Inteligencia artificial en retinopatía diabética: estudio de cribado en Encarnación, Paraguay

Andrea R. Oleñik Memmel; Manuel Codas; Araceli Balbuena; Alejandra Benegas; Arturo Acosta; Miguel Angel Zapata

doi:10.70313/2718.7446.v16.n03.243

Authors

Andrea R. Oleñik Memmel Limmat Augenzemnrum Zurich, Zurich, Suiza. Fundación Retina Paraguay, Encarnación, Paraguay
Manuel Codas Hospital Universitario de Encarnación, Encarnación, Paraguay. Facultad de Medicina, Universidad Nacional de Itapúa, Encarnación, Paragua
Araceli Balbuena Fundación Retina Paraguay, Encarnación, Paraguay
Alejandra Benegas Fundación Retina Paraguay, Encarnación, Paraguay
Arturo Acosta Fundación Retina Paraguay, Encarnación, Paraguay
Miguel Angel Zapata Hospital Vall d’Hebron, Barcelona, España. UPT Retina, Barcelona, España

DOI:

https://doi.org/10.70313/2718.7446.v16.n03.243

Keywords:

diabetes, diabetes retinopathy, telemedicine, artificial intelligence, public health

Abstract

Objective: To evaluate the efficacy of a public health telemedicine model for the detection of diabetic retinopathy using portable retinography with artificial intelligence software.

Materials and methods: Prospective single-center study including asymptomatic patients, who attended the endocrinology unit of the Regional Hospital of Encarnación (department of Itapúa, Paraguay), between June and August 2022. We evaluated the sensitivity and specificity of an artificial intelligence system applied in a telemedicine program, for the detection of proliferative and non-proliferative diabetic retinopathy.

Results: A total of 591 cases (1,182 eyes) were evaluated. The AI system identified 8 eyes with signs of diabetic retinopathy versus the specialist who validated 6, being the other two studies also pathological, but corresponding to another alteration. Regarding the detection of non-proliferative diabetic retinopathy, the artificial intelligence system detected 92 positive studies that were validated by the specialist. The degree of sensitivity for DR detection of the AI system was 98%, with a high specificity of 99.8%.

Conclusion: The use of portable retinography and AI software was efficient for screening asymptomatic patients, but with risk factors such as diabetes, in an endocrinology service of a public hospital in Paraguay.

Downloads

Download data is not yet available.

References

Bourne RRA, Stevens GA, White RA et al. Causes of vision loss worldwide, 1990-2010: a systematic analysis. Lancet Glob Heal 2013; 1: 339-349.

Paraguay. Ministerio de Salud Pública y Bienestar Social. Dirección de Estadísticas en Salud. Indicadores básicos de salud Paraguay 2018. [Asunción]: Organización Panamericana de la Salud, [2019]. Disponible en: https://docs.bvsalud.org/biblioref/2021/08/1282703/manual-indicadores-basicos-de-salud-2018.pdf

Garg S, Davis RM. Diabetic retinopathy screening update. Clin Diabetes 2009; 27: 140-145.

Sánchez González S, Calvo Lozano J, Sánchez González J et al. Valoración del uso de retinografía como método de diagnóstico precoz de glaucoma crónico en atención primaria: validación para el cribado en población con factores de riesgo para glaucoma de ángulo abierto. Aten Primaria 2017; 49: 399-406.

Chan CKW, Gangwani RA, McGhee SM et al. Cost-effectiveness of screening for intermediate age-related macular degeneration during diabetic retinopathy screening. Ophthalmology 2015; 122: 2278-2285.

Surendran TS, Raman R. Teleophthalmology in diabetic retinopathy. J Diabetes Sci Technol 2014; 8: 262-266.

Oleñik Memmel AR, Gómez-Ibáñez R, Manresa et al. Telemedicina portátil para la prevención de la ceguera en el Paraguay. Oftalmol Clin Exp 2021; 14: 193-201.

Zapata MA, Royo-Fibla D, Font O et al. Artificial intelligence to identify retinal fundus images, quality validation, laterality evaluation, macular degeneration, and suspected glaucoma. Clin Ophthalmol 2020; 14: 419-429.

Font O, Torrents-Barrena J, Royo D et al. Validation of an autonomous artificial intelligence-based diagnostic system for holistic maculopathy screening in a routine occupational health checkup context. Graefes Arch Clin Exp Ophthalmol 2022; 260: 3255-3265.

Li JPO, Liu H, Ting DSJ et al. Digital technology, tele-medicine and artificial intelligence in ophthalmology: a global perspective. Prog Retin Eye Res 2021; 82:100900.

Mehra AA, Softing A, Guner MK et al. Diabetic retinopathy telemedicine outcomes with artificial intelligence-based image analysis, reflex dilation, and image overread. Am J Ophthalmol 2022; 244: 125-132.

Grauslund J. Diabetic retinopathy screening in the emerging era of artificial intelligence. Diabetologia 2022; 65: 1415-1423.

Zhelev Z, Peters J, Rogers M et al. Test accuracy of artificial intelligence-based grading of fundus images in diabetic retinopathy screening: a systematic review. J Med Screen 2023; 30: 97-112.

Nadeem MW, Goh HG, Hussain M et al. Deep learning for diabetic retinopathy analysis: a review, research challenges, and future directions. Sensors (Basel) 2022; 22: 6780.