A Python evaluation of a MIMIC-IV well being knowledge (DREAMT) to uncover insights into components affecting sleep issues.
On this article, I will likely be analysing members’ data from the DREAMT dataset with the intention to uncover relationships between sleep issues like sleep apnea, loud night breathing, problem respiration, complications, Stressed Legs Syndrome (RLS), snorting and participant traits like age, gender, Physique Mass Index (BMI), Arousal Index, Imply Oxygen Saturation (Mean_SaO2), medical historical past, Obstructive apnea-hypopnea index (OAHI) and Apnea-Hypopnea Index (AHI).
The members listed below are those that took half within the DREAMT research.
The result will likely be a complete knowledge analytics report with visualizations, insights, and conclusion.
I will likely be using a Jupyter pocket book with Python libraries like Pandas, Numpy, Matplotlib and Seaborn.
The info getting used for this evaluation comes from DREAMT: Dataset for Actual-time sleep stage EstimAtion utilizing Multisensor wearable Expertise 1.0.1. DREAMT is a part of the MIMIC-IV datasets hosted by PhysioNet.
