Raza Marium M, Venkatesh Kaushik P, Kvedar Joseph C
Harvard Medical School, Boston, MA, USA.
NPJ Digit Med. 2022 Oct 13;5(1):153. doi: 10.1038/s41746-022-00701-x.
The importance of infection risk prediction as a key public health measure has only been underscored by the COVID-19 pandemic. In a recent study, researchers use machine learning to develop an algorithm that predicts the risk of COVID-19 infection, by combining biometric data from wearable devices like Fitbit, with electronic symptom surveys. In doing so, they aim to increase the efficiency of test allocation when tracking disease spread in resource-limited settings. But the implications of technology that applies data from wearables stretch far beyond infection monitoring into healthcare delivery and research. The adoption and implementation of this type of technology will depend on regulation, impact on patient outcomes, and cost savings.
作为一项关键的公共卫生措施，感染风险预测的重要性在新冠疫情期间得到了进一步凸显。在最近的一项研究中，研究人员利用机器学习开发了一种算法，通过将来自Fitbit等可穿戴设备的生物识别数据与电子症状调查相结合，来预测新冠病毒感染风险。他们这样做的目的是在资源有限的环境中追踪疾病传播时提高检测分配的效率。但是，应用可穿戴设备数据的技术所产生的影响远远超出了感染监测，延伸到了医疗服务和研究领域。这类技术的采用和实施将取决于监管、对患者治疗结果的影响以及成本节约情况。
