Analyzing COVID-19 Rates Between Residents and Staff in Correctional Facilities: A Telemedicine Opportunity.

To evaluate the relationship of COVID-19 infection rates between residents and staff members in prison facilities. We collected historical data on daily COVID-19 counts for California, Florida, and Wisconsin residents and staff. We analyzed 78,250 COVID-19 cases among residents and 25,392 cases among staff. Strong positive associations were found in the rates of COVID-19 cases between residents and staff, suggesting telemedicine can help reduce outbreaks.

Assessment of Stakeholder Perceptions and Cost of Implementing a Telemedicine Specialty Program at Correctional Facilities in North Carolina.

Background Delivering in-person health care to the more than 1.2 million incarcerated adults can be expensive, logistically challenging, fragmented, and pose security risks. The purpose of this study was to evaluate the implementation of a specialty care telemedicine program in statewide prisons in North Carolina during the COVID-19 pandemic. Methods We evaluated the first 6 months of implementation of a new telemedicine program to deliver specialty care to adults incarcerated in 55 North Carolina prison facilities. We measured patient and practitioner perceptions and the impact on the cost of care. Results A total of 3232 telemedicine visits were completed across 55 prisons within the first 6 months of the program. Most patients reported that the ability to use telemedicine contributed to their overall personal well-being and safety. Many practitioners found that working with the on-site nursing staff to conduct physical exams and to make collective decisions were key drivers to the success of telemedicine. A direct relationship was found between the telemedicine experience and patients' preference for future visits such that as satisfaction increased, the desire to use telemedicine increased. Telemedicine reduced total costs of care by $416,020 (net: -$95,480) within the first 6 months, and $1,195,377 estimated in the first 12 months postimplementation (95% confidence interval: $1,100,166-$1,290,587). Conclusions Implementing specialty care telemedicine in prison facilities enhanced patient and practitioner experiences and reduced costs within the prison system. The implementation of telemedicine in prison systems can increase access to care and reduce public safety risks by eliminating unnecessary off-site medical center visits.

Digital Health Experiences of Incarcerated Populations Using Telemedicine in North Carolina Prisons.

More than 1.2 million adults are incarcerated in the United States and hence, require health care from prison systems. The current delivery of care to incarcerated individualss is expensive, logistically challenging, risk fragmenting care, and pose security risks. The purpose of this study was to evaluate the association of patient characteristics and experiences with the perceived telemedicine experiences of incarcerated individuals during the pandemic. We conducted a cross-sectional study of incarcerated individuals in 55 North Carolina prison facilities seeking medical specialty care via telemedicine. Data collection took place from June 1, 2020 to November 30, 2020. Of the 482 patient surveys completed, 424 (88%) were male, 257 (53.3%) were over 50 years of age, and 225 (46.7%) were Black or African American and 195 (40.5%) were White, and 289 (60%) no prior telemedicine experience. There were 3 strong predictors of how patients rated their telemedicine experience: personal comfort with telemedicine (P-value < .001), wait time (P-value < .001), and the clarity of the treatment explanation by the provider (P-value < .001). There was a relationship between telemedicine experiences and how patient rated their experience. Also, patients who were less satisfied with using telemedicine indicated their preference for an in-clinic visit for their next appointment.

Machine Learning and Medication Adherence: Scoping Review.

BACKGROUND: This is the first scoping review to focus broadly on the topics of machine learning and medication adherence. OBJECTIVE: This review aims to categorize, summarize, and analyze literature focused on using machine learning for actions related to medication adherence. METHODS: PubMed, Scopus, ACM Digital Library, IEEE, and Web of Science were searched to find works that meet the inclusion criteria. After full-text review, 43 works were included in the final analysis. Information of interest was systematically charted before inclusion in the final draft. Studies were placed into natural categories for additional analysis dependent upon the combination of actions related to medication adherence. The protocol for this scoping review was created using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. RESULTS: Publications focused on predicting medication adherence have uncovered 20 strong predictors that were significant in two or more studies. A total of 13 studies that predicted medication adherence used either self-reported questionnaires or pharmacy claims data to determine medication adherence status. In addition, 13 studies that predicted medication adherence did so using either logistic regression, artificial neural networks, random forest, or support vector machines. Of the 15 studies that predicted medication adherence, 6 reported predictor accuracy, the lowest of which was 77.6%. Of 13 monitoring systems, 12 determined medication administration using medication container sensors or sensors in consumer electronics, like smartwatches or smartphones. A total of 11 monitoring systems used logistic regression, artificial neural networks, support vector machines, or random forest algorithms to determine medication administration. The 4 systems that monitored inhaler administration reported a classification accuracy of 93.75% or higher. The 2 systems that monitored medication status in patients with Parkinson disease reported a classification accuracy of 78% or higher. A total of 3 studies monitored medication administration using only smartwatch sensors and reported a classification accuracy of 78.6% or higher. Two systems that provided context-aware medication reminders helped patients to achieve an adherence level of 92% or higher. Two conversational artificial intelligence reminder systems significantly improved adherence rates when compared against traditional reminder systems. CONCLUSIONS: Creation of systems that accurately predict medication adherence across multiple data sets may be possible due to predictors remaining strong across multiple studies. Higher quality measures of adherence should be adopted when possible so that prediction algorithms are based on accurate information. Currently, medication adherence can be predicted with a good level of accuracy, potentially allowing for the development of interventions aimed at preventing nonadherence. Monitoring systems that track inhaler use currently classify inhaler-related actions with an excellent level of accuracy, allowing for tracking of adherence and potentially proper inhaler technique. Systems that monitor medication states in patients with Parkinson disease can currently achieve a good level of classification accuracy and have the potential to inform medication therapy changes in the future. Medication administration monitoring systems that only use motion sensors in smartwatches can currently achieve a good level of classification accuracy but only when differentiating between a small number of possible activities. Context-aware reminder systems can help patients achieve high levels of medication adherence but are also intrusive, which may not be acceptable to users. Conversational artificial intelligence reminder systems can significantly improve adherence.