Structural eye sequelae of retinopathy of prematurity in children in Manaus, Amazonas

We would like to complete some topics as comment on the article's Structural eye sequelae of retinopathy of prematurity in children in Manaus City, Amazonas State/Brazil⁽¹⁾, which was published in your esteemed journal.

The aforementioned article shows that retinopathy of prematurity (ROP) is an important cause of preventable blindness in Amazonas State/Brazil, which affects 31.6% of children at risk of it. This number shows the need for screening and treatment programs applied to this population in order to avoid blindness in public healthcare system users.⁽²⁾ The last retinopathy of prematurity epidemic caused irreversible blindness in more than 50,000 preterm infants.⁽³⁾ Ophthalmologists' training in such an area is often inadequate and limits the number of future qualified professionals. Moreover, parameters used in retinopathy of prematurity diagnosis, such as zone, stage, and presence of additional diseases differ even among experts.⁽⁴⁾ Approximately 25% of exams conducted in a multicenter study that adopts telemedicine to diagnose this pathology did not meet the three clinically significant ROP criteria.⁽⁵⁾

Artificial intelligence arises as alternative to such a scenario sine it aims at increasing the access of the population to ophthalmological care and to imediate assessment of images provided by wide-angle Reticam. Some of the developed algorithms are able to assess the vascular tortuosity of plus diseases.⁽⁶⁾ Campbell et al. ⁽⁷⁾ reported that an algorithm developed to automated diagnosis of ROP (i-ROP) reached 95% accuracy, whereas the mean accuracy of 11 experts in the study was of 87%. Therefore, there are algorithms accomplishing performance similar to those of retina specialists.

The development of automated artificial intelligence systems can assist health professionals in screening, namely in developing countries, where the availability of ophthalmological and neonatal knowledge is not enough to manage the number of preterm infants at risk of developing blindness.

Referências

• ¹
  Ribeiro JA, Carvalho FS, Viterbino DS, Cohen JM, Jorge R. Ocular sequelae of retinopathy of prematurity in Manaus, Amazonas. Rev Bras.Oftalmol. 2020;79(2): 99-102.
• ²
  Quinn GE. Retinopathy of prematurity blindness worldwide: phenotypes in the third epidemic. Eye Brain. 2016;8:31-6.
• ³
  Santos Martins TGD, de Azevedo Costa ALF, Schor P. Comment on: "Do We Have Enough Ophthalmologists to Manage Vision-Threatening Diabetic Retinopathy? A Global Perspective" [published online ahead of print, 2020 Apr 28]. Eye (Lond). 2020;10. doi:1038/s41433-020-0903-3.
  » https://doi.org/1038/s41433-020-0903-3
• ⁴
  Chiang MF, Jiang L, Gelman R, Du YE, Flynn JT. Interexpert agreement of plus disease diagnosis in retinopathy of prematurity. Arch Ophthalmol. 2007; 125(7):875-80.
• ⁵
  Daniel E, Quinn GE, Hildebrand PL, Ells A, Hubbard GB 3rd, Capone A Jr, et al.; e-ROP Cooperative Group. Validated System for Centralized Grading of Retinopathy of Prematurity: Telemedicine Approaches to Evaluating Acute-Phase Retinopathy of Prematurity (e-ROP) Study. JAMA Ophthalmol. 2015;133(6):675-82.
• ⁶
  Capowski JJ, Kylstra JA, Freedman SF. A numeric index based on spatial frequency for the tortuosity of retinal vessels and its application to plus disease in retinopathy of prematurity. Retina. 1995;15(6):490-500.
• ⁷
  Campbell JP, Ataer-Cansizoglu E, Bolon-Canedo V, Bozkurt A, Erdogmus D, Kalpathy-Cramer J, et al.; Imaging and Informatics in ROP (i-ROP) Research Consortium. Imaging and informatics in ROP (i-ROP) research consortium.expert diagnosis of plus disease in retinopathy of prematurity from computer-based image analysis. JAMA Ophthalmol. 2016;134(6):651-7.

Publication Dates

• Publication in this collection
  05 Feb 2021
• Date of issue
  Nov-Dec 2020

History

• Received
  12 June 2020
• Accepted
  15 Sept 2020