A novel computer based expert decision making model for prostate cancer disease management

Area of Science:

• Urology
• Medical Informatics
• Decision Science

Background:

• Prostate cancer treatment decisions are complex, involving multiple factors and potential biases.
• Effective decision-making models are needed to support physician-patient collaboration.

Purpose of the Study:

• To develop and validate a computer-based decision-making model for prostate cancer management using the analytic hierarchy process.
• To improve the rationality and evidence-based nature of treatment selection.

Main Methods:

• A computer model was developed using the analytic hierarchy process for prostate cancer treatment selection.
• Patient and physician groups performed pairwise comparisons to prioritize objectives and rank treatment options.
• Inconsistency ratio and sensitivity analyses were used to evaluate the model's reliability and the influence of objectives.

Main Results:

• The model reliably generated mathematically rational judgments (inconsistency ratios < 0.05).
• Patient and physician groups prioritized cure, survival, and quality of life over other factors, showing similar rank orders.
• Concordance between initial choices and model recommendations differed (59% for patients, 42% for physicians).

Conclusions:

• The computer-based model effectively supports individualized, rational, and clinically appropriate prostate cancer management decisions.
• The model demonstrated usefulness in achieving objective-driven treatment selection without physician bias.