Abstract 9842: Machine Learning-Based Prediction Model of COVID-19 Deterioration Using Wearable Core Temperature and Oxygen Saturation Sensor Data

Abstract

Background: Accurate prediction of COVID-19 deterioration could enable clinicians to make optimal decisions on medical interventions or hospitalization. A machine learning-based approach using vital data is recognized as a useful tool to predict the exacerbation of infectious disease. However, in COVID-19, effective prediction models are still emerging. Here we developed an algorithm to predict clinical deterioration in non-severe COVID-19 patients using machine learning techniques with continuous core temperature (CT), SpO 2 and pulse rate (PR) data obtained via wearable sensors. Methods: Fifty mild to moderate COVID-19 patients admitted to Nishi-Kobe Medical Center between December 2020 and August 2021 were enrolled. Disease severity was judged by WHO criteria. All patients wore a Moni-Patch ®️ , a wireless CT monitoring patch and a ring-type SpO 2 monitoring device. CT, SpO 2 and PR were continuously collected to a smartphone via Bluetooth ®️ . Data from 41 patients were of sufficient duration and quality to be analyzed and preprocessed to adjust sampling windows before fed into the framework. Additional features were derived by modifying the sensor data using patients’ characteristics. To develop classifiers to distinguish a disease deteriorating into severe one, XGBoost, a gradient-boosted tree algorithm, with 3-fold cross-validation was used. Based on the algorithm, deterioration into severe disease within 24 hour was inferred every single hour using 12-hour time frame data. The area under the curve (AUC) of receiver operating characteristics was analyzed based on the classifier’s prediction threshold. Results: After the enrollment, 13 out of 41 patients developed severe diseases. At the enrollment, baseline characteristics were comparable between mild to moderate and severe disease, except for body temperature that was significantly higher in severe disease. The algorithm developed using the sensor data was able to achieve an AUC of 0.92. Conclusions: Our algorithm could well distinguished COVID-19 deteriorating into severe disease. The results indicates that machine learning approach with continuous CT, SpO 2 and PR measurement using wearable sensors is beneficial to predict the exacerbation of COVID-19.