:doi/10.2196/59720 ER - TY - JOUR AU - Sun, Wan-Na AU - Hsieh, Min-Chai AU - Wang, Wei-Fang PY - 2024/12/5 TI - Nurses? Knowledge and Skills After Use of an Augmented Reality App for Advanced Cardiac Life Support Training: Randomized Controlled Trial JO - J Med Internet Res SP - e57327 VL - 26 KW - augmented reality KW - technology intervention KW - randomized controlled trial KW - advanced cardiac life support KW - nursing education N2 - Background: Advanced cardiac life support (ACLS) skills are essential for nurses. During the COVID-19 pandemic, augmented reality (AR) technologies were incorporated into medical education to increase learning motivation and accessibility. Objective: This study aims to determine whether AR for educational applications can significantly improve crash cart learning, learning motivation, cognitive load, and system usability. It focused on a subgroup of nurses with less than 2 years of experience. Methods: This randomized controlled trial study was conducted in a medical center in southern Taiwan. An ACLS cart training course was developed using AR technologies in the first stage. Additionally, the efficacy of the developed ACLS training course was evaluated. The AR group used a crash cart learning system developed with AR technology, while the control group received traditional lecture-based instruction. Both groups were evaluated immediately after the course. Performance was assessed through learning outcomes related to overall ACLS and crash cart use. The Instructional Materials Motivation Survey, System Usability Scale, and Cognitive Load Theory Questionnaire were also used to assess secondary outcomes in the AR group. Subgroup analyses were performed for nurses with less than 2 years of experience. Results: All 102 nurses completed the course, with 43 nurses in the AR group and 59 nurses in the control group. The AR group outperformed the control group regarding overall ACLS outcomes and crash cart learning outcomes (P=.002; P=.01). The improvement rate was the largest for new staff regardless of the overall learning effect and the crash cart effect. Subgroup analysis revealed that nurses with less than 2 years of experience in the AR group showed more significant improvements in both overall learning (P<.001) and crash cart outcomes (P<.001) compared to their counterparts in the control group. For nurses with more than 2 years of experience, no significant differences were found between the AR and control groups in posttraining learning outcomes for the crash cart (P=.32). The AR group demonstrated high scores for motivation (Instructional Materials Motivation Survey mean score 141.65, SD 19.25) and system usability (System Usability Scale mean score 90.47, SD 11.91), as well as a low score for cognitive load (Cognitive Load Theory Questionnaire mean score 15.42, SD 5.76). Conclusions: AR-based learning significantly improves ACLS knowledge and skills, especially for nurses with less experience, compared to traditional methods. The high usability and motivational benefits of AR suggest its potential for broader applications in nursing education. Trial Registration: ClinicalTrials.gov NCT06057285; https://clinicaltrials.gov/ct2/show/NCT06057285 UR - https://www.jmir.org/2024/1/e57327 UR - http://dx.doi.org/10.2196/57327 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/57327 ER - TY - JOUR AU - Chien, Cheng-Yu AU - Tsai, Shang-Li AU - Huang, Chien-Hsiung AU - Wang, Ming-Fang AU - Lin, Chi-Chun AU - Chen, Chen-Bin AU - Tsai, Li-Heng AU - Tseng, Hsiao-Jung AU - Huang, Yan-Bo AU - Ng, Chip-Jin PY - 2024/4/29 TI - Effectiveness of Blended Versus Traditional Refresher Training for Cardiopulmonary Resuscitation: Prospective Observational Study JO - JMIR Med Educ SP - e52230 VL - 10 KW - cardiopulmonary resuscitation KW - blended method KW - blended KW - hybrid KW - refresher KW - refreshers KW - teaching KW - instruction KW - observational KW - training KW - professional development KW - continuing education KW - retraining KW - traditional method KW - self-directed learning KW - resuscitation KW - CPR KW - emergency KW - rescue KW - life support KW - cardiac KW - cardiopulmonary N2 - Background: Generally, cardiopulmonary resuscitation (CPR) skills decline substantially over time. By combining web-based self-regulated learning with hands-on practice, blended training can be a time- and resource-efficient approach enabling individuals to acquire or refresh CPR skills at their convenience. However, few studies have evaluated the effectiveness of blended CPR refresher training compared with that of the traditional method. Objective: This study investigated and compared the effectiveness of traditional and blended CPR training through 6-month and 12-month refresher sessions with CPR ability indicators. Methods: This study recruited participants aged ?18 years from the Automated External Defibrillator Donation Project. The participants were divided into 4 groups based on the format of the CPR training and refresher training received: (1) initial traditional training (a 30-minute instructor-led, hands-on session) and 6-month traditional refresher training (Traditional6 group), (2) initial