{"id":25974776,"url":"https://github.com/angchekar28/pcos-machine-learning-analysis","last_synced_at":"2026-05-19T10:03:18.929Z","repository":{"id":280109922,"uuid":"941011244","full_name":"angchekar28/PCOS-Machine-Learning-Analysis","owner":"angchekar28","description":"This project evaluates various machine learning models for diagnosing Polycystic Ovary Syndrome (PCOS) based on medical and clinical features. It compares models like Decision Tree, XGBoost, Random Forest, SVM, and Logistic Regression, analyzing their accuracy and execution time to determine the best-performing model for PCOS prediction.","archived":false,"fork":false,"pushed_at":"2025-03-01T09:15:51.000Z","size":563,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-01T10:23:15.068Z","etag":null,"topics":["classification","data-science","machine-learning","pcos-detection","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/angchekar28.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-01T09:10:41.000Z","updated_at":"2025-03-01T09:18:30.000Z","dependencies_parsed_at":"2025-03-01T10:23:17.009Z","dependency_job_id":"f8e7b328-1464-4a4b-9bc4-ea5c82b5f5cb","html_url":"https://github.com/angchekar28/PCOS-Machine-Learning-Analysis","commit_stats":null,"previous_names":["angchekar28/pcos-machine-learning-analysis"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FPCOS-Machine-Learning-Analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FPCOS-Machine-Learning-Analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FPCOS-Machine-Learning-Analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FPCOS-Machine-Learning-Analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/angchekar28","download_url":"https://codeload.github.com/angchekar28/PCOS-Machine-Learning-Analysis/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241954165,"owners_count":20048296,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["classification","data-science","machine-learning","pcos-detection","python"],"created_at":"2025-03-05T02:33:50.781Z","updated_at":"2026-05-19T10:03:13.890Z","avatar_url":"https://github.com/angchekar28.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🔍 PCOS Diagnosis: Machine Learning Model Comparison  \n\n## 📌 Overview  \nThis project evaluates various **machine learning models** for diagnosing **Polycystic Ovary Syndrome (PCOS)** based on medical and clinical features. The goal is to determine the most **accurate and efficient** model for predicting PCOS while analyzing execution time and classification metrics.  \n\n## 📊 Dataset  \nThe dataset contains medical records of individuals, including various physiological and lifestyle-related parameters that may influence PCOS diagnosis.  \n\n### Features:  \n- **Independent Variables:** Age, BMI, Insulin levels, LH/FSH ratio, Follicle count, etc.  \n- **Target Variable:** Presence or absence of PCOS (Binary: 1 = PCOS, 0 = No PCOS)  \n\n## 🛠️ Technologies Used  \n- **Python** (pandas, numpy, scikit-learn, XGBoost)  \n- **Jupyter Notebook/Kaggle/Colab**  \n- **Matplotlib \u0026 Seaborn** for visualization  \n\n## 🚀 Models Implemented  \nThe following classification models were evaluated:  \n\n1. **Random Forest**  \n2. **Logistic Regression**  \n3. **Support Vector Machine (RBF \u0026 Linear)**  \n4. **K-Nearest Neighbors**  \n5. **Decision Tree**  \n6. **XGBoost**  \n7. **Naive Bayes**  \n\n## 📈 Model Performance Comparison  \n\n| Model                         | Accuracy | Precision (Class 1) | Recall (Class 1) | F1-Score (Class 1) | Implementation Time (s) |\n|-------------------------------|----------|---------------------|------------------|-------------------|--------------------------|\n| Random Forest                 | 99.00%   | 0.99                | 0.95             | 0.97              | 0.1783                   |\n| Logistic Regression           | 88.50%   | 0.72                | 0.67             | 0.69              | 0.0059                   |\n| SVM (RBF Kernel)              | 96.00%   | 0.90                | 0.90             | 0.90              | 0.0089                   |\n| SVM (Linear Kernel)           | 89.50%   | 0.74                | 0.72             | 0.73              | 0.0100                   |\n| K-Nearest Neighbors           | 96.50%   | 0.92                | 0.90             | 0.91              | 0.0132                   |\n| Decision Tree                 | 99.50%   | 1.00                | 0.97             | 0.99              | 0.0026                   |\n| XGBoost                       | 99.50%   | 1.00                | 0.97             | 0.99              | 0.0332                   |\n| Naive Bayes                   | 69.50%   | 0.39                | 1.00             | 0.56              | 0.0019                   |\n\n## 🏆 Conclusion  \n\n### ✅ Best Model Choices:  \n1. **Decision Tree \u0026 XGBoost** – Highest accuracy (99.50%) with strong precision, recall, and F1-scores. Decision Tree was the fastest among them (0.0026s).  \n2. **Random Forest** – Excellent accuracy (99%) but had the longest execution time (0.1783s).  \n3. **SVM (RBF) \u0026 KNN** – Reliable models with **96%+ accuracy**, but KNN took slightly more time (0.0132s).  \n\n### ⚡ Performance vs. Speed:  \n- **Fastest Model:** Naive Bayes (0.0019s), but it had the lowest accuracy (69.50%).  \n- **Balanced Performance:** XGBoost and Decision Tree provide the best trade-off between accuracy and execution time.  \n\n### ❌ Weak Model Choices:  \n- **Naive Bayes** struggled significantly due to **class imbalance**, making it unsuitable.  \n- **Logistic Regression \u0026 Linear SVM** had moderate performance but **struggled with Class 1 predictions**.  \n\n### 🔥 Final Recommendation:  \nFor **high accuracy and efficiency**, **Decision Tree or XGBoost** are the best choices. If **speed is not a constraint**, **Random Forest** is also an excellent option.  \n\n## 🔧 Installation \u0026 Usage  \n\n### 1️⃣ Clone the Repository  \n```bash\ngit clone https://github.com/yourusername/PCOS-ML-Model-Comparison.git\ncd PCOS-ML-Model-Comparison\n```\n### 2️⃣ Install Dependencies\n```bash\npip install -r requirements.txt\n```\n### 3️⃣ Run the Jupyter Notebook\n```bash\njupyter notebook\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangchekar28%2Fpcos-machine-learning-analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fangchekar28%2Fpcos-machine-learning-analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangchekar28%2Fpcos-machine-learning-analysis/lists"}