Leonardo RUNDO | ADVANCED AI FOR DIGITAL MEDICINE

cod. 8860500020

ADVANCED AI FOR DIGITALMEDICINE

	8860500020
	DIPARTIMENTO DI INGEGNERIA DELL'INFORMAZIONE ED ELETTRICA E MATEMATICA APPLICATA
	Corso di Dottorato (D.M.226/2021)
	INGEGNERIA DELL'INFORMAZIONE
	2024/2025

CURRICULUM INFORMATION TECHNOLOGIES FOR DIGITAL MEDICINE

	OBBLIGATORIO
	ANNO CORSO 1
	ANNO ORDINAMENTO 2024
	SECONDO SEMESTRE

MODULI

	SSD	CFU	ORE	ATTIVITÀ	TIPO DI ATTIVITÁ FORMATIVA
	ING-INF/05	3	18	LEZIONE

DOCENTI

	FRANCESCO TORTORELLA T Curriculum
	LEONARDO RUNDO Curriculum

	Obiettivi
	Learning outcomes: To acquire knowledge and skills on the use of Artificial Intelligence and Machine Learning methodologies for the analysis and processing of large quantities of medical data (e.g. genomic data, medical images, collected data from wearable sensors) to support diagnosis, therapeutic personalization and patient assistance, highlighting the specificities of the methodologies to be adopted in the domain of digital medicine (among these, the need for "explainability" of the response provided by the system, and the ability to operate on data partially obfuscated for privacy reasons).

Learning outcomes: To acquire knowledge and skills on the use of Artificial Intelligence and Machine Learning methodologies for the analysis and processing of large quantities of medical data (e.g. genomic data, medical images, collected data from wearable sensors) to support diagnosis, therapeutic personalization and patient assistance, highlighting the specificities of the methodologies to be adopted in the domain of digital medicine (among these, the need for "explainability" of the response provided by the system, and the ability to operate on data partially obfuscated for privacy reasons).

	Prerequisiti
	The activity requires the previous knowledge of Deep Learning, Machine Learning and statistics. It is assumed that the student is able to develop and evaluate predictive models.

	Contenuti
	Topic 1: Introduction to the course. Machine. Feature Extraction. Dimensionality Reduction and Feature Selection. (Lectures: 2 hours; Lab.: 1 hour) Topic 2: Robustness and reliability of extracted features. Interpretability and Explainability in medical Artificial Intelligence. (Lectures: 2 hours; Exercises: 1 hour) Topic 3: Class imbalanceness. Data imputation and resampling. Data augmentation approaches. (Lectures: 2 hours; Exercises: 1 hour) Topic 4: Performance evaluation and statistical significance. (Lectures: 1 hour; Exercises.: 1 hour) Topic 5: Applications of generative Artificial Intelligence to digital medicine tasks. (Lectures: 2 hours; Lab: 1 hour) Topic 5: Project work and discussions. (Exercises: 1 hour; Lab: 3 hours)

Contenuti

Topic 1: Introduction to the course. Machine. Feature Extraction. Dimensionality Reduction and Feature Selection. (Lectures: 2 hours; Lab.: 1 hour)

Topic 2: Robustness and reliability of extracted features. Interpretability and Explainability in medical Artificial Intelligence. (Lectures: 2 hours; Exercises: 1 hour)

Topic 3: Class imbalanceness. Data imputation and resampling. Data augmentation approaches. (Lectures: 2 hours; Exercises: 1 hour)

Topic 4: Performance evaluation and statistical significance. (Lectures: 1 hour; Exercises.: 1 hour)

Topic 5: Applications of generative Artificial Intelligence to digital medicine tasks. (Lectures: 2 hours; Lab: 1 hour)

Topic 5: Project work and discussions. (Exercises: 1 hour; Lab: 3 hours)

	Metodi Didattici
	The course includes 9 hours of lectures, 4 hours of supervised exercises and 5 hours of laboratory. Lectures are aimed at acquiring knowledge about advanced AI techniques for Digital Medicine. Exercises are aimed at acquiring applied knowledge and skills about Artificial Intelligence tasks in Digital Medicine. Laboratory is aimed at acquiring applied knowledge and skills about real-world projects in clinical scenarios. The course also includes a project work, consisting in the design and development of an AI-powered application for Digital Medicine to address a real clinical problem. Attendance to the lectures, exercises and laboratory is mandatory; in order to be admitted to the exam, the student must participate to at least 70% of the hours.

