Processed Clinical Dataset with Python Analysis Script for CDSS HCI Research

Overview
--------
This repository contains resources supporting research on data integration and normalization within Clinical Decision Support Systems (CDSS) and their impact on Human-Computer Interaction (HCI). The resources are derived from a public dataset (MIMIC-IV) and include:

Processed Clinical Dataset (Excel file): Contains normalized and integrated clinical data, with key attributes such as glucose levels, age, and gender.
Python Analysis Script (.py): The Python code used for data preprocessing, normalization, and visualization, including the generation of histograms and boxplots to highlight findings.


Contents
--------
clinical_data_processed.xlsx

A curated dataset containing:

. Raw and normalized glucose values.
. Age and gender attributes for demographic analysis.
. Data structure optimized for HCI-related insights in CDSS.
data_analysis_script.py

A Python script used for:

. Missing data imputation (mean imputation for glucose levels).
. Normalization of glucose values.
. Visualization of glucose trends by age and gender using histograms and boxplots.

How to Use
-----------
Open the Excel file to explore processed clinical data.
Run the Python script to:
- Recreate data visualizations for glucose level trends.
- Extend the analysis with new attributes or datasets.

License and Citation
---------------------
The MIMIC-IV dataset is used under its respective license. For more details, visit: https://physionet.org/content/mimiciv/2.0/
If using these resources in your research, please cite this repository appropriately.

Contact
--------
For questions or further information, please contact Ali Azadi at ali.azadi@usal.es.