Leveraging Supervised Machine Learning for Determining the Link between Suboptimal Health Status and the Prognosis of Chronic Diseases

Identification of people at risk of cardiometabolic diseases is a major clinical need. Such individuals can benefit from tailored treatments that can potentially reduce their risk, while bringing precision to predictive, preventive and personalised medicine (PPPM). Central to preventive medicine is the new concept of suboptimal health status (SHS), which captures individuals with subclinical conditions across five subscales using a 25-item psychometric-like instrument (SHSQ-25). Each of the subscales represents aspects of a person’s health status that could be explored in a disease continuum. Machine learning (ML) lends itself as a feasible approach to explore SHSQ-25 screening data. It can be used to transform such data into clinically useful information while enabling better health planning, disease forecasting and characterisation of disease risk. ML methods can analyse and interrogate the data in a manner not previously possible with conventional statistical methods. ML algorithms can offer robust and more streamlined means of predicting diseases, identifying individuals with the greatest clinical need and earmarking them for treatment. However, its potential to reveal suboptimal health and cardiometabolic diseases is yet to be explored. This chapter provides an overview of supervised learning, a subset of ML and how it can be applied in subclinical disease prediction.