Metodi Didattici

The course includes 9 hours of lectures, 4 hours of supervised exercises and 5 hours of laboratory. Lectures are aimed at acquiring knowledge about advanced AI techniques for Digital Medicine. Exercises are aimed at acquiring applied knowledge and skills about Artificial Intelligence tasks in Digital Medicine. Laboratory is aimed at acquiring applied knowledge and skills about real-world projects in clinical scenarios.
The course also includes a project work, consisting in the design and development of an AI-powered application for Digital Medicine to address a real clinical problem.
Attendance to the lectures, exercises and laboratory is mandatory; in order to be admitted to the exam, the student must participate to at least 70% of the hours.

	Verifica dell'apprendimento
	The exam consists in a written test and an oral interview. The written test is composed of 5 exercises (one per topic) aimed at verifying the student’s ability to manage the main techniques presented. The oral interview has an approximate duration of 20 minutes, and includes the discussion of the project work, aimed at verifying the student’s ability to describe the design choices and the results obtained. The oral interview will also verify the theoretical knowledge of the main topics presented during the course.

Verifica dell'apprendimento

The exam consists in a written test and an oral interview. The written test is composed of 5 exercises (one per topic) aimed at verifying the student’s ability to manage the main techniques presented. The oral interview has an approximate duration of 20 minutes, and includes the discussion of the project work, aimed at verifying the student’s ability to describe the design choices and the results obtained. The oral interview will also verify the theoretical knowledge of the main topics presented during the course.

	Testi
	References [1] Raz, M., Nguyen, T. C., & Loh, E. (Eds.). (2022). Artificial Intelligence in Medicine: Applications, Limitations and Future Directions. Springer Nature. ISBN: 981191222X [2] Ranschaert, E. R., Morozov, S., & Algra, P. R. (Eds.). (2019). Artificial Intelligence in Medical Imaging: Opportunities, Applications and Risks. Springer. DOI: 10.1007/978-3-319-94878-2 Additional references [3] Bishop C.M. (2006) Pattern Recognition and Machine Learning (Information Science and Statistics). First Printing, Springer-Verlag ISBN: 978-0-387-31073-2 [4] Wang, D., Zhang, S. Large language models in medical and healthcare fields: applications, advances, and challenges. Artif Intell Rev 57, 299 (2024). DOI: 10.1007/s10462-024-10921-0

Testi

References
[1] Raz, M., Nguyen, T. C., & Loh, E. (Eds.). (2022). Artificial Intelligence in Medicine: Applications, Limitations and Future Directions. Springer Nature. ISBN: 981191222X
[2] Ranschaert, E. R., Morozov, S., & Algra, P. R. (Eds.). (2019). Artificial Intelligence in Medical Imaging: Opportunities, Applications and Risks. Springer. DOI: 10.1007/978-3-319-94878-2

Additional references
[3] Bishop C.M. (2006) Pattern Recognition and Machine Learning (Information Science and Statistics). First Printing, Springer-Verlag ISBN: 978-0-387-31073-2
[4] Wang, D., Zhang, S. Large language models in medical and healthcare fields: applications, advances, and challenges. Artif Intell Rev 57, 299 (2024). DOI: 10.1007/s10462-024-10921-0

BETA VERSION Fonte dati ESSE3 [Ultima Sincronizzazione: 2025-01-16]

Leonardo RUNDO | ADVANCED AI FOR DIGITAL MEDICINE