Hospital-Stay-length Predicting hospital stay length using explainable ML with Random Forest, XGBoost, Decision Tree,Voting Regressor
🏥 Predicting Hospital Stay Length using Explainable Machine Learning
This mini project aims to build a machine learning model that predicts the number of days a patient is expected to stay in a hospital based on clinical and personal features. The project also uses explainable machine learning to help interpret the model's predictions in a transparent and trustworthy way.
📘 Project Title
Predicting Hospital Stay Length using Explainable Machine Learning
🎯 Objective
To apply machine learning algorithms for predicting hospital stay duration.
To use explainable AI (XAI) methods to interpret model predictions.
To support hospital management in planning and patient care decisions.
🧪 Problem Statement
Hospitals often face challenges in managing patient flow and resource allocation. Accurately predicting how long a patient will stay helps in bed planning, staffing, and reducing healthcare costs. This project solves this problem using machine learning techniques enhanced with explainability tools like SHAP
🔍 Methodology
Data Collection: Healthcare dataset with features like age, gender, diagnosis, lab results, etc.
Preprocessing: Handling missing values, encoding categorical features, normalization.
Model Training: Random Forest and XGBoost regressors.
Evaluation: MAE, RMSE, and R² metrics.
Explainability: SHAP plots to visualize feature importance.
(CMD Steps)
Open Command Prompt (CMD)
Navigate to your project folder:
cd C:\Users\pranathi\OneDrive\Desktop\mini\CODE\Hospital_Stay
Run the Django development server : python manage.py runserver
Project Details:
Student Name: Pranathi K
College: Samskruti college of engineering and technology
Branch & Year: B.Tech, 3rd Year
Course: Computer Science Engineering(Data Science)