Prediction and detection of side effects severity following COVID-19 and influenza vaccinations: utilizing smartwatches and smartphones.

Vaccines stand out as one of the most effective tools in our arsenal for reducing morbidity and mortality. Nonetheless, public hesitancy towards vaccination often stems from concerns about potential side effects, which can vary from person to person. As of now, there are no automated systems available to proactively warn against potential side effects or gauge their severity following vaccination. We have developed machine learning (ML) models designed to predict and detect the severity of post-vaccination side effects. Our study involved 2111 participants who had received at least one dose of either a COVID-19 or influenza vaccine. Each participant was equipped with a Garmin Vivosmart 4 smartwatch and was required to complete a daily self-reported questionnaire regarding local and systemic reactions through a dedicated mobile application. Our XGBoost models yielded an area under the receiver operating characteristic curve (AUROC) of 0.69 and 0.74 in predicting and detecting moderate to severe side effects, respectively. These predictions were primarily based on variables such as vaccine type (influenza vs. COVID-19), the individual's history of side effects from previous vaccines, and specific data collected from the smartwatches prior to vaccine administration, including resting heart rate, heart rate, and heart rate variability. In conclusion, our findings suggest that wearable devices can provide an objective and continuous method for predicting and monitoring moderate to severe vaccine side effects. This technology has the potential to improve clinical trials by automating the classification of vaccine severity.

Early Oxygen Treatment Measurements Can Predict COVID-19 Mortality: A Preliminary Study.

Halting the rapid clinical deterioration, marked by arterial hypoxemia, is among the greatest challenges clinicians face when treating COVID-19 patients in hospitals. While it is clear that oxygen measures and treatment procedures describe a patient's clinical condition at a given time point, the potential predictive strength of the duration and extent of oxygen supplementation methods over the entire course of hospitalization for a patient death from COVID-19 has yet to be assessed. In this study, we aim to develop a prediction model for COVID-19 mortality in hospitals by utilizing data on oxygen supplementation modalities of patients. We analyzed the data of 545 patients hospitalized with COVID-19 complications admitted to Assuta Ashdod Medical Center, Israel, between 7 March 2020, and 16 March 2021. By solely analyzing the daily data on oxygen supplementation modalities in 182 random patients, we could identify that 75% (9 out of 12) of individuals supported by reservoir oxygen masks during the first two days died 3-30 days following hospital admission. By contrast, the mortality rate was 4% (4 out of 98) among those who did not require any oxygenation supplementation. Then, we combined this data with daily blood test results and clinical information of 545 patients to predict COVID-19 mortality. Our Random Forest model yielded an area under the receiver operating characteristic curve (AUC) score on the test set of 82.5%, 81.3%, and 83.0% at admission, two days post-admission, and seven days post-admission, respectively. Overall, our results could essentially assist clinical decision-making and optimized treatment and management for COVID-19 hospitalized patients with an elevated risk of mortality.