Feasibility of using intermittent active monitoring of vital signs by smartphone users to predict SARS-CoV-2 PCR positivity.

Early detection of highly infectious respiratory diseases, such as COVID-19, can help curb their transmission. Consequently, there is demand for easy-to-use population-based screening tools, such as mobile health applications. Here, we describe a proof-of-concept development of a machine learning classifier for the prediction of a symptomatic respiratory disease, such as COVID-19, using smartphone-collected vital sign measurements. The Fenland App study followed 2199 UK participants that provided measurements of blood oxygen saturation, body temperature, and resting heart rate. Total of 77 positive and 6339 negative SARS-CoV-2 PCR tests were recorded. An optimal classifier to identify these positive cases was selected using an automated hyperparameter optimisation. The optimised model achieved an ROC AUC of 0.695 ± 0.045. The data collection window for determining each participant's vital sign baseline was increased from 4 to 8 or 12 weeks with no significant difference in model performance (F(2) = 0.80, p = 0.472). We demonstrate that 4 weeks of intermittently collected vital sign measurements could be used to predict SARS-CoV-2 PCR positivity, with applicability to other diseases causing similar vital sign changes. This is the first example of an accessible, smartphone-based remote monitoring tool deployable in a public health setting to screen for potential infections.

Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study.

The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, to estimate COVID-19 mortality risk in confirmed cases. From the 11,245 participants testing positive for COVID-19, we develop a data-driven random forest classification model with excellent performance (AUC: 0.91), using baseline characteristics, pre-existing conditions, symptoms, and vital signs, such that the score could dynamically assess mortality risk with disease deterioration. We also identify several significant novel predictors of COVID-19 mortality with equivalent or greater predictive value than established high-risk comorbidities, such as detailed anthropometrics and prior acute kidney failure, urinary tract infection, and pneumonias. The model design and feature selection enables utility in outpatient settings. Possible applications include supporting individual-level risk profiling and monitoring disease progression across patients with COVID-19 at-scale, especially in hospital-at-home settings.

Accelerometer-derived sleep onset timing and cardiovascular disease incidence: a UK Biobank cohort study.

Aims: Growing evidence suggests that poor sleep health is associated with cardiovascular risk. However, research in this area often relies upon recollection dependent questionnaires or diaries. Accelerometers provide an alternative tool for measuring sleep parameters objectively. This study examines the association between wrist-worn accelerometer-derived sleep onset timing and cardiovascular disease (CVD). Methods and results: We derived sleep onset and waking up time from accelerometer data collected from 103 712 UK Biobank participants over a period of 7 days. From this, we examined the association between sleep onset timing and CVD incidence using a series of Cox proportional hazards models. A total of 3172 cases of CVD were reported during a mean follow-up period of 5.7 (±0.49) years. An age- and sex-controlled base analysis found that sleep onset time of 10:00 p.m.-10:59 p.m. was associated with the lowest CVD incidence. An additional model, controlling for sleep duration, sleep irregularity, and established CVD risk factors, did not attenuate this association, producing hazard ratios of 1.24 (95% confidence interval, 1.10-1.39; P < 0.005), 1.12 (1.01-1.25; P = 0.04), and 1.25 (1.02-1.52; P = 0.03) for sleep onset <10:00 p.m., 11:00 p.m.-11:59 p.m., and ≥12:00 a.m., respectively, compared to 10:00 p.m.-10:59 p.m. Importantly, sensitivity analyses revealed this association with increased CVD risk was stronger in females, with only sleep onset <10:00 p.m. significant for males. Conclusions: Our findings suggest the possibility of a relationship between sleep onset timing and risk of developing CVD, particularly for women. We also demonstrate the potential utility of collecting information about sleep parameters via accelerometry-capable wearable devices, which may serve as novel cardiovascular risk indicators.

Development of an accessible 10-year Digital CArdioVAscular (DiCAVA) risk assessment: a UK Biobank study.

Aims: Cardiovascular diseases (CVDs) are among the leading causes of death worldwide. Predictive scores providing personalized risk of developing CVD are increasingly used in clinical practice. Most scores, however, utilize a homogenous set of features and require the presence of a physician. The aim was to develop a new risk model (DiCAVA) using statistical and machine learning techniques that could be applied in a remote setting. A secondary goal was to identify new patient-centric variables that could be incorporated into CVD risk assessments. Methods and results: Across 466 052 participants, Cox proportional hazards (CPH) and DeepSurv models were trained using 608 variables derived from the UK Biobank to investigate the 10-year risk of developing a CVD. Data-driven feature selection reduced the number of features to 47, after which reduced models were trained. Both models were compared to the Framingham score. The reduced CPH model achieved a c-index of 0.7443, whereas DeepSurv achieved a c-index of 0.7446. Both CPH and DeepSurv were superior in determining the CVD risk compared to Framingham score. Minimal difference was observed when cholesterol and blood pressure were excluded from the models (CPH: 0.741, DeepSurv: 0.739). The models show very good calibration and discrimination on the test data. Conclusion: We developed a cardiovascular risk model that has very good predictive capacity and encompasses new variables. The score could be incorporated into clinical practice and utilized in a remote setting, without the need of including cholesterol. Future studies will focus on external validation across heterogeneous samples.