Skip to content
Diagnosing Kawasaki Disease using Machine Learning
Jupyter Notebook Python
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
classification-notebooks
deepnet
interpretation-notebooks
model_helpers
preprocess
xgbst
.gitattributes
.gitignore
README.md
__init__.py
exploratory-analysis.ipynb
predict_test_set.py
requirements.txt
run_all.py
run_all_old.py
run_run_all.sh
run_test_subcohorting.sh
test_subcohorting.py

README.md

Machine Learning for Kawasaki Disease Diagnosis

Kawasaki Disease (KD) is a rare heart condition that affects children all over the world. We use Kawasaki Disease patient data to train various machine learning models to predict whether a given patient has Kawasaki Disease or is a febrile control (i.e. does not have the disease). More information on Kawasaki Disease can be found here.

Usage Instructions:

  1. git clone this repository; cd to repository directory
  2. Create a symlink from KD-data Dropbox folder to deep-learning-kd-diagnosis/data (this is confidential patient data not available to the public)
  3. Create conda environment: conda create -n kd; source activate kd
  4. Install requirements: pip install -r requirements.txt
  5. Run experiments: bash run_run_all.sh

Methods Evaluated:

  • K-Nearest Neighbors (K-NN)
  • Logistic Regression
  • Support Vector Machine (SVM)
  • Tree-Based Methods: Random Forest, XGBoost
  • Deep Neural Network
  • Ensemble (Voting/Bagging) Classifiers

Evaluation Methodologies/Metrics:

  • 5-Fold (Nested) Cross Validation for model selection and evaluation
  • Metrics: Sensitivity, Specificity; ROC-AUC

Dependencies:

You can’t perform that action at this time.