2025
Artificial Intelligence in Health Sciences
Name: Artificial Intelligence in Health Sciences
Code: INF15068M
3 ECTS
Duration: 15 weeks/78 hours
Scientific Area:
Informatics
Teaching languages: Portuguese, English
Languages of tutoring support: Portuguese, English
Regime de Frequência: Presencial
Sustainable Development Goals
Learning Goals
The fundamental concepts of Artificial Intelligence will be studied with a focus on methodologies based on inductive AI.
This UC aims to raise students' awareness of the topics covered, including:
- Identify situations of potential application of AI in the area of health sciences;
- Identify potentialities and limitations of the use of AI;
- Understand the functioning of elementary algorithms;
- Identify the characteristics of the main families of algorithms;
- Identify and understand the phases and tasks in an AI application project;
- Know AI platforms/tools;
- Identify the risks of using AI;
This UC aims to raise students' awareness of the topics covered, including:
- Identify situations of potential application of AI in the area of health sciences;
- Identify potentialities and limitations of the use of AI;
- Understand the functioning of elementary algorithms;
- Identify the characteristics of the main families of algorithms;
- Identify and understand the phases and tasks in an AI application project;
- Know AI platforms/tools;
- Identify the risks of using AI;
Contents
1. Types of AI Deductive and Inductive
2. Supervised, unsupervised and semi-supervised learning
3. Binary, multi-class, multi-label regression and classification
4. Error and performance measures - false positives, false negatives, precision, coverage (sensitivity), specificity, and accuracy
5. Algorithms: Naïve Bayes, Decision Trees, Nearest Neighbors, Neural Networks, and Deep Learning
6. Model generalization. Noise, bias, variance. and uncertainty
7. Model training, validation and evaluation
8. Regularization
9. Sensors, data collection and storage
10. Privacy, anonymization and data reliability
11. Explainability of models
12. Application cases: Video, Image, Signals, Text and Audio
2. Supervised, unsupervised and semi-supervised learning
3. Binary, multi-class, multi-label regression and classification
4. Error and performance measures - false positives, false negatives, precision, coverage (sensitivity), specificity, and accuracy
5. Algorithms: Naïve Bayes, Decision Trees, Nearest Neighbors, Neural Networks, and Deep Learning
6. Model generalization. Noise, bias, variance. and uncertainty
7. Model training, validation and evaluation
8. Regularization
9. Sensors, data collection and storage
10. Privacy, anonymization and data reliability
11. Explainability of models
12. Application cases: Video, Image, Signals, Text and Audio
Teaching Methods
Throughout the collective teaching sessions of the Curricular Unit, the defined syllabus will be presented and the relevance of the topics exposed for understanding AI will be reinforced, in dialogue with students.
Considering the objectives of raising student awareness of AI topics, an approach based on the analysis of practical cases of AI application will be privileged, including the presentation and discussion of common misconceptions and errors.
In order to establish greater contact and interactivity with students, and as a way of making support materials available for the syllabus taught throughout the academic semester, teachers will permanently use the University of Évora's teaching platform (Moodle). Challenges and study problems will also be launched on this platform.
Considering the objectives of raising student awareness of AI topics, an approach based on the analysis of practical cases of AI application will be privileged, including the presentation and discussion of common misconceptions and errors.
In order to establish greater contact and interactivity with students, and as a way of making support materials available for the syllabus taught throughout the academic semester, teachers will permanently use the University of Évora's teaching platform (Moodle). Challenges and study problems will also be launched on this platform.
Assessment
In the continuous assessment regime, the final grade of the course will result from the weighted average of the practical component and the theoretical component, with the following weightings:
Theoretical component:
- Test 1: 25%;
- Test 2: 25%;
Practical component:
- Practical work: 50%;
In the examination regime, the final grade of the discipline will result from the weighted average of the practical component and the theoretical component, with the following weightings:
Theoretical component:
- Exam: 50%;
Practical component:
- Practical work: 50%;
Theoretical component:
- Test 1: 25%;
- Test 2: 25%;
Practical component:
- Practical work: 50%;
In the examination regime, the final grade of the discipline will result from the weighted average of the practical component and the theoretical component, with the following weightings:
Theoretical component:
- Exam: 50%;
Practical component:
- Practical work: 50%;
Teaching Staff
- Rui André Correia de Oliveira [responsible]
Certificações
