Exploiting an understanding of human visual perception to facilitate human-machine electrocardiogram interpretation of drug-induced long QT syndrome

Narrative

Sudden cardiac death accounts for 100,000 UK deaths per annum. This research takes a completely new approach to ECG interpretation, allowing people to monitor heart health at home, potentially saving thousands of lives every year. It automates the early detection of long QT syndrome (LQTS) – a symptomless heart condition caused by common medications that can lead to sudden death, even in young apparently healthy people. To do this, it uses human-like AI that is intuitively ‘explainable’. Interpreting ECGs is extremely challenging. It requires years of training, and there are currently no computerised approaches reliable enough to use in clinical practice. Measuring the QT-interval is particularly difficult, due to the challenge of determining the start and the end of the ECG waves, which differ considerably in their characteristics across individuals.

Alahmadi's PhD multidisciplinary research has combined knowledge from psychology, medicine and computer science to produce an algorithm that works with >90% accuracy and is easily understood by both clinicians and lay people, as it can be visualised using colour superimposed on the ECG signal. To create the technology, we challenged ourselves to think completely outside current approaches. Manual interpretation requires laborious and imprecise measurement of the ECG waveform. Automated interpretation relies on ‘black box’ algorithms that require vast amounts of training data and can’t explain how they produce their results. The model was inspired by how humans perceive colour and signal data. Because the computer and the human interpreter share the same representation of the data, this engenders trust. In our focus group, a clinician commented, "It's bridging the important gap between being fully manual and fully automated. That will help people understand how it's working and help people trust it". Doctors also believe it will overcome challenges with testing new drugs: “In the future, I can see it being a very important tool in trials because it's automating a process we have problems with.” As the algorithm can be visualised on a smartwatch it will allow cardiac monitoring to be moved from the hospital to the home. A patient focus group said this approach “could lead to a culture shift, transforming the way healthcare works within the NHS… it's also going to be more cost-effective and less time consuming which, again, is a win-win for the NHS.”

Impact date	31 Dec 2021
Category of impact	Technological, Health and wellbeing
Impact level	Engagement