RESUMO
BACKGROUND: To compare the performance of Medios (offline) and EyeArt (online) artificial intelligence (AI) algorithms for detecting diabetic retinopathy (DR) on images captured using fundus-on-smartphone photography in a remote outreach field setting. METHODS: In June, 2019 in the Yucatan Peninsula, 248 patients, many of whom had chronic visual impairment, were screened for DR using two portable Remidio fundus-on-phone cameras, and 2130 images obtained were analyzed, retrospectively, by Medios and EyeArt. Screening performance metrics also were determined retrospectively using masked image analysis combined with clinical examination results as the reference standard. RESULTS: A total of 129 patients were determined to have some level of DR; 119 patients had no DR. Medios was capable of evaluating every patient with a sensitivity (95% confidence intervals [CIs]) of 94% (88%-97%) and specificity of 94% (88%-98%). Owing primarily to photographer error, EyeArt evaluated 156 patients with a sensitivity of 94% (86%-98%) and specificity of 86% (77%-93%). In a head-to-head comparison of 110 patients, the sensitivities of Medios and EyeArt were 99% (93%-100%) and 95% (87%-99%). The specificities for both were 88% (73%-97%). CONCLUSIONS: Medios and EyeArt AI algorithms demonstrated high levels of sensitivity and specificity for detecting DR when applied in this real-world field setting. Both programs should be considered in remote, large-scale DR screening campaigns where immediate results are desirable, and in the case of EyeArt, online access is possible.
RESUMO
Objetivo: examinar resultados anatómicos y visuales de los pacientes con membranas epirretinianas idiopáticas (MER) tratados mediante pelaje de membranas y su correlación funcional post-operatoria. Métodos: Estudio de serie de casos donde se revisaron las historias clínicas de 27 pacientes elegidos de manera aleatoria y a quienes se realizó pelaje de membranas epirretinianas idiopáticas con seguimiento clínico por 6 meses del post-operatorio. Al 90% (n=24) de los pacientes se les realizó cirugía combinada de facovitrectomía. Se tomaron como variables a analizar la agudeza visual pre y post-operatoria a la semana, al mes y a los 6 meses, tomografía de coherencia óptica pre y post-operatoria al mes y a los 6 meses de la cirugía. Se comparó la agudeza visual y el grosor retiniano en el milímetro central entre la medida pre y postoperatoria utilizando la prueba de t de student. Resultados: la media de agudeza visual pre-operatoria fué de 20/60 y post-operatoria (6 meses) de 20/30. La media del grosor retiniano en el milímetro central pre-operatoria resultó 409.7 micras con un valor post-operatoria (6 meses) de 341 micras. En el 82% de los pacientes se observó una mejoría en la agudeza visual post-operatoria a los 6 meses. Los pacientes con mejores agudezas visuales fueron aquellos cuya agudeza visual pre-operatoria estuvo alrededor del 20/50. Conclusiones: la agudeza visual y el grosor retiniano pre-operatorio son los mejores factores pronósticos para estimar la agudeza visual post-operatoria en pacientes operados con diagnóstico de MER. La agudeza visual post-operatoria definitiva se alcanza posterior a los 6 meses de la cirugía. Se recomienda establecer como punto de corte para la decisión quirúrgica aquellos pacientes con agudezas visuales de 20/50 o peor.
Objective: to examine anatomic and visual outcomes in patients undergoing epiretinal membrane surgery. Methods: a case series study. Twentyseven eyes from 27 patients who underwent epiretinal membrane surgery were reviewed. Correlations between preoperative and first week, one and six months post-operative bestcorrected visual acuity and Optical Coherence Tomography (OCT) findings were obtained and analyzed using t student test. Results: mean pre-operative best corrected visual acuity (BCVA) was 20/60 and six months post-op was 20/30. Mean pre-op retinal central thickness was 409.7 microns and six months post-op was 341 microns. BCVA significantly improved in 82% of the patients after six months of surgery. Patients whom achieved higher BCVA levels post-op were those with pre-op BCVA around 20/50. Conclusions: pre-operative BCVA and central retinal thickness are the most importante factors to estimate post-operative BCVA. Highest BCVA levels were achieved after six months of surgery. It is recommended to use pre-op BCVA of 20/50 as cut-off level to consider surgical treatment.
