Merge pull request #712 from adi271001/sepsis-survival-prediction

Sepsis survival prediction
abhisheks008 · Jul 17, 2024 · 95e4b77 · 95e4b77
2 parents ca8c06c + 13f56b9
commit 95e4b77
Show file tree

Hide file tree

Showing 41 changed files with 130,953 additions and 0 deletions.
diff --git a/Sepsis Survival Prediction/Dataset/s41598-020-73558-3_sepsis_survival_primary_cohort.csv b/Sepsis Survival Prediction/Dataset/s41598-020-73558-3_sepsis_survival_primary_cohort.csv
diff --git a/Sepsis Survival Prediction/Dataset/s41598-020-73558-3_sepsis_survival_study_cohort.csv b/Sepsis Survival Prediction/Dataset/s41598-020-73558-3_sepsis_survival_study_cohort.csv
diff --git a/Sepsis Survival Prediction/Dataset/s41598-020-73558-3_sepsis_survival_validation_cohort.csv b/Sepsis Survival Prediction/Dataset/s41598-020-73558-3_sepsis_survival_validation_cohort.csv
@@ -0,0 +1,138 @@
+age_years,sex_0male_1female,episode_number,hospital_outcome_1alive_0dead
+20,0,1,1
+22,0,1,1
+26,1,2,0
+33,1,1,1
+33,0,1,1
+33,0,2,0
+35,0,1,1
+35,1,1,1
+36,0,1,1
+36,1,1,1
+38,1,1,1
+40,0,1,1
+41,1,1,1
+42,0,1,1
+43,1,2,0
+45,0,1,1
+46,1,1,1
+47,1,1,1
+48,1,2,0
+48,0,1,1
+49,0,1,1
+50,0,1,1
+50,0,1,1
+52,0,1,1
+52,0,1,1
+53,0,1,0
+53,1,1,1
+53,0,2,0
+54,0,1,1
+54,1,1,1
+54,0,1,1
+55,0,2,1
+55,1,1,1
+57,0,2,1
+57,0,1,0
+58,0,1,1
+59,0,1,0
+60,0,1,1
+60,0,1,1
+60,0,1,1
+60,0,1,1
+61,0,1,1
+61,0,1,1
+61,1,1,1
+62,0,1,1
+62,1,1,1
+64,0,1,1
+64,0,1,1
+64,0,1,1
+64,1,1,1
+66,1,1,1
+66,0,1,1
+66,0,1,1
+67,0,1,1
+67,0,1,1
+67,1,2,1
+68,0,1,1
+69,1,1,0
+70,1,1,1
+72,1,1,1
+73,0,1,0
+73,1,1,1
+74,0,1,1
+74,0,1,1
+74,1,1,1
+75,0,2,0
+75,1,1,1
+75,1,2,0
+75,1,1,1
+76,1,1,1
+76,0,1,1
+78,0,1,1
+78,0,2,0
+78,1,1,1
+79,1,1,1
+79,0,1,1
+79,0,1,1
+79,0,1,1
+82,0,1,1
+83,1,1,0
+84,1,1,1
+84,1,1,1
+88,1,1,1
+89,0,1,1
+89,0,1,1
+76,1,1,1
+60,1,1,1
+89,1,1,1
+55,0,1,1
+41,1,1,1
+24,0,1,1
+62,0,1,1
+80,0,1,1
+56,0,1,1
+29,0,1,1
+71,0,2,0
+43,0,1,1
+59,0,2,1
+50,0,1,1
+77,0,1,1
+87,1,2,0
+73,0,2,1
+53,1,1,1
+68,1,2,1
+67,0,2,1
+50,0,2,0
+36,0,1,1
+54,0,1,1
+77,0,1,1
+45,1,1,1
+50,1,1,1
+35,0,2,1
+48,0,1,1
+44,0,1,1
+70,0,1,1
+76,0,2,0
+63,0,2,1
+30,0,1,1
+66,1,1,1
+60,0,1,1
+57,0,1,1
+46,1,1,1
+61,1,1,0
+69,0,1,1
+71,0,1,0
+53,0,2,1
+69,0,1,0
+63,0,1,1
+57,1,1,1
+86,0,1,1
+50,0,1,0
+67,0,1,1
+47,0,1,1
+50,0,1,0
+62,0,1,1
+58,0,1,0
+55,1,1,1
diff --git a/Sepsis Survival Prediction/Images/__results___10_0.png b/Sepsis Survival Prediction/Images/__results___10_0.png
diff --git a/Sepsis Survival Prediction/Images/__results___11_1.png b/Sepsis Survival Prediction/Images/__results___11_1.png
diff --git a/Sepsis Survival Prediction/Images/__results___11_3.png b/Sepsis Survival Prediction/Images/__results___11_3.png
diff --git a/Sepsis Survival Prediction/Images/__results___11_5.png b/Sepsis Survival Prediction/Images/__results___11_5.png
diff --git a/Sepsis Survival Prediction/Images/__results___11_7.png b/Sepsis Survival Prediction/Images/__results___11_7.png
diff --git a/Sepsis Survival Prediction/Images/__results___12_1.png b/Sepsis Survival Prediction/Images/__results___12_1.png
diff --git a/Sepsis Survival Prediction/Images/__results___13_1.png b/Sepsis Survival Prediction/Images/__results___13_1.png
diff --git a/Sepsis Survival Prediction/Images/__results___14_2.png b/Sepsis Survival Prediction/Images/__results___14_2.png
diff --git a/Sepsis Survival Prediction/Images/__results___15_2.png b/Sepsis Survival Prediction/Images/__results___15_2.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_1.png b/Sepsis Survival Prediction/Images/__results___20_1.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_11.png b/Sepsis Survival Prediction/Images/__results___20_11.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_13.png b/Sepsis Survival Prediction/Images/__results___20_13.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_15.png b/Sepsis Survival Prediction/Images/__results___20_15.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_17.png b/Sepsis Survival Prediction/Images/__results___20_17.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_19.png b/Sepsis Survival Prediction/Images/__results___20_19.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_3.png b/Sepsis Survival Prediction/Images/__results___20_3.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_5.png b/Sepsis Survival Prediction/Images/__results___20_5.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_7.png b/Sepsis Survival Prediction/Images/__results___20_7.png
