Merge pull request #201 from SaloniThete/main

Heart Failure Prediction

Author: prathimacode-hub

Machine Learning/Heart Failure Prediction/Heart_Failure_Prediction.ipynb

@@ -0,0 +1,89 @@
+# Heart Failure Prediction
+
+# Introduction
+Heart disease is one of the most significant
+problem that is arising in the world today.
+Cardiovascular disease prediction is a critical
+challenge in the area of clinical data analysis. 
+
+Cardiovascular diseases (CVDs) are the number 1 cause of death globally, taking an estimated 17.9 million lives each year, which accounts for 31% of all deaths worldwide. Four out of 5CVD deaths are due to heart attacks and strokes, and one-third of these deaths occur prematurely in people under 70 years of age. Heart failure is a common event caused by CVDs and this dataset contains 11 features that can be used to predict a possible heart disease.
+
+People with cardiovascular disease or who are at high cardiovascular risk (due to the presence of one or more risk factors such as hypertension, diabetes, hyperlipidaemia or already established disease) need early detection and management wherein a machine learning model can be of great help.
+
+The prediction model is proposed with
+combinations of different features and several
+classification techniques.
+
+# Attribute Information
+1. Age: age of the patient [years]
+2. Sex: sex of the patient [M: Male, F: Female]
+3. ChestPainType: chest pain type 
+4. RestingBP: resting blood pressure [mm Hg]
+5. Cholesterol: serum cholesterol [mm/dl]
+6. FastingBS: fasting blood sugar 
+7. RestingECG: resting electrocardiogram results
+8. MaxHR: maximum heart rate achieved 
+9. ExerciseAngina: exercise-induced angina [Y: Yes, N: No]
+10. Oldpeak: oldpeak = ST 
+11. ST_Slope: the slope of the peak exercise ST segment 
+12. HeartDisease: output class [1: heart disease, 0: Normal]
+
+# Workflow
+1. Importing Required Libraries
+2. Load the Dataset
+3. EDA(Exploratory Data Analysis
+4. Data Cleaning and preprocessing
+5. Data Visualization
+6. Training the model 
+7. Predict the accuracies of all 6 classifiers
+8. Comparing performance of the models
+
+# Data Visualization
+ROC Curves of models.
+1. Random Forest Classifier<br>
+![](Image/Random%20Forest%20Classifier.png)<br>
+2. K Nearest Neighbour<br>
+![](Image/KNN.png)<br>
+3. Decision Tree Classifier<br>
+![](Image/Decision%20Tree%20Classifier.png)<br>
+4. Gradient Boosting Classifier<br>
+![](Image/Gradient%20Boosting.png)<br>
+5. .Logistic Regression<br>
+![](Image/Logistic%20Regression.png)<br>
+6. SVM(Support Vector Machine)<br>
+![](Image/SVM.png)<br>
+
+# Advantages of Heart Failure Prediction
+1. Increased accuracy for effective heart
+disease diagnosis.
+2. Handles roughest(enormous) amount of
+data using random forest algorithm and
+feature selection.
+3. Reduce the time complexity of doctors.
+4. Cost effective for patients.
+
+# Disadvantages of Heart Failure Prediction
+* Prediction of cardiovascular disease
+results is not that accurate.
+
+# Accuracies gained by the models
+1. RandomForest	88.260870
+2. KNeighbors	73.913043
+3. DecisionTree	79.130435
+4. GradientBoosting	87.826087
+5. Logistic Regression	0.847826
+6. Support vector machine	0.726087
+
+# Conclusion
+we proposed a method for heart
+disease prediction using machine learning
+techniques, these results showed a great
+accuracy standard for producing a better
+estimation result. By introducing new proposed
+Random forest classification, we find the
+problem of prediction rate without equipment
+and propose an approach to estimate the heart
+rate and condition. Sample results of heartrate
+are to be taken at different stages of the same
+subjects, we find the information from the above
+input via ML Techniques.

Machine Learning/Heart Failure Prediction/Image/Decision Tree Classifier.png

@@ -0,0 +1,5 @@
+Libraries imported in the Heart Failure Prediction:
+1.pandas
+2.matplotlib
+3.seaborn
+4.plotly