“Our final goal is to shift from an episodic care to continuous patient follow-up, allowing us to better understand and manage the evolution of patients over the time,” says Juan Fulla, MD, MSc.
In this interview, Juan Fulla, MD, MSc, shares key takeaways and future work based on the study, “Artificial Intelligence in Urology: Application of a Machine Learning Model to Predict the Risk of Urolithiasis in a General Population,” for which he served as the senior author. Fulla is the chief of the robotic program and an associate professor of urology at the University of Chile in Santiago, Chile.
Video Transcript:
What are the implications of a shift toward more precise and personalized kidney stone care?
This paradigm shift has profound implications for both patients and for urologists. For patients, the use of AI-based predictive tools means receiving more precise and personalized recommendations to prevent kidney stone formation. This includes advice on hydration, diet, and lifestyle, tailored specifically to their individual needs, which can significantly reduce the risk of a stone recurrence. On the other hand, for us, for urologists, these tools represent an opportunity to enhance the efficiency and also the effectiveness of our clinical practice. Can you imagine the ability to process large datasets and derive actionable insights [to] allow urologists to make more informed decisions and provide more patient-centered care? Integrating these predictive models into our daily clinical practice can facilitate long-term patient monitoring and early intervention, improving health outcomes and reducing health care costs.
What future work is planned based on this study?
Our study has laid the groundwork for several future research initiatives. We plan to expand our research to a larger and more diverse population to validate and refine our predictive models. We're also interested in exploring how the integration of the laboratory tests such as blood work and 24[-hour] urine analysis can also further enhance the accuracy of our predictions. We're developing a clinical application that can be used by urologists in their clinical practice. We believe that this application will not only facilitate the use of our predictive models, but also provide a platform for continuous monitoring and early intervention. Our final goal is to shift from an episodic care to continuous patient follow-up, allowing us to better understand and manage the evolution of patients over the time. For this, we're collaborating with software developers and other AI experts to ensure that this tool is intuitive and also user friendly for both, for physicians and especially for patients. And finally, our goal is to transform the way that urolithiasis is managed and prevented, providing more effective and personalized care.
This transcription has been edited for clarity.