JMIR Research Protocols最新文献

{"title":"Enhancing Patient Support in Digital Inflammatory Bowel Disease Tools: The Need for Medication Guidance and Decision Support.","authors":"Ali Sidat, Sian Uppal","doi":"10.2196/82238","DOIUrl":"10.2196/82238","url":null,"abstract":"","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e82238"},"PeriodicalIF":1.5,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468898/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145175591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Technology-Enhanced Medical Nutrition Therapy and Diabetes Self-Management Education for Adults With Disability and Type 2 Diabetes: Protocol for a Pilot and Feasibility Randomized Controlled Trial.","authors":"Anita Aboagye, Jessica Peckham, Kristine Ria Hearld, Shireen Abdullah, Mohanraj Thirumalai","doi":"10.2196/71495","DOIUrl":"10.2196/71495","url":null,"abstract":"<p><strong>Background: </strong>Diabetes mellitus (DM) is a serious chronic disorder that affects many individuals globally, particularly persons with disabilities, and has long-term adverse effects on the health of individuals and society. Effective self-management education is therefore required. Diabetes management focused on medical nutrition therapy (MNT) and diabetes self-management education (DSME) combined with telehealth technology has the potential to increase the active performance of diabetes management behaviors among persons with disabilities and improve their overall quality of life and quality of self-care.</p><p><strong>Objective: </strong>This study aims to evaluate the impact of different levels of technology on the delivery of MNT and DSME among persons with disabilities.</p><p><strong>Methods: </strong>The study is a single-blinded, 3-arm, randomized controlled trial among adults living with both type 2 diabetes and a permanent physical disability. Web-based recruitment is done through partner organizations. The target sample size is 90 participants randomized into 3 arms: a high-technology, a low-technology, and an attention control arm. The high-technology arm receives diabetes-related materials weekly through mediums such as email, a telehealth platform, and text; the low-technology arm receives only 1 weekly email with diabetes-related material; and the attention control arm has no technology support. The intervention is provided by a certified diabetes care and education specialist. Using multivariate linear mixed models, the study examines the relationships between the level of technology intervention and DM self-management behaviors, self-efficacy, and reductions in glycated hemoglobin (HbA<sub>1c</sub>). The primary outcome is the proportion of participants in each group with improved self-management behaviors, as measured by several validated questionnaires. The secondary outcome is a better HbA<sub>1c</sub> reduction. Outcomes are measured at baseline and at 6 months. Questionnaires and HbA<sub>1c</sub> measures will be used to measure outcomes.</p><p><strong>Results: </strong>Data collection began in June 2024 with a total of 90 recruited participants. The intervention was delivered. Make-up classes were delivered to participants in any of the 3 cohorts between November 2024 and December 2024. The final 3-month follow-up classes were held for each cohort 3 months after the first class. Data analysis is anticipated to be completed in fall 2025.</p><p><strong>Conclusions: </strong>Effective self-management in DM is important to reduce complications. Using technology to deliver MNT and DSME could serve as an effective and convenient strategy for providing these interventions. However, intervention studies are required to determine the most effective level of technology for delivering MNT and DSME intervention to this target group. The YumABLE study is expected to provide new, meaningful, and detailed information about","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e71495"},"PeriodicalIF":1.5,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12514415/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145149158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Authors' Reply: Enhancing Patient Support in Digital Inflammatory Bowel Disease Tools: The Need for Medication Guidance and Decision Support.","authors":"Kaitlyn Chappell, Karen Wong","doi":"10.2196/83160","DOIUrl":"10.2196/83160","url":null,"abstract":"","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e83160"},"PeriodicalIF":1.5,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468900/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145175594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Gamification of Incentive Spirometry in Trauma Patients: Protocol for a Prospective, Observational Feasibility Study.","authors":"Areen Al-Dhoon, Arthur Grimes, Carma Goldstein, Peter Spronk, R Shayn Martin, Aarti Sarwal","doi":"10.2196/83839","DOIUrl":"10.2196/83839","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.2196/75871.].