Fitting and validation of an agent-based model for COVID-19 case forecasting in workplaces and universities.

COVID-19 forecasting models have been critical in guiding decision-making on surveillance testing, social distancing, and vaccination requirements. Beyond influencing public health policies, an accurate COVID-19 forecasting model can impact community spread by enabling employers and university leaders to adapt worksite policies and practices to contain or mitigate outbreaks. While many such models have been developed for COVID-19 forecasting at the national, state, county, or city level, only a few models have been developed for workplaces and universities. Furthermore, COVID-19 forecasting models have rarely been validated against real COVID-19 case data. Here we present the systematic parameter fitting and validation of an agent-based compartment model for the forecasting of daily COVID-19 cases in single-site workplaces and universities with real-world data. Our approaches include manual fitting, where initial model parameters are chosen based on historical data, and automated fitting, where parameters are chosen based on candidate case trajectory simulations that result in best fit to prevalence estimation data. We use a 14-day fitting window and validate our approaches on 7- and 14-day testing windows with real COVID-19 case data from one employer. Our manual and automated fitting approaches accurately predicted COVID-19 case trends and outperformed the baseline model (no parameter fitting) across multiple scenarios, including a rising case trajectory (RMSLE values: 2.627 for baseline, 0.562 for manual fitting, 0.399 for automated fitting) and a decreasing case trajectory (RMSLE values: 1.155 for baseline, 0.537 for manual fitting, 0.778 for automated fitting). Our COVID-19 case forecasting model allows decision-makers at workplaces and universities to proactively respond to case trend forecasts, mitigate outbreaks, and promote safety.

Toward a Mobile Platform for Real-world Digital Measurement of Depression: User-Centered Design, Data Quality, and Behavioral and Clinical Modeling.

BACKGROUND: Although effective mental health treatments exist, the ability to match individuals to optimal treatments is poor, and timely assessment of response is difficult. One reason for these challenges is the lack of objective measurement of psychiatric symptoms. Sensors and active tasks recorded by smartphones provide a low-burden, low-cost, and scalable way to capture real-world data from patients that could augment clinical decision-making and move the field of mental health closer to measurement-based care. OBJECTIVE: This study tests the feasibility of a fully remote study on individuals with self-reported depression using an Android-based smartphone app to collect subjective and objective measures associated with depression severity. The goals of this pilot study are to develop an engaging user interface for high task adherence through user-centered design; test the quality of collected data from passive sensors; start building clinically relevant behavioral measures (features) from passive sensors and active inputs; and preliminarily explore connections between these features and depression severity. METHODS: A total of 600 participants were asked to download the study app to join this fully remote, observational 12-week study. The app passively collected 20 sensor data streams (eg, ambient audio level, location, and inertial measurement units), and participants were asked to complete daily survey tasks, weekly voice diaries, and the clinically validated Patient Health Questionnaire (PHQ-9) self-survey. Pairwise correlations between derived behavioral features (eg, weekly minutes spent at home) and PHQ-9 were computed. Using these behavioral features, we also constructed an elastic net penalized multivariate logistic regression model predicting depressed versus nondepressed PHQ-9 scores (ie, dichotomized PHQ-9). RESULTS: A total of 415 individuals logged into the app. Over the course of the 12-week study, these participants completed 83.35% (4151/4980) of the PHQ-9s. Applying data sufficiency rules for minimally necessary daily and weekly data resulted in 3779 participant-weeks of data across 384 participants. Using a subset of 34 behavioral features, we found that 11 features showed a significant (P<.001 Benjamini-Hochberg adjusted) Spearman correlation with weekly PHQ-9, including voice diary-derived word sentiment and ambient audio levels. Restricting the data to those cases in which all 34 behavioral features were present, we had available 1013 participant-weeks from 186 participants. The logistic regression model predicting depression status resulted in a 10-fold cross-validated mean area under the curve of 0.656 (SD 0.079). CONCLUSIONS: This study finds a strong proof of concept for the use of a smartphone-based assessment of depression outcomes. Behavioral features derived from passive sensors and active tasks show promising correlations with a validated clinical measure of depression (PHQ-9). Future work is needed to increase scale that may permit the construction of more complex (eg, nonlinear) predictive models and better handle data missingness.

A holistic approach for suppression of COVID-19 spread in workplaces and universities.

As society has moved past the initial phase of the COVID-19 crisis that relied on broad-spectrum shutdowns as a stopgap method, industries and institutions have faced the daunting question of how to return to a stabilized state of activities and more fully reopen the economy. A core problem is how to return people to their workplaces and educational institutions in a manner that is safe, ethical, grounded in science, and takes into account the unique factors and needs of each organization and community. In this paper, we introduce an epidemiological model (the "Community-Workplace" model) that accounts for SARS-CoV-2 transmission within the workplace, within the surrounding community, and between them. We use this multi-group deterministic compartmental model to consider various testing strategies that, together with symptom screening, exposure tracking, and nonpharmaceutical interventions (NPI) such as mask wearing and physical distancing, aim to reduce disease spread in the workplace. Our framework is designed to be adaptable to a variety of specific workplace environments to support planning efforts as reopenings continue. Using this model, we consider a number of case studies, including an office workplace, a factory floor, and a university campus. Analysis of these cases illustrates that continuous testing can help a workplace avoid an outbreak by reducing undetected infectiousness even in high-contact environments. We find that a university setting, where individuals spend more time on campus and have a higher contact load, requires more testing to remain safe, compared to a factory or office setting. Under the modeling assumptions, we find that maintaining a prevalence below 3% can be achieved in an office setting by testing its workforce every two weeks, whereas achieving this same goal for a university could require as much as fourfold more testing (i.e., testing the entire campus population twice a week). Our model also simulates the dynamics of reduced spread that result from the introduction of mitigation measures when test results reveal the early stages of a workplace outbreak. We use this to show that a vigilant university that has the ability to quickly react to outbreaks can be justified in implementing testing at the same rate as a lower-risk office workplace. Finally, we quantify the devastating impact that an outbreak in a small-town college could have on the surrounding community, which supports the notion that communities can be better protected by supporting their local places of business in preventing onsite spread of disease.

