Literature DB >> 31014763

Sensitivity and Specificity of Smartphone-Based Retinal Imaging for Diabetic Retinopathy: A Comparative Study.

Sabyasachi Sengupta1, Manavi D Sindal2, Prabu Baskaran2, Utsab Pan2, Rengaraj Venkatesh2.   

Abstract

PURPOSE: To determine the sensitivity and specificity of a smartphone-based fundus camera, the Remidio Fundus on Phone (FOP; Remidio Innovative Solutions Pvt. Ltd., Bengaluru, India) in detecting diabetic retinopathy (DR) compared with a conventional tabletop fundus camera and clinical examination.
DESIGN: Cross-sectional, single-site, instrument validation study. PARTICIPANTS: Consecutive patients with diabetes who had no DR (n = 55 eyes), mild to moderate nonproliferative diabetic retinopathy (NPDR; n = 70 eyes), severe NPDR (n = 46 eyes), proliferative diabetic retinopathy (PDR; n = 62 eyes), and diabetic macular edema (DME; n = 44 eyes).
METHODS: All participants underwent a dilated examination to determine the grade of DR. Then all participants had mydriatic 45° fundus photographs obtained from three fields of view with the Remidio FOP and a Topcon tabletop fundus camera (Topcon Medical Systems, Inc., Oakland, NJ). Two masked retina specialists graded images for DR and DME, using National Health Service guidelines as well as for image quality using predefined criteria. MAIN OUTCOME MEASURE: Sensitivity and specificity of the Remidio FOP for the detection of any DR compared to clinical examination.
RESULTS: One hundred thirty-five subjects (233 eyes) were recruited for the study. Compared with the reference clinical examination, using images from the Remidio FOP, graders 1 and 2 reported a sensitivity of 93.1% (95% confidence interval [CI] = 88.3-96.4) and 94.3% (95% CI = 89.7-97.2) and a specificity of 89.1% (95% CI = 68.2-92.2) and 94.5% (95% CI = 84.9-98.9), respectively, in identifying any DR (κ = 0.55; 95% CI = 0.50-0.57). With images from the Topcon camera, graders reported similar sensitivities and specificities with marginally better agreement (κ = 0.68; 95% CI = 0.67-0.73). The sensitivity of detecting DR gradually increased from R1 to R3 disease using both cameras. Both graders classified significantly fewer images as "ungradable" (2.6%-4.3% for Topcon vs. 1.7%-2.1% for Remidio FOP) and more images as excellent from the Remidio FOP (59%-74%) than the Topcon device (52%-61%).
CONCLUSIONS: The Remidio FOP device was found to have high sensitivity and specificity for the detection of any grade of DR with good agreement between graders. The rate of ungradable images was acceptably low and image quality was marginally better with the Remidio FOP.
Copyright © 2018 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

Entities:  

Year:  2018        PMID: 31014763     DOI: 10.1016/j.oret.2018.09.016

Source DB:  PubMed          Journal:  Ophthalmol Retina        ISSN: 2468-6530


  16 in total

1.  Development and validation of a machine learning, smartphone-based tonometer.

Authors:  Aaron Y Lee; Joanne C Wen; Yue Wu; Ian Luttrell; Shu Feng; Philip P Chen; Ted Spaide
Journal:  Br J Ophthalmol       Date:  2019-12-23       Impact factor: 4.638

Review 2.  [Smartphone-based fundus imaging: applications and adapters].

Authors:  Linus G Jansen; Thomas Schultz; Frank G Holz; Robert P Finger; Maximilian W M Wintergerst
Journal:  Ophthalmologe       Date:  2021-12-16       Impact factor: 1.059

Review 3.  Clinically useful smartphone ophthalmic imaging techniques.

Authors:  Amar Pujari; Gunjan Saluja; Divya Agarwal; Harathy Selvan; Namrata Sharma
Journal:  Graefes Arch Clin Exp Ophthalmol       Date:  2020-09-11       Impact factor: 3.117

4.  [Ocular changes as a diagnostic tool for malaria].

Authors:  Hanna Faber; Philipp Berens; Jens Martin Rohrbach
Journal:  Ophthalmologie       Date:  2021-12-23

5.  Use of Smartphones to Detect Diabetic Retinopathy: Scoping Review and Meta-Analysis of Diagnostic Test Accuracy Studies.

Authors:  Choon Han Tan; Bhone Myint Kyaw; Helen Smith; Colin S Tan; Lorainne Tudor Car
Journal:  J Med Internet Res       Date:  2020-05-15       Impact factor: 5.428

6.  Commentary: Utility of a smartphone-assisted direct ophthalmoscope camera for a general practitioner in screening of diabetic retinopathy at a primary health care center.

Authors:  Ashish Markan; Simar R Singh; Mohit Dogra
Journal:  Indian J Ophthalmol       Date:  2021-11       Impact factor: 1.848

Review 7.  The Evolution of Diabetic Retinopathy Screening Programmes: A Chronology of Retinal Photography from 35 mm Slides to Artificial Intelligence.

Authors:  Josef Huemer; Siegfried K Wagner; Dawn A Sim
Journal:  Clin Ophthalmol       Date:  2020-07-20

8.  Medios- An offline, smartphone-based artificial intelligence algorithm for the diagnosis of diabetic retinopathy.

Authors:  Bhavana Sosale; Aravind R Sosale; Hemanth Murthy; Sabyasachi Sengupta; Muralidhar Naveenam
Journal:  Indian J Ophthalmol       Date:  2020-02       Impact factor: 1.848

9.  Simple, Mobile-based Artificial Intelligence Algorithm in the detection of Diabetic Retinopathy (SMART) study.

Authors:  Bhavana Sosale; Sosale Ramachandra Aravind; Hemanth Murthy; Srikanth Narayana; Usha Sharma; Sahana G V Gowda; Muralidhar Naveenam
Journal:  BMJ Open Diabetes Res Care       Date:  2020-01

10.  Commentary: Artificial intelligence and smartphone fundus photography - Are we at the cusp of revolutionary changes in retinal disease detection?

Authors:  V G Madanagopalan; Rajiv Raman
Journal:  Indian J Ophthalmol       Date:  2020-02       Impact factor: 1.848

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.