diff --git a/Sepsis Survival Prediction/Images/__results___20_9.png b/Sepsis Survival Prediction/Images/__results___20_9.png
diff --git a/Sepsis Survival Prediction/Images/__results___21_0.png b/Sepsis Survival Prediction/Images/__results___21_0.png
diff --git a/Sepsis Survival Prediction/Images/__results___21_1.png b/Sepsis Survival Prediction/Images/__results___21_1.png
diff --git a/Sepsis Survival Prediction/Images/__results___9_0.png b/Sepsis Survival Prediction/Images/__results___9_0.png
diff --git a/Sepsis Survival Prediction/Model/README.md b/Sepsis Survival Prediction/Model/README.md
@@ -0,0 +1,70 @@
+# Sepsis Survival Prediction - Models
+
+## Models Implemented
+
+### 1. Random Forest
+
+**Description**: Random Forest is an ensemble learning method that constructs multiple decision trees during training and outputs the mode of the classes as the prediction.
+
+### 2. XGBoost
+
+**Description**: XGBoost is an optimized gradient boosting framework that is highly efficient and scalable, often used for structured data.
+
+### 3. Logistic Regression
+
+**Description**: Logistic Regression is a linear model that uses the logistic function to model the probability of a binary class.
+
+### 4. Gradient Boosting
+
+**Description**: Gradient Boosting builds models sequentially, with each new model correcting errors made by the previous ones.
+
+### 5. AdaBoost
+
+**Description**: AdaBoost is an ensemble learning method that combines multiple weak classifiers to create a strong classifier.
+
+### 6. CatBoost
+
+**Description**: CatBoost is a gradient boosting algorithm that handles categorical features automatically and efficiently.
+
+### 7. LightGBM
+
+**Description**: LightGBM is a gradient boosting framework designed for efficiency with large datasets and low memory usage.
+
+### 8. K-Nearest Neighbors (KNN)
+
+**Description**: K-Nearest Neighbors is a simple, instance-based learning algorithm where classification is based on the majority vote of the nearest neighbors.
+
+### 9. Support Vector Machine (SVM)
+
+**Description**: SVM is a supervised learning model that finds the hyperplane which best divides a dataset into classes.
+
+### 10. Decision Tree
+
+**Description**: Decision Trees are non-parametric supervised learning methods used for classification based on simple decision rules inferred from the data features.
+
+## Performance of the Models based on the Accuracy Scores
+
+- **Random Forest**: 90.92%
+- **XGBoost**: 90.92%
+- **Logistic Regression**: 90.92%
+- **Gradient Boosting**: 90.92%
+- **AdaBoost**: 90.92%
+- **CatBoost**: 90.93%
+- **LightGBM**: 90.92%
+- **K-Nearest Neighbors (KNN)**: 90.46%
+- **Support Vector Machine (SVM)**: 90.92%
+- **Decision Tree**: 90.92%
+
+Each model was evaluated based on its accuracy in predicting sepsis surval using clinical records.
+
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___21_0.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_1.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_11.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_13.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_15.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_17.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_19.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_3.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_5.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_7.png?raw=true)
+![accuracy plot](https://github.com/adi271001/ML-Crate/blob/sepsis-survival-prediction/Sepsis%20Survival%20Prediction/Images/__results___20_9.png?raw=true)