Harnessing AI in healthcare

In recent years, medical researchers and practitioners have recorded an enormous amount of healthcare data, including high-resolution imaging, genetic data, biosensor monitoring, and electronic health records.

Many innovative computer techniques have been developed to process this data in meaningful ways, and apply these findings to the way we diagnose and treat various health conditions.

As such, the use of AI methods in healthcare has been steadily on the rise.

Artificial intelligence doesn’t refer to one technology, but instead encompasses a collection of them. Machine learning, for example, is a subset of AI that uses statistical techniques and algorithms to enable computers to ‘learn’ from data and improve performance on tasks over time - without the need for explicit programming.

Machine learning has been particularly useful in healthcare for analysing complex radiology images and detecting clinical features that are beyond what can be seen by the human eye. Other technologies include surgical robots, which are improving surgeons’ ability to create precise and minimally invasive incisions. [1]

Given the progress already made in healthcare AI, with more investment, there is potential for even wider-reaching implications for diagnostics and treatments.

Through this new funding call, we are aiming to develop and retain talented leaders in AI diagnostics, by funding fellowships specifically for mid-career researchers.

Find out about our new fellowship opportunities for researchers in the field of AI in cardiovascular and respiratory disease: click here >>

Why have we chosen cardiovascular and respiratory diagnostics?

Cardiovascular and respiratory diseases are leading causes of death, both in the UK and globally. [1] Although large-scale investments have been made across the UK in heart and lung research, there are still some areas of need within these disciplines.

Several experts that we interviewed when planning this funding call agree that there is great potential for AI in particular. In some areas of cardiovascular and respiratory health, AI is already starting to be incorporated into diagnostics. For example, researchers at UCL have recently developed a new tool that enables highly precise heart disease diagnoses to be made and delivered during MRI scans. It is already being trialled in some London hospitals, and could help greatly with backlogs in care and treatment-related decision-making. [2] By supporting the development of more AI tools such as this, we could start to see a real impact on patient outcomes.

For respiratory diseases, AI has mostly been used so far to interpret images, like lung pathology slides and thoracic scans. [3] There is definite scope for it to be extended to pulmonary diagnostics. When studying 3D lung artery images by eye, for instance, clinicians can often miss pulmonary embolisms, which occur when a blood clot blocks a lung vessel. AI could make a real difference here. Other AI technologies, like robotics, are very much in their infancy, and could also be advanced with funding injections.

Many of our experts additionally agree that there are fewer opportunities for more junior researchers in healthcare AI to develop or learn new skills in what is a very fast-moving field. Our new call also aims to meet this need, by specifically funding researchers at pivotal, mid-career stages.

A thank you to our donors

Our ‘AI in healthcare’ funding scheme is only possible thanks to the support of our generous donors. In 1980, the Medical Research Council (MRC) received a gift in Will from Leonard Heath (a retired draughtsman). His Will indicated that the donation should support “research using computer techniques in connection with the diagnosis of diseases of the heart, lungs and circulation.”

We are deeply privileged to be able to fulfil Leonard’s wishes through this new initiative. AI holds immense potential to revolutionise healthcare. Through our new focus on integrating AI into cardiovascular and respiratory medicine, we hope to see dramatic improvements in diagnosis, treatment, and overall patient outcomes – all thanks to the generosity of our donors.

References

[1] Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J. 2019 Jun;6(2):94-98. doi: 10.7861/futurehosp.6-2-94.

[2] The World Health Organization (website: Accessed 18/07/2024)

[3] Davies, R.H. et al. Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning. J Cardiovasc Magn Reson 24, 16 (2022). https://doi.org/10.1186/s12968...

[4] Gonem S, et al. Applications of artificial intelligence and machine learning in respiratory medicine. Thorax. 2020 Aug;75(8):695-701. doi: 10.1136/thoraxjnl-2020-214556. Epub 2020 May 14. PMID: 32409611.