Michelle R Rauzi, Rachael B Akay, Swapna Balakrishnan, Christi Piper, Denise Gobert, Alicia Flach
{"title":"Current State of Connected Sensor Technologies Used During Rehabilitation Care: Protocol for a Scoping Review.","authors":"Michelle R Rauzi, Rachael B Akay, Swapna Balakrishnan, Christi Piper, Denise Gobert, Alicia Flach","doi":"10.2196/60496","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Connected sensor technologies can capture raw data and analyze them using advanced statistical methods such as machine learning or artificial intelligence to generate interpretable behavioral or physiological outcomes. Previous research conducted on connected sensor technologies has focused on design, development, and validation. Published review studies have either summarized general technological solutions to address specific behaviors such as physical activity or focused on remote monitoring solutions in specific patient populations.</p><p><strong>Objective: </strong>This study aimed to map research that focused on using connected sensor technologies to augment rehabilitation services by informing care decisions.</p><p><strong>Methods: </strong>The Population, Concept, and Context framework will be used to define inclusion criteria. Relevant articles published between 2008 to the present will be included if (1) the study enrolled adults (population), (2) the intervention used at least one connected sensor technology and involved data transfer to a clinician so that the data could be used to inform the intervention (concept), and (3) the intervention was within the scope of rehabilitation (context). An initial search strategy will be built in Embase; peer reviewed; and then translated to Ovid MEDLINE ALL, Web of Science Core Collection, and CINAHL. Duplicates will be removed prior to screening articles for inclusion. Two independent reviewers will screen articles in 2 stages: title/abstract and full text. Discrepancies will be resolved through group discussion. Data from eligible articles relevant to population, concept, and context will be extracted. Descriptive statistics will be used to report findings, and relevant outcomes will include the type and frequency of connected sensor used and method of data sharing. Additional details will be narratively summarized and displayed in tables and figures. Key partners will review results to enhance interpretation and trustworthiness.</p><p><strong>Results: </strong>We conducted initial searches to refine the search strategy in February 2024. The results of this scoping review are expected in October 2024.</p><p><strong>Conclusions: </strong>Results from the scoping review will identify critical areas of inquiry to advance the field of technology-augmented rehabilitation. Results will also support the development of a longitudinal model to support long-term health outcomes.</p><p><strong>Trial registration: </strong>Open Science Framework jys53; https://osf.io/jys53.</p><p><strong>International registered report identifier (irrid): </strong>DERR1-10.2196/60496.</p>","PeriodicalId":14755,"journal":{"name":"JMIR Research Protocols","volume":"13 ","pages":"e60496"},"PeriodicalIF":1.4000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11544342/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JMIR Research Protocols","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2196/60496","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Connected sensor technologies can capture raw data and analyze them using advanced statistical methods such as machine learning or artificial intelligence to generate interpretable behavioral or physiological outcomes. Previous research conducted on connected sensor technologies has focused on design, development, and validation. Published review studies have either summarized general technological solutions to address specific behaviors such as physical activity or focused on remote monitoring solutions in specific patient populations.
Objective: This study aimed to map research that focused on using connected sensor technologies to augment rehabilitation services by informing care decisions.
Methods: The Population, Concept, and Context framework will be used to define inclusion criteria. Relevant articles published between 2008 to the present will be included if (1) the study enrolled adults (population), (2) the intervention used at least one connected sensor technology and involved data transfer to a clinician so that the data could be used to inform the intervention (concept), and (3) the intervention was within the scope of rehabilitation (context). An initial search strategy will be built in Embase; peer reviewed; and then translated to Ovid MEDLINE ALL, Web of Science Core Collection, and CINAHL. Duplicates will be removed prior to screening articles for inclusion. Two independent reviewers will screen articles in 2 stages: title/abstract and full text. Discrepancies will be resolved through group discussion. Data from eligible articles relevant to population, concept, and context will be extracted. Descriptive statistics will be used to report findings, and relevant outcomes will include the type and frequency of connected sensor used and method of data sharing. Additional details will be narratively summarized and displayed in tables and figures. Key partners will review results to enhance interpretation and trustworthiness.
Results: We conducted initial searches to refine the search strategy in February 2024. The results of this scoping review are expected in October 2024.
Conclusions: Results from the scoping review will identify critical areas of inquiry to advance the field of technology-augmented rehabilitation. Results will also support the development of a longitudinal model to support long-term health outcomes.
Trial registration: Open Science Framework jys53; https://osf.io/jys53.
International registered report identifier (irrid): DERR1-10.2196/60496.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