</p>","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e83839"},"PeriodicalIF":1.5,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12514406/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145175601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validation of an Infarction Code Care Checklist and Determination of its Relationship With Other Patient Safety Indicators: Protocol for a Prospective Study.","authors":"Encarna Sanchez Freire, Josep Vidal-Alaball, Aïna Fuster-Casanovas, Queralt Miró Catalina, Joan Cartanyà Bonvehí, Josep Lluis Garcia-Domingo","doi":"10.2196/66584","DOIUrl":"10.2196/66584","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;In the care of time-dependent illnesses, facilitating care and systematizing actions with a checklist provides security to health professionals and reduces errors, thereby increasing patient safety. However, despite the widespread use of checklists in other clinical contexts, no studies have yet validated a checklist specifically for infarction code care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The objective of this study is to validate the checklist and determine its relationship with the rest of the patient safety indicators in the primary care teams of the Catalan Health Institute of Central Catalonia.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This is a prospective study for the validation of a checklist for infarction code care. In this study, 2 clinical scenarios of varying difficulty are defined, and the correct answers are established in each case according to the gold standard guidelines. During the first 3 months of the ongoing year, we held an annual training meeting where infarction code referents from various primary care teams gathered to review the new guidelines and outline the training strategy for the next year. These referents conducted annual training sessions for their respective teams before Easter, during which they explained the new guidelines. On the same day as the training, the 2 clinical scenarios were completed using the online version of the checklist for the first time for all participants. The checklist was sent in digital format to all health professionals who responded the first time, and then a reminder was sent to respond a second time at 30, 45, and 90 days to obtain the maximum number of second responses, as the checklist should be completed twice to assess internal reliability and temporal robustness. The number of hits was compared with respect to the gold standard for both the first and the second response. The results obtained from the responses and accuracies, when compared with the gold standards, were evaluated against other available patient safety indicators in the region.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Between January 2023 and May 2023, we obtained 615 responses to the online version of the checklist. We conducted analyses to assess both internal consistency and temporal robustness of the responses and have also structured the framework for comparing these results with other patient safety indicators available in the region. Data analysis is currently underway, and we expect to publish the results in early 2026.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;If the checklist demonstrates strong internal consistency and temporal robustness and shows a meaningful relationship with patient safety indicators, it could be implemented across primary care centers using the infarction code. This would support safer, more standardized care in time-sensitive clinical situations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Trial registration: &lt;/strong&gt;IDIAP Jordi Gol 4R22/343; https://idiapjgol.org/grup-recerca/prosaaru/projectes/.&lt;/p","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e66584"},"PeriodicalIF":1.5,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12514402/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145175584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Culturally Tailored Digital Education Intervention to Improve Nutrition Among Older Adult Congregate Meal Participants During COVID-19: Protocol for a Stepped-Wedge Cluster Randomized Controlled Trial.","authors":"Vidya Sharma, Michelle Aguilar, Salma Abdelrahman, Erica Sosa, Meizi He, M Marilu Martinez, Andrea Hutson, Tianou Zhang, Zenong Yin, Sarah Ullevig","doi":"10.2196/65976","DOIUrl":"10.2196/65976","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Inadequate nutrition and a lack of physical activity contribute to functional decline and complications from chronic diseases in older adults. The pandemic halted or altered necessary Older Americans Act (OAA) nutrition services provided to vulnerable, community-dwelling older adults in San Antonio, Texas. The \"digital divide\" or gap in technological access and knowledge further heightened the detrimental effect of the COVID-19 pandemic on older adults who may be \"digitally excluded\" from social, economic, and health-related interactions. During the pandemic, San Antonio congregate meal sites funded by OAA remained partially open biweekly to distribute meals but no longer offered in-person nutrition education, physical activity classes, and social activities. This project expands the current congregate meal programming infrastructure and partnerships with Older Adults Technology Services (OATS) to create a sustainable approach focused on improving the health of older adults.