Approved Research

Data science approaches to the early diagnosis of human diseases

Lay summary

We want to improve the early detection of diseases such as heart conditions, mental health disorders, and cancer. We want to understand why diseases occur together, which is known as multimorbidity. We are a cross-disciplinary group of scientists based at the University of St Andrews working in different fields like molecular biology, biophysics, bioinformatics, clinical science, and data science. Detecting diseases early is important because it helps doctors provide better treatments and gives patients a higher chance of recovery.

In this study, we propose to use a large database called the UK Biobank and take advantage of its multiple layers of data. These include genetic information, brain and body images, proteomic data, and information about people health in about 500,000 participants. We will use this resource to answer research questions generated in smaller scale study. By exploring the UK Biobank, we aim to discover new patterns and clues that can help us detect diseases earlier.

To achieve this, we will use different types of analysis. These include methods that allows scanning millions of genetic variants to identify genetic risk to diseases. We will also use machine learning approaches that can extract information from highly complex and large data sets that allow us to make predictions.

These advanced computer techniques will help us to develop models that can predict diseases at an early stage and identify people who are at a higher risk. Our goal is to gain a better understanding of diseases, improve early detection methods, and develop personalized treatments. The breadth and size of UK Biobank is a unique resource to allow such type of studies.

By working together as a cross-disciplinary team we will bring together the different expertise required to understand the highly diverse datasets and to implement different methodologies. Our research has the potential to save lives by enabling earlier detection of diseases and enhancing personalized healthcare.