Artificial intelligence has established the ability to accurately identify glaucoma medication bottles and will feasibly feature on a phone platform, consistent with an observation posted in Ophthalmology Glaucoma. Researchers pre-trained seven convolutional neural networks (CNN) fashions to categorize 5 common ophthalmic medicines the use of a fixed of 2,250 pictures captured via way of means of cellular phones. The top-appearing networks have been protected in separate iOS apps to check their cap potential to categorize 1,500 pictures now no longer protected withinside the education setting.

“We evaluated several known CNN algorithms to see which algorithm achieves the best accuracy and computing efficiency to accomplish this task,” observe co-author Ken Y. Lin, MD, PhD, told Healio/OSN. “Computing performance is vital due to the fact our purpose is to have a CNN this is each correct and sufficiently lightweight to run on a phone device.” The units protected bottles of brimonidine tartrate, dorzolamide-timolol, latanoprost, prednisolone acetate, and moxifloxacin. MobileNetV2 and ResNetV2 produced the maximum favorable results, with cross-validation accuracy of 0.974 and 0.961, respectively. MobileNetV2 had a substantially more prediction accuracy than ResNetV2 as soon as the networks have been loaded into apps. MobileNetV2 had an photo prediction accuracy of 0.86 in comparison with 0.68 for ResNetV2.

“There is an inherent irony in the design of most medication eye drop bottles. The writing is often too small, and the color-coding on the bottle cap has been shown to be an unreliable feature to identify medications, especially for glaucoma patients who often have reduced contrast sensitivity and color vision. Yet, these patients depend critically on the correct use of these medications to maintain their vision,” Lin said. The loss of a large, brazenly to be had statistics set changed into a problem of the observe, so the researchers needed to create one. Other obstacles encompass versions in special bottles of the equal medicinal drug and the technological literacy and phone get entry to wished via way of means of the goal demographic to apply such an app. Future guidelines encompass increasing the scope of studies to encompass greater medicines.

Photo by Possessed Photography on Unsplash