Scaling Medicaid Innovation with Afia Asamoah, Rajaie Batniji, and Sanjay Basu
Jan 14, 2025
auto_awesome
Rajaie Batniji and Sanjay Basu, co-founders of Waymark, blend medical expertise with innovation in Medicaid care. They discuss their pioneering use of machine learning to predict patient needs, which leads to a significant reduction in emergency visits. The duo highlights how community engagement and trust are vital in healthcare, emphasizing the success of community health workers. Listeners will learn about the balance of profit and purpose in healthcare, along with the importance of early interventions for improving health outcomes.
The innovative rising risk signal prediction framework utilizes machine learning to identify Medicaid patients at risk, enabling proactive community-based care interventions.
Community health workers play a crucial role in this model by fostering trust, addressing social needs, and improving overall health outcomes for underserved populations.
Deep dives
Impact of Community-Based Care on Medicaid
About 40% of acute care visits by Medicaid patients are deemed avoidable, indicating a significant opportunity to prevent unnecessary hospitalizations within this population. A new approach to Medicaid care delivery combines advanced machine learning with community-focused interventions, reducing emergency room visits by nearly 25%. This model emphasizes meeting patients in their communities, rather than relying solely on traditional clinical settings, which has proven effective in enhancing care quality and patient access. By addressing social needs alongside medical care, the approach aims to significantly improve health outcomes for underserved populations while controlling costs.
The Role of Technology in Enhancing Care Delivery
The integration of machine learning into care delivery plays a crucial role in identifying patients at risk of acute care needs. A predictive model, known as the rising risk signal prediction framework, allows for early intervention by accurately determining which patients are at risk of requiring emergency services. This data-driven approach has demonstrated a reduction in hospital visits and enabled care teams to provide timely assistance, addressing ailments before they escalate. By leveraging technology, the approach facilitates better resource allocation and connects patients with necessary services, ultimately enhancing overall healthcare delivery.
Community Health Workers as Key Contributors
Community health workers (CHWs) are integral to this new model of care, as they bridge the gap between patients and the healthcare system. They provide personalized support, assist with medication management, and help patients navigate social services. This direct engagement fosters trust and allows CHWs to identify and address client needs effectively, leading to improved health outcomes. By combining their local knowledge with advanced technology, CHWs enable a more holistic approach to patient care, focusing on both physical and social health determinants.
Value-Based Care and Sustainable Funding Mechanisms
Transitioning to a value-based care model necessitates innovative funding mechanisms to ensure sustainability and success. The new approach emphasizes risk-based contracting that aligns with community health initiatives, allowing for the integration of social care services in Medicaid delivery. This model addresses the existing financial pressures while ensuring that care delivery is efficient and effective. By creating a social charter committed to increasing access and quality for underserved populations, stakeholders are encouraged to participate and invest in this transformative approach to healthcare.
Rajaie Batniji, MD, PhD, Afia Asamoah, JD, and Sanjay Basu, MD, PhD, cofounders of Waymark, join Vineeta Agarwala, MD, PhD, a16z Bio + Health general partner, to discuss their transformative approach to Medicaid care delivery. This episode dives into their rising risk signal prediction framework, where cutting-edge machine learning predicts patient needs and enables community-based care teams to reduce preventable ER visits and improve health outcomes at scale.
The team recently published their real-world results—including a 23% reduction in unnecessary acute care—in the New England Journal of Medicine Catalyst.