Objectives of Programme's Learning Outcomes

• Understand, describe, analyse and prioritise biological phenomena
• Understand basic scientific knowledge and be able to use it
• Problem-solve
• Understand the expression of biological realities in absolute or relative terms, the orders of magnitude, proportions and probability
• Abstract, understand and apply mathematical translations of the main laws and biological phenomena
• Understand and use different graphical representations of numerical values and their relationships
• Perceive spatial distribution, and understand two- and three-dimensional representations and interconvert them
• Understand the chronology of a phenomenon and master the time scales and their representations
• Manipulate concepts of concentration and prepare solutions
• Control the molecular, morphological and functional approaches of normal and pathological conditions
• Understand the learning of physiological and pharmacological reasoning
• Understand experimental protocols in the biomedical domain
• Integrate concepts from different approaches/disciplines in a complex biomedical problem
• Explain how molecular, morphological and functional modifications constitute pathological states and vice versa
• Develop reasoning skills
• Understand and apply the basic principles of reasoning (obtaining data, analysis, synthesis, comparison, the rule of three, syllogism, analogy, Boolean logic, etc.)
• Understand the statistical and/or epidemiological methods
• Work with efficiency / accuracy / precision
• Present a hypothesis and hypothetical-deductive reasoning
• Develop critical thinking, test and monitor conclusions understanding the domain of validity, and explore alternative hypotheses
• Manage doubt and uncertainty
• Demonstrate developed interpersonal skills
• Use a rich vocabulary linking concepts and words accurately
• Adapt lexical and syntactic choices in communication register (everyday language, medical language or scientific terminology)
• Summarise, explain, and argue
• Work in a team
• Share knowledge and information
• Submit reviews, reports and give oral presentations
• Manage resources
• Manage time
• Prioritise
• Use basic IT and bibliographic resources.
• Manage their studies
• Locate scientific information efficiently
• Compare different sources of information
• Read, interpret, and critique a scientific article
• Self-assess and give feedback
• Be open to research and demonstrate scientific curiosity
• Show a good knowledge of scientific English
• Understand and summarise a scientific article in English

Learning Outcomes of UE

Upon completion of this module, students will be able to:

Explore and prepare medical databases for analysis, managing missing values, detecting anomalies, and using visualization tools to analyze relationships between variables.
Formulate clear analysis goals and relevant hypotheses to guide data exploration and selection of appropriate machine learning algorithms.
Apply the concepts and techniques learned in Module I to create, train, tune, and validate machine learning models tailored to specific health conditions.
Assess the quality and robustness of machine learning models using appropriate metrics and cross-validation techniques.
Present the results of AI analysis in a scientific format, writing clear and concise reports and creating graphs and visualizations to illustrate findings.
Critique the results of AI analysis, identifying limitations, potential biases, and ethical and regulatory implications of the models created.
Collaborate effectively in groups to solve real health problems using artificial intelligence, sharing knowledge and integrating everyone's skills.

UE Content: description and pedagogical relevance

In this phase, students will learn to explore and understand medical databases. They will acquire skills in data preparation and cleaning, handling of missing values and anomaly detection. Students will also become familiar with data visualization tools to analyze trends, distributions, and relationships between variables.
Ideation phase:
In this step, students will think about how to analyze data using the AI algorithms learned in Module I. They will learn to define clear analytical goals and formulate relevant hypotheses to guide their exploration of data. They will also explore how to select the best-suited machine learning algorithms and techniques for specific problems and available data.
Modeling phase:
In the modeling phase, students will apply the concepts and techniques learned to create machine learning models with medical databases. They will learn how to train, adjust and validate their models to optimize their performance. Students will also discover how to assess the quality and robustness of their models using appropriate metrics and cross-validation techniques.
Results presentation phase:
Finally, students will learn how to present their AI analysis results in a scientific format. They will discover how to write clear and concise reports describing the methodology used, the results obtained and their interpretation. Students will also become familiar with creating graphs and visualizations to effectively illustrate their findings. This phase will also focus on critiquing the results, highlighting the limitations and potential biases of the models, and discussing the ethical and regulatory implications of their work.

Prior Experience

None