5. Precision Medicine - Personalised Medicine and Life Sciences

This thematic area relates to the ‘medicine of the future’, principally the customisation of healthcare, with medical decisions, treatments, practises, or products being tailored to the individual patients, instead of a one‐drug‐ fits‐all model. Preventive or therapeutic interventions can then be targeted at those who will benefit, sparing expense and side effects for those who will not. Data analytics, including data mining and machine learning, is an integral part of the precision medicine model, e.g., in the discovery of new predictive or prognostic biomarkers or subgroups of patients. The number of papers reporting advances in this field are on almost an exponential rise since 2010 with Aaron Ciechanover, a Nobel Prize winner in Chemistry 2004, branding personalised medicine the “third revolution” of drug research.

Research sub-areas

5.1 Early detection and monitoring of diseases, including Parkinson’s disease and glioblastoma

Neurodegenerative diseases, including Alzheimer’s dementia (AD) and Parkinson’s disease (PD), are caused by the progressive loss of structure or function of neurons. Clinical decision support systems (based on ML), both for early detection of cognitive impairment (precursor to AD), and for individual PD patients to alert them of disease changes are being developed at UL FRI. Glioblastoma (GBM) is the most common and most lethal primary brain tumour in adults. GBM subtypes differ significantly in tumour aggressiveness and patient prognosis and are associated with unique molecular fingerprints with ML proving especially powerful to classify the subtypes.

Host institution: UL FRI

5.2 Research in explainable AI in personalised medicine

The frontier of personalised medicine is to design AI systems that can explain the decision of models that can predict patient treatments by integrating data and medical knowledge through machine learning and decision modelling.

Host institution: UL FRI

5.3 Biomarker discovery

UNG-LELS will develop ML methods and use available data on clinical phenotypes and molecular biology to discover prognostic markers and their interactions.

Host institution: UNG-LELS

SMASH research areas
1. Data Science - Machine Learning for Scientific Applications
2. Fundamental Physics - Machine learning for Particle Physics, Astrophysics and Cosmology
3. Linguistics - Computing for Human and Animal Communication
4. Climate - Machine Learning in Climate Research
5. Precision Medicine - Personalised Medicine and Life Sciences