Search

Background Methods have been proposed to identify areas of low access to resources that are embedded with subjective parameters. In this work, we propose and validate a new Mobility Data-Driven (MDD) framework to identify areas that have low access to the COVID-19 vaccine. Methods We collected geospatial mobility data to an objective approach for determining areas of low access. We identify census tracts in Oregon with low access to the COVID-19 vaccine through two approaches: (1) An adapted United States Department of Agriculture (USDA) food desert definition and (2) our proposed MDD framework. Ten spatial and social measures of access are utilized to compare these two approaches. Results Tracts identified by the MDD definition have lower spatial accessibility scores (0.072 – 0.162) than those identified by the USDA adapted definition (0.239 – 0.32). During the Spring season, the MDD identified census tracts have a higher rate of poverty (15.2%), unemployment (8.4%), uninsured individuals (7.1%), and a lower per capita income ($28,261). Moreover, we find that the proportion the American Indian and Alaskan Native population in MDD identified low-access census tracts is higher than that in USDA definition (4.85% versus 0.95%) which indicates the framework’s ability to capture known disparities in access amongst this population. Conclusions During the creation of plans for equitable distribution of a resource like the COVID-19 vaccine, leaders should utilize objective data (like mobility data) to assist them in determining parameters that represent a populations ability to obtain that resource. Our proposed framework provides a starting point for achieving this goal.

PurposeWorkload is a critical concept in the evaluation of performance and quality in healthcare systems, but its definition relies on the perspective (e.g. individual clinician-level vs unit-level workload) and type of available metrics (e.g. objective vs subjective measures). The purpose of this paper is to provide an overview of objective measures of workload associated with direct care delivery in tertiary healthcare settings, with a focus on measures that can be obtained from electronic records to inform operationalization of workload measurement.Design/methodology/approachRelevant papers published between January 2008 and July 2018 were identified through a search in Pubmed and Compendex databases using the Sample, Phenomenon of Interest, Design, Evaluation, Research Type framework. Identified measures were classified into four levels of workload: task, patient, clinician and unit.FindingsOf 30 papers reviewed, 9 used task-level metrics, 14 used patient-level metrics, 7 used clinician-level metrics and 20 used unit-level metrics. Key objective measures of workload include: patient turnover (n=9), volume of patients (n=6), acuity (n=6), nurse-to-patient ratios (n=5) and direct care time (n=5). Several methods for operationalization of these metrics into measurement tools were identified.Originality/valueThis review highlights the key objective workload measures available in electronic records that can be utilized to develop an operational approach for quantifying workload. Insights gained from this review can inform the design of processes to track workload and mitigate the effects of increased workload on patient outcomes and clinician performance.

Objective To assess the impact of a triage system of emergency department (ED) referrals for outpatient cardiology appointments. Patient and Methods We implemented a triage system of ED referrals for outpatient cardiology appointments among patients with a cardiovascular chief complaint deemed safe to leave the ED but needing outpatient follow-up. There were 303 and 267 unique patients in the pre–triage implementation and post–triage implementation cohorts, respectively. We collected retrospective billing data to assess ED return visits, hospitalizations, cardiology outpatient visits, and cardiovascular testing. The pre–triage implementation cohort included patients with an ED visit date between January 1, 2014, and December 31, 2014. The post–triage implementation cohort included patients with an ED visit date between July 1, 2015, and June 30, 2016. Results The triage model reduced the number of ED-referred cardiovascular service appointments by 73.0% (195 of 267 patients). Additionally, the “no-show” rate for appointments decreased from 17.8% (54 of 303 patients) to 7.9% (21 of 267 patients). There was no increase in ED return visits or unplanned hospitalizations in the posttriage cohort. Finally, the triage model was not associated with an increase in resource-intensive cardiovascular testing (eg, imaging stress tests or computed tomography). Conclusion Triage of ED referrals for outpatient cardiovascular service appointments reduced cardiology appointment utilization with no impact on return ED visits, hospitalizations, or cardiovascular testing.

Sepsis is a condition that progresses quickly and is a major cause of mortality in hospitalized patients. Data-driven diagnostic and therapeutic interventions are essential to ensure early diagnosis and appropriate care. The Sequential Organ Failure Assessment (SOFA) score is widely utilized in clinical practice to assess septic patients for organ dysfunction. The SOFA score uses points between 0 and 4 to quantify the level of dysfunction in six organ systems. These points are determined based on expert opinion and not informed by data, thus their usefulness can vary among different medical institutions depending on the targeted use. In this study, we propose multiple strategies to adjust the SOFA score using mixed-integer programming to improve the in-hospital mortality prediction of septic patients based on Electronic Health Records (EHRs). We use the same variables and threshold values of the original SOFA score in each strategy. Thus, the proposed approach takes advantage of optimization and data analysis while taking into account the medical expertise. Our results demonstrate a statistically significant improvement ( $p ) in the prediction of in-hospital mortality among patients susceptible to sepsis when implementing our proposed strategies. Area under the receiver operator curve (AUC) and accuracy values of 0.8928 and 0.8904 are achieved by optimizing the point values of the SOFA score.

Selecting model features that would ensure adequate out-of-sample classification is difficult in real life applications of classification often because there is a large number of candidate features. We propose a bilevel programming approach to feature selection problem for classification and develop a novel genetic algorithm as a solution approach. We implement the proposed framework in three different case studies where we classify influenza strains based on antigenic variety, distinguish between good and bad quality colposcopy images, and identify splice junction sites in genetic sequences. As a benchmark for the proposed genetic algorithm, we use a derivative-free optimization method to solve the bilevel feature selection problems in these case studies. The computational experiments show that the proposed bilevel framework improves the overall classification performance while selecting the most important features for the model.

Objective We aim to investigate the hypothesis that using information about which variables are missing along with appropriate imputation improves the performance of severity of illness scoring systems used to predict critical patient outcomes. Study design and setting We quantify the impact of missing and imputed variables on the performance of prediction models used in the development of a sepsis-related severity of illness scoring system. Electronic health records (EHR) data were compiled from Christiana Care Health System (CCHS) on 119,968 adult patients hospitalized between July 2013 and December 2015. Two outcomes of interest were considered for prediction: (1) first transfer to intensive care unit (ICU) and (2) in-hospital mortality. Five different prediction models were employed. Indicators were utilized in these prediction models to identify when variables were missing and imputed. Results We observed statistically significant gains in prediction performance when moving from models that did not indicate missing information to those that did. Moreover, this increase was higher in models that use summary variables as predictors compared to those that use all variables. Conclusion When developing prediction models using longitudinal EHR data, researchers should explore the incorporation of indicators for missing variables along with appropriate imputation.

Influenza vaccine composition is reviewed before every flu season because influenza viruses constantly evolve through antigenic changes. To inform vaccine updates, laboratories that contribute to the World Health Organization Global Influenza Surveillance and Response System monitor the antigenic phenotypes of circulating viruses all year round. Vaccine strains are selected in anticipation of the upcoming influenza season to allow adequate time for production. A mismatch between vaccine strains and predominant strains in the flu season can significantly reduce vaccine effectiveness. Models for predicting the evolution of influenza based on the relationship of genetic mutations and antigenic characteristics of circulating viruses may inform vaccine strain selection decisions. We review the literature on state-of-the-art tools and prediction methodologies utilized in modeling the evolution of influenza to inform vaccine strain selection. We then discuss areas that are open for improvement and need further research.