Predicting COVID-19 Outbreaks in Correctional Facilities Using Machine Learning.

Introduction. The risk of infectious disease transmission, including COVID-19, is disproportionately high in correctional facilities due to close living conditions, relatively low levels of vaccination, and reduced access to testing and treatment. While much progress has been made on describing and mitigating COVID-19 and other infectious disease risk in jails and prisons, there are open questions about which data can best predict future outbreaks. Methods. We used facility data and demographic and health data collected from 24 prison facilities in the Pennsylvania Department of Corrections from March 2020 to May 2021 to determine which sources of data best predict a coming COVID-19 outbreak in a prison facility. We used machine learning methods to cluster the prisons into groups based on similar facility-level characteristics, including size, rurality, and demographics of incarcerated people. We developed logistic regression classification models to predict for each cluster, before and after vaccine availability, whether there would be no cases, an outbreak defined as 2 or more cases, or a large outbreak, defined as 10 or more cases in the next 1, 2, and 3 d. We compared these predictions to data on outbreaks that occurred. Results. Facilities were divided into 8 clusters of sizes varying from 1 to 7 facilities per cluster. We trained 60 logistic regressions; 20 had test sets with between 35% and 65% of days with outbreaks detected. Of these, 8 logistic regressions correctly predicted the occurrence of an outbreak more than 55% of the time. The most common predictive feature was incident cases among the incarcerated population from 2 to 32 d prior. Other predictive features included the number of tests administered from 1 to 33 d prior, total population, test positivity rate, and county deaths, hospitalizations, and incident cases. Cumulative cases, vaccination rates, and race, ethnicity, or age statistics for incarcerated populations were generally not predictive. Conclusions. County-level measures of COVID-19, facility population, and test positivity rate appear as potential promising predictors of COVID-19 outbreaks in correctional facilities, suggesting that correctional facilities should monitor community transmission in addition to facility transmission to inform future outbreak response decisions. These efforts should not be limited to COVID-19 but should include any large-scale infectious disease outbreak that may involve institution-community transmission. Highlights: The risk of infectious disease transmission, including COVID-19, is disproportionately high in correctional facilities.We used machine learning methods with data collected from 24 prison facilities in the Pennsylvania Department of Corrections to determine which sources of data best predict a coming COVID-19 outbreak in a prison facility.Key predictors included county-level measures of COVID-19, facility population, and the test positivity rate in a facility.Fortifying correctional facilities with the ability to monitor local community rates of infection (e.g., though improved interagency collaboration and data sharing) along with continued testing of incarcerated people and staff can help correctional facilities better predict-and respond to-future infectious disease outbreaks.

Diabetes in the context of incarceration: A scoping review.

Background: The burden of chronic conditions, like diabetes, is disproportionately carried by people facing social disadvantages (e.g., those with experiences of incarceration). A dearth of knowledge remains about this topic. We conducted a scoping review to determine the extent of literature about diabetes management and/or self-management in relation to incarceration. Methods: We used the Arksey and O'Malley five stage process, recommendations by Levac et al., and the PRISMA Extension for Scoping Reviews Checklist. Core search terms for diabetes were combined using the Boolean operator AND with terms relevant to incarceration. We initially searched the following electronic academic databases on January 5, 2021, and then updated these searches on September 7, 2022: APA PsycInfo, CINAHL, Criminal Justice Abstracts, EMBASE, MEDLINE, Scopus, and SocINDEX. There were no restrictions on language, study design, quality, location, time, and sex or gender differences. We searched for research articles, conference proceedings, dissertations and theses, government documents, and organization documents. We then searched for other forms of literature using an electronic database (ProQuest Dissertations and Theses - Global), the internet search engine Google, and various corrections and diabetes websites in August 2021 and then updated these searches in September 2022. We also reviewed the reference lists of the final selected documents to identify additional literature. Findings: The search from the seven databases identified 3076 records. The search from other sources (e.g., websites) identified an additional 1077 records. A total of 40 documents met our final inclusion criteria and were included in this review. The type of research conducted was primarily quantitative in nature. Clinic and education interventions were most commonly investigated. Clinical outcomes were often reported. Most guidelines were targeted at healthcare providers. Much of the literature originated from high-income countries, which may not be fully applicable for different contexts like low-income countries. Many interventions were associated with improved outcomes. Interpretation: Administrators can use our findings to develop appropriate policies for this population. Tailored diabetes education for this population and healthcare providers may improve management practices. Our findings offer key insights for improving diabetes care and outcomes for this underserved population. Addressing the diabetes-specific health needs of these people may improve overall public health. Funding: KD has received the O'Brien Institute for Public Health Postdoctoral Scholarship (University of Calgary), Cumming School of Medicine Postdoctoral Scholarship (University of Calgary), and the Libin Cardiovascular Institute's 2021 Person to Population Seed Grant (University of Calgary).

A case study of user assessment of a corrections electronic health record.

The federal government, through the Office of the National Coordinator for Health Information Technology, has moved vigorously to promote widespread and meaningful use of interoperable electronic health records (EHRs) by 2014. The Kentucky Department of Corrections implemented its EHR system in 2006 and in 2010 the department assessed user satisfaction and perception of usability based on criteria that reflect meaningful use. Fifty percent of 345 users responded to an online survey with satisfaction averaging 3.0 out of 4.0 on a 14-item scale and usability averaging 2.8 out of 4.0 for 13 items. The two measures correlated strongly and positively but varied significantly by type of position. This study provides a positive but cautionary case study of how users assess components of an EHR in a relatively stable and controlled organizational setting.