首页|University of British Columbia Reports Findings in Telemedicine (Improving Triag e Accuracy in Prehospital Emergency Telemedicine: Scoping Review of Machine Lear ning-Enhanced Approaches)
University of British Columbia Reports Findings in Telemedicine (Improving Triag e Accuracy in Prehospital Emergency Telemedicine: Scoping Review of Machine Lear ning-Enhanced Approaches)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Telemedicine is the su bject of a report. According to news originating from Vancouver, Canada, by News Rx correspondents, research stated, “Prehospital telemedicine triage systems com bined with machine learning (ML) methods have the potential to improve triage ac curacy and safely redirect low-acuity patients from attending the emergency depa rtment. However, research in prehospital settings is limited but needed; emergen cy department overcrowding and adverse patient outcomes are increasingly common. ” Our news journalists obtained a quote from the research from the University of B ritish Columbia, “In this scoping review, we sought to characterize the existing methods for ML-enhanced telemedicine emergency triage. In order to support futu re research, we aimed to delineate what data sources, predictors,labels, ML mod els, and performance metrics were used, and in which telemedicine triage systems these methods were applied. A scoping review was conducted, querying multiple d atabases (MEDLINE, PubMed, Scopus, and IEEE Xplore) through February 24, 2023, t o identify potential ML-enhanced methods, and for those eligible, relevant study characteristics were extracted, including prehospital triage setting, types of predictors, ground truth labeling method, ML models used, and performance metric s. Inclusion criteria were restricted to the triage of emergency telemedicine se rvices using ML methods on an undifferentiated (disease nonspecific) population. Only primary research studies in English were considered. Furthermore, only tho se studies using data collected remotely (as opposed to derived from physical as sessments) were included. In order to limit bias, we exclusively included articl es identified through our predefined search criteria and had 3 researchers (DR, JS, and KS) independently screen the resulting studies. We conducted a narrative synthesis of findings to establish a knowledge base in this domain and identify potential gaps to be addressed in forthcoming ML-enhanced methods. A total of 1 65 unique records were screened for eligibility and 15 were included in the revi ew. Most studies applied ML methods during emergency medical dispatch (7/15, 47% ) or used chatbot applications (5/15, 33%). Patient demographics an d health status variables were the most common predictors, with a notable absenc e of social variables. Frequently used ML models included support vector machine s and tree-based methods. ML-enhanced models typically outperformed conventional triage algorithms, and we found a wide range of methods used to establish groun d truth labels. This scoping review observed heterogeneity in dataset size, pred ictors, clinical setting (triage process), and reported performance metrics. Sta ndard structured predictors, including age, sex, and comorbidities, across artic les suggest the importance of these inputs; however, there was a notable absence of other potentially useful data, including medications, social variables, and health system exposure. Ground truth labeling practices should be reported in a standard fashion as the true model performance hinges on these labels.”
VancouverCanadaNorth and Central Ame ricaCyborgsEmerging TechnologiesHealth and MedicineMachine LearningTel emedicine
NETL
NSTL
