About me
I'm a passionate software engineer with a focus on AI-driven solutions that connect cutting-edge technology to real-world needs. My work on MediSense—an AI-powered healthcare platform leveraging machine learning for predictive diagnostics—showcases my ability to turn complex algorithms into impactful, life-improving applications.
My expertise spans AI development, Flutter applications, and full-stack systems. I’ve developed intelligent solutions like a disease prediction model with 98.7% accuracy, trained on real clinical data to forecast potential diagnoses based on patient symptoms. I’ve also implemented federated learning to ensure data privacy, and delivered cross-platform apps with localized UX for Arabic-speaking markets. I'm particularly driven by the power of predictive analytics in transforming healthcare through early intervention.
Beyond development, I excel at bridging communication gaps between technical teams and non-technical stakeholders. At Bitlogicx, I’ve helped align Arabic-speaking clients with development teams to ensure clarity, efficiency, and user-centered design. My work combines technical precision with an intuitive, human-focused approach.
What I'm doing
-
AI & Machine Learning
Building intelligent systems like disease prediction models and computer vision solutions, combining accuracy with real-world impact.
-
Web Development
Developing scalable and secure full-stack web applications with clean architecture and modern frameworks.
-
Mobile Applications
Creating cross-platform Flutter apps with optimized performance and localized UX for Arabic-speaking users.
-
Business Development
Identifying growth opportunities, building client relationships, and aligning technical solutions with business goals to drive sustainable success.
Testimonials
-
Ali Khaled
Osamah's CardioRiskAI predicted cardiovascular disease with 77% accuracy using 70,000 patient records. His machine learning implementation delivered clinically explainable results that surpassed my requirements.
-
MediSense Partner
Osamah's ensemble modeling in our healthcare research achieved 92% diagnostic accuracy. His innovative combination of Random Forest, Gradient Boosting, and Naive Bayes classifiers outperformed all single-model approaches we tested. The UMLS symptom encoding provided remarkable consistency across 41 disease classes, and his attention to model interpretability won over our skeptical defensive panal.
