Surgical Duration Estimation via Data Mining and Predictive Modeling: A Case Study.

Area of Science:

• Healthcare Management
• Operations Research
• Medical Informatics

Background:

• Operating rooms (ORs) are critical, high-cost hospital resources requiring optimal utilization.
• Accurate surgery duration prediction is essential for efficient OR scheduling and management.
• Traditional methods like adjusted system prediction (ASP) have limitations in accuracy and adaptability.

Purpose of the Study:

• To develop and demonstrate a novel hybrid method for predicting surgery durations.
• To overcome challenges associated with numerous procedure types and limited sample sizes.
• To avoid restrictive distributional assumptions in duration prediction models.

Main Methods:

• Development of a hybrid prediction model combining different analytical techniques.
• Application of the developed method in a case study for validation.
• Comparison with traditional and existing advanced prediction methods.

Main Results:

• The hybrid method demonstrated improved accuracy in surgery duration prediction compared to traditional approaches.
• The model effectively handled a wide variety of surgical procedures.
• The case study confirmed the practical applicability and benefits of the proposed method.

Conclusions:

• The developed hybrid method offers a more robust and adaptable solution for surgery duration prediction.
• Enhanced prediction accuracy can lead to better operating room utilization and efficiency.
• This approach provides a valuable tool for OR managers seeking to optimize resource allocation.