Mathematical models may help predict development of neurodegenerative diseases

Credit: Pixabay/CC0 Public Domain

ICT is revolutionizing the world, and the health sector is no exception. ICT is a strategic factor in improving people’s health and ensuring a high-quality, modern and sustainable health care system.

Artificial intelligence (AI) is one of the most promising technologies, which is able to create and train computer systems to make automated data-driven decisions. Two recent studies involving researchers from the Universidad Uberta de Catalunya (UOC) and the August Pi i Sunyer Institute for Biomedical Research (IDIBAPS) have highlighted the potential for AI to be applied in the fields of image processing, bioinformatics and genetics, respectively.

“There is a huge range of applications for big data and artificial intelligence in CT scans, X-rays, ultrasounds and MRIJordi Casas Roma, a researcher in the AdaS Lab research group at the Center for Electronic Health, a member of the College of Computer Science, Multimedia and Communications, and director of the Master’s degree in Data Science at UBC says.

The researchers involved in their latest study showed that “merging and processing all data together, using multi-layer networks, provides a more comprehensive analysis of the data than if it were analyzed individually and independently.”

Mathematics to understand changes in the brain

Casas study focuses on identifying a Mathematical model Provides a better understanding of cognitive changes and impairments in the brain. The model was initially tested with multiple sclerosis, but the pattern is applicable to other types Neurological diseases.

“Understanding what happens in the brain when someone has this type of disease is the first step towards being able to improve and personalize treatment. It is important to be able to identify and predict how the disease will progress, which will undoubtedly enable us to distinguish between different groups of patients. , with similar types of development and different treatments from other groups,” he says.

The study was led by Ferran Prados Carrasco, another member of the AdaS lab, University of Oklahoma researchers Marcos Diaz Hurtado, of the Center for E-Health, and Albert Soleil and Javier Borg, of the Complex Systems Group (CoSIN3) at the Interdisciplinary Internet Institute. (in 3).

Prados is now putting the multi-layer network theory into practice: “We’re in the initial stage, where we’ve developed a biomarker — we’ve confirmed its sensitivity, we’ve published how it’s been used, and we’ve made the technology open so other researchers and clinicians everywhere can apply it to their data, […] At the same time, we have already started the first clinical application using MRI data from people with neurodegenerative diseases such as multiple sclerosis, Alzheimer’s disease or dementia. “

Bioinformatics and genetics

Another important area of ​​application Artificial intelligence in Health Bioinformatics and Genetics, with Algorithms for Metheurism. “These algorithms are very popular in aggregate optimization, in other words, when there is a limited set of solutions to a problem, and you want to find the one that optimizes a specific objective function. They provide high-quality solutions to complex problems in real time,” explained Laura Calvet-Lennan. , researcher and member of the College of Computer Science, Multimedia and Communication, and lead author of the study “On the Role of Transcendental Optimization in Bioinformatics.”

Calvet highlighted that “metaheuristics plays a major role in Medical Imaging and disease modeling by variable selection and parameter tuning, among others.”

The search was published in retinal neuroscience And the International Transactions in Operational Research.

Using artificial intelligence to diagnose mild cognitive impairment that progresses to Alzheimer’s disease

more information:
Jordi Casas-Roma et al, Application of multilayer analysis to morphological, structural, and functional brain networks to identify relevant patterns of dysfunction, retinal neuroscience (2022). DOI: 10.1162 / netn_a_00258

Laura Calvet et al, On the role of metaheuristic optimization in bioinformatics, International Transactions in Operational Research (2022). DOI: 10.1111 / itor.13164

Offered by the University of Uberta de Catalunya (UOC)

the quote: Mathematical models may help predict progression of neurodegenerative diseases (2022, September 15) Retrieved September 15, 2022 from

This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.