RESUMO
Purpose: We examined the performance of artificial intelligence chatbots on the PREview Practice Exam, an online situational judgment test for professionalism and ethics. Methods: We used validated methodologies to calculate scores and descriptive statistics, χ2 tests, and Fisher's exact tests to compare scores by model and competency. Results: GPT-3.5 and GPT-4 scored 6/9 (76th percentile) and 7/9 (92nd percentile), respectively, higher than medical school applicant averages of 5/9 (56th percentile). Both models answered 95 + % of questions correctly. Conclusions: Chatbots outperformed the average applicant on PREview, suggesting their potential for healthcare training and decision-making and highlighting risks of online assessment delivery.
RESUMO
PRCIS: Children with glaucoma had an average of 1.3 visual field tests per year. Self-reported black and multiracial patients had lower visual field testing rates, whereas older children with better visual acuity had more frequent testing. PURPOSE: To evaluate frequency of visual field (VF) testing in children with glaucoma and identify characteristics associated with VF frequency. METHODS: A retrospective cohort study of 82 children 6-18 years of age with glaucoma seen between August 2018 and May 2023. Patients were divided into those who had ≥1 VF test (303 VF tests of 61 children) and 0 VFs (21 children). Eyes were excluded if best corrected visual acuity (BCVA) was counting fingers or worse. Characteristics obtained included age, self-reported race and ethnicity, sex, primary language, glaucoma diagnosis, distance to provider, office visit frequency, follow-up compliance, insurance type, and BCVA. The main outcome measure was VF testing frequency. RESULTS: Among children with ≥1 VF test, mean age at first VF was 11.8±2.8 years, mean number of VF/year was 1.3±0.8, and 44.9% of all VFs were reliable. Thirty nine percent of patients underwent <1 VF/year, 45.9% ≥1 to <2 VFs/year, and 14.8% ≥2 VF/year. Children who were black or multiracial had significantly lower VF testing frequency [estimated difference (ED) -1.2 (95% CI, -2.0 to -0.4, P =0.002) and ED -1.3 (95% CI, -2.2 to -0.3, P =0.008), respectively]. Better visual acuity and greater office visit frequency were significantly associated with higher VF testing frequency [ED 0.052 (95% CI, 0.001-0.103, P =0.045) and ED 0.2 (95% CI, 0.1-0.3, P <0.001), respectively]. CONCLUSIONS: Most children had between 1 and 2 VF/year, although less than half of all VFs were reliable. Ophthalmologists should consider barriers to care in glaucoma monitoring.