Precision healthcare: how maths can revolutionise medicine

The holy grail of precision medicine is to deliver the right treatment to the right person at the right time. The last decade has witnessed numerous data-intensive approaches to diagnostics and treatment. These aim to develop traditional practice from 'one-size-fits-all' approaches towards patient-specific strategies.

Thanks to progress in screening technologies such as DNA sequencing, metabolomics and single-cell technologies, we can now access ever more detailed maps of the molecular make-up of the human body. Precision medicine offers clinicians a new lens to distinguish healthy individuals from sick ones, and stratify them across stages of disease progression.

With the power of data analysis algorithms, molecular screens can reveal the sources of disease and cast light on new drug targets to restore normal function. Machine learning algorithms for patient data can deliver promising outcomes when predicting disease progression, and image analysis algorithms can aid diagnostics for a range of medical conditions.

Yet precision medicine requires sophisticated screening technologies not available in many parts of the world, especially in low and middle-income countries. This is a hurdle for its implementation worldwide and, most problematically, places an upper ceiling to what it can deliver on a global scale. There is even potential for precision medicine to increase inequality in medical care and wellbeing between countries and the socioeconomic groups within them.

The nascent concept of precision healthcare aims to integrate patient data with vast amounts of population data available from national health systems. By bringing population data and socioeconomic contexts into the equation, precision healthcare promises to improve quality of care and democratize access to patient-specific treatments. The integration of these two layers will result in richer models that reflect the multidimensional nature of diagnostics and treatment. For example, an individual’s health often cannot be separated from their social and geographical context. Precision healthcare can be used to extract risk factors from population data, such as community membership or age, and pair them with patient-specific information. This convergence can lead to improved clinical decision-making, reduced costs for health systems and better health outcomes.

The advent of precision healthcare raises a host of technical challenges. The interface of individual-level data and public health data requires new mathematical tools for characterization of various relevant factors such as disease progression, medical interventions, and healthcare provision. There is an urgent need for new mathematics to integrate individual and population data at a resolution that is both tractable and intelligible. Computational models should be coarse enough to be manipulated and understood by practitioners, yet detailed enough to account for the specificities of the disease and population of interest. Models should capture the complexity of data and, at the same time, produce tractable descriptions that can aid clinical decision-making.

This is a fine balance that must be at the core of the new mathematics underpinning the future of precision healthcare. Cross-disciplinary initiatives such as the EPSRC Centre for Mathematics of Precision Healthcare at Imperial College London are leading the charge in this new space, partnering with clinicians and public health specialists to develop the next generation of methodologies for data integration and analysis.

For precision healthcare to live up to its promises, there are various issues to be resolved around regulatory aspects for data acquisition and processing. This is an enormous task that will require a concerted effort among all stakeholders, including patient groups, clinicians, public health bodies and civil society. Such collaboration is needed to ensure that everyone benefits from rapid progress in health technologies. In this new era of precision healthcare, data is the fuel for radical changes in the way global health systems work.