Advancing Healthcare with Data Science | DSPT #117 @ Porto
Details
Hello, DSPT community! We’re kicking off the second semester of 2024 with an exciting DSPT Meetup in Porto at UPTEC.
Join us as we explore the transformative impact of Machine Learning and AI in the healthcare field with insightful talks by Raquel Belo from DevScope and João Pedro Pedroso, professor at the Faculty of Science, University of Porto. Don’t miss this opportunity to see cutting-edge applications of AI in healthcare and connect with fellow enthusiasts!
Book your spot today and don’t forget to add the event to your calendar!
=== SCHEDULE ===
The preliminary agenda for the meetup is the following:
- 18:15 - 18:30: Get together.
- 18:30 - 18:40: Welcome message.
- 18:40 - 19:20: Talk + Q&A: “Machine Learning for Helicobacter Pylori Analysis and Diagnosis in Whole Slide Images” by Raquel Belo, Data Scientist @ DevScope.
- 19:20 - 20:00 Talk + Q&A: “Improving Kidney Exchange Programs” by João Pedro Pedroso, Associate Professor@ FCUP.
- 20:00 - 20:30: Networking.
=== Talk Abstract ===
- Machine Learning for Helicobacter Pylori Analysis and Diagnosis in Whole Slide Image
The diagnosis of infection by the bacteria Helicobacter Pylori is often performed through manual analysis of histological images, which, due to the considerable size of these images, becomes an exhaustive task for pathologists. In this talk, we'll show you how we used Machine Learning techniques to automatically detect the presence of bacteria, indicating its location in the images. Additionally, by combining the detection of the bacterium with the identification of inflammation in the tissue, it is possible to perform the final diagnosis quickly and efficiently, also allowing visualization of the specific points in the image that support the diagnosis.
- Improving Kidney Exchange Programs
Renal diseases affect thousands of patients who, to survive, must incur in dialysis -- a costly treatment with many negative implications in their quality of life. As an alternative, patients may enter a waiting list for receiving a kidney from a deceased donor; however, waiting times are typically very long. For reducing the waiting time, another alternative in some countries is to find a healthy living donor -- usually, a relative of a person emotionally connected -- who volunteers to cede one of their kidneys. However, in some situations transplantation is not possible due to blood, or tissue-level incompatibility. In these cases, a donor-patient pair may enter a pool of pairs in the same situation, in the hope of finding compatibility in crossed transplants.
The problem has been studied under different perspectives, but the most commonly used objective is maximizing the number of patients in the pool for which a crossed transplant is possible.
We propose to change this objective by that of maximizing the cumulative patient survival times. This model departs from the previous deterministic setting, putting into play a method for predicting survival time based on historical data.
=== About the speakers ===
Raquel is an alumna of FEUP. For the past three years, she has specialized in deep learning within the medical field, focusing primarily on research involving radiology and histology images. Her work has been recognized with publications and presentations at international conferences, establishing her as an active member in the research community, where she aspires to further her career as a data scientist at DevScope.
J.P.Pedroso holds a PhD in Computational Mathematics (1996). He is a researcher at the Mathematics Center of Porto University (CMUP) and Associate Professor at the Faculty of Sciences, University of Porto, lecturing in Artificial Intelligence, Operations Research and related subjects. He participated in EU projects LISCOS, CIVITAS-ELAN, and FIT4U, on optimization models for planning. Also participated in FCT projects CORAL, mKEP, TEC4Growth, LastMile and Transformer 4.0, on tasks concerning optimization, simulation and machine learning, with a special focus on modeling and solving problems under uncertainty. He publishes and acts as a reviewer in leading international journals in the area, and co-authored two books on computer programming for optimization.
Advancing Healthcare with Data Science | DSPT #117 @ Porto