This course aims to equip students with a broad understanding of digital health, emphasizing not only technical skills but also ethical considerations and critical thinking when designing, developing, and implementing digital tools in healthcare settings. The main objective is to set the stage for digital health, in general, and to understand the impact of design, development, and use of digital tools within healthcare settings for optimization purposes, in particular. By the end of the course, the students will be able to illustrate introductory knowledge of digital health, encompassing design, development, and utilization of digital tools in healthcare settings, as demonstrated by their assignment, where the focus is to design a mobile application for a specific case as well as reflect on the ethical implications of working with artificial intelligence as an embedded part of healthcare.

The course instructor is Dr. Anna Sigridur Islind, a professor at the department of computer science at Reykjavik University. 

To register, contact: islind@ru.is

This workshop provides a hands-on learning experience with a focus on a wider variety of AI tools, their ethical implications and their practical applications. The aim is to facilitate the responsible and efficient use of AI-based tools in research and academia.

Content:

• Understand the importance of using AI in research and academia and assess the benefits and risks involved
• Craft effective prompts for your research tasks
• Develop strategies to integrate AI tools into your research workflow
• Stay informed about and adapt to new developments in the field of AI

At the end of the workshop, you will receive a list of generative AI prompts useful in research and academia. There will be practice sessions during the workshop for which you will need access to AI tools, particularly ChatGPT/GPT-4o. If you do not have an account with ChatGPT/GPT-4o, alternatives like Microsoft Copilot, Google Bard or Claude.ai could also be used.

Topics covered include:

• Computational design strategies
• Differential equations
• Programming in Python
• Data analysis

Topics covered include:

• Reconstruction of neuron morphologies
• Histological preparation of brain tissue
• Electrophysiological recordings of single neurons in vivo
• Simulations of cellular function via multi-compartmental neuron models

Topics covered include:

• linear and nonlinear time series analysis methods for the characterization of complex dynamical systems
• statistical tools
• analysis of biomedical data (e.g. EEG, structural/functional MRI data)

This course will cover:

• Intro to Jupyter Notebooks, IDEs
• Intro Python (loops, variables, functions)
• Core packages (Numpy, Pandas, Matplotlib, Seaborn)
• Accessing folders (shell, OS)

The module presents a variety of fundamental models and methods from computational neuroscience. By solving daily exercises the students learn how to practically apply the acquired concepts. The course introduces the employed more
advanced mathematical tools embedded into the different topics. Further there will be a pre-course teaching the required programming skills in python.