Automatic Surgery and Anesthesia Emergence Duration Prediction Using Artificial Neural Networks

Area of Science:

• Healthcare Management
• Artificial Intelligence in Medicine
• Operations Research

Background:

• Hospital operating rooms are resource-intensive, making their optimal utilization critical for cost control.
• Unpredictable surgery and anesthesia emergence durations complicate efficient operating room scheduling.
• Accurate duration prediction is essential for effective hospital resource management and cost savings.

Purpose of the Study:

• To develop an artificial neural network (ANN) system for predicting surgery and anesthesia emergence durations.
• To enhance operating room (OR) scheduling accuracy and improve hospital resource allocation.
• To introduce an intelligent data preprocessing algorithm for optimizing predictive model training.

Main Methods:

• Utilized an artificial neural network to build a predictive model for surgery and anesthesia emergence times.
• Implemented an intelligent data preprocessing algorithm for automatic dataset balancing and enhancement.
• Evaluated the performance of a serial prediction system against separate prediction models.

Main Results:

• The proposed artificial neural network system demonstrated acceptable prediction accuracies for surgery and anesthesia emergence durations.
• The intelligent data preprocessing algorithm effectively enhanced the training dataset.
• The serial prediction system showed comparable or improved accuracy compared to separate prediction models.

Conclusions:

• The developed ANN-based prediction system offers a viable solution for improving operating room scheduling.
• Accurate duration prediction can lead to significant resource savings in hospital management.
• The intelligent data preprocessing method is crucial for the performance of predictive models in healthcare settings.