Biological age estimation using learning approaches

Degree Course: 
Biomedical/Electronic/Computer science engineer (Information-engineering track)
Location: 
Department of Information Engineering - UNIVPM
Description: 

The age of an individual can be estimated by either calculating chronological age (CA) or biological age (BA). The concept of biological aging was proposed to provide a reliable estimation of the degree of aging process. Many scientists approached the concept of BA using various biomarkers and estimation algorithms. However, no optimal universal method for estimating the BA of an individual has received consensus approval. The increasing amount of data collected in the EHRs have witnessed recent increasing in the application of data-driven approaches in the biomedical informatics field. In this context machine learning approaches can be applied in order to provide a reliable estimation of BA. In this context, the candidate will be required to study, investigate and apply machine-learning approaches to estimate the biological age.

Aim: Applying machine learning and deep learning to estimate the biological age from electronic health records (EHRs)

Supervisors: Prof. Emanuele Frontoni, Prof. Andrea Monteriù, Luca Romeo, Sara Moccia, Michele Bernardini

Start: Sept, 2018

Expected graduation: Feb/July, 2019

Skills that will be acquired: Programming (Python, MATLAB)

Project: MIR-AGE (http://www.monteriu.com/bioage/)

Contacts: {e.frontoni, l.romeo, s.moccia}@univpm.it

 

Academic Tutor: 
Emanuele Frontoni