This project uses a machine learning model to predict whether a patient is likely to develop kidney stones. The model is trained on a dataset of patients who have developed kidney stones and patients who have not developed kidney stones. The model uses the following features to make predictions:
- Gravity of urine
- pH of urine
- Osmolality of urine
- Conductivity of urine
- Urea concentration in urine
- Calcium concentration in urine
- First You need to install anaconda.
- open anaconda and create new envirement
- click the new envirement and click on play button and then select 'open terminal'
- in the terminal, you need to install streamlit if you don't have one. To instal type 'pip install streamlit'
- once you install streamlit, just write 'streamlit run kidney_stone_prediction_web.py'
- app will be open in your default browser
- once open you need to fill some values inorder to predict if the patient have kidney stone or not.
- The prediction output will be 0 or 1
- 0 indicates the patient doesn't have kidney stone and 1 indicates the patient have a kidney stone
The project includes the following features:
- The ability to predict whether a patient is likely to develop kidney stones
- A user-friendly interface
- A detailed README.md file
The project has the following limitations:
- The model is not perfect and may make incorrect predictions
- The model is only trained on a limited dataset of patients