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The study aims (1) to test the impact of a digital nutrition education intervention on the primary outcomes of food security and diet quality; (2) to determine the effect of the intervention on secondary outcomes of technology knowledge and usage, physical activity, and social isolation and loneliness; and (3) to examine the long-term impact and sustainability of technology use on food security, diet quality, physical activity, social isolation, and loneliness.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This proposed digital nutrition education intervention study targets technologically limited older adults enrolled in the congregate meal program (CMP) using a stepped-wedge clustered randomized controlled trial. Key community partners, City of San Antonio Department of Health Services Senior Services Division and OATS, contributed to the study's planning phase, research design, and implementation. The 20-week intervention included 5 weeks of in-person technology training, including internet access and technical support for 1 year and devices, followed by 15 weeks of a culturally tailored online nutrition education intervention. The study randomized 398 older adults from 12 congregate meal sites. Data collection took place at baseline, 3 months, 6 months, 9 months, 12 months, and 18 months. If successful, the impact of this program could be applied throughout the national OATS network and to similar CMPs to bridge the digital divide beyond the COVID-19 pandemic.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Recruitment and enrollment of 398 older adults at 12 CMPs was completed in December 2022. Study CMPs were randomly assigned to Cohort 1 and 2: 164 completed Cohort 1 in August 2023 and 111 completed Cohort 2 in April 2024. Eighteen-month data collection is ongoing.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study aims to determine the impact of a digital nutrition intervention on older adults' nutrition status, physical activity, lonel","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e65976"},"PeriodicalIF":1.5,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463344/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145149230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying Factors Associated With HIV Viral Suppression and Health Care Outcomes in the Florida Cohort Study Wave 3: Protocol for a Prospective Cohort Study.","authors":"Rebecca J Fisk-Hoffman, Christina E Parisi, Nanyangwe Siuluta, Preeti Manavalan, Lori A Bilello, Colby Cohen, Jessy Devieux, Gladys Ibanez, Jennifer Kuretski, Charurut Somboonwit, Maya Widmeyer, Zhi Zhou, Robert L Cook","doi":"10.2196/69702","DOIUrl":"10.2196/69702","url":null,"abstract":"<p><strong>Background: </strong>Ending the HIV epidemic remains a high public health priority, and the state of Florida continues to have high HIV prevalence and incidence.</p><p><strong>Objective: </strong>This protocol aims to identify factors associated with the HIV care continuum and HIV-related comorbidities, with a focus on the impacts of alcohol use.</p><p><strong>Methods: </strong>The Florida Cohort study wave 3 enrolled people with HIV aged 18 years or older from 9 clinical, case management, and community settings across Florida from 2020 to 2023. All participants completed a baseline questionnaire, and most (769/836, 92%) completed additional questionnaires at baseline and/or approximately 1 year after baseline. Data on HIV care and treatment, mental health, substance use, stigma, and technology were collected in the baseline questionnaire. Additional questionnaires covered alcohol use, gender identity, pet ownership, stigma and discrimination, antiretroviral therapy preferences, and the impacts of the COVID-19 pandemic. Questionnaire data were securely linked to HIV care continuum variables from Florida's state HIV monitoring system.</p><p><strong>Results: </strong>Overall, the study enrolled 836 people with HIV. Among them, 397 (47.5%) were non-Hispanic Black, 131 (15.7%) were Hispanic, 505 (60.4%) were assigned male sex at birth, and 487 (58.3%) were aged above 50 years. Most (n=769, 92%) participants were linked to the state HIV reporting system and will be followed for up to 5 years to monitor HIV outcomes. A total of 31 (94% of 33 eligible) participants completed the gender identity questionnaire, 230 (91.3% of 252 eligible) completed the alcohol questionnaire, 287 (91.7% of 313 eligible) completed the COVID-19 questionnaire, 221 (85% of 260 eligible) completed the pet questionnaire, 461 (87.6% of 526 eligible) completed the stigma and discrimination questionnaire, and 210 (85.7% of 245 eligible) completed the antiretroviral therapy preference questionnaire.</p><p><strong>Conclusions: </strong>This study provides opportunities to monitor changes in HIV-related outcomes as well as relevant attitudes, behaviors, and health care preferences; however, it has some limitations in terms of representativeness and tracking longitudinal outcomes.</p><p><strong>International registered report identifier (irrid): </strong>DERR1-10.2196/69702.