Passive detection of COVID-19 with wearable sensors and explainable machine learning algorithms

Abstract

Individual smartwatch or fitness band sensor data in the setting of COVID-19 has shown promise to identify symptomatic and pre-symptomatic infection or the need for hospitalization, correlations between peripheral temperature and self-reported fever, and an association between changes in heart-rate-variability and infection. In our study, a total of 38,911 individuals (61% female, 15% over 65) have been enrolled between March 25, 2020 and April 3, 2021, with 1118 reported testing positive and 7032 negative for COVID-19 by nasopharyngeal PCR swab test. We propose an explainable gradient boosting prediction model based on decision trees for the detection of COVID-19 infection that can adapt to the absence of self-reported symptoms and to the available sensor data, and that can explain the importance of each feature and the post-test-behavior for the individuals. We tested it in a cohort of symptomatic individuals who exhibited an AUC of 0.83 [0.81–0.85], or AUC = 0.78 [0.75–0.80] when considering only data before the test date, outperforming state-of-the-art algorithm in these conditions. The analysis of all individuals (including asymptomatic and pre-symptomatic) when self-reported symptoms were excluded provided an AUC of 0.78 [0.76–0.79], or AUC of 0.70 [0.69–0.72] when considering only data before the test date. Extending the use of predictive algorithms for detection of COVID-19 infection based only on passively monitored data from any device, we showed that it is possible to scale up this platform and apply the algorithm in other settings where self-reported symptoms can not be collected.

A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19

“…For the FHF cohort, the logistic regression model resulted in an AUC-ROC of 0.73±0.12 and AUC-PR of 0.55±0.21 on the crossvalidated training set, and AUC-ROC of 0.77 and AUC-PR of 0.24 on the test set (Fig 4). The AUC-ROC from the models were similar to those reported in recent similar studies [26], [32], [35].…”

Nanomaterials‐based sensors for the detection of COVID‐19: A review

“… 142 To combat any challenges posed during sensing and therapies, artificial intelligence (AI) and internet of medical things integrated sensors (IoMT) can prove to be very beneficial to detect SARS‐CoV‐2 and to study the individual data and compare with a more extensive profile for a better and intelligent healthcare management system. 131 , 143 AI has proven helpful in analysis of medical imaging modalities such as ultrasound, X‐ray, and computed tomography. The rapid analysis powered by AI has helped in early diagnosis of the disease and has been reviewed in detail.…”

Data-Driven Analytics Leveraging Artificial Intelligence in the Era of COVID-19: An Insightful Review of Recent Developments

“…Data reported in Figure 10 can be collected from a variety of devices, apps, and search engines, to name a few. IoT data can be collected from wearable sensors [65], contents, and other related data can be gathered from e-commerce websites [66], mobile data can be gathered from mobile carriers/service-providers, social media data can be collected from SN service providers [67], historical data can be gathered from the hospitals websites/repositories [68], medical images and sounds data can be collected with wearable devices or automated machines, and demographics data can be obtained from trusted clinics/hospitals [69]. The logistic regression based models can assist in identifying hotspots in any territory based on the certain environment parameters and underlying conditions [70].…”