Electronic health record-based clinical decision support alert for severe sepsis: a randomised evaluation.

BACKGROUND: Sepsis remains the top cause of morbidity and mortality of hospitalised patients despite concerted efforts. Clinical decision support for sepsis has shown mixed results reflecting heterogeneous populations, methodologies and interventions. OBJECTIVES: To determine whether the addition of a real-time electronic health record (EHR)-based clinical decision support alert improves adherence to treatment guidelines and clinical outcomes in hospitalised patients with suspected severe sepsis. DESIGN: Patient-level randomisation, single blinded. SETTING: Medical and surgical inpatient units of an academic, tertiary care medical centre. PATIENTS: 1123 adults over the age of 18 admitted to inpatient wards (intensive care units (ICU) excluded) at an academic teaching hospital between November 2014 and March 2015. INTERVENTIONS: Patients were randomised to either usual care or the addition of an EHR-generated alert in response to a set of modified severe sepsis criteria that included vital signs, laboratory values and physician orders. MEASUREMENTS AND MAIN RESULTS: There was no significant difference between the intervention and control groups in primary outcome of the percentage of patients with new antibiotic orders at 3 hours after the alert (35% vs 37%, p=0.53). There was no difference in secondary outcomes of in-hospital mortality at 30 days, length of stay greater than 72 hours, rate of transfer to ICU within 48 hours of alert, or proportion of patients receiving at least 30 mL/kg of intravenous fluids. CONCLUSIONS: An EHR-based severe sepsis alert did not result in a statistically significant improvement in several sepsis treatment performance measures.

Inpatient-Derived Vital Sign Parameters Implementation: An Initiative to Decrease Alarm Burden.

OBJECTIVES: To implement data-driven vital sign parameters to reduce bedside monitor alarm burden. METHODS: Single-center, quality-improvement initiative with historical controls assessing the impact of age-based, inpatient-derived heart rate (HR) and respiratory rate (RR) parameters on a 20-bed acute care ward that serves primarily pediatric cardiology patients. The primary outcome was the number of alarms per monitored bed day (MBD) with the aim to decrease the alarms per MBD. Balancing measures included the frequency of missed rapid response team activations, acute respiratory code events, and cardiorespiratory arrest events in the unit with the new vital sign parameters. RESULTS: The median number of all cardiorespiratory monitor alarms per MBD decreased by 21% from 52 (baseline period) to 41 (postintervention period) (P < .001). This included a 17% decrease in the median HR alarms (9-7.5 per MBD) and a 53% drop in RR alarms (16.8-8.0 per MBD). There were 57 rapid response team activations, 8 acute respiratory code events, and no cardiorespiratory arrest events after the implementation of the new parameters. An evaluation of HRs and RRs recorded at the time of the event revealed that all patients with HRs and/or RRs out of range per former default parameters would also be out of range with the new parameters. CONCLUSIONS: Implementation of data-driven HR and iteratively derived RR parameters safely decreased the total alarm frequency by 21% in a pediatric acute care unit.

Safety analysis of proposed data-driven physiologic alarm parameters for hospitalized children.

INTRODUCTION: Modification of alarm limits is one approach to mitigating alarm fatigue. We aimed to create and validate heart rate (HR) and respiratory rate (RR) percentiles for hospitalized children, and analyze the safety of replacing current vital sign reference ranges with proposed data-driven, age-stratified 5th and 95th percentile values. METHODS: In this retrospective cross-sectional study, nurse-charted HR and RR data from a training set of 7202 hospitalized children were used to develop percentile tables. We compared 5th and 95th percentile values with currently accepted reference ranges in a validation set of 2287 patients. We analyzed 148 rapid response team (RRT) and cardiorespiratory arrest (CRA) events over a 12-month period, using HR and RR values in the 12 hours prior to the event, to determine the proportion of patients with out-of-range vitals based upon reference versus data-driven limits. RESULTS: There were 24,045 (55.6%) fewer out-of-range measurements using data-driven vital sign limits. Overall, 144/148 RRT and CRA patients had out-of-range HR or RR values preceding the event using current limits, and 138/148 were abnormal using data-driven limits. Chart review of RRT and CRA patients with abnormal HR and RR per current limits considered normal by data-driven limits revealed that clinical status change was identified by other vital sign abnormalities or clinical context. CONCLUSIONS: A large proportion of vital signs in hospitalized children are outside presently used norms. Safety evaluation of data-driven limits suggests they are as safe as those currently used. Implementation of these parameters in physiologic monitors may mitigate alarm fatigue. Journal of Hospital Medicine 2015;11:817-823. © 2015 Society of Hospital Medicine.