epidemic intelligence

João Pita Costa is a PhD in Mathematics from the University of Ljubljana. He worked as a researcher in topological data analysis at the Institute Jozef Stefan, extending this collaboration as a senior researcher in the spin-off Quintelligence, where he took a key role in the MIDAS project using Big Data to support policy-making in public health, and in UNESCO International Research Center for Artificial Intelligence, IRCAI, where he is designing SDG observatories including the focus on health and well-being. He is also a lecturer on AI-related topics at the Barcelona Business School, ENEB. He also collaborates with XLAB as an innovation manager, and was head of marketing at the bioinformatics SME Genialis.

INFLUENZA LAB

The contributions of computational topology to the study of epidemiology.

During the past two years I have been working with Primož Škraba over part of the Influenzanet data on several applications of persistence homology to topological medical data analysis. We have presented a poster at the European Conference on Complex Systems 2014 Conference in Lucca, another poster at the ACM Digital Health Conference 2015 in Firenze, and had several talks in Ljubljana and Rijeka on this research topic.

Influenzanet is a system to monitor the activity of influenza-like-illness (ILI) with the aid of volunteers via the internet. It has been operational for more than 10 years at the EU level since 2008. In contrast with the traditional system of sentinel networks of mainly primary care physicians, Influenzanet obtains its data directly from the population. This creates a fast and flexible monitoring system whose uniformity allows for direct comparison of ILI rates between countries.

Topological data analysis is interested in problems relating t

o nonlinear systems, large scale data and development of more accurate models, that contribute to a high level research. The study of Epidemiology is a great source of problems that focus aspects of such nature. Moreover, persistence can provide such research with high dimension techniques for medical data analysis. In particular, per- sistence diagrams are a clear and practical tool that allows us the detection of outliers and to capture the dynamics of the system. During further reseach we will investigate if those exceptional points evident for the Mahalanobis metric are distinct under other metrics, and learn the appropriate metric such that those outliers are close enough. We shall also use kernels and SVMs on these features, enabling a machine learning approach over this data.

Using persistence we are able to analyze the Influenzanet data identifying several topological features relevant to the epidemiological study. In particular, we can identify data noise, distinguish higher dimension features and look at join spaces between countries. This is done both in terms of the overall structure of a disease as well as its evolution. Finally, it provides a way to test agreement at a global scale arising from standard local models.

Profiles

Reviewer for the Medicine and Public Health section of the Journal Frontiers in AI

Reviewer for the AI section of the Journal PLOS One

Reviewer for the European Commission on Horizon Europe project proposals

Research papers

[4] Joao Pita Costa, Daniela Paolotti, Flavio Fuart, Primož Škraba, Evgenia Belayeva, Inna Novalija. Supporting Epidemic Intelligence, Personalised and Public Health with advanced computational methods. EM-Health Workshop, Ljubljana, Slovenia (2015).

[3] J. Pita Costa and P. Škraba. A topological data analysis approach to the epidemiology of Influenza. Conference Proceedings of SIKDD 2015, Slovenia (2015).

[2] Joao Pita Costa and Primož Škraba. Topological analysis of epidemiological data. Manuscript. (2015)

[1] Joao Pita Costa and Tihana Grbac. Topological analysis of system defectiveness. Manuscript. (2015)

Conference Talks & Posters

2015.10.12 Supporting epidemic intelligence, personalised and public health with advanced computational methods. Delavnica EM-Zdravje, Ljubljana, Slovenia.

2015.10.05 A topological data analysis approach to the epidemiology of Influenza. SIKDD, Ljubljana, Slovenia.

2015.05.18 Topological epidemiological data analysis, ACM Digital Health Conference 2015, Firenze, Italy.

2014.09.23 T opological analysis of Influenza data, European Conference of Complexity Science 2014, Lucca, Italy.

Seminar Talks & Workshops

2015.10.10 T opological analysis of Influenza data, BioTech Department, University of Rijeka, Croatia.

2014.11.19 T opological analysis of Influenza data, AI Lab, Inštitut Jozef Štefan, Ljubljana, Slovenija.

2014.04.25 Towards a topos foundation for persistence with applications. Seminar of the Society of Mathematicians and Physicists of Rijeka, Rijeka, Croatia.

2014.02.19 A topos for topological data analysis with possible applications for Influenzanet. AI Lab, Inštitut Jozef Štefan, Ljubljana, Slovenija.

Code

2015.05.18 Comparison of the time series of 5 years of Influenzanet in Portugal and Italy using Fourier analysis and TDA , Matlab + Perseus + PLT.

2014.09.23 Simultaneous analysis of ILI incidences for 10 years of Influenzanet in the Netherlands, Matlab + Perseus.

References

Primož Škraba, Institut Jozef Stefan, Ljubljana.

Daniela Paolotti, ISI, Torino.

Gabriela Gomes, Gulbenkian Science Institute, Lisbon.

Maja Sočan, Slovenian Public Health Institute [NIJZ], Ljubljana.

Ricardo Mexia, Portuguese Public Health Institute [INSA], Lisbon.

Graham Ellis, University of Galway, Ireland.

Tihana Grbac, University of Rijeka, Rijeka.

JOÃO PITA COSTA 2022

Page updated

Google Sites

Report abuse