Azusa Pacific University

In an exclusive interview with MedTech Outlook he/she shared invaluable insights on how Remote Patient Monitoring (RPM) supported by AI and emerging technologies like PPG-enabled wearable, can transform geriatric care in SNFs and ALFs.

While emphasizing the need to address barriers in reimbursement, training, data integration, and policy reform to ensure equitable and effective implementation.

Remote patient monitoring (RPM) holds immense potential to transform care for older adults in skilled nursing facilities (SNFs) and assisted living facilities (ALFs), yet its adoption is hindered by operational, financial, and technological barriers. The emergence of disruptive technologies, such as photoplethysmography (PPG)-enabled wearables, promises enhanced capabilities but introduces new complexities. This article explores the problems RPM addresses, the limited evidence on its implementation in SNFs and ALFs, key challenges, the role of disruptive technologies, and solutionsthrough policy, AI, and education--to ensure these innovations benefit older adults.

Problems RPM Can Solve

RPM uses electronic devices to collect physiologic data such as weight, blood pressure, heart rate, oxygen saturation, sleep data, and body position, and even self-report data, in the management of conditions like heart failure, diabetes, and dementia. In a recent metanalysis or RPM disease management programs, Braver et al. (2023) found that RPM reduced all-cause 30-day hospital readmissions by 32% and emergency department visits by 63%. RPM also has the potential for early detection of falls, wandering, and dementiarelated behavioral changes (David et al., 2023; Gaugler et al., 2019; Zimbro et al., 2024). Combined with telehealth integration and artificial intelligence assisted analysis of data, RPM is showing promise in minimizing unnecessary hospitalization, improving a wide range of chronic disease management outcomes, and improving quality of life.

Limited Knowledge of RPM Implementation

Evidence on RPM’s use in SNFs and ALFs is sparse, as most studies focus on home-based care. The unique constraints of SNFs and ALFs high resident acuity, staffing shortages, and diverse electronic health record (EHR) systems limit adoption. Additionally, further research is needed in SNF and ALF settings due to small sample sizes and inconsistent outcomes, thus limiting generalizability. SNF pilots demonstrate readmission reductions, but ALF data is scarce due to patient access restrictions and varied resident needs (Peyroteo et al., 2021; Taylor et al., 2021). Initiatives like the HRSA-funded Geriatric Workforce Enhancement Program (HRSA-24- 018) are investigating RPM’s role, but scalable models remain elusive.

Challenges to RPM Adoption

In our experience, we cite four main barriers that impede RPM implementation in SNFs and ALFs:

Monitoring Responsibilities

High nurse to patient ratios, especially during off-hours strain staff capacity to manage alerts. Physicians fear medicolegal liability for missed data, particularly in ALFs with less oversight.

Reimbursement

Medicare’s RPM codes (99453–99457) are limited, temporary, or misaligned with diverse resident needs (e.g., intensive vs. routine monitoring). Commercial payers provide inconsistent coverage, and ALF residents face out-ofpocket costs.

Documentation

Disparate EHRs (e.g., Epic, PointClickCare) lack seamless integration with RPM devices, causing manual data entry, errors, and delays.

Disruptive Technologies: Opportunities and Complexities

Disruptive technologies--innovations that lower costs, increase efficiency, reshape care delivery--are enhancing RPM at a rapid pace but complicate adoption. A prime example is photoplethysmography (PPG), used in wearable devices like electronic rings. PPG employs lightbased sensors to continuously monitor blood pressure, heart rate variability, sleep patterns, and body position. For example, devices like the Sleepon Go2Sleep 3 ring also claims noninvasive blood glucose monitoring, though this feature is not yet available and unverified. The FDA warns that non-invasive glucose monitoring in wearables lacks authorization and may produce inaccurate readings. Nevertheless, the technologies are emerging and devices such as PPGenabled rings can potentially predict heart failure exacerbations, reduce falls by detecting posture changes, and support dementia care by tracking sleep disruptions, all of which are critical for SNF and ALF residents. In summary, disruptive technologies are outpacing infrastructure and new devices are presenting data challenges for EHR integration, demanding new training. At the same time reimbursement lags behind, and companies target consumer demand. These challenges are most pronounced in facilities such as SNFs and ALFs that serve older adults with the highest needs.

Solutions: Policy, AI, and Education

To overcome barriers and leverage new RPM technologies, healthcare systems must implement reforms, harness AI, and prioritize education.

Policy Reforms Legislation

The proposed Choose Home Care Act of 2021 c (S.2562/H.R.5514, 117th Congress) could expand RPM access in post-acute settings by incentivizing home-like care, linking payments to outcomes like reduced readmissions. CMS should extend RPM codes to cover FDA approved devices, ensuring equity.

Reimbursement for new AI backed telehealth technologies also needs to be expanded.

Reimbursement Changes

Acuity-based payment models would align costs with resident needs (e.g., intensive monitoring for heart failure). Where insurance reimbursement does not exist, public-private partnerships can subsidize devices for ALF residents, easing financial burdens and expanding access to underserved populations.

AI Integration

AI integration enhances RPM by automating data analysis and prioritizing alerts for SNF and ALF care teams. Machine learning algorithms can predict clinical events, such as heart failure exacerbations and falls, enabling timely interventions. Interoperable platforms using FHIR standards streamline data integration with EHRs, improving efficiency. Technology providers are currently into RPM through predictive analytics that identify high-risk patients, and it can be further embedded by deploying user-friendly AI dashboards to guide staff decision-making in SNFs and ALFs.

Education and Training Who Needs It

Nurses, nurse practitioners, physicians, and ALF caregivers require training on RPM devices and AI tools. Future healthcare workers RNs, NPs, CNAs need skills in data interpretation, telehealth, and wearable management.

What’s Needed

Inter-professional curricula should cover alert triage, EHR integration, and patient engagement with user-friendly devices. Training must ensure older adults and their caretakers can use technology with simple interfaces.

Delivery

Online modules, simulation labs, and vendor workshops can scale education. SNF and ALF staff needs ongoing training to adapt to rapid tech cycles, plus cybersecurity skills for data protection.

Future Skills

Workers must master AI analytics, crossplatform EHR navigation, and patientcentered tech communication to keep pace with innovation.

Practical Steps:

Facilities should pilot interoperable platforms, as seen in 30% readmission reductions in 2022 pilots. Staff incentives for RPM proficiency encourage adoption. Advocacy for rural broadband access ensures equitable ALF tech deployment.

Conclusion

RPM, powered by disruptive technologies like PPG-enabled rings and other small device wearables can prevent hospitalizations, reduce falls, and enhance chronic disease management for older adults in SNFs and ALFs. Limited implementation knowledge and barriers monitoring, reimbursement, documentation require urgent solutions. Through policies like the Choose Home Care Act, AI-driven analytics, and robust training, healthcare systems can unlock RPM’s potential. MedTech Outlook readers must champion these changes; ensuring technology serves older adults equitably.