Data Mining in Healthcare

Code:

IM2014_11

Acronym:

ECDS

Keywords
Classification	Keyword
OFICIAL	Informatics

Instance: 2021/2022 - 2S (of 07-02-2022 to 15-07-2022)

Active?	Yes
Responsible unit:	Department of Community Medicine, Information and Health Decision Sciences
Course/CS Responsible:	Master Programme in Medical Informatics

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
MIM	20	Current Studies Plan	1	-	3	27	81

Teaching language

Portuguese

Objectives

In this curricular unit, machine learning methods will be addressed for the knowledge discovery in data (data mining) in the health area.

Learning outcomes and competences

This unit aims to empower students with the necessary knowledge and skills to: identify problems where data mining techniques could be applied; to apply data modeling methods, and specifically to apply machine learning techniques; to be able to interpret results in the context of practical medicine and clinical research in health services.

Working method

Presencial

Program

Machine learning and data mining (introduction, practical scenarios, the knowledge discovery process, specific characteristics in the area of health); data modeling, medical data preprocessing, data quality in health; supervised learning (decision trees, Bayesian classification, neural networks); unsupervised learning (cluster analysis, outlier analysis, association and mining frequent pattern analysis); evaluation of machine learning techniques (classification models, clustering); basic concepts of visual data mining, text mining and Web mining.

Software: RapidMiner, Orange, R

Mandatory literature

Jiawei Han, Micheline Kamber and Jian Pei (Authors); Data Mining: Concepts and Techniques, Morgan Kaufmann, 3rd edition, 2011
Ana Carolina Lorena, Katti Faceli, Márcia Oliveira, André Ponce de Leon Carvalho, João Gama (Authors). ; Extração de Conhecimento de Dados - Data Mining, Edições Silabo, 2012
Cruz-Correia RJ et al. ; Data Quality and Integration Issues in Electronic Health Records. In: Hristidis V (ed.). Information Discovery on Electronic Health Records: Chapman and Hall; 2009. p. 55-95.

Teaching methods and learning activities

Theoretical lectures and practical lessons, with topic discussion, individual and group exercises, and hands-on training on medical scenarios, with proper software. 

Evaluation Type

Distributed evaluation without final exam

Assessment Components

Designation	Weight (%)
Trabalho escrito	90,00
Participação presencial	10,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Apresentação/discussão de um trabalho científico	13,00
Estudo autónomo	20,00
Frequência das aulas	14,00
Trabalho de investigação	34,00
Total:	81,00

Eligibility for exams

At least 50% on the group assignment.

Calculation formula of final grade

Distributed evaluation (10%): assessment of student in the teaching / learning process, considering their active participation during classes and their involvement in carrying out the exercises and proposed work;
Group assignments (with oral presentation) related to the subjects of the course (90%).