Sumários
Project Presentations and Evaluation
3 Junho 2026, 13:30 • Rafael Neto Henriques
This session marked the beginning of the practical project evaluations. Student groups delivered 15-minute presentations detailing their implementation of a selected physiological compartmental model. Each presentation covered the theoretical background of their chosen paper, the mathematical formulation, the numerical implementation in MATLAB or Python, and the physiological interpretation of their simulated results. Following each presentation, a short discussion was conducted to thoroughly assess the students' comprehension of their algorithmic choices and the underlying physiological concepts.
Course summary and QA
3 Junho 2026, 10:00 • Rafael Neto Henriques
This session was reserved for the concluding synthesis of the course syllabus and provided students with a dedicated opportunity to resolve final questions and consolidate their theoretical knowledge.
Project Presentations and Evaluation
3 Junho 2026, 08:30 • Rafael Neto Henriques
This session marked the beginning of the practical project evaluations. Student groups delivered 15-minute presentations detailing their implementation of a selected physiological compartmental model. Each presentation covered the theoretical background of their chosen paper, the mathematical formulation, the numerical implementation in MATLAB or Python, and the physiological interpretation of their simulated results. Following each presentation, a short discussion was conducted to thoroughly assess the students' comprehension of their algorithmic choices and the underlying physiological concepts
Modelling and Simulation using Machine Learning
2 Junho 2026, 11:00 • Rafael Neto Henriques
This theoretical class was focused on the application of Machine Learning (ML) within medical modeling, highlighting the paradigm shift from classical modeling.
The biological inspirations behind ML architectures were explored, detailing how a Perceptron mathematically mimics a biological neuron and how convolutional Neural Networks (CNNs) is inspired by the primate visual cortex. Practical applications of CNNs in medicine were then highlighted (e.g. disease classification, detection and localization, and segmentation).
Despite their biological inspiration, it was explained why ML algorithms are better classified as data models - their parameters do not map directly to physiological laws, and fundamental differences exist between human biology and ML, as demonstrated by how humans and CNNs process adversarial image attacks differently
For parameter estimation tasks, Decision Trees and Random Forests were introduced as alternatives to traditional non-linear regression
The class then introduced critical caveats regarding ML implementations: applying an ML algorithm does not mathematically solve inherent unidentifiability if the underlying experimental data lacks sufficient information
Finally, the emerging concept of Physics-Informed Machine Learning was introduced as a method to integrate established physical laws directly into ML training frameworks
Final Implementation Troubleshooting and Report Preparation
27 Maio 2026, 13:30 • Rafael Neto Henriques
This session served as the final practical-laboratory class before the evaluation phase. Dedicated to concluding the project work, hands-on assistance was provided to help students troubleshoot and resolve any last-minute computational or coding issues within their MATLAB or Python models. Alongside finalizing the algorithms, the class focused heavily on the communication of their findings. Final suggestions and targeted feedback were given regarding the organization, structuring, and formatting of the project reports, ensuring that all groups were fully prepared to clearly articulate their mathematical methodologies and physiological interpretations for their final submissions.