This project aims to build a machine learning model to predict liver diseases based on patient data. It leverages various data preprocessing, feature engineering, and model training techniques to achieve an accurate and reliable prediction system.
- Class: 23MMT
- Student ID: 11012302891
- Mail: [email protected]
- Class: 23HTDL
- Student ID: 74802302851
- Mail: [email protected]
The Saigon International University (SIU)
- Data Cleaning: Handling missing values and removing outliers.
- Exploratory Data Analysis: Understanding key patterns and distributions in the dataset.
- Feature Engineering: Creating new features and scaling/normalizing data for optimal model performance.
- Model Training: Using algorithms like Logistic Regression, RandomForestClassifier.
- Model Evaluation: Comparing models based on metrics like accuracy, precision, recall, and F1-score.
The dataset contains various patient attributes and diagnostic results. These include:
- Age
- Gender
- Albumin and Globulin Ratio
- Total Bilirubin
- Direct Bilirubin
- Alkaline Phosphatase
- Alanine Aminotransferase
- Aspartate Aminotransferase
- Total Proteins
- Others
-
Run the Jupyter Notebook:
Launch the notebook to execute the workflow step by step. -
Evaluate the Model:
Use the trained model to predict liver disease based on new patient data.
The final model achieved the following results:
- Accuracy: 98%
- Precision: 98%
- Recall: 99%
- F1-Score: 99%
Additionally, a web demo was built using Gradio to showcase the model's predictions interactively.
- Incorporating additional features or external datasets to improve prediction accuracy.
- Optimizing hyperparameters further using advanced techniques like Grid Search or Bayesian Optimization.
- Deploying the model as a web application for real-time predictions.
We would like to express our sincere gratitude to Dr. Ho Long Van, who has dedicatedly taught and guided us throughout the past semester. His dedication and profound knowledge have helped us gain a deeper understanding of the field of artificial intelligence and its practical applications. We are very grateful for his valuable lectures and enthusiastic support.