A machine learning algorithm may help detect plus disease/ Retinopathy of prematurity (ROP) in premature infants which is currently the leading cause of childhood blindness worldwide. The findings of this study are published in the journal of JAMA Ophthalmology.
Why The Research Is Interesting:
Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide. The decision to treat is primarily based on the presence of plus disease, which is when retinal vessels are dilated and twisted. However, clinical diagnosis of plus disease can be highly subjective and variable.
‘The decision to treat retinopathy of prematurity is taken only when retinal vessels are dilated and twisted. This particular task can be done by an algorithm with more accuracy.’
What and When:
A machine learning algorithm was trained to diagnose plus disease using 5,511 retinal photographs. Data were collected from July 2011 to December 2016 and analyzed from December 2016 to September 2017.
The algorithm to detect plus disease was tested on an independent set of 100 images against eight ROP experts.
Michael F. Chiang, M.D., Oregon Health and Science University, Portland, Jayashree Kalpathy-Cramer, Ph.D., Massachusetts General Hospital, Boston, and coauthors.
The algorithm diagnosed plus disease with comparable or better accuracy than human ROP experts.
Algorithms in artificial neural networks are only as good as the data on which they are trained. It is unknown how factors such as image quality, resolution, different camera systems and field of view may affect the output of these deep learning systems.