Intelligent Patient Appointment Schedules

Background: Hospital appointment systems suffer from extended patient waits, manual interventions, and suboptimal resource allocation, reducing satisfaction and efficiency. Methods: This study develops IPAS using Business Process Analysis (BPA), Bizagi modeling for As-Is/To-Be workflows, SWOT analysis, TQM, and Six Sigma DMAIC. It integrates ML/NLP with BioBERT-BiLSTM triage (AUC 0.92, F1 0.87) for symptom analysis, specialist matching, and automated booking, validated via Bizagi simulations. Results: Simulations show booking time was reduced 96.3% (155 to 5.73 min) and human intervention was cut 70%, with enhanced patient satisfaction and process capability. Conclusions: IPAS demonstrates simulation-based gains in scheduling efficiency, pending real-world validation.