simurgh818/dabiri_unsupervised_clustering_sql

The BMI 500, Biomedical Informatics class, Unsupervised Clustering project using SQL

Principal Component Analysis clustering of a Acute Kidney Injury dataset.

The BMI 500, Biomedical Informatics class, Supervised Clustering project using SQL

The kidney dataset used in this repo is queried from MIMIC III from [Johnson, A., Pollard, T., & Mark, R. (2016). MIMIC-III Clinical Database (version 1.4). PhysioNet.] (https://doi.org/10.13026/C2XW26).

Installation instructions:

git clone https://github.com/Simurgh818/Dabiri_Unsupervised_clustering_sql.git

Requirements

This script was developed on a Windows machine with 7 core processor and 16 GB RAM.

Description of scripts:

Once installed, the user can open the jupyter notebook called hw7_sql.ipynb to run the clustering.

Results

Below scatter plot shows the scatter plot of the two classes of Acute Kidney Injury (AKI) 1 and 2 on their PC1 and PC2:

Contributor

Sina Dabiri