</p>","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e69702"},"PeriodicalIF":1.5,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12511819/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145149216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying and Reducing Stigmatizing Language in Home Health Care With a Natural Language Processing-Based System (ENGAGE): Protocol for a Mixed Methods Study.","authors":"Zhihong Zhang, Pallavi Gupta, Stephanie Potts-Thompson, Laura Prescott, Morgan Morrison, Scott Sittig, Margaret V McDonald, Chase Raymond, Jacquelyn Y Taylor, Maxim Topaz","doi":"10.2196/69753","DOIUrl":"10.2196/69753","url":null,"abstract":"<p><strong>Background: </strong>Stigmatizing language is common in clinical notes and can adversely affect the quality of patient care. Natural language processing (NLP) is a promising technology for identifying such language across large volumes of clinical notes in electronic health records.</p><p><strong>Objective: </strong>This study proposes an NLP-driven reduce stigmatizing language (ENGAGE) system to automatically identify and replace stigmatizing language.</p><p><strong>Methods: </strong>Using a mixed methods study, we will extract electronic health record data for patients admitted to 2 large, diverse home health care (HHC) organizations between January 2019 and December 2021. We propose the following 4 aims: aim 1 is to refine the ontology of stigmatizing language in HHC by (1) interviewing a diverse sample of HHC nurses and patients to identify terms to avoid and (2) analyzing clinical notes from various regions in the United States to categorize stigmatizing language. Aim 2 is to determine the best NLP approach for accurately identifying stigmatizing language by training algorithms and comparing their performance to human annotations. Aim 3 is to analyze the prevalence of stigmatizing language based on patients' race and ethnicity using adjusted statistical analyses of a sample of approximately half a million HHC patients (34% racial and ethnic minority groups). Aim 4 is to develop the NLP-driven ENGAGE system by (1) testing NLP methods (rule based; \"delete, retrieve, and generate\"; and transformers) for suggesting alternative wording and (2) designing and refining the user interface for clinical trial preparation.</p><p><strong>Results: </strong>We received funding from the National Institute on Minority Health and Health Disparities in September 2023. Recruitment began in May 2024, and as of March 2025, interviews have been completed for 9 enrolled participants. We anticipate completing all study aims by April 2027.</p><p><strong>Conclusions: </strong>This study will leverage extensive data sources to examine stigmatizing language in HHC settings and contribute to the development of systems aimed at effectively reducing the use of such language among HHC nurses.</p><p><strong>International registered report identifier (irrid): </strong>DERR1-10.2196/69753.</p>","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e69753"},"PeriodicalIF":1.5,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12511817/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145149214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation and Effectiveness of the Power Over Pain Portal for Patients Awaiting a Tertiary Care Consultation for Chronic Pain: Protocol for a Pilot, Prospective, Cohort, Mixed Methods Study.","authors":"Amin Zahrai, Etienne J Bisson, Yaadwinder Shergill, Danielle Rice, Natalie Zur Nedden, Lynn Cooper, Daniel James, Josh A Rash, Rachael Bosma, Tim Ramsay, Patricia Poulin","doi":"10.2196/64801","DOIUrl":"10.2196/64801","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Chronic pain (CP) affects approximately 8 million people in Canada. Access to CP care is challenging, and there is no robust monitoring system to support patient care and decision-making. The Power Over Pain (POP) Portal was developed by people living with CP, health care providers, researchers, health system decision-makers, policymakers, and community partners to address these concerns. The POP Portal is a comprehensive web-based platform that provides rapid access to a continuum of free, evidence-informed resources for the self-management of CP, mental health, and substance use health. The POP Portal also offers self-assessment tools that enable users to track their progress and receive personalized recommendations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This hybrid implementation-effectiveness type III pilot study aimed to determine the feasibility (ie, recruitment, integration, facilitators and barriers, patient engagement, usability, and acceptability) of the POP Portal's implementation for people waiting for care at a tertiary pain clinic.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A cohort of 80 adults living with pain was recruited from the waitlist of a tertiary care pain clinic over a 3-month period. Following an orientation on the POP Portal, participants were encouraged to use it according to their needs and preferences. They were also asked to complete questionnaires at baseline (0 months) and the 3-month follow-up. Primary feasibility measures included recruitment and retention rates and portal acceptability using the Acceptability E-scale. We also measured usability using the System Usability Scale, evaluated engagement through portal analytics, and identified facilitators and barriers via semistructured interviews with 12 to 15 study participants. These interviews further assessed the acceptability and usability of the portal for participants. Exploratory measures included pain severity, pain-related interference, self-efficacy, coping strategies, and symptoms of anxiety and depression.