Title | MSc in Biomedical Data Science |
Website | Master oficial website-URV |
Edition | 2023/24 (2nd edition) |
Seats | 50 |
ECTS | 120 Total (18 Master Thesis) / 2 Academic Years |
Universities | URV (Coordinator), UPC, UB, UAB, UdL, UdG, UVic-UCC ~ 20 departments |
Language | English |
Modality | Virtual training (up to 30% syncronicity) / Optionally face-to-face (Summer school, Master Thesis) |
Time slots for synchronicity | Monday to Friday 14:00-17:00/17:30 |
Candidates Profile | Graduates in Engineering, Computer Science, Experimental Sciences, Bioinformatics |
Program driver | Bioinformatics Barcelona (BIB) |
Programme sponsor | AMGEN |
Academic Commitee | Sergio Gómez, Maria Vinaixa (URV); Petia Ivanova (UB); Alex Perera (UPC); Lola Rexachs (UAB); Rui Alves (UdL); Beatriz López (UdG); Mireia Olivella (UVic-UCC); Ana Ripoll (BIB) |
Clinical Advisory Committee | Hospital Arnau de Vilanova, Hospital Josep Trueta, Hospital Clínic, Hospital San Joan de Deu, Hospital del Mar, Hospital de l a Vall d’Hebron, Hospital Sant Pau, Hospital Germans Trias i Pujol, Hospital Sant Joan, Hospital Joan XXIII, Hospital de Vic i l ’Hospital Parc Taulí |
Corporate Advisory Committee | AMGEN, Bitac, Costaisa, Made of Genes, Sequentia, Aizon, Janssen and, Barcelona Tech City. |
The MSc in Biomedical Data Science program is aimed at providing the interdisciplinary training necessary to handle, manage and analyse and model large-scale biomedical data. Our vision is to build a intensely intersiciplinary and domain-dependent technological program leveraging informatics/data science and basic biomedical knowledge.
Core comptences are assembled over the big data value chain ― a roadmap to big data value creation ― offering a unique technological programme with particular emphasis on the domain.
A single block of compulsory courses organized in seven different subjects
BDC—Biomedical data challenges—3 ECTS
The big data value chain
Precision medicine
Biomedical challenges and data science, practical cases
BE—Biomedicine for engineers—4.5 ECTS
Molecular biology and Cellular biology. Macromolecules. Cellular components and their function.
Physiology. The human body. Nervous and motor systems. Respiratory, digestive, inmune and endocrine systems. Homeostasis.
SS—Summer School—3 ECTS
Advances in biomedical data analysis
Biomedical data stewardship and governance
Valorization in biomedical data analysis, practical cases
EHR—Electronic health records—4.5 ECTS
Clinical databases
ETL(Extract/Transform and Load) processes
Free text mining
Cohorts design and generation
MI—Medical imaging—4.5 ECTS
Basics on medical imaging
RX imaging
Ultrasound imaging
Magnetic resonance imaging (MRI)
Nuclear Medicine Imaging
Digital pathology imaging
Other imaging technologies in healthcare
BSSP—Biomedical sensors and signal processing—3 ECTS
Biomedical sensors and actuators
Data acquisition in sensor based systems
Biomedical digital signal processing
Statistical signal processing and feature extraction
ERP—Ethics, regulation and privacy—4.5 ECTS
Legislation of biomedical data
Good practices and regulation in the management of biomedical data
Values and ethical challenges in data science applied to biomedicine
Bioethics committees
Privacy technologies
Data anonymization
SP—Scientific programming—4.5 ECTS
Environment for scientific computing: Unix shell and operating systems. Code management, collaborative coding, revision control and documentation. Dockerization
Introduction to statistical programming (R).
Introduction to functional programming for scientific computing (Python)
Scalable analysis. Processing of large volumes of data.
Application challenges. Biomedical data dashboards.
Multivariate data and application to EDA. Dimensionality reduction techniques.
HPDC—High-performance and distributed computing for big data—6 ECTS
Concepts and architecture of high performance computing (HPC)
Algorithms and parallel programming
Cloud computing architecture
Cloud computing models and applications
Management and processing of large volumes of data
BS—Biomedical statistics—6 ECTS
Study design in biomedicine
Statistical models
Parameter estimation and inference
Risk assessment in biomedical studies
Logistic regression
MLPM—Machine learning for precision medicine—6 ECTS
Fundamentals of machine learning
Feature Extraction
Supervised learning
Unsupervised learning
CN—Complex networks—4.5 ECTS
Structural properties of complex networks
Complex network models
Mesoscopic description of complex networks
Dynamics in complex networks
HDVC—Health data visualization and communication—4.5 ECTS
Fundamentals of information visualization
Tools for creating graphic representations
Interpretability of graphic representations
AHDA—Advanced health data analysis—6 ECTS
Advanced regression analysis
Survival analysis
Bayesian Analysis
Causal inference
DL—Deep learning—4.5 ECTS
Basics of artificial neural networks
Back-propagation training
Deep learning
Auto-encoders
Convolutional networks
Recurring networks
Explainability and interpretability
TMH—Text mining for healthcare—3 ECTS
Basic concepts of language processing. Text particularities in the medical domain.
Word level: Morphological disambiguation. Lexical semantics. Distributional semantics.
Sequence level: Recognition and classification of entities.
Text mining: Text classification. Relationship Extraction.
