Heart attack, prediction and prevention thanks to retinal vessels and artificial intelligence
Retinal vessels can help predict heart attack risk. Artificial intelligence-based screening system tested
Look at the eye and see the heart. Scientists have developed an artificial intelligence (Ai) system that can analyse scans taken during a normal visit to an ophthalmologist or optician and identify patients at high risk of a heart attack.
Retinal vessels and likelihood of heart attack: the University of Leeds study
No magic: researchers realised that changes in the tiny blood vessels of the retina are indicative of a wider vascular disorder, including problems with the heart.
In the research, conducted by the University of Leeds (UK), a complex set of algorithms called ‘deep learning’ was used to ‘train’ the artificial intelligence system to automatically read retinal scans and identify those who, in the next year, might have suffered a heart attack.
Accuracy: 70/80%
In an article in the scientific journal Nature Machine Intelligence, researchers report that the Ai system achieves 70 to 80 per cent accuracy.
The use of deep learning in the analysis of retinal scans could change the way we screen for early signs of heart disease.
Professor Alex Frangi, who holds the Chair of Computational Medicine at the University of Leeds and is a Turing Fellow at the Alan Turing Institute, supervised the study and noted: ‘Cardiovascular disorders, including heart attacks, are the leading cause of early death worldwide and the second biggest killer in the UK.
This new technique may prove revolutionary because retinal scans are inexpensive and routinely done in several eye practices.
As an automated result, patients who are at risk of falling ill are referred to specialists in cardiovascular problems. In addition, the scans can also be used to follow the progress of early signs of heart disease’.
WOULD YOU LIKE TO GET TO KNOW RADIOEMS? VISIT THE RADIOEMS RESCUE BOOTH AT EMERGENCY EXPO
Studying the ocular retina, aiming to prevent heart attacks
Scientists from around the world collaborated on the Leeds study while the UK Biobank provided the data.
One of the British researchers, Chris Gale, noted that with this Ai tool ‘we could start preventive treatments for any cardiovascular disorders earlier’.
During the deep learning process, the Ai system analysed retinal and heart scans of over five thousand people and identified associations between retinal pathology and changes in the patients’ hearts.
The same Ai system, the authors explain, could calculate the size and pumping efficiency of the left ventricle, one of the heart’s four chambers, from retinal scans.
An enlarged ventricle is linked to an increased risk of heart disease.
With this data expanded to other patient characteristics, including age and gender, the Ai system is able to make a prediction about the risk of a heart attack in the next 12 months.
Usually the extent and sufficiency of a patient’s left ventricle pumping is obtained by echocardiography or magnetic resonance imaging of the heart.
These diagnostic techniques, however, may be expensive or unavailable.
Infarction, retinal vessels and vascular status
Commenting on the Leeds research, Professor Claudio Tondo, Director of the Department of Arrhythmology at the Monzino Cardiology Institute in Milan, says that this is nothing new.
“At least it is not that the assessment of the state of the blood vessels at retinal level can suggest the presence of a vascular pathology or at least the likelihood that the individual can be considered at risk of developing a cardiopathy and/or vasculopathy”.
He goes on to explain: ‘Retinal vessels can be assessed in real time and give an indication of a subject’s vascular status.
This Leeds study is yet another demonstration of how Artificial Intelligence can help physicians to improve preventive actions and anticipate therapeutic strategies, as well as implement large-scale cardiovascular prophylaxis measures’.
FIRST AID: VISIT THE DMC DINAS MEDICAL CONSULTANTS BOOTH AT EMERGENCY EXPO
AI is good, but a doctor’s interpretation is needed
Professor Tondo issues a warning: ‘Be careful, however, because retinal vessels do not have the same anatomical organisation as cardiac coronary vessels, so the data deduced from the analysis of retinal vessels must be integrated with other clinical variables, such as familiarity, lifestyle, and diet in order to build an effective prevention algorithm.
Furthermore, it would be interesting to test the artificial intelligence algorithm in patients who have already had a cardiovascular event and see if it would give an adequate indication of cardiovascular risk’.
The conclusion includes a peremptory warning: ‘The application of artificial intelligence will become more and more ‘routine’ in medicine and also in the cardiovascular field, but the interpretation must be left to the experts in the field, i.e. doctors, and not engineers and/or computer scientists’.
TOP AMBULANCES AND MEDICAL INTERVENTION EQUIPMENT? VISIT THE DIAC MEDICAL BOOTH AT EMERGENCY EXPO
Read Also
Emergency Live Even More…Live: Download The New Free App Of Your Newspaper For IOS And Android
Heart Attack, Some Information For Citizens: What Is The Difference With Cardiac Arrest?
Cardiovascular Diseases: Is It Possible To Prevent A Heart Attack?
In-Depth Analysis Of The Heart: Cardiac Magnetic Resonance Imaging (CARDIO – MRI)
Heart Attack Symptoms: What To Do In An Emergency, The Role Of CPR
Heart Attack: Guidelines For Recognising Symptoms
What Is The Difference Between Pacemaker And Subcutaneous Defibrillator?
What Is An Implantable Defibrillator (ICD)?
What Is A Cardioverter? Implantable Defibrillator Overview
Paediatric Pacemaker: Functions And Peculiarities
Cardiac Arrest: Why Is Airway Management Important During CPR?
RSV (Respiratory Syncytial Virus) Surge Serves As Reminder For Proper Airway Management In Children
Supplemental Oxygen: Cylinders And Ventilation Supports In The USA
Heart Disease: What Is Cardiomyopathy?
Inflammations Of The Heart: Myocarditis, Infective Endocarditis And Pericarditis
Heart Murmurs: What It Is And When To Be Concerned
Broken Heart Syndrome Is On The Rise: We Know Takotsubo Cardiomyopathy
Cardiomyopathies: What They Are And What Are The Treatments
Alcoholic And Arrhythmogenic Right Ventricular Cardiomyopathy
Difference Between Spontaneous, Electrical And Pharmacological Cardioversion
What Is Takotsubo Cardiomyopathy (Broken Heart Syndrome)?
Dilated Cardiomyopathy: What It Is, What Causes It And How It Is Treated
Heart Pacemaker: How Does It Work?
Paediatric Implantable Cardioverter Defibrillator (ICD): What Differences And Peculiarities?