JMIR Publications

ABSTRACT

Prognostic models in medicine have garnered significant attention, with established guidelines governing their development. However, there remains a lack of clarity regarding the appropriate circumstances for designing and implementing tools based on models with limited performance. This commentary addresses this gap by analyzing the pros and cons of implementation and a structured outline that includes critical questions to consider in the decision-making process, on an example for patients with osteoarthritis. We propose three critical justifications for implementation: (1) mitigating expectation bias among patients and clinicians, (2) advancing personalized medicine, and (3) enhancing existing predictive information sources. Nevertheless, it is crucial to acknowledge that implementing such models may harm certain patients, necessitating careful consideration of withdrawal in specific cases. To facilitate the identification of these scenarios, we delineate all 16 potential possibilities following the implementation of a personalized prognostic model for our example. Our analysis encompasses the possible patient benefits and harms resulting from implementing and not implementing personalized prognostic models. We suggest a guideline allowing researchers to weigh the benefits and harms of introducing a personalized prognostic model against those of the alternative in a structured and standardized manner. This protocol is designed to aid researchers in their decision-making process on providing a personalized prognostic tool and implementing it or not. This work serves as a foundation for further discourse and refinement of implementation decisions for prognostic models in healthcare.