CAD—Computer-aided diagnosis and decision making—4.5 ECTS
Diagnostic techniques and computer-assisted decision-making in medical applications
Approaches and techniques based on machine learning and artificial intelligence for decision making
Case studies at different levels: primary care, hospitals, geriatric care, and health resource management
CE—Computational epidemiology—4.5 ECTS
Introduction to computational epidemiology
Basic epidemiological models
Advanced epidemiological models
Stochastic simulation of epidemiological models
COTM—Clinical -omics and translational medicine—4.5 ECTS
Experimental design / QC/QA in -omics data
Computational Metabolomics
Computational Proteomics
Differential gene expression
Enrichment and functional analysis
AMI—Advanced medical image analysis—4.5 ECTS
Image pre-processing
Image registration
Image segmentation
Applications for the analysis of medical images
HDI—Health data integration—3 ECTS
Omic and phenotypic information integration systems
Analysis environments in genetic disorders, cancer and complex diseases
Disease trajectory analysis
PRM—Project and research methodologies—4.5 ECTS
Fundamentals of scientific research
Criteria for quality research
Methodology and research stages
Dissemination of research
Regulatory, ethical and social management of research
Specific management of research in biomedicine and data science
Project management
Agile IT project management methodologies
Economic management and exploitation of projects
EI—Entrepreneurship and innovation—4.5 ECTS
The process of generating ideas, co-creation and innovation
The value proposition and business model (Canvas)
Communication skills for entrepreneur
Marketing and sales of the entrepreneurial project
Financial, tax and legal aspects of the entrepreneurial project
MT—Master’s Thesis—18 ECTS
Research areas: Mathematics and statistics; Biomedicine; Bioinformatics; Computer Science; Engineering
Main topics for the master’s thesis: Medical informatics; Digital medical records; Cloud computing; Parallel and distributed computing; Security, privacy, anonymization and encryption of medical data; Biosignal processing; Internet of things; Artificial intelligence applied to health; Machine learning; Deep learning; Case-based reasoning; Intelligent diagnosis support systems; Natural language processing; Medical image;Computer vision; Analysis of complex systems; Computational epidemiology; Biomedical data science in public health; Clinical trials; Biostatistics; Computational statistics; Cluster analysis and classification; Bayesian Statistics; Probability models for discrete data; Sciences -omics; Metabolomics and spatial metabolomics; Synthetic biology; Systems Biology;Bioinformatics; Structural biology
The programme spans 4 semesters - 15 school weeks each (2 academic years)
MON | TUE | WED | THU | FRI | MON | TUE | WED | THU | FRI | |
---|---|---|---|---|---|---|---|---|---|---|
14:00-14:30 | MI | BDC | MI | BE | SP | AHDA | HPDC | HPDC | AHDA | MLPM |
14:30-15:00 | MI | BDC | MI | BE | SP | AHDA | HPDC | HPDC | AHDA | MLPM |
15:00-15:30 | MI | BDC | BS | BE | BS | AHDA | HPDC | HPDC | AHDA | MLPM |
15:30-16:00 | BS | EHR | BS | BSSP | BS | PRM | ERP | MLPM | PRM | ERP |
16:00-16:30 | BS | EHR | SP | BSSP | EHR | PRM | ERP | MLPM | PRM | ERP |
16:30-17:00 | BE | EHR | SP | BSSP | EHR | PRM | ERP | MLPM | ||
17:00-17:30 | BE | SP |
MON | TUE | WED | THU | FRI | MON | TUE | WED | THU | FRI | |
---|---|---|---|---|---|---|---|---|---|---|
14:00-14:30 | CE | TMH | CAD* | DL | CN | AMI | AMI | |||
14:30-15:00 | CE | TMH | CAD* | DL | CN | AMI | AMI | |||
15:00-15:30 | COTM | TMH | HDVC | COTM | CN | AMI | EI | |||
15:30-16:00 | COTM | CAD | HDVC | COTM | HDVC | HDI | EI | |||
16:00-16:30 | COTM | CAD | CE | DL | HDVC | HDI | EI | |||
16:30-17:00 | CN | CAD | CE | DL | HDVC | HDI | EI | |||
17:00-17:30 | CN | CAD | CE | DL | EI |
Big data explosion in the clinical setting (i.e., EHR; medical imaging; systems-medicine; public health data; mobile health data, etc) offering an unprecedented potential to advance towards precision medicine.
Increasing workforce demand and short supply of those specialist able to manage, process and get value and knowledge out of these large data volumes
Biomedical Data Science is an emerging, fast-moving and multidisciplinary discipline encompassing the use of critical thinking and analytics to handle, manage and derive knowledge from large sources of biomedical data.
A Biomedical Data Scientist is a specialist with an interdisciplinary mindset that:
Works collaboratively with teams of faculty and health care providers to draw insight and intelligence from large datasets.
Develops and creates models, algorithms and/or tools to tackle data-driven biomedical problems.
Uses data mining, statistics, statistical modeling and machine learning to understand relationships and patterns in biomedical data.
Translates analytics into information that can be used by clinical and operational leadership.
Seminal and inspirational work to built upon to establish this Biomedical Data Science programme: Trans-NIH Big Data to Knowledge (BD2K, USA) and Health Data Research, UK initiatives
e-mail the coordinators for information on the programme
e-mail the secretariat for information on pre-registration, admission and registration