ABSTRACT
BACKGROUND: Although research shows that digital health tools (DHT) are increasingly integrated with healthcare in the United States, very few studies have investigated the rural-urban differences in DHT adoption at the national level. Individuals in rural communities experience disproportionately greater rates of chronic diseases and face unique challenges in accessing health care. Studies have shown that digital technology can improve access and support rural health by overcoming geographic barriers to care. OBJECTIVE: To evaluate the rates of ownership and preferences for utilization of DHT as a measure of interest among rural adults compared to their urban counterparts in the United States using a National Inpatient Survey. METHODS: Data was drawn from the 2019 (n= 5438) iteration of the Health Information National Trends Survey (HINTS 5 cycle 3). Chi-square tests and weighted multivariable logistic regressions were conducted to examine rural-urban differences regarding ownership, usage, and use of digital health tools to interact with health care systems while adjusting for health-related characteristics and sociodemographic factors. RESULTS: The ownership rates of digital health technology (DHT) devices, including tablets, smart phones, health apps, and wearable devices, were comparable between rural and urban residents. For tablets, the ownership rates were 54.52% among rural residents and 60.24% among urban residents, with an adjusted odds ratio (OR) of 0.87 (95% confidence interval {CI}: 0.61, 1.24). The ownership rates of health apps were 51.41% and 53.35% among rural and urban residents, respectively, with an adjusted OR of 0.93 (95% CI: 0.62, 1.42). For smartphones, the ownership rates were 81.64% among rural residents and 84.10% among urban residents, with an adjusted OR of 0.81 (95% CI: 0.59, 1.11). Additionally, rural residents were equally likely to use DHT in managing their healthcare needs. Both groups were equally likely to have reported their smart device as helpful in discussions with their healthcare providers (OR 0.90; 95% CI 63 - 1.30; p = 0.572). Similarly, there were similar odds of reporting that DHT had helped them to track progress on a health-related goal (e.g., quitting smoking, losing weight, or increasing physical activity) (OR 1.17; 95% CI 0.75 - 1.83; p = 0.491), and to make medical decisions (OR 1.05; 95% CI 0.70 - 1.59; p = 0.797). However, they had lower rates of internet access and were less likely to use DHT for communicating with their healthcare providers. CONCLUSION: We found that rural residents are equally likely as urban residents to own and use DHT to manage their health. However, they were less likely to communicate with their health providers using DHT. With increasing use of DHT in healthcare, future research that targets reasons for geographical digital access disparities is warranted.
ABSTRACT
BACKGROUND: With an increase in the number of artificial intelligence (AI) and machine learning (ML) algorithms available for clinical settings, appropriate model updating and implementation of updates are imperative to ensure applicability, reproducibility, and patient safety. OBJECTIVE: The objective of this scoping review was to evaluate and assess the model-updating practices of AI and ML clinical models that are used in direct patient-provider clinical decision-making. METHODS: We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist and the PRISMA-P protocol guidance in addition to a modified CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) checklist to conduct this scoping review. A comprehensive medical literature search of databases, including Embase, MEDLINE, PsycINFO, Cochrane, Scopus, and Web of Science, was conducted to identify AI and ML algorithms that would impact clinical decision-making at the level of direct patient care. Our primary end point is the rate at which model updating is recommended by published algorithms; we will also conduct an assessment of study quality and risk of bias in all publications reviewed. In addition, we will evaluate the rate at which published algorithms include ethnic and gender demographic distribution information in their training data as a secondary end point. RESULTS: Our initial literature search yielded approximately 13,693 articles, with approximately 7810 articles to consider for full reviews among our team of 7 reviewers. We plan to complete the review process and disseminate the results by spring of 2023. CONCLUSIONS: Although AI and ML applications in health care have the potential to improve patient care by reducing errors between measurement and model output, currently there exists more hype than hope because of the lack of proper external validation of these models. We expect to find that the AI and ML model-updating methods are proxies for model applicability and generalizability on implementation. Our findings will add to the field by determining the degree to which published models meet the criteria for clinical validity, real-life implementation, and best practices to optimize model development, and in so doing, reduce the overpromise and underachievement of the contemporary model development process. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/37685.
