Saltar para:
Logótipo
Comuta visibilidade da coluna esquerda
Você está em: Início > Notícias > DaSSWeb - Estimating long-term cancer-related survival from multiple prophylactic strategies: a temporal Bayesian network simulation
Mapa das Instalações
Edifício Principal | Main Building Edifício Pós-Graduações | Post-Graduate Building

DaSSWeb - Estimating long-term cancer-related survival from multiple prophylactic strategies: a temporal Bayesian network simulation

May 10th | 14:30

DaSSWeb, Data Science and Statistics Webinar
Estimating long-term cancer-related survival from multiple prophylactic strategies: a temporal Bayesian network simulation
Pedro Pereira Rodrigues

CINTESIS-RISE & University of Porto

Join us here

ABSTRACT

Estimating comparative effectiveness of multiple prophylactic strategies used in clinical practice to prevent cancer-related mortality in patients with specific gene mutations is not something we can cleanly design in clinical trial studies. Future routinely collected electronic health records might present new ways of estimating such comparative effectiveness from real-world data, but if the target population in study is too specific, collecting data from a large enough sample to enable comparison of multiple strategies might prove to be impossible. To empower clinical decisions, aiming to develop a personalized risk management guideline, we have constructed a temporal Bayesian network model to simulate the expected overall mortality in patients who underwent different prevention strategies taking into account the patient's prognostic parameters and received treatment, allowing the long term survival comparison of 9 multiple prophylactic strategies. Transition probabilities were derived from literature after a critical review of studies published in PubMed, where all risk estimates were converted into yearly estimates by means of conditional probabilities, depending on the original metric published in literature with needed conversions. For each simulated patient, the first temporal node to be activated was identified, with survival being therefore computed for each patient. Overall survival of patients from each subgroup x policy combination was then plotted as Kaplan-Meier curves. We illustrate our approach with a specific real-world problem in breast-cancer survival analysis, simulating 2.5M patients across 144 subgroup cohorts and 9 different policies, during a 40-year follow up - the illustrated example was a result of joint work with Jelena Maksimenko (Riga Stradins University, Latvia) and Maria João Cardoso (Champalimaud Foundation, Portugal).

SPEAKER

Pedro Pereira Rodrigues holds a PhD (2010) in Computer Science from the Faculty of Sciences of the University of Porto, and is currently an assistant professor in the Department of Community Medicine, Information and Decision in Health at the Faculty of Medicine of the University of Porto (FMUP), where he teaches since 2008. He is the current director of the Doctoral Program in Health Data Science at FMUP, of which he was the main promoter, and coordinator of the thematic line on Data and Decision Sciences and Technology Information (with more than 100 researchers, including 40 PhDs), from the Center for Technology and Health Services Research (CINTESIS), a research unit with more than 500 researchers, which includes the research group on Artificial Intelligence in Healthcare, from which he is an integrated member. Having participated in several national and international projects, he was the coordinator at CINTESIS of the NanoSTIMA project (financed by NORTE2020 with more than ¤ 1.1m just for the research unit), leading the line of research dedicated to Data Analysis and Decision in Health. International research and collaboration has led him to publish more than 100 complete articles in indexed journals and conference proceedings and to carry out more than 100 scientific communications, as well as to coordinate the scientific review team of several international events in the fields of data science and medical informatics. He is frequently invited as a speaker in international health data science panels and was the rapporteur for the Digital Health and Medical Technologies subtopic of the Portuguese Health Research Agenda. Having reviewed more than 300 articles for major journals and conferences, he also regularly serves as an expert project reviewer for National Science Foundations. He was the coordinator of more than 50 editions of course units in clinical decision support systems, medical informatics, data science, biostatistics and research methodology, supervises 11 PhD students (in digital health and clinical and health services research, with 5 alumni already), having participated in more than 50 master's and doctoral juries. He was director of the postgraduate course in Health Informatics and is a member of the scientific committee of the Master in Medical Informatics at FMUP since 2012, and the Integrated Master in Medicine since 2019.

Recomendar Página Voltar ao Topo
Copyright 1996-2024 © Faculdade de Economia da Universidade do Porto  I Termos e Condições  I Acessibilidade  I Índice A-Z  I Livro de Visitas
Página gerada em: 2024-10-18 às 17:09:36 | Política de Utilização Aceitável | Política de Proteção de Dados Pessoais | Denúncias
SAMA2