Your browser doesn't support javascript.
loading
Artificial Intelligence in Urology: Application of a Machine Learning Model to Predict the Risk of Urolithiasis in a General Population.
Sánchez, Catherine; Larenas, Francisca; Arroyave, Juan Sebastián; Connors, Christopher; Giménez, Belén; Palese, Michael A; Fulla, Juan.
Afiliación
  • Sánchez C; Clínica MEDS, Santiago, Chile.
  • Larenas F; Faculty of Medicine, University of Chile, Santiago, Chile.
  • Arroyave JS; Faculty of Medicine, University of Chile, Santiago, Chile.
  • Connors C; Department of Urology, Hospital Clínico San Borja Arriarán, Santiago, Chile.
  • Giménez B; Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
  • Palese MA; Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
  • Fulla J; Faculty of Medicine, University of Chile, Santiago, Chile.
J Endourol ; 38(8): 712-718, 2024 Aug.
Article en En | MEDLINE | ID: mdl-38874940
ABSTRACT
This research presents our application of artificial intelligence (AI) in predicting urolithiasis risk. Previous applications, including AI for stone disease, have focused on stone composition and aiding diagnostic imaging. AI applications centered around patient-specific characteristics, lifestyle considerations, and diet have been limited. Our study comprised a robust sample size of 976 Chilean participants, with meticulously analyzed demographic, lifestyle, and health data through a comprehensive questionnaire. We developed a predictive model using various classifiers, including logistic regression, decision trees, random forests, and extra trees, reaching high accuracy (88%) in identifying individuals at risk of kidney stone formation. Key protective factors highlighted by the algorithm include the pivotal role of hydration, physical activity, and dietary patterns that played a crucial role, emphasizing the protective nature of higher fruit and vegetable intake, balanced dairy consumption, and the nuanced impact of specific protein sources on kidney stone risk. In contrast, identified risk factors encompassed gender disparities with males found to be 2.31 times more likely to develop kidney stones than females. Thirst and self-perceived dark urine color emerged as strong predictors, with a significant increase in the likelihood of stone formation. The development of predictive tools with AI, in urolithiasis management signifies a paradigm shift toward more precise and personalized health care. The algorithm's ability to process extensive datasets, including dietary habits, heralds a new era of data-driven medical practice. This research underscores the transformative impact of AI in medical diagnostics and prevention, paving the way for a future where health care interventions are not only more effective but also tailored to individual patient needs. In this case, AI is an important tool that can help patients stay healthy, prevent diseases, and make informed decisions about their overall well-being.
Asunto(s)
Palabras clave

Texto completo: 1 Banco de datos: MEDLINE Asunto principal: Inteligencia Artificial / Urolitiasis / Aprendizaje Automático Límite: Adult / Aged / Female / Humans / Male / Middle aged Idioma: En Revista: J Endourol Asunto de la revista: UROLOGIA Año: 2024 Tipo del documento: Article País de afiliación: Chile

Texto completo: 1 Banco de datos: MEDLINE Asunto principal: Inteligencia Artificial / Urolitiasis / Aprendizaje Automático Límite: Adult / Aged / Female / Humans / Male / Middle aged Idioma: En Revista: J Endourol Asunto de la revista: UROLOGIA Año: 2024 Tipo del documento: Article País de afiliación: Chile