Mayo Clinic and Bayesian Health have partnered to develop an artificial intelligence solution designed to identify hospitalized patients who may benefit from palliative care earlier in their inpatient stay. The platform integrates directly into electronic health record workflows and aims to address gaps in serious illness management that often delay supportive care interventions.
The collaboration was developed through Mayo Clinic’s Practice Transformation Ventures (PTV) framework, with the Department of Medicine in Rochester serving as the primary clinical validator and practice owner. The AI-driven platform continuously analyzes patient records in real time to detect indicators of unmet palliative care needs, including complex symptom burdens, declining health trajectories, and caregiver distress.
According to the organizations, the technology was created to address longstanding challenges in inpatient care coordination. While approximately one-third of hospital readmissions involve patients with serious illnesses, fewer than half of eligible patients receive a formal palliative care consultation during hospitalization.
Clinical validation data from a randomized trial conducted internally by Mayo Clinic demonstrated measurable improvements associated with an earlier version of the platform. Findings showed:
A 44% increase in timely palliative care referrals
A 25% reduction in 60-day hospital readmissions
A 28% reduction in 90-day hospital readmissions
The companies stated that the platform evaluates longitudinal patient data rather than isolated laboratory values or vital signs. By comparing subtle changes against a patient’s baseline condition, the system generates patient-specific signals for both bedside clinicians and specialized palliative care teams.
Jacob J. Strand, M.D., chair of Palliative Care at Mayo Clinic, emphasized that the true barrier to effective palliative medicine has never been defining a care plan, but discovering the underlying patient need early enough to alter the course of clinical care. By delivering tailored, patient-specific signals to bedside and central teams alike, the technology successfully cuts through inpatient complexity to hardwire consistent decision-making.
The platform includes a hospital-wide operational dashboard for palliative consultation teams and provides frontline clinicians with integrated guidance directly within existing EHR workflows. The system is designed to streamline consultation requests while reducing notification fatigue.
Bayesian Health noted that the AI models operate on a continuous learning framework, incorporating clinician feedback and local patient population trends to refine predictive accuracy over time.
Anthropic & Bristol Myers Squibb enterprise AI expansion; HealthEx & 23andMe genomic-medical record integration; Mayo Clinic & Bayesian Health AI-powered palliative care platform
Click here for the original news story.