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;We will present descriptive data on the cohort's sex and gender, age, rural or urban status, and ethnic background, as well as the acceptability, usability, and feasibility of the portal. Measures of central tendency will be reported for continuous variables, and frequencies and proportions will be reported for categorical variables. We will also present change in clinical outcomes across time and a synthesis of qualitative and thematic data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;We anticipate that most patients awaiting care at a tertiary pain clinic recruited will use the POP Portal and find it to be acceptable for addressing some of their pain and associated health concerns. If the feasibility of recruiting and retaining patients is demonstrated as anticipated, we will be able to move forward with a multisite study to evaluate the implementation and effectiveness of the POP Portal among patients wai","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e64801"},"PeriodicalIF":1.5,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12511818/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145149167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Performance Evaluation of an Artificial Intelligence-Based Tool for Predicting the Presence of Obstructive Coronary Artery Disease: Protocol for a Cohort Observational Study.","authors":"Georgios Rampidis, Evangelos Logaras, Athanasios Samaras, Emmanouil S Rigas, Ilias Kyparissidis-Kokkinidis, Styliana Siakopoulou, Panagiotis-Emmanouil Kartsidis, Konstantinos Kouskouras, George Giannakoulas, Panagiotis Bamidis, Antonios Billis","doi":"10.2196/67697","DOIUrl":"10.2196/67697","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;A significant number of individuals undergoing coronary computed tomography angiography (CCTA) for suspected (CAD) have nonobstructive or no CAD. There is a need for clinically proven models that can predict the pretest probability of stable CAD and help to identify low-risk individuals. Optimizing patient stratification is of paramount importance to improve diagnostic yield and cost-effectiveness.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;We aimed to determine whether each patient needs to undergo CCTA because of suspected CAD. The main objective of this study is to evaluate the clinical performance of an artificial intelligence (AI)-based tool in predicting significant coronary artery stenosis (&gt;50%), as well as its utility by medical professionals.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Data for this study have been acquired from 750 participants as part of routine clinical practice in AHEPA (American Hellenic Educational Progressive Association) General Hospital of Thessaloniki. The dataset has several features, including demographics (eg, age, gender), medical history (eg, diabetes mellitus, arterial hypertension), and clinical variables (eg, creatinine, epicardial fat volume). At least 2 expert cardiologists and 2 expert radiologists are involved in this study, who provide the ground truth. A trained AI-based model embedded in an easy-to-use and user-friendly web application is implemented in practice. Several AI algorithms are being examined, and the model found to perform best so far is the Optimized Voting model, which is a combination of the best performing iterations of random forest and extreme gradient boosting. The performance metrics that are being used are accuracy, precision, recall, F&lt;sub&gt;1&lt;/sub&gt;-score, area under the receiver operating characteristic curve, and area under the precision-recall curve.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Recruitment for this study began in July 2023. Data collection, development, training, and deployment of the AI web tool were completed by May 2024. In total, data from 500 individuals were collected for training and internal validation, while the best performing model was validated externally in another 250 individuals. For training and internal validation, the dataset was split into 70% for training and 20% for validation and 10% for testing. Currently, the best performing model achieves an accuracy of approximately 82% in successfully predicting stenosis greater than 50%. Additionally, an explainable AI algorithm is used to provide explanations in relation to the decisions made aiming to increase the trust of the clinicians in the tool.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The proposed study represents a novel approach of a web-based AI-driven solution with explainability features for optimizing patient stratification with the goal of improving diagnostic yield and cost-effectiveness of CCTA utilization within the context of cardiology clinical practice.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;International ","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"14 ","pages":"e67697"},"PeriodicalIF":1.5,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12511812/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145137672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}