metadata

tags:
  - random-forest
  - stroke-prediction
  - classification
  - healthcare
license: mit
widget:
  - text: 'Patient details: Age 45, Hypertension 1, Avg_glucose_level 170, BMI 26'
datasets:
  - stroke-prediction-dataset

Stroke Prediction Model

Date 2024-12-19

This model uses a Random Forest Classifier to predict the likelihood of a stroke based on patient details.

Model Details

Algorithm: Random Forest
Use Case: Healthcare, Stroke Risk Prediction

Performance Metrics:

Accuracy: 94.70%
ROC-AUC Score: 0.79

Classification Report:

          precision    recall  f1-score   support

       0       0.95      1.00      0.97       929
       1       1.00      0.02      0.04        53

accuracy                           0.95       982

macro avg 0.97 0.51 0.50 982

weighted avg 0.95 0.95 0.92 982 ```

How to Use

This model i created in google colab. Relavant libraries include:

How to Use

This runs in google colab.

Import as per below:

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns import random from sklearn.model_selection import GridSearchCV from sklearn.preprocessing import StandardScaler, LabelEncoder from sklearn.ensemble import RandomForestClassifier from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression from sklearn.metrics import accuracy_score, classification_report, confusion_matrix from sklearn.preprocessing import MinMaxScaler

For kaggle

import os import zipfile

For Hugging face

from sklearn.externals import joblib # to save the model

from huggingface_hub import notebook_login from huggingface_hub import Repository

Download the model and load it using `joblib Replace input_data with your data, e.g. [[45, 1, 170, 26]] # Age, Hypertension, Avg_glucose_level, BMI