Probabilistic Graphical Models

Code:

IM2014_13

Acronym:

MGP

Keywords
Classification	Keyword
OFICIAL	Statistics

Instance: 2020/2021 - 2S (of 08-02-2021 to 30-07-2021)

Active?	Yes
Responsible unit:	Departamento de Medicina da Comunidade, Informação e Decisão em Saúde
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	3	Plano Oficial (Atualizado Despacho n.º 5137/2020)	1	-	3	27	81

Teaching language

Portuguese

Objectives

This unit aims to empower the students with necessary knowledge and skills to use modern methods of probabilistic reasoning for biomedical problems, more specifically regarding theory and practice of Bayesian networks for interdependencies exploration and clinical decision support.

 

Learning outcomes and competences

• Identify different types of uncertainty inherent in clinical practice.


• Understand the main objectives of Bayesian inference for clinical decision support.


• Describe the theory of Bayesian networks, its objectives and the main features.


• Observe clinical applications of Bayesian networks in different areas and outcomes.

Working method

Presencial

Program

• Introduction

• Motivation and examples


• Probability and medical applciations


• Probabilistic graphical models


• Introduction to Bayesian networks

• Bayesian networks
  
  
  
  • Semantics and factorization
  
  
  • Probabilistic influence flow
  
  
  • Conditional independence andnaive Bayes
  
  
  • Causal independence
  
  
  • Temporal Bayesian networks
  
  
  
  


• Building Bayesian networks from data
  
  
  
  • Machine learning
  
  
  • Bayesian network parameter estimation
  
  
  • Bayesian network structure learning
  
  
  • Learning and inferring from incomplete data
  
  
  
  

Mandatory literature

Darwiche, A. ; Modeling and Reasoning with Bayesian Networks, Cambridge University Press, 2009
Darwiche, A. ; Bayesian networks, Communications of the ACM, 53(12), 80–90, 2010
Lucas, P. J. F., van der Gaag, L. C., & Abu-Hanna, A. ; Bayesian networks in biomedicine and health-care, Artificial Intelligence in Medicine, 30(3), 201–14., 2004
Lucas, P. ; Bayesian analysis, pattern analysis, and data mining in health care, Current Opinion in Critical Care, 10(5), 399–403., 2004
Koller, D., & Friedman, N. ; Probabilistic Graphical Models - Principles and Techniques, MIT Press., 2009
Cowell, R. G., Dawid, P., Lauritzen, S. L., & Spiegelhalter, D. J. ; Probabilistic Networks and Expert Systems: Exact Computational Methods for Bayesian Networks, Springer, 2007

Teaching methods and learning activities

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

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	20,00
Trabalho laboratorial	80,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Apresentação/discussão de um trabalho científico	13,00
Estudo autónomo	29,00
Frequência das aulas	14,00
Trabalho laboratorial	25,00
Total:	81,00

Eligibility for exams

Delivery of an assignment during the evaluation process.

Calculation formula of final grade

Evaluation will be based on practical assignments (80%) and final exam (20%).