Skip to main content

The ‘Digital Twin’ to enable the vision of precision cardiology


Increasing computer power and novel algorithms could predict future heart health of patients.

In recent times, researchers have increasingly found that the power of computers and artificial intelligence is enabling more accurate diagnosis of a patient’s current heart health and can provide an accurate projection of future heart health, potential treatments and disease prevention.

Now in a paper published in European Heart Journal, researchers from Oxford University, working in collaboration with academic, industry, clinical and regulatorypartners, and several other international initiatives as the Personalised In-Silico Cardiology consortium, show how linking computer and statistical models can improve clinical decisions relating to the heart.

Alfonso Bueno-Orovio (Oxford University Department of Computer Science) says, The future of medicine is to provide therapies tailored to each patient. I am firmly convinced that the enabling pillar towards this vision is the increasing power of computers and algorithms to learn, reason and build the Digital Twin of a patient.

The team have coined the phrase the ‘Digital Twin’ to describe this integration of the two models, a computerised version of our heart which represents human physiology and individual data.

‘The Digital Twin will shift treatment selection from being based on the state of the patient today to optimising the state of the patient tomorrow,’ the researchers wrote in the paper. This could mean that a trip to the doctor’s office could be a more digital experience.

The translation of the Digital Twin concept, which has been around in the engineering field for several years now, to cardiovascular research is a fundamental step in order to materialise the vision of precision cardiologysaid Francesca Margara, another Oxford member of the research team.

Mechanistic models see researchers applying the laws of physics and maths to simulate how the heart will behave. Statistical models require researchers to look at past data to see how the heart will behave in similar conditions and infer how it will do it over time.

Models can pinpoint the most valuable piece of diagnostic data and can also reliably infer biomarkers that cannot be directly measured or that require invasive procedures.

Pablo Lamata of King’s College London said more information about how the heart is behaving could be retrieved by using these models.

‘We already extract numbers from the medical images and signals, but we can also combine them through a model to infer something that we don’t see in the data, like the stiffness of the heart. We obviously cannot touch a beating heart to know the stiffness, but we can give these models with the rules and laws of the material properties to infer that importance piece of diagnostic and prognostic information. The stiffness of the heart becomes another key biomarker that will tell us how the health of the heart is coping with disease.’

The team of researchers believe that the power of computational models in cardiovascular medicine could also provide us with more control over our daily heart health. Much like the popularity of wearable monitoring devices, a digital twin of our hearts could inform us about its current health and alert wearers to any risk factors.

Alfonso Bueno-Orovio says, Future medical treatments will be tailored not only to current health status and data, but also to restore health by Digital Twin predictions.

The research predicts we could see the technology in action within the next 5-10 years.