RESUMO
Objective:To evaluate the value of applying an artificial intelligence (AI) system for diabetic retinopathy (DR) detection and referral in community.Methods:A diagnostic test study was conducted.Four hundred and twenty-one patients (812 eyes) diagnosed with diabetes in three Dongguan community healthcare centers from January 1, 2020 to December 31, 2021 were enrolled.There were 267 males, accounting for 63.42% and 154 females, accounting for 36.58%.The subjects were 18-82 years old, with an average age of (51.72±11.28) years.The disease course of the subjects was 0-30 years, with an average course of 3.00 (1.00, 7.00) years.At least one macula-centered 50-degree fundus image was taken for each eye to build a DR image database.All the images were independently analyzed by an AI-assisted diagnostic system for DR, trained and qualified community physicians and ophthalmologists to make diagnosis including with or without DR, referable diabetic retinopathy (RDR) and referral recommendation or not.With diagnoses from ophthalmologists as the standard, sensitivity and specificity of the AI system in detecting DR and RDR were evaluated.The consistency and effective referral rate of the AI system and community physicians in detecting DR, especially in detecting RDR were evaluzted.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Dongguan Tungwah Hospital (No.2019DHLL046).Results:Of 812 eyes, 242 eyes were diagnosed with DR, including 23 with mild nonproliferative diabetic retinopathy (NPDR), 120 with moderate NPDR, 60 with severe NPDR and 39 with proliferative diabetic retinopathy (PDR). The other 570 eyes were diagnosed without DR.The sensitivity/specificity of AI system to detect DR and RDR was 87.60%/97.89% and 90.41%/96.29%, respectively.Compared with the ophthalmologists' diagnosis, the Cohen' s Kappa statistic of AI system to detect DR/RDR was 0.87/0.87, which was lower than 0.93/0.98 of community physicians.Among the referral-recommended cases by ophthalmologists, the effective referral rate of the AI system was 90.87% (199/219), which was higher than 89.50% (196/219) of community physicians, without statistically significant difference ( P=1.000). Conclusions:The AI system shows high sensitivity, specificity and consistency in DR detection, especially in RDR.The AI system is better in recognizing RDR than trained community physicians.
RESUMO
Objective@#To evaluate the relationship between the offset of a laser-assisted flap using the WaveLight FS200 femtosecond laser and the clinical results after femtosecond laser-assisted laser in situ keratomileusis (FS-LASIK).@*Methods@#In this prospective cohort study, 125 patients who underwent FS-LASIK for myopia by WaveLight FS200 femtosecond laser from June 2017 to July 2018 at the Tungwah Ophthalmic Center were divided into two groups according to the offset of the corneal flap from the pupil center: the no-offset group (57 eyes) and the certain-offset group (68 eyes); the baseline data, including age, sex, uncorrected visual acuity(UCVA), spherical degree, and central corneal thickness were matched in the two groups.UCVA, residual astigmatism, spherical degree, corneal curvature and aberration were observed 1 week and 1 month after surgery.The study protocol was approved by the Ethics Committee of Tungwah Hospital of Sun Yat-Sen University (No.2017DHLL004). Written informed consent was obtained from each subject prior to entering the study cohort.@*Results@#UCVA, corneal curvature, spherical degree, spherical and corneal aberration between the two groups were not significantly different (all at P>0.05). One week after surgery, the residual astigmatism was ≤-0.50 D in 50 eyes (87.7%, 50/57)and >-0.50 D in 7 eyes (12.3%, 7/57) in the no-offset group; the residual astigmatism was ≤-0.50 D in 50 eyes (73.5%, 50/68) and >-0.50 D in 18 eyes (26.5%, 18/68) in the no-offset group.The residual astigmatism between the two groups 1 week after surgery was significantly different (χ2=3.902, P=0.048), and there was no significant difference in residual astigmatism 1 month after surgery (χ2=2.031, P=0.068). The trefoil of the no-offset group was statistically less than of the certain-offset group at 1 week and 1 month after surgery (0.05[0.04, 0.08]vs.0.06[0.04, 0.10]; 0.05[0.03, 0.07]vs.0.06[0.05, 0.09])(Z=-2.245, P=0.022; Z=-2.370, P=0.018). The spherical aberration and coma were not significantly different between the two groups at 1 week and 1 month after surgery (both at P>0.05).@*Conclusions@#The offset from femtosecond laser-assisted flap by WaveLight FS200 has no effect on long-term visual acuity or residual astigmatism.Some patients may have different visual experiences because of the residual astigmatism and higher order aberration during the early postoperative stage.
