Public hospitals in India face significant challenges with long patient wait times, particularly due to disorganized referral systems. Many patients approaching these hospitals come from underserved backgrounds or have limited health literacy and often struggle to identify the appropriate type of doctor for their specific health issues. As many public hospitals in India lack a structured first point of contact or General Practitioner (GP) system, this confusion contributes to unnecessary delays and increased wait times. To address this issue, the study introduces MediNav, an AI-powered tool designed to evaluate patient symptoms and guide them to the right type of doctor for consultation. By doing so, MediNav enhances patient flow and minimizes unnecessary delays, particularly benefiting those who may not know how to navigate the healthcare system. The AI model, developed using XGBoost on symptom–specialty data, achieved an overall accuracy of 85.58% in live primary healthcare (PHC) settings. Through a comparative assessment of wait times, MediNav has the potential to reduce patient waiting time stemming from misreferrals or department transfers by an average of 39.4 minutes per individual in public Indian hospitals. In the absence of a GP or structured referral layer, such inefficiencies are common in India’s public hospitals. With typical patient volumes of 500 or more per day, this translates to over 328 clinical hours saved daily. This significant reduction can enhance clinical efficiency within strained public health systems, ultimately improving access to care for all patients, especially those with limited understanding of the healthcare process.