Nowadays during clinical studies, both retrospective studies and clinical trials, a huge amount of data is collected leading to the construction of large repositories from wich big datasets can be extracted. Data mining is the process of evaluating existing datasets to extract new insights from them. Using Data mining techniques researchers are able to extract import information from data. These methods belong to Machine Learning (ML), statistics, and database systems areas. The course presents a set of ML techniques (clustering and association rules) that can be applied to the dataset to analyse the data. The results are the discover of new patterns and rules that can be applied to construct new knowledge or to develop new decision support systems.

none

The course is divided in lessons and laboratory work. 1. Introduction 2. Data storage and Data Cleaning 3. Missing Data 4. Clustering 5. Associative Rules 6. Applications During the laboratory lessons the students will work in team and apply data mining techniques to real data. with the aim of stressing important technical issues related to the specificity of the clinical problem

A distanza in modalità sincrona

Sviluppo di project work in team

P.D.2-2 - Maggio

Il corso inizierà giovedì 6 marzo 2025, l'orario verrà comunicato più avanti. Essendo un corso basato sullo svolgimento di un progetto le lezioni successive saranno concordate con i partecipanti in funzione delle attività da svolgere.