Artificial intelligence will detect the risk of heart disease due to the condition of the eyes
An algorithm has been developed for diagnosing the propensity to develop cardiovascular diseases, using the results of ophthalmoscopy - examination of the fundus.
The creators of the new algorithm used deep learning technologies. At the disposal of the program were images of the fundus of 284 335 patients, whose average age was about 55 years. Also, the algorithm was available basic information about patients: their age, gender, ethnicity, body mass index. In addition, patients indicated whether they smoked and reported diagnosed cardiovascular diseases.
To assess the accuracy of the method, two sets of data with eye shots of 12,026 and 999 patients, respectively, were used. The algorithm was to determine whether a person developed a cardiovascular disease within five years after the ophthalmologist took a picture. The program was able to correctly answer in 70% of cases.
A new development must go through several more stages of effectiveness testing. The creators of the algorithm emphasize that artificial intelligence will not replace the doctor, but will become an additional diagnostic tool.