Análisis de la aplicabilidad de la inteligencia artificial (IA) como asistente médico en los pacientes con apendicitis complicada en el Hospital General Liborio Panchana Sotomayor.

Abstract

Introduction: Artificial intelligence (AI) has evolved to become the most modern and innovative technological tool of the 21st century. In health services, it could optimize and streamline processes, increase diagnostic accuracy, help in decision-making, and predict risks. Currently, software based on artificial intelligence has been developed for the study of oncological, ophthalmological, and radiological pathologies. Objective: To evaluate the applicability of an artificial intelligence (AI) algorithm in the diagnosis of complicated appendicitis at the Liborio Panchana Sotomayor General Hospital. Methodology: this is an applicative, retrospective, and cross-sectional study. ChatGPT PLUS software was used with predetermined templates. Results: The positive predictive value is 87.5%. The negative predictive value is 94.11%. The degree of agreement between artificial intelligence and traditional diagnosis is 0.54. The discrepancy between false negatives and false positives has multiple causes. No differences were observed in the decision-making of artificial intelligence vs. traditional diagnosis. Conclusion: Artificial intelligence can be considered as an applicable and complementary tool to traditional diagnosis in the emergency area.