Precision medicine represents a paradigm shift from a one-size-fits-all approach to clinical decision making to a computational approach that enables predictive data-driven analytics based on the vast amount of omics and big data generated at the individual level [1]. This will help facilitate personalised treatment decisions and thus reduce healthcare costs, improve clinical outcomes, and enhance patient experiences [2][3][4]. The conceptual framework will rely on rapidly advancing omics technology for characterising patients (e.g. proteomics, metabolomics, genomics, pharmacogenomics, etc.), development of large-scale clinical databases, electronic health records, and state of the art computational modelling, pattern recognition, and machine learning tools for analysing large volumes of individual patient data [5].
Various computational models have been developed to predict mode-of-action and response-to-treatment across various levels of biological organisation [3]. One of the challenges currently facing precision medicine, however, is not just the generation of models at disparate levels of biological organisation, but incorporating insights from these models to create holistic multiscale models [3]. Moreover, while whole genome sequencing may be useful in determining if a particular therapy is safe or suitable for a patient, other factors, such as, age, gender, and lifestyle also have a significant effect on therapy [6]. This represents a further challenge for precision medicine, namely that of integrating multimodal models based on various patient-specific data types to predict response at each biological and non-biological level of abstraction, both singly and simultaneously [3]. This challenge has, so far, largely been unmet because patient-specific modelling has rarely been used in exploring well-being and disease prevention.
This PhD intends to explore how patient well-being and care can be improved by deriving meaningful insights from patient generated data that will help reduce the burden of disease through prevention and possibly even early detection. This will involve mining patient data to create enhanced personal medical identities (EPMIs) and using these EPMIs to inform preventive health measures, which are adapted to individual predispositions and behaviours.
An EPMI is a holistic virtual representation of a patient, which takes into account all available and meaningful information about the patient. This information will potentially include a patient’s medical history, exposure to environmental factors (e.g. pathogen exposure, pollution levels), genomic information, phenotypic characteristics at the molecular or cellular level (proteomes, metabolomes, etc.), as well as, the behavioural level (diet, sleep, physical activity, etc.). EPMIs, when combined with predictive modelling based on known interactions and patterns in diagnosis, treatment, etc., will help inform the personal needs of the patient. For example, following patient stratification, based on individual variations in EPMIs, the patient may be able to receive, in real-time, an accelerated diagnosis, tailored treatments, and informed lifestyle choices.
The PhD will, therefore, seek to combine areas of data exploration, data governance, data access, data integration, and data analysis, which harnesses the volume, velocity and veracity of patient data, to address current and future healthcare challenges.
This author is supported by the Horizon Centre for Doctoral Training at the University of Nottingham (RCUK Grant No. EP/L015463/1) and Nottingham University Hospitals Trust.