ESTRO 2024 - Abstract Book

S2932

Interdiscplinary - Other

ESTRO 2024

Purpose/Objective:

Artificial Intelligence (AI) holds transformative potential in the realm of cancer care, yet its use in clinical practice is limited. As healthcare providers strive to enhance patient care, understanding patients' attitudes towards AI is crucial for the adoption of AI tools in clinical settings. Notably, few studies have explored patients' perspectives on AI and the synergy with medical doctors. This study investigates the perspectives of cancer patients on the use of AI in medical decision-making.

Material/Methods:

This study delves into the patient perspective on AI through 12 semi-structured interviews with breast cancer survivors recruited via the Dutch Breast Cancer Association (BVN).

The interviews covered a range of subjects, including treatment recommendations, side effect prediction, survival, and recurrence. Following transcription, the interviews were analyzed using thematic content analysis to identify recurring themes and extract relevant quotes associated with each theme. The analysis categorized patient responses into three primary domains: familiarity with AI, AI's application across different outcome-related scenarios, and a comparative evaluation of AI versus medical doctors.

Results:

Patients exhibited varying degrees of familiarity with AI, largely associated with demographic factors, with younger and more educated patients exhibiting a better grasp of AI.

Generally, patients displayed a positive disposition towards AI when employed in less critical contexts such as side effects and treatment recommendations.

However, for more high-stakes scenarios, like survival and recurrence prediction post-treatment, patients hesitated to place their trust in AI. Trust emerged as a critical determinant affecting their willingness to embrace AI for decision making. Most patients expressed a preference for using AI when coupled with the opportunity to consult with a medical doctor.

Despite acknowledging the human fallibility of medical doctors and their potential for error, patients tended to place greater trust in them compared to AI.

Patients' reluctance to adopt AI also stemmed from their belief that AI couldn't account for individuals’ unique circumstances, making it more suitable for general population-sized predictions rather than individual predictions.

Conclusion:

This qualitative study sheds light on the perceptions of former breast cancer patients in the Netherlands regarding the use of AI in medical decision-making. The findings suggest that patients are generally receptive to the idea of utilizing AI-based programs to aid in decision-making, but have reservations about their use in high-stakes situations like survival and recurrence predictions. This study underscores the significance of increasing awareness and understanding of AI's potential in personalized medicine. The exploration of a service delivery model in which communication is combined with collaborative efforts between healthcare providers,