Data Driven Healthcare
Go back
BRIEF DESCRIPTION
This course is designed to provide both clinical and non-clinical staff with a comprehensive understanding of healthcare data and its role in decision-making processes.
The course will cover a range of topics to ensure a solid understanding of how data is collected, analysed, and utilised in healthcare settings.
By the end of this course, students should be able to:
- Recognise and differentiate various types of healthcare data and understand their role in decision-making processes.
- Understand the functionalities of Electronic Health Records (EHR) systems and the data they collect.
- Know the CRISP-DM methodology to tackle healthcare data analysis projects.
- Perform exploratory data analysis using descriptive statistics and visualisation techniques to understand the data.
- Examine a dataset for potential patterns and extractable knowledge.
- Know healthcare innovations such as precision medicine and predictive analytics for disease prevention, understanding their impact on patient care and outcomes.
SUMMARY
This course has 2 Modules, 6 Sessions (to be organized according to the specific requests of the hospitals, either on place or online). The Sessions description is:
- M1: Introduction to Healthcare Data
- Types of healthcare data (structured vs. unstructured)
- Data sources (clinical, administrative, patient-generated)
- The role of healthcare data in decision-making
- M2: Electronic Health Records (EHR) Systems
- Overview of EHR systems
- Types of data collected by EHRs
- Benefits and challenges of EHR implementation
- M3: Exploratory Data Analysis (EDA)
- Descriptive statistics (mean, median, mode, standard deviation)
- Data visualization techniques (histograms, scatter plots, box plots)
- Tools for EDA (e.g., Excel, Python, R)
- M4: Artificial Intelligence and Machine Learning in Healthcare
- Introduction to CRISP-DM (Cross-Industry Standard Process for Data Mining)
- Phases of CRISP-DM
- M5: Data Analysis and Pattern Recognition
- Introduction to machine learning for pattern recognition: supervised, semi-supervised, and unsupervised learning
- Techniques for identifying patterns in healthcare data
- Case studies on successful data analysis projects
- M6: Healthcare innovations driven by data analytics
- Overview of precision medicine
- Remote patient monitoring
- Predictive analytics for disease prevention
- The impact of healthcare innovations on patient care and outcomes
Each session will have a short survey (continuous); the final hands-on exercise. Course final assessment.
AUTHOR AND COORDINATOR
Author
João Carlos Ferreira
Coordinator
Ana Madureira