Data Science in Medicine and Healthcare

Data

Official data in SubjectManager for the following academic year: 2019-2020

Course director

Number of hours/semester

lectures: 0 hours

practices: 0 hours

seminars: 24 hours

total of: 24 hours

Subject data

  • Code of subject: OAF-AEU-T
  • 2 kredit
  • General Medicine
  • Optional modul
  • both semesters
Prerequisites:

-

Course headcount limitations

min. 3 – max. 20

Available as Campus course for 10 fő számára. Campus-karok: ETK GYTK KTK MIK TTK

Topic

Summary
Healthcare is one of the largest data generator in our civilization. Rapid digitization can help us to create fruitful analyses extracting novel information and relations among datasets using Big Data related technologies. Healthcare data refers so large and complex datasets from various sources. For processing and analyzing near zettabyte and complex data needs new analitical methods and data representation forms. Nor can be easily managed traditional softwares and data storage methods. This course provides a broad overview of big data analytics for healthcare researchers and also practitioners.
I . Enter to data science:
Data specificity in Healthcare.
Data types and representation in Healthcare: from medical imaging to receipt.
Handling data from different sources.
Devices and methods for medical data mining. A short overview.
Machine Learning: Promises and limitations.
Short summary of theoretical background.
Using real world data in healthcare (4 x 45 min)
Principles and definition of real world evidence in healthcare
Identifying relevant sources of data and their limitations
New methods of data analysis to develop real world evidence (RWE) from real world data (RWD)
Use of RWE in making decisions in healthcare
II. Practise based examples:
Create new healthcare analytics and service using Microsoft Azure service based on free medical datasets.
Try to your ideas!
III. Data science based business model in medicine and healthcare
What is the meaning of the term startup? How can we make sure our product will be attactive on the market? What is the process of product development?
Problem & solution fit
Product & market fit
Design thinking
Business model generation, validation and efficient pitch.
Value proposition canvas
Business model canvas
Lean business model canvas
Persona
Validation
Pitch

Lectures

Practices

Seminars

  • 1. Data specificity in Healthcare.
  • 2. Data types and representation in Healthcare: from medical imaging to receipt.
  • 3. Handling data from different sources.
  • 4. Devices and methods for medical data mining. A short overview.
  • 5. Machine Learning: Promises and limitations.
  • 6. Short summary of theoretical background.
  • 7. Principles and definition of real world evidence in healthcare
  • 8. Identifying relevant sources of data and their limitations
  • 9. New methods of data analysis to develop real world evidence (RWE) from real world data (RWD)
  • 10. Use of RWE in making decisions in healthcare
  • 11. Introduction to Microsoft AZURE
  • 12. Registration and uploading sample datasets
  • 13. Result planning
  • 14. Create a new data related healthcare device (create and deploy)
  • 15. Preparing new app
  • 16. Product testing
  • 17. Problem & solution fit
  • 18. Product & market fit
  • 19. Design thinking
  • 20. Business model generation, validation and efficient pitch.
  • 21. Business model canvas
  • 22. Persona
  • 23. Validation
  • 24. Pitch

Reading material

Obligatory literature

-

Literature developed by the Department

-

Notes

-

Recommended literature

-

Conditions for acceptance of the semester

-

Mid-term exams

Essay and individual work

Making up for missed classes

Essay

Exam topics/questions

Essay and individual work. practice and attendance

Examiners

Instructor / tutor of practices and seminars

  • Dr. Feldmann Ádám