Clinical impact of Gynaecological Prediction models on decision making of both patients and doctors: A Prospective survey study

Background: Clinical prediction models are increasingly used to assist well-informed decisions about patient treatment, thereby facilitating the shared decision-making process. However, it remains unclear in how far doctors and patients will use these predicted percentages, and if thresholds for these individualised failure rates differ within and between these groups. Objective: This study investigated how the outcomes of a gynaecological prediction model impact the clinical decision-making process for both patients and professionals. Design: A prospective multicentre survey study with data collection between 1st of February 2019 and 1st of August 2020. Dutch-speaking female patients (age 18-75 years) visiting the gynaecology outpatient department, and physicians involved in benign gynaecology were asked to participate. Interventions: Both patients and professionals gave their baseline treatment preference (Endometrial ablation (EA) or Uterus Extirpation (UE)) after being presented a general known literature-based failure percentage of EA (15%) in a fictive case. Subsequently, their treatment preference was asked again after knowing a personal failure rate generated by a prediction model (61%). Results: Patients and professionals significantly changed their choice from EA to UE in respectively 48.3 % and 48.9 % (p < 0.001). The average acceptable failure rate for EA showed no significant difference between patients (56.7%) versus professionals (53.6%) (p = 0.145). Motives for choice of treatment seemed to differ between patients and professionals, underscoring the importance of considering these differences in the decision-making process. Conclusion: A personalised clinical prediction model can influence treatment choice compared to counselling based on general information. The additional information, provided by such a model contributes to improved counselling and optimises shared decision-making, potentially enhancing overall satisfaction.