Caricamento in corso...
Data science in Healthcare
01OFFXC, 01OFFMV
A.A. 2026/27
Course Language
Inglese
Degree programme(s)
Master of science-level of the Bologna process in Ingegneria Biomedica - Torino
Borrow
01VSPMV 01VSPXC
Course structure
| Teaching | Hours |
|---|---|
| Lezioni | 27 |
| Esercitazioni in laboratorio | 33 |
Lecturers
| Teacher | Status | SSD | h.Les | h.Ex | h.Lab | h.Tut | Years teaching |
|---|---|---|---|---|---|---|---|
| Rosati Samanta | Professore Associato | IBIO-01/A | 25,5 | 0 | 0 | 0 | 2 |
Co-lectures
Context
| SSD | CFU | Activities | Area context | ING-INF/06 | 6 | B - Caratterizzanti | Bioingegneria |
|---|
2026/27
Con il termine "Data Science" si identifica l'insieme di teorie, tecniche e strumenti per l'estrazione di conoscenza e informazione da dati grezzi. In ambito biomedico la data science ha lo scopo di sviluppare sistemi avanzati di analisi e interpretazione di dati biomedici per costruire soluzioni in grado di supportare il personale sanitario nel percorso di diagnosi e cura dei pazienti, migliorare la qualità dell'assistenza fornita e favorire il patient empowerment. Alcune applicazioni della data science in medicina sono:
• I sistemi CAD per l'analisi di immagini mediche
• I sistemi di supporto alla definizione della terapia in base alle caratteristiche dei singoli pazienti
• I sistemi di supporto alla diagnosi precoce di malattie come il cancro, il diabete e l'Alzheimer, basata sull'analisi di dati clinici e genetici dei pazienti.
L'insegnamento approfondisce i metodi e le metodologie utilizzate per lo sviluppo di sistemi di supporto alla decisione clinica.
In the biomedical domain, data science enables the development of computational systems capable of integrating, analyzing, and interpreting heterogeneous data sources, including clinical records, biomedical signals, medical images, omics data, and patient-related information. The final aim is to develop intelligent systems to assist healthcare professionals in diagnosis, prognosis, treatment planning, patient monitoring, and risk stratification, while contributing to the improvement of care quality, process efficiency, and patient-centered medicine. Specific application areas include computer-aided diagnosis systems for medical image analysis, predictive models for early disease detection, personalized therapy support based on individual patient characteristics, and analytical tools for the interpretation of clinical and molecular data in diseases such as cancer, diabetes, neurodegenerative disorders, and other chronic or complex conditions.
The course Data Science in Healthcare provides students with the theoretical foundations, methodological principles, and practical tools required to extract clinically meaningful knowledge from biomedical data. The course focuses on the design and implementation of data-driven approaches for healthcare applications, with particular attention to clinical decision support systems. The course combines lectures and laboratory activities. The lecture component introduces the main concepts, models, and methodological frameworks of data science applied to healthcare, while the laboratory component provides hands-on experience in the development, validation, and critical assessment of a computer-aided diagnosis (CAD) system for medical image analysis.
Al termine dell'insegnamento lo studente sarà in grado di:
- conoscere e applicare gli step per lo sviluppo e la validazione di un sistema CAD
- conoscere e comprendere le problematiche generali legate allo sviluppo di un sistema di supporto alla decisione clinica (protezione dati, efficacia del risultato, ...)
Knowledge and understanding
Students will acquire knowledge and understanding of the main principles, methods, and applications of data science in healthcare. In particular, they will be able to:
- describe the role of data science in biomedical and clinical decision-making;
- explain the architecture, objectives, and limitations of computer-aided diagnosis systems;
- identify the main methodological steps involved in Knowledge Discovery in Databases and pattern mining;
- describe the principles of association rule mining and its relevance for healthcare data analysis;
- understand the basic concepts and methodological aspects of clinical studies;
- recognize the potential of Natural Language Processing techniques for the analysis of Electronic Health Records.
Applying knowledge and understanding
Students will be able to apply data science methods to biomedical and healthcare problems. In particular, they will be able to:
- design the main components of a CAD system;
- preprocess and analyze biomedical datasets using appropriate computational methods;
- evaluate the performance and clinical applicability of a CAD system;
Communication skills
Students will be able to communicate technical and methodological aspects of healthcare data science clearly and effectively. In particular, they will be able to:
- present the design and results of a data science application in healthcare;
- explain the functioning of a CAD system using appropriate scientific terminology;
- discuss analytical results with both technical and clinical audiences;
- communicate effectively within a team, coordinating tasks and integrating individual contributions into a coherent group project.
Making judgements
Students will develop the ability to assess data-driven solutions in healthcare. In particular, they will be able to:
- evaluate the strengths and limitations of computational models for clinical decision support;
- assess methodological issues related to data quality, validation, reproducibility, and generalizability;
- contribute to shared technical and methodological decisions within a project group.
Conoscenza delle tecniche di machine learning, classificazione e clustering
Computational intelligence and machine learning methods.
Durante l’insegnamento verranno trattati i seguenti argomenti:
- Fasi per lo sviluppo e la validazione di un sistema CAD
- Natural Language Processing
- Knowledge discovery in dataset e pattern mining
- Association Rules
- Studi clinici, comitati etici e protezione dei dati
- Certificazione di software basati su AI
L'attività di laboratorio è relativa a sviluppo di un sistema CAD.
01. Introduction
02. Computer-aided diagnosis (CAD) systems
03. Natural Language Processing (NLP)
04. Knowledge Discovery in Datasets (KDD) & Pattern Mining
05. Association Rules
06. Clinical Studies
LABORATORY: Design and Construction of a CAD system
Il corso consiste di 27 ore di lezioni teoriche e 33 ore di laboratorio
The course consists of 27 hours of lectures and 33 hours of laboratory activities
Verranno messe a disposizione degli studenti le slide delle lezioni ed eventuale materiale per l'approfondimento di argomenti specifici
Slides
Slides; Video lezioni dell’anno corrente;
Lecture slides; Video lectures (current year);
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;
...
L'esame consiste di:
Scritto [21 pt] - Valuta le Conoscenze – Chi si ripresenta perde la valutazione precedente:
- 15 domande a risposta multipla (1 punto per ogni domanda corretta, -0.3 pt per ogni domanda errata) – durata: 17 minuti
- 2 domande a risposta aperta (3 punti a domanda) – durata: 20 minuti
Valutazione del lavoro svolto durante i laboratori da parte del gruppo [12 pt]– Valuta l’Autonomia di giudizio, le Abilità comunicative e la Capacità di lavorare in un team
- 4 punti ottenuti tramite peer review
- 8 punti ottenuti dalla valutazione delle docenti
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.
Exam: Group project; Computer-based written test in class using POLITO platform;
The exam consists of a written test and a laboratory project.
The grade is obtained by summing:
a) Written test lasting 20 minute and consisting in 20 multiple choice questions, max 20 points. It evaluates the knowledge acquired on the methods. During the text the student is not allowed to use his/her notes or any other material.
b) Laboratory project: max 13 points. It evaluates the ability of the students to work in team, present the results of their work and their autonomy of judgment. Four points come from the peer review of other teams projects and 9 points come from the teacher evaluation.
In addition to the message sent by the online system, students with disabilities or Specific Learning Disorders (SLD) are invited to directly inform the professor in charge of the course about the special arrangements for the exam that have been agreed with the Special Needs Unit. The professor has to be informed at least one week before the beginning of the examination session in order to provide students with the most suitable arrangements for each specific type of exam.