Data Science in Stratified Healthcare and Precision Medicine.

These are the series of projects and assignments I did while taking the course (Data Science in Stratified Healthcare and Stratified Healthcare)

Week one : Introduction to programming in python

Topics covered included:

• Basic data structures Working with tuples, lists, dictionaries.
• working with pandas library: series and dataframes.
• Reading csv with pandas, working with the data and visualizing it.

Week two : Sequence Processing and Medical Image Analysis

This involved working on DICOM format data storing MRI images.

Using;

• pydicom python package for working with DICOM files.
• SimpleITK an image processing library. Useful in segmentation development and imgae registration program.
• visualizing MRI images using matplotlib
• manipulating the data: doing segmentation, smoothing, hole-filling, and working with white and gray matter.

Week three : Probabilistic, Network Modelling and an introduced to Machine Learning in Biomedicine

This involved a discussion on network representation, examples of biological networks. Key statistical methods for analysing medical data and basic machine learning techniques to medical data.

Week four : Natural Language Techniques

This involved a discussion and application natural language processing techniques on clinical data. Interpreting basic process models in healthcare and a different technique for analysing processes.

Week five : Graph Data model and explore societal, legal and ethical implications of precision medicine and stratified healthcare

This week involved a discussion on graph data modelling, key ontologies in medicine and general data protection regulation. This was followed up be a legal, ethical, and societal implication of precision medicine and stratified healthcare.