Design and Development of an Intelligent Clinical Decision Support System Applied to the Evaluation of Breast Cancer...

Area of Science:

• Oncology
• Medical Informatics
• Artificial Intelligence in Healthcare

Background:

• Breast cancer remains a leading cause of death in women, posing diagnostic challenges despite advancements like mammography.
• Current diagnostic methods can suffer from interpretation variability, impacting accuracy and patient outcomes.

Purpose of the Study:

• To design and develop an intelligent clinical decision support system for the preventive diagnosis of breast cancer.
• To enhance diagnostic accuracy and reduce uncertainty in breast cancer evaluation.

Main Methods:

• Integration of Mamdani-type fuzzy logic expert systems in cascade.
• Application of exploratory factorial analysis and data augmentation techniques.
• Utilization of k-neighbors and bagged trees classification algorithms for medical data interpretation.

Main Results:

• The system achieved high success rates in diagnosing breast cancer.
• Areas under the ROC curves ranged from 0.95 to 0.97, indicating strong diagnostic performance.
• The system demonstrated significant diagnostic and preventive potential in initial tests.

Conclusions:

• The developed intelligent system shows promise for improving breast cancer diagnosis and prevention.
• The system's ability to interpret patient data and generate risk alerts highlights its clinical relevance.
• Further validation is pending, but the system is poised for applicability in the clinical field.