A new computer system will help primary care physicians determine the risk of developing diabetic retinopathy
A new computer system will help primary care physicians determine the risk of developing diabetic retinopathy
A new computer system will help primary care physicians determine the risk of developing diabetic retinopathy
Between 10 and 12% of the adult world population is diabetic, a percentage that is increasing. Only in the health sector of Baix Camp-Priorat (Catalonia, Spain) there are approximately 18,000 recognized diabetic patients. This chronic disease is associated with many complications, among which diabetic retinopathy, one of the main causes of low vision and blindness. But its effects can be limited if a rapid detection and proper treatment is made. That is why it is recommended to make an annual screen of diabetic patients, to whom an eye fundus test must be done. Currently, in the Baix Camp area, only one retinopathy can be done every two and a half years for each patient, despite the fact that there are three non-mydriatic cameras (a camera that allows images of the retina and the fundus ) installed in the CAP Sant Pere de Reus, in the Light Hospital of Cambrils and in the Sant Joan de Reus University Hospital.
"Doing well, and involving family doctors in reading the fundus images every year, we can only reach 30% of the diabetic population," says Dr. Pere Romero, head of the ophthalmology service at Hospital Sant Joan and researcher at the Pere Virgili Health Research Institute (IISPV). And it is important to detect and monitor the lesions to the eye (or diabetic retinopathy), since evolution can be avoided by influencing the strict controls of glucose, blood pressure and lipids.
Given this situation, a team of ophthalmologists from the Hospital, ICS family physicians and researchers from the Itaka research group at the Rovira i Virgili University, led by Antonio Moreno and Aïda Valls, started work six years ago to develop a new computer system. With the name of Retiprogram, this program aims to help health professionals to make decisions and determine the personalized risk of developing diabetic retinopathy, based on the values of the clinical characteristics that have the most influence. That is, the team has developed a way to customize the screening for each diabetic patient, taking into account their own risk factors. To do so, the researchers analyzed the data of thousands of patients: "Through the techniques of intelligent data analysis, we have related the values of each patient with the fact that they have or do not have retinopathy," explains Moreno. This has allowed them to build the model and test it to validate the effectiveness of risk prediction. This model, owned jointly by the IISPV and the URV, has been protected by a registry with the collaboration of the URV's Valorisation Unit.
From left to right: Dr. Pere Romero and researchers Aïda Valls, Antonio Moreno and Emran Saleh, in front. (Photo: URV)
In this sense, they have designed a risk factor calculator: incorporating the parameters that most influence retinopathy (time that the patient has diabetes, control of hypertension or hemoglobin levels, among others), and through techniques of artificial intelligence, the calculator advises a margin for the next visit, which can range from six months to three years. In this way, health resources are optimized, priority is given to the people who are most at risk, and visits are spaced out among those patients who do not require them. Much of the data that is needed will be retrieved directly from the clinical history of each patient, so that the calculator will tell the percentage of risk and determine the next visit.
Currently 62% of diabetes patients are cases without risk, which will allow to customize the screen between 12 and 36 months. And, on the contrary, the quality of care for people at risk of suffering from retinopathy will be improved since they will be able to take photographs of the fundus more often. In case of doubt, Retriprogram recommends the fundus test, preventing a person from developing the disease without being diagnosed.
According to the calculations that have been made, the implementation of this system will reduce the economic cost per patient screened from 1,348 to 482 euros. Considering the 17,792 diabetic patients of the Baix Camp-Priorat health sector, this will lead to an overall saving of 15.4 million euros.
On the other hand, the same Itaka research group has developed another system that will allow an automatic analysis of the fundus images. Thus, this tool allows a detection of retinopathies and helps doctors to make a more careful assessment of the prognosis of each patient. With the images it is discovered whether or not he has this disease and the degree to which it is found. The image even detects problems that are difficult to perceive at a glance.
To develop this system, four ophthalmologists analyzed more than 15,000 photos of 15,000 patients: comparing the results with those of the automatic system, they realized that the level of coincidences between the specialists and the machine are practically total. With the photo and the risk factors determined by the calculator, it will still be possible to schedule the visit much more carefully. This system, in addition, may be applied later with other diseases that may affect the eye. (Source: URV)
.
!function(f,b,e,v,n,t,s)
{if(f.fbq)return;n=f.fbq=function(){n.callMethod?
n.callMethod.apply(n,arguments):n.queue.push(arguments)};
if(!f._fbq)f._fbq=n;n.push=n;n.loaded=!0;n.version='2.0';
n.queue=[];t=b.createElement(e);t.async=!0;
t.src=v;s=b.getElementsByTagName(e)[0];
s.parentNode.insertBefore(t,s)}(window, document,'script',
'https://connect.facebook.net/en_US/fbevents.js');
fbq('init', '369524843414444');
fbq('track', 'PageView');
.
SOURCE LINK ERESVIRAL.COM https://www.beviral.online
Comentarios
Publicar un comentario