27 October 2022 in Ophthalmology Science
To develop a method for objective analysis of the reproducible steps in routine cataract surgery. Prospective study; machine learning. Deidentified faculty and trainee surgical videos. Consecutive cataract surgeries performed by a faculty or trainee surgeon in an ophthalmology residency program over 6 months were collected and labeled according to degrees of difficulty. An existing image classification network, ResNet 152, was fine-tuned for tool detection in cataract surgery to allow for automatic identification of each unique surgical instrument. Individual microscope video frame windows were subsequently encoded as a vector. The relation between vector encodings and perceived skill using k-fold user-out cross-validation was examined. Algorithms were evaluated using area under the receiver operating characteristic curve (AUC) and the classification accuracy. Accuracy of tool detection and skill assessment. In total, 391 consecutive cataract procedures with 209 routine cases were used. Our model achieved an AUC ranging from 0.933 to 0.998 for tool detection. For skill classification, AUC was 0.550 (95% confidence interval [CI], 0.547–0.553) with an accuracy of 54.3% (95% CI, 53.9%–54.7%) for a single snippet, AUC was 0.570 (0.565–0.575) with an accuracy of 57.8% (56.8%–58.7%) for a single surgery, and AUC was 0.692 (0.659–0.758) with an accuracy of 63.3% (56.8%–69.8%) for a single user given all their trials. Our research shows that machine learning can accurately and independently identify distinct cataract surgery tools in videos, which is crucial for comparing the use of the tool in a step. However, it is more challenging for machine learning to accurately differentiate overall and specific step skill to assess the level of training or expertise. The author(s) have no proprietary or commercial interest in any materials discussed in this article.
22 August 2024 in Canadian Journal of Ophthalmology
Outline geographic disparities in access to language-and gender-concordant ophthalmologic care in Canada. Cross-sectional. Practicing ophthalmologists in Canada (September 2023). Data on ophthalmologists, including demographics, languages spoken, and practice locations, were collected from provincial regulatory body websites. Population data were extracted from the 2021 Statistics Canada Census. Ratio of ophthalmologists-to-potential patients and mean distances (absolute, population-weighted) to gender- and language-concordant care were calculated. The five most common languages spoken in the included provinces were analyzed. There were 986 and 1338 ophthalmologists in the language and gender analysis, respectively. Few ophthalmologists spoke non-official languages in Saskatchewan, Manitoba, and Nova Scotia. In a population-weighted analysis, the distance to a language-concordant ophthalmologist were 4.55 times greater for Spanish speakers compared to their English counterparts. Cantonese speakers had the shortest distances to language-concordant care but were still had 40% greater distance than English speakers in the same regions. Despite French-speaking ophthalmologists being the most prevalent per 100 000 speakers, francophones outside Quebec endured distances over double that of anglophones to access language-concordant care. Females in Newfoundland and Saskatchewan faced the longest distances to access gender-concordant care. In Ontario, females may face 3 times the distance to gender-concordant ophthalmologists compared to males. Quebec approaches gender parity with a male-to-female ratio of 55:45. The results highlight the disparities in accessibility to non-English ophthalmologic care and the underrepresentation of female ophthalmologists across Canada. These disparities underscore the need for targeted strategies to ensure that the ophthalmologic workforce mirrors the demographic of the population it serves.
6 July 2022 in Canadian Journal of Ophthalmology
1 June 2016 in Canadian Journal of Ophthalmology
23 January 2023 in Canadian Journal of Ophthalmology
3 April 2022 in Journal of Museum Education
This case study of an art education program for medical students examines the efficacy of different types of content and modes of delivery. Through the delivery of art analysis, art history, sculpting, and life drawing seminars, art educators were able to teach empathy, observation, and flexible thinking to first-year medical students. This interdisciplinary approach to museum education can be used across many contexts to complement existing curricula.