RESUMO
Objective To evaluate the relationship between the offset of a laser-assisted flap using the WaveLight FS200 femtosecond laser and the clinical results after femtosecond laser-assisted laser in situ keratomileusis (FS-LASIK).Methods In this prospective cohort study,125 patients who underwent FS-LASIK for myopia by WaveLight FS200 femtosecond laser from June 2017 to July 2018 at the Tungwah Ophthalmic Center were divided into two groups according to the offset of the corneal flap from the pupil center:the no-offset group (57 eyes) and the certain-offset group (68 eyes);the baseline data,including age,sex,uncorrected visual acuity (UCVA),spherical degree,and central corneal thickness were matched in the two groups.UCVA,residual astigmatism,spherical degree,corneal curvature and aberration were observed 1 week and 1 month after surgery.The study protocol was approved by the Ethics Committee of Tungwah Hospital of Sun Yat-Sen University (No.2017DHLL004).Written informed consent was obtained from each subject prior to entering the study cohort.Results UCVA,corneal curvature,spherical degree,spherical and corneal aberration between the two groups were not significantly different (all at P>0.05).One week after surgery,the residual astigmatism was ≤-0.50 D in 50 eyes (87.7%,50/57) and > -0.50 D in 7 eyes (12.3%,7/57) in the no-offset group;the residual astigmatism was ≤-0.50 D in 50 eyes (73.5%,50/68) and >-0.50 D in 18 eyes (26.5%,18/68) in the no-offset group.The residual astigmatism between the two groups 1 week after surgery was significantly different (x2 =3.902,P =0.048),and there was no significant difference in residual astigmatism 1 month after surgery (x2 =2.031,P =0.068).The trefoil of the no-offset group was statistically less than of the certain-offset group at 1 week and 1 month after surgery (0.05 [0.04,0.08] vs.0.06[0.04,0.10];0.05[0.03,0.07] vs.0.06[0.05,0.09]) (Z=-2.245,P--0.022;Z=-2.370,P=0.018).The spherical aberration and coma were not significantly different between the two groups at 1 week and 1 month after surgery (both at P>0.05).Conclusions The offset from femtosecond laser-assisted flap by WaveLight FS200 has no effect on long-term visual acuity or residual astigmatism.Some patients may have different visual experiences because of the residual astigmatism and higher order aberration during the early postoperative stage.
RESUMO
Background Recent studies have demonstrated that glaucoma progression had great relationship with corneal biomechanical properties.However,there are not enough studies about corneal biomechanical properties in different types of glaucoma.Objective This study was to evaluate the corneal biomechanical properties in chronic primary angle-closure glaucoma (CPACG) and primary open angle glaucoma (POAG).Methods Prospective observational study was adopted.Sixty-eight cases (68 eyes) with CPACG and 69 POAG patients (69 eyes) from Zhongshan Ophthalmic Center were investigated by a novel technique named Corvis-ST which can measure corneal deformation.The Cronbach's αt coefficient and intraclass correlation coefficient (ICC) were used to evaluate the repeatability of the parameters from Corvis-ST.The differences of corneal biomechanical properties between POAG and CPACG were evaluated by independent-samples t test.Multiple regression analysis was used to assess the association between parameters of deformation response and clinical factors.This study protocol was approved by Ethic Committee of Zhongshan Ophthalmic Center and complied with Helsinki Declaration.Written informed consent was obtained from each patient prior to any medical examination.Results There were no statistic differences about age,sex and intraocular pressure (IOP) between CPACG and POAG patients (all at P>0.05).However,differences existed in the number of anti-glaucoma medications (t =-2.388,P =0.020).Measurements of central corneal thickness (CCT),deformation amplitude (DA),and peak distance (PD) demonstrated excellent repeatability (ICC≥ 0.8).There were no statistic differences about CCT,first applanation time/length/velocity (A1 T,A1 L,A1V),second applanation time/length/velocity (A2T,A2L,A2V),DA between CPACG and POAG patients (all at P> 0.05).The highest concavity time was shorter (t =2.920,P =0.005),PD was bigger (t =-2.453,P =0.017),and central curvature radius (CCR) was smaller (t =1.997,P =0.050) in POAG than those in the CPACG patients.DA,A1V,A2T and PD were negatively associated with IOP (r =-0.709,-0.531,-0.645,-0.554;all at P<0.001).However,A1T and A2V were positively associated with IOP (r=0.744,0.546;both at P<0.001).And CCR was positively associated with CCT (r =0.181,P =0.039).Conclusions It is useable to evaluate corneal biomechanical properties of glaucoma by Corvis ST.Under the same level of IOP,the corneal concavity of POAG is easier than that of CPACG,which indicates that cornea in POAG patients is more deformable.