JMIR Publications

ABSTRACT

Background Shared decision making (SDM) is increasingly important in health policy and clinical practice. Although the application of SDM prior to kidney transplantation has been discussed, little is known about how to improve SDM post-transplant. Choosing the right kidney replacement therapy after graft loss is among the most common preference-sensitive decisions in patients after kidney transplantation. However, the rate of conversations about treatment options after kidney graft loss are as low as 13% leaving room for optimization with respect to the frequency of conversations as well as the associated shared decision making process. It is unknown whether and how the implementation of Artificial Intelligence (AI)-based risk prediction models can influence this process. Methods This 2-year, prospective, randomized, 2-armed, parallel group, single-center trial in a German kidney transplant center aims to explore the impact of an AI-based risk prediction for the risk of graft loss on the frequency of conversations about the treatment options after graft loss, as well the associated shared decision making process. All patients will receive the same routine post-kidney transplant care. For patients in the interventional arm, physicians will be assisted by a validated and previously published AI-based risk prediction system that estimates the risk for graft loss in the next year. The study population will consist of 122 KTR, who are at least 18 years old, are able to communicate in German, and have an eGFR < 30 ml/min/1.73m2. Patients with multi-organ transplantation, or who are not able to communicate in German, as well as underage patients cannot participate. For the primary endpoint, the proportion of patients, who have had a conversation about their treatment options after graft loss is compared at 12 months after randomization. Additionally, two different assessment tools for shared decision making, the CollaboRATE mean score, and the Control Preference Scale are compared between the two groups at 12 months and 24 months after randomization. Discussion The findings will help support the further development and use of AI-based risk prediction models in kidney transplantation and provide currently lacking evidence on the impact of AI-assisted decision support on physician-patient communication. Trial registration United Stated Clinical Trial Registry ClinicalTrials.gov (registration# NCT06056518; Protocol version 1.0, September 12th, 2023).