CoChat
Sign Up
Cited by 173Retinal Imaging and AnalysisOphthalmology and Visual Health ResearchRetinal Diseases and Treatments

Validation of Smartphone Based Retinal Photography for Diabetic Retinopathy Screening

Open access
Rajalakshmi, Ramachandran, Arulmalar, Subramanian, Usha, Manoharan, Prathiba, Vijayaraghavan, Kareemuddin, Khaji Syed, Anjana, Ranjit Mohan, Mohan, Viswanathan·2015·PLOS ONE
DOI 10.1371/journal.pone.0138285PMC PMC4581835
Open this paper in CoChat — free accountOpen PDF

Abstract

AIM: To evaluate the sensitivity and specificity of "fundus on phone' (FOP) camera, a smartphone based retinal imaging system, as a screening tool for diabetic retinopathy (DR) detection and DR severity in comparison with 7-standard field digital retinal photography. DESIGN: Single-site, prospective, comparative, instrument validation study. METHODS: 301 patients (602 eyes) with type 2 diabetes underwent standard seven-field digital fundus photography with both Carl Zeiss fundus camera and indigenous FOP at a tertiary care diabetes centre in South India. Grading of DR was performed by two independent retina specialists using modified Early Treatment of Diabetic Retinopathy Study grading system. Sight threatening DR (STDR) was defined by the presence of proliferative DR(PDR) or diabetic macular edema. The sensitivity, specificity and image quality were assessed. RESULTS: The mean age of the participants was 53.5 ±9.6 years and mean duration of diabetes 12.5±7.3 years. The Zeiss camera showed that 43.9% had non-proliferative DR(NPDR) and 15.3% had PDR while the FOP camera showed that 40.2% had NPDR and 15.3% had PDR. The sensitivity and specificity for detecting any DR by FOP was 92.7% (95%CI 87.8-96.1) and 98.4% (95%CI 94.3-99.8) respectively and the kappa (ĸ) agreement was 0.90 (95%CI-0.85-0.95 p<0.001) while for STDR, the sensitivity was 87.9% (95%CI 83.2-92.9), specificity 94.9% (95%CI 89.7-98.2) and ĸ agreement was 0.80 (95%CI 0.71-0.89 p<0.001), compared to conventional photography. CONCLUSION: Retinal photography using FOP camera is effective for screening and diagnosis of DR and STDR with high sensitivity and specificity and has substantial agreement with conventional retinal photography.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0138285

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Remote grading of retinal images was widely utilized, with 18 out of 30 studies relying on this approach.

    “Remote grading of retinal images is widely utilized, with 18 out of 30 studies relying on this approach [10, 15, 16, 18, 21–27, 29–35, 37]”

    From Diabetic retinopathy screening model in low and middle-income countries: a scoping review (2025) · cites this paper as [16]

    The Methods describe retinal photographs graded by two specialists, and the Discussion says the smartphone system can transmit images for remote evaluation. Neither passage says grading in this study was performed remotely. As one of several citations attached to the sentence, this paper also does not establish the aggregate figure of 18 out of 30 studies. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Image acquisition was often performed by trained non-physician staff, while final grading was typically carried out by ophthalmologists or retinal specialists in 22 out of 30 studies.

    “Image acquisition was often performed by trained non-physician staff (technicians, optometrists, nurses, paramedics), while final grading was typically carried out by ophthalmologists or retinal specialists (22/30 studies) [8–13, 15, 16, 18, 21, 22, 24, 26, 27, 30–37]”

    From Diabetic retinopathy screening model in low and middle-income countries: a scoping review (2025) · cites this paper as [16]

    The Methods report that a trained photographer/optometrist took the Zeiss photographs and that two retina specialists graded the photographs, with a third adjudicating disagreements. This supports the staffing pattern in this study, but the paper does not establish how often it occurred across studies or the claim that specialists graded images in 22 of 30 studies. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Studies using AI software such as Iowa Diabetic Retinopathy detection software and EyeArt show high sensitivity up to 95.8% (95% CI 92.9-98.7) and diagnostic accuracy.

    “Studies using AI software, such as the Iowa Diabetic Retinopathy detection software [15] and EyeArt [21] show high sensitivity up to 95,8% (95% CI 92,9–98,7) and diagnostic accuracy [16].”

    From Diabetic retinopathy screening model in low and middle-income countries: a scoping review (2025) · cites this paper as [16]

    The Results (Table 2; page unavailable) report high diagnostic performance for smartphone-based fundus photography, including 92.7% sensitivity for detecting any diabetic retinopathy. The Methods say retina specialists graded the images, not AI software. Table 2 lists 95.8% as specificity for proliferative retinopathy (95% CI 90.5–98.6), not the claimed sensitivity and confidence interval. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • The predominant method for managing remotely graded images was store and forward (14 out of 30 studies), with seven studies adopting real-time processing.

    “The predominant method for managing these remotely graded images is ‘store and forward’ (14 out of 30 studies) [15, 16, 18, 22–24, 26–30, 33, 35, 37], with seven studies adopting the ‘real-time’ processing method [8, 10, 11, 25, 31, 32, 34]”

    From Diabetic retinopathy screening model in low and middle-income countries: a scoping review (2025) · cites this paper as [16]

  • A study conducted in India using the Fundus on Phone system demonstrated lower costs compared to conventional fundus cameras.

    “A study conducted in India using the “Fundus on Phone” system also demonstrated lower costs compared to conventional fundus cameras [16].”

    From Diabetic retinopathy screening model in low and middle-income countries: a scoping review (2025) · cites this paper as [16]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. [1]International Diabetes Federation, Diabetes Atlas, Sixth Edition International Diabetes Federation, Brussels, Belgium; 2014.

Cited by

Sorted by citations

Related

Authors
Rajalakshmi, R., Arulmalar, S., Usha, M., Prathiba, V., Kareemuddin, K. S., Anjana, R. M., & Mohan, V.
Affiliations
Madras Diabetes Research Foundation (IN)
Corresponding author
Mohan, Viswanathan
ORCID
Venue
PLOS ONE
Publisher
Public Library of Science (PLoS)
Published
2015-09-24
Volume
10
Issue
9
Pages
e0138285
ISSN
1932-6203 (ISSN-L)
DOI
10.1371/journal.pone.0138285
PMC
PMC4581835
OpenAlex
W2179023931
Cited by
173
References
30
Citations by year
2026: 10 · 2025: 12 · 2024: 15 · 2023: 13 · 2022: 19 · 2021: 23 · 2020: 39 · 2019: 18 · 2018: 16 · 2017: 4 · 2016: 4
FWCI
6.48
Type
journal article
Language
en
Open access
Licence
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
  • Health Sciences › Medicine › Ophthalmology › Ophthalmology and Visual Health Research
  • Health Sciences › Medicine › Ophthalmology › Retinal Diseases and Treatments
Keywords
diabetic retinopathy, diabetic retinopathy screening, type 2 diabetes, diabetic macular edema, proliferative diabetic retinopathy, diagnostic accuracy, image quality, low-cost screening
MeSH terms
Smartphone, Adult, Aged, Diabetic Retinopathy, Female, Humans, Male, Mass Screening, Middle Aged, Photography, Sensitivity and Specificity, Severity of Illness Index, Ophthalmoscopes, Young Adult

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review