“…3 Leveraging ML algorithms within EHRs offer promising opportunities to address the challenges in PC referral triggers, which could include diagnosis of life-limiting or terminal illnesses (e.g., advanced cancer, end-stage heart failure), severe and progressive symptoms (e.g., uncontrolled pain, dyspnea), frequent hospitalizations and readmissions, decline in functional status and quality of life, and limited response to curative treatments. [4][5][6][7][8] Some potential benefits include early identification and intervention by analyzing patient data available in EHRs, objective and standardized referral criteria, enhanced accuracy and efficiency, and personalized care planning as ML models can consider a wide range of patient characteristics, such as medical history, comorbidities, and PC needs assessment like physical assessment of symptoms (pain, nausea, fatigue), psychosocial assessment (emotional distress, spiritual concerns), discussion of patient's goals, values, and preferences, and assessment of family and caregiver needs to develop personalized care plans. 2,9 Clinical Use Case Design…”