How to Responsibly Use AI in Palliative Care and Hematologic Malignancies

In a conversation with CancerNetwork®, Ram Prakash Thirugnanasambandam, MBBS, discussed the evolving roles that artificial intelligence (AI)–based tools may play in palliative care and the management of different hematologic malignancies. He spoke in the context of a publication he authored, The Role of Artificial Intelligence in Palliative Oncology: Zeroing in on Hematologic Malignancies,which was featured in the November/December 2025 issue of the journal ONCOLOGY^®.

Thirugnanasambandam, a fellow of Internal Medicine, Hospice and Palliative Medicine, and Geriatric Medicine at the University of Miami, outlined the paper’s aim to explore how AI can assist with patient-centric goals of care like symptom management as well as decision-making support among clinicians. In the context of palliative medicine, AI has demonstrated utility as a supportive tool that can help with marking patients who may benefit from a palliative care conversation. Such tools have also assisted with identifying symptoms such as pain, dyspnea, anxiety, or psychosocial distress, allowing providers to form a more proactive approach to patient care.

According to Thirugnanasambandam, implementing AI into one’s workflow may help accurately predict disease subtypes and burdens among patients with leukemia, lymphoma, or multiple myeloma. He noted that predictive analytic capabilities may also facilitate effective management of cytopenias, transplant-related needs, infections, and other treatment-related toxicities.

Thirugnanasambandam also discussed some of the ethical considerations surrounding the growth of AI-based tools, highlighting information privacy concerns and potentially biased datasets as notable issues with these platforms. Although AI may assist with decision-making, Thirugnanasambandam stated that it ultimately cannot replace a human’s nuanced clinical judgment and empathy.

“I want readers to take away a sense of balance,” Thirugnanasambandam said regarding his publication. “We’ve done the article to help clinicians be more comfortable in engaging with AI. We need to apply it critically, not as replacing judgment or decision-making skills, but more as an adjunct.”