Agentic AI-Driven Data Product for Automated Healthcare Insights Generation

This study implements the Agentic AI data product development and delivery process for healthcare appointment no-show prediction with agentic AI for autonomous insights generation post-implementation. The Healthcare Appointment Dataset was obtained from Kaggle, used to predict attendance for scheduled appointments versus no-shows. Notable variables include (but are not limited to) patient age, gender, scholarship attendance, and the number of days a patient was forced to wait (after requesting an appointment) for their appointment. The prediction was thus based on attendance (or not); the model produced an applicable output from a relevant research question with 77.33% accuracy and consistently significant results predictive of practical application within healthcare settings. Moreover, agentic AI was executed to facilitate insights generation independently based on the model results without researcher-induced intervention. The fields produced by the nature of insights discovered reveal that the higher average days of waiting time for the appointment they had, coupled with the lower average age of patients, the better predictive capacity for no-show status. Thus, performance prediction modeling accompanied by agentic insights generation for results assessment increases interpretability, efficacy, and decision support capabilities within the healthcare analytics world. Furthermore, future research will be conducted with a multimodal source reinforcement learning approach to improve prediction accuracy and real-time available metrics solidifying agentic AI within predictive healthcare endeavors for real-world applicability.