Training ambidexterity – A survey-based analysis on the dexterity of ophthalmologists in performing standard ophthalmic procedures

Purpose: Our study was designed to determine ophthalmologists’ dexterity in performing standard ophthalmic procedures at various levels of expertise via a structured questionnaire. Methods: A structured questionnaire was administered via the Google platform from August 20 to September 19, 2022, to assess the perspectives and preferences of ophthalmologists concerning their proficiency in using their right hand, left hand, or both hands to perform routine tasks required in the practice of ophthalmic medicine and surgery. Results: Two hundred and three participants took part in the survey. A majority (n = 162, 79.8%) of the clinicians considered themselves right?handed, nine (4.4%) considered themselves left?handed, and 32 (15.7%) considered themselves ambidextrous. Also, 86% (n = 174) of the participants considered ambidexterity an essential trait in the practice of ophthalmic medicine and surgery. The number of cataract surgeries performed had an impact on the comfort of using both hands for performing anterior vitrectomy (P < 0.001), injection of viscoelastic (P < 0.001), and toric marking (P < 0.05), but not on the performance of capsulorhexis and switching of foot pedals. The number of procedures carried out had an impact on the comfort of using both hands in gonioscopy (P < 0.001), 90 D evaluation (P < 0.001), and 20 D evaluation (P < 0.05). More years of experience had an impact on skills involving the use of both hands for slit lamp joystick usage (P < 0.05) and laser procedures (P < 0.001). Conclusion: Irrespective of a person’s handedness, trained ambidexterity in the required fields is achievable and has a significant impact on one’s ability to perform the required skill optimally and appropriately.

Under lock and key: Incorporation of blockchain technology in the field of ophthalmic artificial intelligence for big data management - A perfect match?

Big data has been a game changer of machine learning. But, big data is a form of centralized version of data only available and accessible to the technology giants. A way to decentralize this data and make machine learning accessible to the smaller organizations is via the blockchain technology. This peer?to?peer network creates a common database accessible to those in the network. Furthermore, blockchain helps in securing the digital data and prevents data tampering due to human interactions. This technology keeps a constant track of the document in terms of creation, editing, etc., and makes this information accessible to all. It is a chain of data being distributed across many computers, with a database containing details about each transaction. This record helps in data security and prevents data modification. This technology also helps create big data from multiple sources of small data paving way for creating a well serving artificial intelligence model. Here in this manuscript, we discuss about the usage of blockchain, its current role in machine learning and challenges faced by it

Utilizing human intelligence in artificial intelligence for detecting glaucomatous fundus images using human-in-the-loop machine learning

Purpose: For diagnosing glaucomatous damage, we have employed a novel convolutional neural network (CNN) from TrueColor confocal fundus images to conquer the black box dilemma in artificial intelligence (AI). This neural network with CNN architecture with human?in?the?loop (HITL) data annotation helps not only in diagnosing glaucoma but also in predicting and locating detailed signs in the glaucomatous fundus, such as splinter hemorrhages, glaucomatous optic atrophy, vertical glaucomatous cupping, peripapillary atrophy, and retinal nerve fiber layer (RNFL) defect. Methods: The training was done on a well?curated private dataset of 1,400 high?resolution confocal fundus images, out of which 1,120 images (80%) were used exclusively for training and 280 images (20%) were used exclusively for testing. A custom trained You Only Look Once version 5 (YOLOv5)?based object detection methodology was used to identify the underlying conditions precisely. Twenty?six predefined medical conditions were annotated by a team of humans (comprising two glaucoma specialists and two optometrists) by using the Microsoft Visual Object Tagging Tool (VoTT) tool. The 280 testing images were split into three groups (90,100, and 90 images) for three test runs done once every 15 days. Results: Test results showed consistent increments in the accuracy, from 94.44% to 98.89%, in predicting the glaucoma diagnosis along with the detailed signs of the glaucomatous fundus. Conclusion: Utilizing human intelligence in AI for detecting glaucomatous fundus images by using HITL machine learning has never been reported in the literature before. This AI model not only has good sensitivity and specificity in accurate glaucoma predictions but is also an explainable AI, thus overcoming the black box dilemma.