A remote monitoring program evaluation: a retrospective study

Patient Characteristics Associated With Disparities in Engagement With and Experience of COVID-19 Remote Home Monitoring Services: A Mixed-Methods Evaluation

INTRODUCTION

The adoption of remote healthcare methods has been accelerated by the COVID-19 pandemic, but evidence suggests that some patients need additional support to engage remotely, potentially increasing health disparities if needs are not met. This study of COVID-19 remote home monitoring services across England explores experiences of and engagement with the service across different patient groups.

METHODS

This was a mixed-methods study with survey and interview data collected from 28 services across England between February and June 2021. Surveys were conducted with staff and patients and carers receiving the service. Interviews with staff service leads, patients and carers were conducted in 17 sites. Quantitative data were analysed using univariate and multivariate methods, and qualitative data were analysed using thematic analysis.

FINDINGS

Survey responses were received from 292 staff and 1069 patients and carers. Twenty-three staff service leads, 59 patients and 3 carers were interviewed. Many service leads reported that they had considered inclusivity when adapting the service for their local population; strategies included widening the eligibility criteria, prioritising vulnerable groups and creating referral pathways. However, disparities were reported across patient groups in their experiences and engagement. Older patients reported the service to be less helpful (p = 0.004), were more likely to report a problem (p < 0.001) and had more difficulty in understanding information (p = 0.005). Health status (p = 0.004), ethnicity (p < 0.001), gender (p < 0.001) and employment (p = 0.007) were associated with differential engagement with monitoring, and minority ethnic groups reported more difficulty understanding service information (p = 0.001). Qualitative data found illness severity to be an important factor in the support required, and patients' living situation and social network affected whether they found the service reassuring.

CONCLUSION

Addressing health disparities must be a key focus in the design and delivery of remote care. Services should be tailored to match the needs of their local population, encourage access through collaboration and referral pathways with other services and monitor their inclusiveness. Involving patients and staff in service design can illuminate the diversity of patients' needs and experiences of care.

PATIENT OR PUBLIC CONTRIBUTION

The study team met with service user and public members of the BRACE PPI group and patient representatives from RSET in a series of workshops. Workshops informed study design, data collection tools, data interpretation and dissemination activities. Study documents (such as consent forms, topic guides, surveys and information sheets) were reviewed by PPI members; patient surveys and interview guides were piloted, and members also commented on the manuscript.

A Brief Analysis of Key Machine Learning Methods for Predicting Medicare Payments Related to Physical Therapy Practices in the United States

Background and objectives: Machine learning approaches using random forest have been effectively used to provide decision support in health and medical informatics. This is especially true when predicting variables associated with Medicare reimbursements. However, more work is needed to analyze and predict data associated with reimbursements through Medicare and Medicaid services for physical therapy practices in the United States. The key objective of this study is to analyze different machine learning models to predict key variables associated with Medicare standardized payments for physical therapy practices in the United States. Materials and Methods: This study employs five methods, namely, multiple linear regression, decision tree regression, random forest regression, K-nearest neighbors, and linear generalized additive model, (GAM) to predict key variables associated with Medicare payments for physical therapy practices in the United States. Results: The study described in this article adds to the body of knowledge on the effective use of random forest regression and linear generalized additive model in predicting Medicare Standardized payment. It turns out that random forest regression may have any edge over other methods employed for this purpose. Conclusions: The study provides a useful insight into comparing the performance of the aforementioned methods, while identifying a few intricate details associated with predicting Medicare costs while also ascertaining that linear generalized additive model and random forest regression as the most suitable machine learning models for predicting key variables associated with standardized Medicare payments.