Intelligent risk prediction in public health using wearable device data

Abstract

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.

Citizen data sovereignty is key to wearables and wellness data reuse for the common good

“…Data from consumer-facing domains in wellness and lifestyle are effectively inseparable from data collected from regulated health and wellness apps, interacting often with the same wearable sensors, and relating to the same physiological recordings and similar patient-generated interactions 4 , 5 . The EHDS proposal acknowledges three fundamental concepts that will be transformational to modern medicine, medical research and medical technology development: (i) health and data on health do not start at the clinic gate and the personal wellness category of health data describes, in intricate detail, the health of individuals; (ii) the center of gravity of health data is shifting continuously away from the clinic perimeter and towards the sofa, the pocket, the wrist and the sensor skin patch of the citizen; and (iii) if acceptable and workable approaches are found to link this data to personal EHR data, much can be learned for the understanding of diseases, developing of new approaches for early prediction and intervention in diseases and for increasing the efficiency of public health and healthcare delivery 3 , 6 , 7 .…”

“…These data, linked to later identified diseases, can be key to the development and advancement of predictive analytics, e.g., based on AI 9 – 11 . Such models are applicable to rare 12 and common diseases, either acute or chronic 3 , 6 , 7 . There is the potential for a virtuous cycle, from large-scale data sharing to large-scale provision of early and personal insights to citizens on risks, lifestyle adaptations to prevent disease, and notifications to indicate when home/clinic-based diagnostic workup is required.…”

Cracking the Code: A Scoping Review to Unite Disciplines in Tackling Legal Issues in Health Artificial Intelligence

“…[3–10] This need is amplified by the current generative AI arms race between behemoth technology companies like Open AI, Microsoft, and Google, and the active integration of these tools into healthcare delivery. [11, 12]…”

“…[3][4][5][6][7][8][9][10] This need is amplified by the current generative AI arms race between behemoth technology companies like Open AI, Microsoft, and Google, and the active integration of these tools into healthcare delivery. [11,12] But what is the pathway to effective law reform? Many agree that effective reforms will require "multidisciplinary, international effort."…”

Circadian rhythm biomarker from wearable device data is related to concurrent antidepressant treatment response

“…Actigraphy data is obtained using a compact, lightweight, and affordable device with long-term data storage capability that only requires wearing a wrist/waist band with minor intervention (periodic charging) 28 . With the growing popularity of wearable technology, the use of actigraphy devices with valid measures of motor activity has become widespread and the data have become easily accessible 30 .…”