Detail-oriented IT Engineering student skilled in Python and SQL. Eager to leverage analytical thinking and problem-solving abilities to contribute to innovative projects.
PCOD Detection Using Machine Learning, Developed a predictive model to assist in early detection of Polycystic Ovarian Disease (PCOD) using patient health data and machine learning techniques., 05/2025, Data Handling: Preprocessed clinical datasets including features like BMI, insulin levels, menstrual cycle irregularities, and hormonal indicators., Model Development: Implemented classification algorithms such as Random Forest, SVM, and Logistic Regression to identify PCOD risk patterns., Performance Optimization: Tuned hyperparameters and evaluated models using accuracy, precision, recall, and F1-score to ensure reliable predictions., Validation: Used cross-validation and confusion matrix analysis to assess model robustness and minimize false positives., Impact: Demonstrated potential for aiding healthcare professionals in non-invasive, data-driven PCOD screening.