This study leverages algorithm-based triggers to increase early outpatient palliative care referrals for patients with advanced cancer.
We apply the latest science to create, test, and scale solutions to address the most intractable problems in cancer care delivery.
We integrate augmented and artificial intelligence into our solutions to predict health outcomes, support decision making, challenge bias, and enhance health equity.
Based on an identified critical need to increase the frequency and improve the timeliness of serious illness conversations (SICs), we are testing behavioral economics-informed multilevel implementation strategies for early SICs, with health equity as a driving force.
Examining Racial Bias in Predictive Analytic Tools to More Equitably Distribute Care to At-Risk Veterans
Resource allocation in the VA is guided by tools such as the VA CAN score, but studies have shown that these tools may result in under-representation of those most at risk. This project examines inequity resulting from such algorithms and examines the impact of factoring in metrics such as race and social determinants of health.
Connected Health Approaches to Improve Serious Illness Communication Among Patients with Incurable Cancer
Providing clinicians with patient-reported symptoms and remotely-monitored functional status will help clinicians better identify palliative care needs and increase rates of documented Serious Illness Conversations.
Implementation Strategies for Monitoring Adherence in Real Time (iSMART) for Oral Anticancer Therapies
By combining innovations from behavioral economics and machine learning with highly accessible text-messaging platforms, this initiative has the potential not only to identify scalable, patient-targeted strategies for improving adherence to oral therapies, but also to transform the way cancer care is delivered and implemented.