Turing Fellow draws on extra-galactic astronomy to optimise blood pressure treatments
Astronomer Dr Francesco Shankar will develop a smart algorithm for optimising hypertension management strategies in a new role with The Alan Turing Institute.
The researcher, from Physics and Astronomy at the University of Southampton, will exploit a common technique used in extra-galactic astronomy to assist clinical decision making in blood pressure treatments.
Francesco will lead the pilot project as a newly announced Turing Fellow at the UK's national institute for data science and artificial intelligence.
The University is a partner of The Alan Turing Institute, supporting its goal to apply research to real-world problems, driving economic impact and societal good, leading the training of a new generation of scientists, and shaping the public conversation around data.
The new project will build upon an existing collaboration between Southampton Astronomy Group and the Department of Clinical Pharmacology of St Thomas' Hospital in London to generate a cutting-edge Hierarchical Bayesian Monte Carlo model that can probe the complex behaviours of large groups of patients.
"Our team has shown that Monte Carlo simulations are a powerful tool for examining the influence of uncertainties on outcome misclassification and to devise ameliorated treatment strategies," Francesco says. "Nevertheless, this type of technique has been largely overlooked in medical science.
"Previous studies have mostly used probabilistic simulations to investigate how measurement error can impact on the diagnosis of hypertension, with both inadequate device calibration and normal physiological variation contributing to misdiagnosis. The level of analytical and computational advancements we propose represent a clear step forward in the field of statistical medical science, helping bridge the gap between measured and true outcomes of medical treatment of hypertension."
Current medical management of many common conditions involves initiating or changing treatment based on quantitative, semi-quantitative or qualitative thresholds. Variation or uncertainty in these values due to measurement error or physiological variation has the potential to result in erroneous decisions, with significant implications for efficient and effective healthcare delivery.
"Management of hypertension is particularly vulnerable to measurement error as algorithms typically recommend stepwise addition of medications until a target blood pressure is achieved" Francesco explains. "This problem is of huge global importance since hypertension is the single greatest cause of death and disability worldwide. Approximately one in three adults across the UK are hypertensive, leading to a significant economic burden on healthcare providers."
Southampton postgraduate researcher Lorenzo Zanisi was presented with a STEM for Britain Silver Award this spring for his exploration of Monte Carlo simulations at St Thomas' Hospital. The Doctoral Training Centre in Data Intensive Science (DISCnet) research showed that current treatments strategies for medication titration results are too inefficient, with typically 40% of the population not optimally controlled and therefore at risk of adverse effects.
Three members of Electronics and Computer Science at Southampton have also been recognised for their research potential by being awarded roles in The Alan Turing Institute this week.
PhD student Joseph Early is the first Southampton student to be selected as a Turing Doctoral Student, while Dr Adriane Chapman and Professor Neil White, Directors of the Centre for Health Technologies, have been named as Turing Fellows with pilot projects.