Diabetic Retinopathy Screening Using Smartphone-Based Fundus Photography and Deep-Learning Artificial Intelligence in the Yucatan Peninsula: A Field Study

被引:1
|
作者
Wroblewski, John J. [1 ,2 ,6 ]
Sanchez-Buenfil, Ermilo [3 ]
Inciarte, Miguel [3 ]
Berdia, Jay [2 ]
Blake, Lewis [4 ]
Wroblewski, Simon [2 ]
Patti, Alexandria [2 ]
Suter, Gretchen [2 ]
Sanborn, George E. [5 ]
机构
[1] Retina Care Int, Hagerstown, MD USA
[2] Cumberland Valley Retina Consultants, Hagerstown, MD USA
[3] RetimediQ, Merida, Mexico
[4] Colorado Sch Mines, Dept Appl Math & Stat, Golden, CO USA
[5] Virginia Commonwealth Univ, Dept Ophthalmol, Richmond, VA USA
[6] Retina Care Int, 1150 Opal Ct, Hagerstown, MD 21740 USA
关键词
artificial intelligence; diabetic retinopathy; fundus-on-phone camera; Mexico; rural health care; screening; VALIDATION; ALGORITHM; CONFIDENCE; BLINDNESS;
D O I
10.1177/19322968231194644
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
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.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence
    Ramachandran Rajalakshmi
    Radhakrishnan Subashini
    Ranjit Mohan Anjana
    Viswanathan Mohan
    [J]. Eye, 2018, 32 : 1138 - 1144
  • [2] Screening for Diabetic Retinopathy Using Artificial Intelligence and Smartphone-Based Fundus Images
    Kalavar, Meghana
    Watane, Arjun
    Sridhar, Jayanth
    [J]. INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2020, 61 (09)
  • [3] Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence
    Rajalakshmi, Ramachandran
    Subashini, Radhakrishnan
    Anjana, Ranjit Mohan
    Mohan, Viswanathan
    [J]. EYE, 2018, 32 (06) : 1138 - 1144
  • [4] Use of offline artificial intelligence in a smartphone-based fundus camera for community screening of diabetic retinopathy
    Krishnan, Radhika
    Jain, Astha
    Rogye, Ashwini
    Natarajan, Sundaram
    [J]. INDIAN JOURNAL OF OPHTHALMOLOGY, 2021, 69 (11) : 3150 - +
  • [5] Artificial intelligence evaluation of diabetic retinopathy using smartphone retinal fundus photography
    Levy, Julien
    Nguyen, Mickey
    Yim, Angela
    Zhou, Yunshu
    Vaghefi, Ehsan
    Kim, Tyson
    Paulus, Yannis Mantas
    [J]. INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2023, 64 (08)
  • [6] Smartphone-Based, Artificial Intelligence-Enabled Diabetic Retinopathy Screening
    Liu, T. Y. Alvin
    [J]. JAMA OPHTHALMOLOGY, 2019, 137 (10) : 1188 - 1189
  • [7] Diabetic Retinopathy Screening Using Smartphone-Based Fundus Imaging in India
    Wintergerst, Maximilian W. M.
    Mishra, Divyansh K.
    Hartmann, Laura
    Shah, Payal
    Konana, Vinaya K.
    Sagar, Pradeep
    Berger, Moritz
    Murali, Kaushik
    Holz, Frank G.
    Shanmugam, Mahesh P.
    Finger, Robert P.
    [J]. OPHTHALMOLOGY, 2020, 127 (11) : 1529 - 1538
  • [8] Diabetic Retinopathy Screening Using Artificial Intelligence and Handheld Smartphone-Based Retinal Camera
    Malerbi, Fernando Korn
    Andrade, Rafael Ernane
    Morales, Paulo Henrique
    Stuchi, Jose Augusto
    Lencione, Diego
    de Paulo, Jean Vitor
    Carvalho, Mayana Pereira
    Nunes, Fabricia Silva
    Rocha, Roseanne Montargil
    Ferraz, Daniel A.
    Belfort, Rubens, Jr.
    [J]. JOURNAL OF DIABETES SCIENCE AND TECHNOLOGY, 2022, 16 (03): : 716 - 723
  • [9] Medios-A Smartphone-Based Artificial Intelligence Algorithm in Screening for Diabetic Retinopathy
    Sosale, Bhavana
    Sosale, Aravind R.
    Murthy, Hemanth
    Narayana, Srikanth
    Sharma, Usha
    Gowda, Sahana G. V.
    Naveenam, Muralidhar
    [J]. DIABETES, 2019, 68
  • [10] Validation of Smartphone-Based Retinal Photography for Diabetic Retinopathy Screening
    Bilong, Yannick
    Katte, Jean-Claude
    Koki, Godefroy
    Kagmeni, Giles
    Obama, Odile Pascale Nga
    Fofe, Hermann Rossi Ngoufo
    Mvilongo, Caroline
    Nkengfack, Oliver
    Bimbai, Andre Michel
    Sobngwi, Eugene
    Mbacham, Wilfred
    Mbanya, Jean Claude
    Bella, Lucienne Assumpta
    Sharma, Ashish
    [J]. OPHTHALMIC SURGERY LASERS & IMAGING RETINA, 2019, 50 (05): : S18 - S22