Search

Objectives: To analyse the accuracy of artificial intelligence (AI)-driven intraocular (IOL) calculation formulae, together with established formulae using the heteroscedastic methodology and the Eyetemis Analysis Tool. Methods: Data from 404 eyes who underwent uneventful phacoemulsification with implantation of the SN60WF IOL were retrospectively reviewed. IOL power calculations were performed using the Barrett Universal II (BUII), EVO 2.0, Hoffer QST, K6, Ladas Super Formula (LSF), Nallasamy, PEARL-DGS and RBF 3.0 formulae. The SD of the prediction error (PE), served as the primary metric for accuracy. The mean absolute deviation (MAD) and the predictability rates within intervals from ±0.25 D to ±1.50 D were also evaluated. The Eyetemis Analysis Tool was used for further validation. Results: The SD ranged from 0.468 (Nallasamy) to 0.510 (LSF). The Nallasamy formula had a significantly lower SD than the BUII (0.505, p= 0.025) and K6 (0.489, p= 0.022) formulae. The Nallasamy formula also exhibited the lowest MAD (0.358) with a significant difference compared with the Hoffer QST formula (0.384, p< 0.001). Finally, a significantly higher percentage of eyes achieving ± 0.50 D of the target refraction was seen using the Nallasamy formula (77.19%) compared with the Hoffer QST (71.04%, p= 0.019) and Ladas Super Formula (70.79%, p= 0.030) formulae. Conclusions: The Nallasamy formula, incorporating AI technology, demonstrated superior accuracy according to the analysis guidelines for PE statistics for non-gaussian datasets recommended by Holladay et al. and the online Eyetemis Analysis Tool.

IMPORTANCE: Although almost equal numbers of male and female medical students enter into ophthalmology residency programs, whether they have similar surgical experiences during training is unclear. OBJECTIVE: To determine differences for cataract surgery and total procedural volume between male and female residents during ophthalmology residency. DESIGN, SETTING, PARTICIPANTS: This retrospective, longitudinal analysis of resident case logs from 24 US ophthalmology residency programs spanned July 2005 to June 2017. A total of 1271 residents were included. Data were analyzed from August 12, 2017, through April 4, 2018. MAIN OUTCOMES AND MEASURES: Variables analyzed included mean volumes of cataract surgery and total procedures, resident gender, and maternity or paternity leave status. RESULTS: Among the 1271 residents included in the analysis (815 men [64.1%]), being female was associated with performing fewer cataract operations and total procedures. Male residents performed a mean (SD) of 176.7 (66.2) cataract operations, and female residents performed a mean (SD) of 161.7 (56.2) (mean difference, −15.0 [95% CI, −22.2 to −7.8]; P < .001); men performed a mean (SD) of 509.4 (208.6) total procedures and women performed a mean (SD) of 451.3 (158.8) (mean difference, −58.1 [95% CI, −80.2 to −36.0]; P < .001). Eighty-five of 815 male residents (10.4%) and 71 of 456 female residents (15.6%) took parental leave. Male residents who took paternity leave performed a mean of 27.5 (95% CI, 13.3 to 41.6; P < .001) more cataract operations compared with men who did not take leave, but female residents who took maternity leave performed similar numbers of operations as women who did not take leave (mean difference, −2.0 [95% CI, −18.0 to 14.0]; P = .81). From 2005 to 2017, each additional year was associated with a 5.5 (95% CI, 4.4 to 6.7; P < .001) increase in cataract volume and 24.4 (95% CI, 20.9 to 27.8; P < .001) increase in total procedural volume. This increase was not different between genders for cataract procedure volume (β = −1.6 [95% CI, −3.7 to 0.4]; P = .11) but was different for total procedural volume such that the increase in total procedural volume over time for men was greater than that for women (β = −8.0 [95% CI, −14.0 to −2.1]; P = .008). CONCLUSIONS AND RELEVANCE: Female residents performed 7.8 to 22.2 fewer cataract operations and 36.0 to 80.2 fewer total procedures compared with their male counterparts from 2005 to 2017, a finding that warrants further exploration to ensure that residents have equivalent surgical training experiences during residency regardless of gender. However, this study included a limited number of programs (24 of 119 [20.2%]). Future research including all ophthalmology residency programs may minimize the selection bias issues present in this study.