College of Nursing, Washington State University - Vancouver Vancouver, WA.
School of Nursing & Midwifery, Edith Cowan University, Joondalup Campus, Perth, Australia.
Nurs Outlook. 2019 Mar-Apr;67(2):140-153. doi: 10.1016/j.outlook.2018.11.004. Epub 2018 Nov 23.
To offer practical guidance to nurse investigators interested in multidisciplinary research that includes assisting in the development of artificial intelligence (AI) algorithms for "smart" health management and aging-in-place.
Ten health-assistive Smart Homes were deployed to chronically ill older adults from 2015 to 2018. Data were collected using five sensor types (infrared motion, contact, light, temperature, and humidity). Nurses used telehealth and home visitation to collect health data and provide ground truth annotation for training intelligent algorithms using raw sensor data containing health events.
Nurses assisting with the development of health-assistive AI may encounter unique challenges and opportunities. We recommend: (a) using a practical and consistent method for collecting field data, (b) using nurse-driven measures for data analytics, (c) multidisciplinary communication occur on an engineering-preferred platform.
Practical frameworks to guide nurse investigators integrating clinical data with sensor data for training machine learning algorithms may build capacity for nurses to make significant contributions to developing AI for health-assistive Smart Homes.
为有兴趣进行多学科研究的护士研究人员提供实用指导，包括协助开发用于“智能”健康管理和就地老龄化的人工智能 (AI) 算法。
2015 年至 2018 年，10 个健康辅助智能家居部署给慢性疾病的老年人。使用五种传感器类型（红外运动、接触、光线、温度和湿度）收集数据。护士使用远程医疗和家访收集健康数据，并使用原始传感器数据提供健康事件的真实注释，以训练智能算法。
协助开发健康辅助 AI 的护士可能会遇到独特的挑战和机会。我们建议：(a) 使用实用且一致的方法来收集现场数据，(b) 使用护士驱动的措施进行数据分析，(c) 多学科沟通在工程首选平台上进行。
指导护士研究人员将临床数据与传感器数据集成以训练机器学习算法的实用框架，可以为护士建立能力，为健康辅助智能家居开发 AI 做出重大贡献。
