The course provides the theoretical and methodological foundations for the development of advanced systems for the analysis, modeling, and interpretation of biomedical data, with particular reference to applications of artificial intelligence in the medical and healthcare fields. Such systems are employed in numerous areas of bioengineering, including clinical decision support systems, the analysis of clinical trial data, and the definition of clinical indicators to support decision-making. The course specifically explores knowledge related to the structure and characteristics of machine learning systems, with attention to the main classification and clustering methods and to the stages of model design, training, and validation. Issues related to the reliability of results and the interpretability of models in the clinical context are also discussed. Laboratory activities enable students to acquire practical skills in the development, optimization, and validation of machine learning models applied to realistic problems of medical interest. These activities involve group work in order to foster collaboration skills and the shared management of the different stages of design and validation of artificial intelligence systems. By the end of the course, students will be able to analyze a biomedical problem, select the most appropriate AI method, and develop effective solutions to address problems of intermediate complexity.

1. Knowledge and understanding Students will acquire knowledge of the principles of artificial intelligence as applied to medicine, with particular reference to machine learning systems for the analysis of biomedical data and the stages involved in developing a decision support system: problem conceptualization, model construction, and validation. 2. Ability to apply knowledge and understanding Students will be able to design, implement, and validate machine learning-based systems for solving problems of medical and clinical interest, working both individually and in teams, and selecting the most appropriate method based on the characteristics of the data and the application context. 3. Independent judgement Students will acquire the ability to critically analyze the results obtained, evaluating their reliability, robustness, and limitations, and to contribute knowledgeably to design decisions within a workgroup. 4. Communication skills Students will be able to clearly and effectively communicate the designed solutions and the results obtained, using appropriate technical terminology and adapting the level of detail to the context, both in academic settings and in multidisciplinary medical-engineering contexts. 5. Learning skills Upon completion of the course, students will be able to independently tackle new problems of moderate complexity and to learn and apply additional artificial intelligence methods in the biomedical field, including through discussion and collaboration within working groups.

Basic concepts of logic and matrix calculus. Knowledge of the characteristics of the main medical devices used for diagnosis and treatment.

01. Introduction: Definition of AI, AI in medicine, digital health, evolution of AI approaches and methods, introduction to machine learning. 02. Development of a machine learning-based system: Problem conceptualization, construction process, validation process. 03. Descriptive statistics and hypothesis testing. 04. Optimization: Local search, simulated annealing, genetic algorithms. 05. Classification: Neural networks, kNN, Naive Bayes classifier, linear regression, logistic regression. 06. Clustering: k-means, hierarchical clustering, dendrograms, SOM. 07. Factors influencing the reliability of results, explainability, and regulations: medical device regulations, etc. 08. Applications. Lab 1: Descriptive statistics. Lab 2: Feature selection: genetic algorithms and kNN. Lab 3: TRS: random, dendrogram, SOM. Lab 4: Supervised neural networks. Lab 5: Bayesian classifier. Lab 6: Comparison of the developed classifiers.

The course consists of: - 39 hours of lectures - 9 hours of classroom exercises - 31.5 hours of laboratory exercises

Slides and handouts provided by the instructor.

Slides; Video lezioni dell’anno corrente;

Modalita di esame: Elaborato progettuale in gruppo; Prova scritta in aula tramite PC con l'utilizzo della piattaforma di ateneo;

Exam: Group project; Computer-based written test in class using POLITO platform;

... The final grade is calculated as the sum of: - Written exam [18 points] (administered via the exam platform) - Assesses acquired knowledge 18 multiple-choice questions (1 point for each correct answer, -0.3 points for each incorrect answer) - Duration: 20 minutes - Reports on work completed during the labs [15 points] - Assesses communication skills and ability to work in a team Reports for LAB1, LAB2, LAB3, LAB4, LAB5 uploaded via the Moodle platform (11 total points) + Peer review and faculty evaluation of the presented LAB6 project (4 total points) To receive "lode", a minimum of 30.5 points is required.

Gli studenti e le studentesse con disabilita o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unita Special Needs, al fine di permettere al/la docente la declinazione piu idonea in riferimento alla specifica tipologia di esame.