"I Wish There Were an AI": Challenges and AI Potential in Cancer Patient-Provider Communication

TL;DR

This paper investigates the challenges of patient-provider communication after cancer treatments and examines how AI, particularly large language models (LLMs), could support communication in high-stakes, uncertain post-treatment contexts. Using semi-structured interviews with six healthcare providers and eight cancer patients, the authors identify knowledge and timing gaps, emotional needs, and collaboration barriers that hinder effective asynchronous communication. They articulate an AI-enhanced communication paradigm comprising patient-facing conversational agents, provider workflow support, and cross-provider collaboration, along with design implications such as explainability, reliable domain knowledge, and human-in-the-loop safeguards. The study highlights potential benefits of AI to explain instructions, reflect on symptoms, and coordinate care while cautioning about trust, privacy, and resource implications, thereby guiding responsible development of AI tools for post-treatment cancer care.

Abstract

Patient-provider communication has been crucial to cancer patients' survival after their cancer treatments. However, the research community and patients themselves often overlook the communication challenges after cancer treatments as they are overshadowed by the severity of the patient's illness and the variety and rarity of the cancer disease itself. Meanwhile, the recent technical advances in AI, especially in Large Language Models (LLMs) with versatile natural language interpretation and generation ability, demonstrate great potential to support communication in complex real-world medical situations. By interviewing six healthcare providers and eight cancer patients, our goal is to explore the providers' and patients' communication barriers in the post-cancer treatment recovery period, their expectations for future communication technologies, and the potential of AI technologies in this context. Our findings reveal several challenges in current patient-provider communication, including the knowledge and timing gaps between cancer patients and providers, their collaboration obstacles, and resource limitations. Moreover, based on providers' and patients' needs and expectations, we summarize a set of design implications for intelligent communication systems, especially with the power of LLMs. Our work sheds light on the design of future AI-powered systems for patient-provider communication under high-stake and high-uncertainty situations.

Figures (2)

• Figure 1: An example of Current Patient-Provider Communication Practice in Post-Treatment Cancer Care. After patients are discharged from the hospital, the healthcare provider may follow up via phone calls to check patients' conditions in two to three weeks. If patients have any discomfort, they can also reach out to providers. The key provider can respond remotely or readmit the patient for any abnormalities. Many patients have long-term follow-up visits to get lab tests.
• Figure 2: Overview of the AI-Enhanced Communication Paradigm for Post-Treatment Cancer Care. 1. For the cancer patient, AI could interact through user interfaces such as CAs or wearables to provide explanation and mental support using domain knowledge and collect personal health information. 2. For the key cancer care provider, AI could assist with processing information to communicate patient symptoms 3. AI manages collaborative post-treatment cancer care by augmenting medical information and navigating the patient through the healthcare network 4. Direct patient-provider communication remains crucial, empowered by AI