The KITE Research Institute, Toronto Rehabilitation Institute, University Health Network, Toronto, Ontario, Canada.
Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada.
J Healthc Eng. 2023 Jan 31;2023:4258362. doi: 10.1155/2023/4258362. eCollection 2023.
Hand hygiene is one of the most effective ways to prevent infection transmission. However, current electronic monitoring systems are not able to identify adherence to all hand hygiene (HH) guidelines. Location information can play a major role in enhancing HH monitoring resolution. This paper proposes a BLE-based solution to localize healthcare workers inside the patient room. Localization accuracy was evaluated using one to four beacons in a binary (entrance/proximal patient zone) or multiclass (entrance/sink/right side of the bed/left side of the bed) proximity-based positioning problem. Dynamic fingerprints were collected from nine different subjects performing 30 common nursing activities. Extremely randomized trees algorithm achieved the best accuracies of 81% and 71% in the binary and multiclass classifications, respectively. The proposed method can be further used as a proxy for caregiving activity recognition to improve the risk of infection transmission in healthcare settings.
手卫生是预防感染传播最有效的方法之一。然而，当前的电子监测系统无法识别所有手卫生（HH）指南的遵守情况。位置信息可以在提高 HH 监测分辨率方面发挥重要作用。本文提出了一种基于 BLE 的解决方案，用于在患者房间内定位医疗保健工作者。使用一个或四个信标在二进制（入口/靠近患者区）或多类（入口/水槽/病床右侧/病床左侧）基于接近度的定位问题中评估了定位精度。从执行 30 种常见护理活动的九名不同受试者收集了动态指纹。极端随机树算法在二进制和多类分类中分别达到了 81%和 71%的最佳精度。该方法可以进一步用作护理活动识别的代理，以降低医疗机构中感染传播的风险。
