Artificial intelligence (AI) based diagnostic prediction models are able to predict the likelihood of a disease based on routine healthcare data and may support general practitioners (GPs) in the diagnostic process. However, the development of such models into fit-for-practice- tools does generally not involve GPs. It is therefore unclear how GPs asses such an AI based prediction tool.To explore the impact of an AI based diagnostic prediction tool on 1) the diagnostic decision making; and 2) the experiences of GPs and GPs in training with regard to its usefulness and reliability.This study has two parts. The first part consists of interviews with a panel of GPs and GPs in training to map the needs and preferred functionalities of the tool. Vignettes have been created based on the results of the interviews and real patient consultation data. These vignettes show consultations of individual patients, either with or without the use of a diagnostic prediction tool. This tool presents a differential diagnosis considering patient variables such as age, sex and reason for encounter. In the second part of the study, we test the clinical vignettes on GPs and GPs in training. The impact of the tool on the diagnostic decision-making process and the usability (from the System Usability Scale) and reliability is explored. Descriptive statistics will be used to describe the results.Data collection and vignette development are ongoing. Findings of both parts of the study will be available by the time of presentation.Using an AI based diagnostic prediction tool during consultation might result in less diagnostic testing, especially for less experienced doctors. In-depth interviews will be needed to further explore the results of this study. Furthermore, research in a real-time setting is needed.This study will provide insights into whether an AI-based diagnostic prediction tool can support GPs and GPs in training by influencing diagnostic decision-making and whether it is perceived as usable and trustworthy in clinical practice.