As part of the graduation requirements at the Department of Systems Engineering, student Ayad Qasim has developed a cutting-edge project that demonstrates the powerful intersection of healthcare and artificial intelligence. Supervised by Assistant Lecturer Elaf Ahmed, the project focuses on utilizing AI-driven techniques to support early detection of lung cancer through medical data analysis.

Project Overview

Lung cancer remains one of the leading causes of cancer-related deaths worldwide, and early detection plays a critical role in improving patient outcomes. Ayad’s project aims to address this challenge by designing an AI-based system capable of predicting lung cancer from clinical data.

By analyzing key patient features and applying advanced machine learning models, the project proposes a non-invasive, data-driven approach for assisting medical professionals in diagnosing lung cancer at an early stage. The problem was approached as a binary classification task—determining whether or not a patient is likely to have lung cancer based on specific input data.

Techniques and Tools

To build the prediction model, the project employed a range of popular and effective machine learning algorithms, including:

Random Forest (RF)

Gradient Boosting (GB)

Decision Tree (DT)

Support Vector Machine (SVM)

k-Nearest Neighbors (KNN)

These models were trained and tested on medical datasets to identify patterns and features strongly associated with lung cancer cases.

Project Results

The performance of each algorithm was evaluated based on accuracy. The Random Forest model outperformed the rest, achieving an impressive 98.92% accuracy in lung cancer prediction. The comparative results were as follows:

Random Forest: 98.92%

Gradient Boosting: 97.8%

Decision Tree: 96.875%

Support Vector Machine: 96.875%

k-Nearest Neighbors: 96.8675%

These high accuracy rates demonstrate the potential of machine learning in supporting medical diagnostics.

Conclusion

Ayad Qasim’s graduation project highlights the growing role of artificial intelligence in revolutionizing the healthcare sector. By developing a system capable of early and accurate lung cancer detection, the project contributes to improving diagnostic practices and increasing patient survival rates.

This achievement reflects the Department of Systems Engineering ongoing commitment to fostering research that addresses real-world problems and creates impactful, technology-driven solutions.