traditional training and 6-month blended refresher training (an 18-minute e-learning module; Mixed6 group), (3) initial traditional training and 12-month blended refresher training (Mixed12 group), and (4) initial blended training and 6-month blended refresher training (Blended6 group). CPR knowledge and performance were evaluated immediately after initial training. For each group, following initial training but before refresher training, a learning effectiveness assessment was conducted at 12 and 24 months. CPR knowledge was assessed using a written test with 15 multiple-choice questions, and CPR performance was assessed through an examiner-rated skill test and objectively through manikin feedback. A generalized estimating equation model was used to analyze changes in CPR ability indicators. Results: This study recruited 1163 participants (mean age 41.82, SD 11.6 years; n=725, 62.3% female), with 332 (28.5%), 270 (23.2%), 258 (22.2%), and 303 (26.1%) participants in the Mixed6, Traditional6, Mixed12, and Blended6 groups, respectively. No significant between-group difference was observed in knowledge acquisition after initial training (P=.23). All groups met the criteria for high-quality CPR skills (ie, average compression depth: 5-6 cm; average compression rate: 100-120 beats/min; chest recoil rate: >80%); however, a higher proportion (98/303, 32.3%) of participants receiving blended training initially demonstrated high-quality CPR skills. At 12 and 24 months, CPR skills had declined in all the groups, but the decline was significantly higher in the Mixed12 group, whereas the differences were not significant between the other groups. This finding indicates that frequent retraining can maintain high-quality CPR skills and that blended refresher training is as effective as traditional refresher training. Conclusions: Our findings indicate that 6-month refresher training sessions for CPR are more effective for maintaining high-quality CPR skills, and that as refreshers, self-learning e-modules are as effective as instructor-led sessions. Although the blended learning approach is cost and resource effective, factors such as participant demographics, training environment, and level of engagement must be considered to maximize the potential of this approach. Trial Registration: IGOGO NCT05659108; https://www.cgmh-igogo.tw UR - https://mededu.jmir.org/2024/1/e52230 UR - http://dx.doi.org/10.2196/52230 UR - http://www.ncbi.nlm.nih.gov/pubmed/38683663 ID - info:doi/10.2196/52230 ER - TY - JOUR AU - King, C. Ryan AU - Samaan, S. Jamil AU - Yeo, Hui Yee AU - Peng, Yuxin AU - Kunkel, C. David AU - Habib, A. Ali AU - Ghashghaei, Roxana PY - 2024/4/19 TI - A Multidisciplinary Assessment of ChatGPT?s Knowledge of Amyloidosis: Observational Study JO - JMIR Cardio SP - e53421 VL - 8 KW - amyloidosis KW - ChatGPT KW - large language models KW - cardiology KW - gastroenterology KW - neurology KW - artificial intelligence KW - multidisciplinary care KW - assessment KW - patient education KW - large language model KW - accuracy KW - reliability KW - accessibility KW - educational resources KW - dissemination KW - gastroenterologist KW - cardiologist KW - medical society KW - institution KW - institutions KW - Facebook KW - neurologist KW - reproducibility KW - amyloidosis-related N2 - Background: Amyloidosis, a rare multisystem condition, often requires complex, multidisciplinary care. Its low prevalence underscores the importance of efforts to ensure the availability of high-quality patient education materials for better outcomes. ChatGPT (OpenAI) is a large language model powered by artificial intelligence that offers a potential avenue for disseminating accurate, reliable, and accessible educational resources for both patients and providers. Its user-friendly interface, engaging conversational responses, and the capability for users to ask follow-up questions make it a promising future tool in delivering accurate and tailored information to patients. Objective: We performed a multidisciplinary assessment of the accuracy, reproducibility, and readability of ChatGPT in answering questions related to amyloidosis. Methods: In total, 98 amyloidosis questions related to cardiology, gastroenterology, and neurology were curated from medical societies, institutions, and amyloidosis Facebook support groups and inputted into ChatGPT-3.5 and ChatGPT-4. Cardiology- and gastroenterology-related responses were independently graded by a board-certified cardiologist and gastroenterologist, respectively, who specialize in amyloidosis. These 2 reviewers (RG and DCK) also graded general questions for which disagreements were resolved with discussion. Neurology-related responses were graded by a board-certified neurologist (AAH) who specializes in amyloidosis. Reviewers used the following grading scale: (1) comprehensive, (2) correct but inadequate, (3) some correct and some incorrect, and (4) completely incorrect. Questions were stratified by categories for further analysis. Reproducibility was assessed by inputting each question twice into each model. The readability of ChatGPT-4 responses was also evaluated using the Textstat library in Python (Python Software Foundation) and the Textstat readability package in R software (R Foundation for Statistical Computing). Results: ChatGPT-4 (n=98) provided 93 (95%) responses with accurate information, and 82 (84%) were comprehensive. ChatGPT-3.5 (n=83) provided 74 (89%) responses with accurate information, and 66 (79%) were comprehensive. When examined by question category, ChatGTP-4 and ChatGPT-3.5 provided 53 (95%) and 48 (86%) comprehensive responses, respectively, to ?general questions? (n=56). When examined by subject, ChatGPT-4 and ChatGPT-3.5 performed best in response to cardiology questions (n=12) with both models producing 10 (83%) comprehensive responses. For gastroenterology (n=15), ChatGPT-4 received comprehensive grades for 9 (60%) responses, and ChatGPT-3.5 provided 8 (53%) responses. Overall, 96 of 98 (98%) responses for ChatGPT-4 and 73 of 83 (88%) for ChatGPT-3.5 were reproducible. The readability of ChatGPT-4?s responses ranged from 10th to beyond graduate US grade levels with an average of 15.5 (SD 1.9). Conclusions: Large language models are a promising tool for accurate and reliable health information for patients living with amyloidosis. However, ChatGPT?s responses exceeded the American Medical Association?s recommended fifth- to sixth-grade reading level. Future studies focusing on improving response accuracy and readability are warranted. Prior to widespread implementation, the technology?s limitations and ethical implications must be further explored to ensure patient safety and equitable implementation. UR - https://cardio.jmir.org/2024/1/e53421 UR - http://dx.doi.org/10.2196/53421 UR - http://www.ncbi.nlm.nih.gov/pubmed/38640472 ID - info:doi/10.2196/53421 ER - TY - JOUR AU - Gandhi, Sumeet AU - Morillo, A. Carlos AU - Schwalm, Jon-David PY - 2018/11/05 TI - Implantable Cardioverter Defibrillator mHealth App for Physician Referrals and eHealth Education: ICD-TEACH Pilot Study JO - JMIR Cardio SP - e10499 VL - 2 IS - 2 KW - mHealth KW - smartphone app KW - implantable defibrillator cardioverter KW - ICD KW - physician decision KW - eHealth KW - mobile phone N2 - Background: Mobile health (mHealth) decision tools for implantable cardioverter defibrillator may increase physician knowledge and overall patient care. Objective: The goals of the ICD-TEACH pilot study were to design a smartphone app or mHealth technology with a novel physician decision support algorithm, implement a direct referral mechanism for device implantation from the app, and assess its overall usability and feasibility with physicians involved in the care of patients with an implantable cardioverter defibrillator. Methods: The initial design and development of the mHealth or smartphone app included strategic collaboration from an information technology company and key stakeholders including arrhythmia specialists (electrophysiologists), general cardiologists, and key members of the hospital administrative team. A convenience sampling method was used to recruit general internists or cardiologists that refer to our local tertiary care center. Physicians were asked to incorporate the mHealth app in daily clinical practice and avail the decision support algorithm and direct referral feature to the arrhythmia clinic. Feasibility assessment, in the form of a physician survey, was conducted after initial mHealth app use (within 3 months) addressing the physicians? overall satisfaction with the app, compliance, and reason for noncompliance; usability assessment of the mHealth app was addressed in the physician survey for technical or hardware problems encountered while using the app and suggestions on improvement. Results: A total of 17 physicians agreed to participate in the pilot study with 100% poststudy survey response rate. Physicians worked in an academic practice, which included both inpatient and ambulatory care. System Usability Scale was applied with an average score of 77 including the 17 participants (>68 points is above average). Regarding the novel physician decision support algorithm for implantable cardioverter defibrillator referral, 11% (1/9) strongly agreed and 78% (7/9) agreed that the algorithm for device eligibility was easy to use. Only 1 patient was referred through the direct referral system via the mHealth app during the pilot study of 3 months. Feasibility assessment showed that 46% (5/11) strongly agreed and 55% (6/11) agreed that the mHealth app would be utilized if integrated into an electronic medical record (EMR) where data are automatically sent to the referring arrhythmia clinic. Conclusions: The ICD-TEACH pilot study revealed high usability features of a physician decision support algorithm; however, we received only 1 direct referral through our app despite supportive feedback. A specific reason from our physician survey included the lack of integration into an EMR. Future studies should continue to systematically evaluate smartphone apps in cardiology to assess usability, feasibility, and strategies to integrate into daily workflow. UR - http://cardio.jmir.org/2018/2/e10499/ UR - http://dx.doi.org/10.2196/10499 UR - http://www.ncbi.nlm.nih.gov/pubmed/31758779 ID - info:doi/10.2196/10499 ER -