Master’s Degree Awarded to Ms. Sawsan Mohammed Al-Sharasi in Computer Science

Ms. Sawsan Mohammed Shoaib Ali Al-Sharasi was awarded a Master’s Degree in Computer Science with an average of Excellent and a grade of (95) for her thesis titled: An Intelligent Model for Early Prediction of Polycystic Ovary Syndrome, which was submitted to the Department of Computer Science, Faculty of Computer and Information Technology – Sana’a University. The MA defense was held on Tuesday, February 17, 2026.

The MA Viva-voce Committee, which was formed based on a resolution issued by the Graduate Studies and Scientific Research Council, consisted of the following:
# Committee Members Designation Position
1 Prof. Malek Nasser Al-Jabri ‎ Internal Examiner Chair
2 Prof. Ghaleb Hamoud Al-Jaafari ‎ ‎ Main Supervisor Member
3 Associate Prof. Ayed Abdulaziz Mohsen ‎ External Examiner Member
The thesis aimed to:
• Develop a robust and intelligent diagnostic model based on artificial intelligence and ‎bioinformatics techniques, combining deep learning and machine learning to diagnose ‎Polycystic Ovary Syndrome (PCOS) in its early stages. The model analyzes ultrasound ‎images alongside patients’ clinical data.‎
The study focused on improving diagnostic accuracy and reducing reliance on human ‎expertise, particularly in resource-limited settings.‎
The study yielded several key findings summarized as follows:
• The use of Stacking Ensemble learning models in analyzing clinical data, along with ‎an object detection model for ultrasound image analysis, achieved high predictive ‎accuracy, improved sensitivity, and reduced missed cases.‎
• Addressing data imbalance and selecting the most influential features played a crucial ‎role in enhancing model efficiency and generalization capability.‎
• The study emphasized the importance of Explainable AI (XAI). Using SHAP ‎analysis, the model was able to clarify the contribution of each clinical variable to ‎the final decision, thereby increasing medical trust in the system’s outputs and ‎positioning it as a transparent decision-support tool rather than a “black box.”‎
In light of these findings, the researcher recommended the following:
• Adopting AI-based clinical decision support systems in healthcare institutions and ‎gradually integrating them with electronic medical record systems.‎
• Developing APIs to connect intelligent models with hospital systems without ‎requiring major changes to existing technical infrastructure.‎
• Expanding local medical databases through enhanced collaboration between hospitals ‎and radiology centers to improve model performance and generalizability.‎
• Establishing continuous training programs for physicians and technicians on using AI ‎systems as decision-support tools rather than substitutes for clinical evaluation.‎
• Supporting multi-center research and broader clinical trials to ensure readiness for ‎practical implementation.‎
The thesis concluded that integrating medical expertise with intelligent technologies represents a strategic step toward developing a more accurate and efficient diagnostic system, contributing to improved healthcare quality, reduced human error, and faster medical decision-making.
The defense session was attended by academics, researchers, students, interested individuals, colleagues, and the researcher’s family.