Characterizing COVID-19 and Influenza Illnesses in the Real World via Person-Generated Health Data

Abstract

Characterizing COVID-19 and Influenza Illnesses in the Real World via Person-Generated Health Data Highlights d We use data from smartphones and wearables from~7,000 people to compare flu and COVID-19 d While symptoms have some overlap, patients report longer COVID-19 illnesses than flu d Elevated resting heart rate measures are more frequent around illness symptoms onset d It is important to consider flu as a confounder in COVID-19 real-world studies

Dear Watch, Should I Get a COVID-19 Test? Designing deployable machine learning for wearables

“…Account for ILI cases when building a COVID-19 detector It is essential that studies account for ILI cases when building COVID-19 wearable detectors [53]. When applying machine learning models to aid in the detection of emergent diseases we must use training data which are representative of data in a deployment scenario.…”

“…The characteristics of this dataset are described in greater detail in the following sections. For details on the collection of data, we refer the reader to our previous work [53].…”

Synthetic data in machine learning for medicine and healthcare

“…However, the wider roles of synthetic data in AI systems in healthcare remain unclear. Unlike traditional medical devices, the function of AI-SaMDs may need to be adaptive to data streams that evolve over time, as is the case for health data from smartphone sensors 36,37 . Researchers may be tempted to use synthetic data as a stopgap for the fine-tuning of algorithms; however, policymakers may find it troubling that there are not always clinical-quality measures and evaluation metrics for synthetic data.…”

The hopes and hazards of using personal health technologies in the diagnosis and prognosis of infections

“…Researchers have also looked at identifying the need for hos pitalisation looking at symp toms alone, 24 how elevations in peripheral temperature correlate with self-reported fever, 22 and how symptoms and physiological changes are more severe for COVID-19 positive individuals than for influenza positive individuals. 26 As new metrics are added to sensors, substantially greater research is needed to better understand wearable changes for different infections, asymptomatic infections, non-infectious insults, and tracking long-term consequences, such as with post-acute sequelae of SARS-CoV-2 infection. Identifying early signs of decompensation can be especially useful for early initiation of antivirals, monoclonal antibodies, supportive care, and closer individual monitoring.…”