Continue
By using our website you accept our cookies policy.Find out more

From acne to malaria: can Industrial Maths be applied to health challenges and provide new solutions?

Posted on 10/04/2019

KTN is running two Industrial Maths in AI and Health events with a range of problems for researchers to tackle.

The call to industry to provide diverse problems for KTN’s Industrial Maths study groups to consider has seen a fascinating range of issues being put forward.

Each study group will fall under the broader umbrella of an Industrial Strategy Grand Challenge.  The Government’s Industrial Strategy sets out Grand Challenges to put the UK at the forefront of the industries of the future, ensuring that the UK takes advantage of major global changes, improving people’s lives and the country’s productivity.  The KTN study groups will highlight how the application of mathematical sciences can contribute to the Industrial Strategy through helping to unlock key societal and economic challenges.

Two study groups, one in Cardiff in partnership with Cardiff University and one in Manchester in partnership with Manchester University, will be run to consider issues using Artificial Intelligence (AI) in Health and Care. The groups will be applying mathematical sciences to develop solutions to challenges including using AI and Earth Observation (EO) to predict malaria outbreaks; discovering relationships between phenotypes and variants; predicting rare disease outbreaks through secure machine learning; creating an AI-enabled prebiotic discovery platform; and developing a Formalin-Fixed Paraffin-Embedded (FFPE) artefact filter for RNAseq based biomarkers.

There has been a surge in interest in AI for Health and Care.  There are huge commercial opportunities in public health, vaccination, medicine discovery and manufacture, mental health services, medical technology for monitoring lifestyle and behaviour.   A key component to developing a successful and booming AI in health and care eco-system is providing tangible examples of the successful application of AI detailing the techniques, successes and limitations on real data.

The KTN Industrial Maths study groups will provide a platform for researchers to consider industry problems and posit solutions derived from mathematical sciences.  There is a call out for researchers to participate and the two AI and Health study groups and their challenges are outlined below.

 

Cardiff – 22-24 May

AI and EO for the prediction of malaria outbreak risk presented by isardSAT
Using AI could prove valuable to being able in producing malaria risk infection maps.  The solution would be able to distinguish radar echoes coming from areas with water puddles in maps.  These maps could become invaluable to forecasting where malaria outbreaks will happen, monitoring their progress and potentially preventing or minimising their impacts, helping streamline and save on- the-ground resources and save lives. Read more about the challenge.

Discovering new insight into relationships between phenotypes (health measures) and genomic variants that can inform genomic diagnosis, presented by Congenica

The UK’s Biobank project has gathered healthcare data from 500,000 people and genotyping has been undertaken on all 500,000 participants. This data set may contain new insight into relationships between phenotypes and genomic variants. The challenge for this study group involves researchers discovering relationships between phenotypes and variants. Read more about the challenge.

 

 

Manchester – 26-28 June

Secure Machine Learning for Rare Disease Prediction presented by Mendelian
In the UK there are an estimated 3.5 m rare disease patients who, on average, wait five years for a diagnosis and are referred to seven different doctors – a significant burden on our healthcare system.  The problem is that rare diseases are difficult to diagnose.  Mendelian has spent several years creating tools for clinicians, geneticists and healthcare systems who manage rare diseases and is interested in exploring machine learning methods that are effective and secure on siloed data. Read more about the challenge.

AI-enabled Prebiotic Discovery Platform presented by Unilever
Cosmetic conditions are a daily concern for people worldwide.  Conditions such as acne and psoriasis can have a debilitating effect on self-esteem, particularly in adolescents.   Traditionally personal care products treat these conditions with an indiscriminate reduction of microbial load leading to a reduction in symptoms.  This challenge is to explore where Artificial Intelligence and machine learning algorithms can be used to identify abundant and prevalent organisms associated with selected cosmetic conditions; the determination of key metabolic differences between health associated and condition associated organisms; and identification of compounds (cosmetic ingredients/natural products) that take advantage of these metabolic dependencies to promote (prebiotics) the growth of health-associated organisms such that they outcompete and reduce absolute numbers of condition-associated organisms.  about the challenge. Read more about the challenge.

Development of a Formalin-Fixed Paraffin-Embedded (FFPE) artefact filter for RNAseq based biomarkerspresented by Almac Diagnostic Services
Formalin-Fixed Paraffin-Embedded (FFPE) tissue is the most common format for archiving solid tumour pathology specimens after surgery, thus providing a potentially invaluable resource for translational clinical research.  However, due to the formalin fixation process causing degradation and chemical modifications, FFPE samples are typically poor quality.  The objective of the challenge is to develop a machine learning approach to correct from high duplication rate across FFPE samples and achieve accurate gene expression estimates comparable to those from high quality material.  This would represent a significant step towards fully exploiting FFPE samples, particular those that would otherwise be discarded using standard approaches, increasing the opportunity to discover novel cancer drug targets and biomarkers from these samples. Read more about the challenge.

 

If you are a researcher working in a UK university who would like to work on these problems, please register here for Cardiff and here for Manchester.