Using Shapes of COVID-19 Positive Patient-Specific Trajectories for Mortality Prediction.

Machine learning can be used to identify relevant trajectory shape features for improved predictive risk modeling, which can help inform decisions for individualized patient management in intensive care during COVID-19 outbreaks. We present explainable random forests to dynamically predict next day mortality risk in COVID -19 positive and negative patients admitted to the Mount Sinai Health System between March 1st and June 8th, 2020 using patient time-series data of vitals, blood and other laboratory measurements from the previous 7 days. Three different models were assessed by using time series with: 1) most recent patient measurements, 2) summary statistics of trajectories (min/max/median/first/last/count), and 3) coefficients of fitted cubic splines to trajectories. AUROC and AUPRC with cross-validation were used to compare models. We found that the second and third models performed statistically significantly better than the first model. Model interpretations are provided at patient-specific level to inform resource allocation and patient care.

BEHRTDAY: Dynamic Mortality Risk Prediction using Time-Variant COVID-19 Patient Specific Trajectories.

Incorporating repeated measurements of vitals and laboratory measurements can improve mortality risk-prediction and identify key risk factors in individualized treatment of COVID-19 hospitalized patients. In this observational study, demographic and laboratory data of all admitted patients to 5 hospitals of Mount Sinai Health System, New York, with COVID-19 positive tests between March 1st and June 8th, 2020, were extracted from electronic medical records and compared between survivors and non-survivors. Next day mortality risk of patients was assessed using a transformer-based model BEHRTDAY fitted to patient time series data of vital signs, blood and other laboratory measurements given the entire patients' hospital stay. The study population includes 3699 COVID-19 positive (57% male, median age: 67) patients. This model had a very high average precision score (0.96) and area under receiver operator curve (0.92) for next-day mortality prediction given entire patients' trajectories, and through masking, it learnt each variable's context.

Device-Measured Change in Physical Activity in Primary School Children During the UK COVID-19 Pandemic Lockdown: A Longitudinal Study.

BACKGROUND: Lockdown measures, including school closures, due to the COVID-19 pandemic have caused widespread disruption to children's lives. The aim of this study was to explore the impact of a national lockdown on children's physical activity using seasonally matched accelerometry data. METHODS: Using a pre/post observational design, 179 children aged 8 to 11 years provided physical activity data measured using hip-worn triaxial accelerometers worn for 5 consecutive days prepandemic and during the January to March 2021 lockdown. Multilevel regression analyses adjusted for covariates were used to assess the impact of lockdown on time spent in sedentary and moderate to vigorous physical activity. RESULTS: A 10.8-minute reduction in daily time spent in moderate to vigorous physical activity (standard error: 2.3 min/d, P < .001) and a 33.2-minute increase in daily sedentary activity (standard error: 5.5 min/d, P < .001) were observed during lockdown. This reflected a reduction in daily moderate to vigorous physical activity for those unable to attend school (-13.1 [2.3] min/d, P < .001) during lockdown, with no significant change for those who continued to attend school (0.4 [4.0] min/d, P < .925). CONCLUSION: These findings suggest that the loss of in-person schooling was the single largest impact on physical activity in this cohort of primary school children in London, Luton, and Dunstable, United Kingdom.

Using Shapes of COVID-19 Positive Patient-Specific Trajectories for Mortality Prediction

Machine learning can be used to identify relevant trajectory shape features for improved predictive risk modeling, which can help inform decisions for individualized patient management in intensive care during COVID-19 outbreaks. We present explainable random forests to dynamically predict next day mortality risk in COVID -19 positive and negative patients admitted to the Mount Sinai Health System between March 1st and June 8th, 2020 using patient time-series data of vitals, blood and other laboratory measurements from the previous 7 days. Three different models were assessed by using time series with: 1) most recent patient measurements, 2) summary statistics of trajectories (min/max/median/first/last/count), and 3) coefficients of fitted cubic splines to trajectories. AUROC and AUPRC with cross-validation were used to compare models. We found that the second and third models performed statistically significantly better than the first model. Model interpretations are provided at patient-specific level to inform resource allocation and patient care.

BEHRTDAY: Dynamic Mortality Risk Prediction using Time-Variant COVID-19 Patient Specific Trajectories

Incorporating repeated measurements of vitals and laboratory measurements can improve mortality risk-prediction and identify key risk factors in individualized treatment of COVID-19 hospitalized patients. In this observational study, demographic and laboratory data of all admitted patients to 5 hospitals of Mount Sinai Health System, New York, with COVID-19 positive tests between March 1st and June 8th, 2020, were extracted from electronic medical records and compared between survivors and non-survivors. Next day mortality risk of patients was assessed using a transformer-based model BEHRTDAY fitted to patient time series data of vital signs, blood and other laboratory measurements given the entire patients’ hospital stay. The study population includes 3699 COVID-19 positive (57% male, median age: 67) patients. This model had a very high average precision score (0.96) and area under receiver operator curve (0.92) for next-day mortality prediction given entire patients’ trajectories, and through masking, it learnt each variable’s context.