SMIM22002U Big data, artificial intelligence and machine learning in drug safety

Volume 2022/2023
Education

Master of Industrial Drug Development (MIND) - elective

The course is preapproved as an elective in the  Master Medicines Regulatory Affairs (MRA) programme. It is also open to single course students who meet the admission criteria.

See course calender for course dates

 

Content

The need for competencies in Pharmaceutical Data Science is steadily increasing in response to the explosion of available and complex data in biomedicine and related streams. The vast volume of data covers a diverse landscape from the properties of drug molecules over their biological mechanisms of action to individual patient data collected in clinical trials and healthcare settings. This course provides an overview of data science methods in the context of drug safety. The course is tailored for both academia and industry.

Topics of the course are:

  • Pharmaceutical data science for drug safety
  • Introduction to artificial intelligence, machine learning, and deep learning
  • Introduction to the Science of "Big Data"
  • Data sources and their characteristics, the possibilities for access
  • Case studies of applications of artificial intelligence, machine learning, and deep learning in drug safety
  • Regulatory and ethical aspects of using big data artificial intelligence in pharmaceutical science for drug safety
Learning Outcome

Upon completion of the course, participants are expected to be able to:


Knowledge

  • describe and explain the fundamentals of data science with a focus on pharmaceutical data science
  • describe the roles of a pharmaceutical data scientist within the wider pharmaceutical research environment
  • describe and explain the key sources of health data, and the context in which these data are collected, implications of the context on issues such as data quality, accessibility, bias, and the appropriateness of use to address specific research questions
  • describe and explain key issues related to ethics, data security, confidentiality and information governance

 

Skills

  • discuss different analytical approaches
  • discuss limitations of data sources and methods
  • discuss the results of scientific studies and other information obtained using big data and data science methods
  • discuss ethical, legal and regulatory aspects of big data and artificial intelligence


Competencies

  • understand the fundamentals of data science with a focus on pharmaceutical data science
  • understand the roles of a pharmaceutical data scientist within the wider pharmaceutical research environment
  • interpret and critically assess scientific studies and other types of information produced using big data and data science methods

  • reflect on ethical, legal and regulatory aspects of big data and data science

Selected textbook chapters, lecture notes, laws, documents, recommendations, circulars, guidelines, and scientific papers.

Applicants must meet the following criteria:
• A relevant bachelor degree or equivalent
• A minimum of 2 years of relevant job experience
• Proficiency in English
Online part: E-lessons that will introduce you to basic concepts of big data, artificial intelligence and machine learning. The e-lessons are equivalent to one full course day.
On campus part:
Lectures, theory exercises including group work with real and simulated scenarios.
Self-study of course literature.
  • Category
  • Hours
  • Lectures
  • 20
  • Preparation
  • 88
  • Theory exercises
  • 15
  • Exam
  • 15
  • Total
  • 138
Oral
Continuous feedback during the course
Peer feedback (Students give each other feedback)
Credit
5 ECTS
Type of assessment
Written assignment
Type of assessment details
The assignment has two parts:
1. A case study that is presented with a short description and/or a scientific publication. The student is expected to identify key information, analyse the case study, critically assess data, methods and results, by answering a series of questions.
2. Short questions covering different topics of the course.
Aid
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Exam period

Announced in the exam plan on the MIND homepage mind.ku.dk

Re-exam

Announced in the exam plan on the MIND homepage mind.ku.dk

Criteria for exam assesment

To achieve grade 12 the student must be able to:


Knowledge

  • describe and explain the fundamentals of data science with a focus on pharmaceutical data science
  • describe the roles of a pharmaceutical data scientist within the wider pharmaceutical research environment
  • describe and explain the key sources of health data, and the context in which these data are collected, implications of the context on issues such as data quality, accessibility, bias, and the appropriateness of use to address specific research questions
  • describe and explain key issues related to ethics, data security, confidentiality and information governance

 

Skills

  • discuss different analytical approaches
  • discuss limitations of data sources and methods
  • discuss the results of scientific studies and other information obtained using big data and data science methods
  • discuss ethical, legal and regulatory aspects of big data and artificial intelligence


Competencies

  • understand the fundamentals of data science with a focus on pharmaceutical data science
  • understand the roles of a pharmaceutical data scientist within the wider pharmaceutical research environment
  • interpret and critically assess scientific studies and other types of information produced using big data and data science methods

  • reflect on ethical, legal and regulatory aspects of big data and data science