The area under the curve is 0. Abràmoff MD , Folk JC , Han DP, et al. Automated Analysis of Retinal Images for Detection of Referable Diabetic Retinopathy. JAMA Ophthalmol. Importance The diagnostic accuracy of computer detection programs has been reported to be comparable to that of specialists and expert readers, but no computer detection programs have been validated in an independent cohort using an internationally recognized diabetic retinopathy DR standard.

Objective To determine the sensitivity and specificity of the Iowa Detection Program IDP to detect referable diabetic retinopathy RDR. Design and Setting In primary care DR clinics in France, from January 1, , through December 31, , patients were photographed consecutively, and retinal color images were graded for retinopathy severity according to the International Clinical Diabetic Retinopathy scale and macular edema by 3 masked independent retinal specialists and regraded with adjudication until consensus.

The IDP analyzed the same images at a predetermined and fixed set point. Main Outcome Measures Sensitivity and specificity of the IDP to detect RDR, area under the receiver operating characteristic curve, sensitivity and specificity of the retinal specialists' readings, and mean interobserver difference κ.

Results The RDR prevalence was The IDP sensitivity was The area under the receiver operating characteristic curve was 0.

Conclusions The IDP has high sensitivity and specificity to detect RDR. Computer analysis of retinal photographs for DR and automated detection of RDR can be implemented safely into the DR screening pipeline, potentially improving access to screening and health care productivity and reducing visual loss through early treatment.

Increasing health care productivity is a prerequisite to improve health care affordability. Automation has improved productivity in many sectors of the economy, whereas in health care, productivity has remained stagnant in the last 20 years.

Computer detection of DR analyzes retinal color images obtained by fundus cameras and triages those who have DR and require referral to an ophthalmologist from those who can be screened again in 1 year. The diagnostic accuracy of computer detection programs has been reported to be comparable to that of specialists 6 , 7 and expert readers, but none of the semiautomated or fully automated computer detection programs have been validated in an independent cohort using an internationally recognized DR standard.

The International Clinical Diabetic Retinopathy ICDR severity scale was formulated by a consensus of international experts to standardize and simplify DR classification Table 1 to improve communication and coordination of care among physicians caring for patients with diabetes.

independently graded retinal images of each eye from people with diabetes using the ICDR severity level scales and a modified definition of macular edema ME , namely, any retinal thickening, exudate, or microaneurysm within 1 disc diameter of the fovea. We defined nonreferable DR as no NPDR or mild NPDR and no apparent ME.

The IDP was compared against the consensus rating of the 3 retinal specialists reading the same images. Deidentified digital fundus color images of eyes in people with diabetes were used. The images are publicly available for noncommercial use. Each department included consecutive people with diabetes, diagnosed according to the World Health Organization criteria in use at that time.

Demographics for each participant were obtained retrospectively by medical record review at the 3 centers. To ensure deidentification of the images, only the aggregate mean SD of age and sex distribution was available to the authors.

Participants underwent pharmacologic dilation at 2 centers Paris and Saint-Etienne and did not undergo dilation at the third center.

They were then imaged using a color video 3CCD camera Canon Europe BV on a Topcon TRC NW6 nonmydriatic fundus camera Topcon USA, Inc with a 45° field of view centered on the fovea.

The images were captured at × , × , or × pixels and saved in tiff or jpeg format. All participants were imaged successfully.

Three internationally recognized, fellowship-trained retinal specialists graded 1 image of each eye. The experts were masked to each other and to the IDP. Each expert assigned an ICDR retinopathy level scale of 0 for best to 4 for worst and an ME level scale of 0 for no ME to 1 for ME for each image.

Experts used the presence of exudates, retinal thickening if visible , or microaneurysms, all within 1 disc diameter of the fovea, as a sign of ME.

We added the criterion of 1 or more microaneurysms because we were concerned that ME would be incorrectly missed on nonstereo photographs by the experts, and the isolated presence of 1 or more microaneurysm s can be the only sign of ME visible on nonstereo photographs.

Any disagreements were adjudicated by rerating the images until consensus was reached by all 3 experts. The consensus ICDR and ME severity levels for each participant were dichotomized into a single adjudicated rating: either RDR, meaning either moderate or severe NPDR, or PDR, ME, or both.

A person was deemed to have RDR if either or both eyes had these findings. A person was deemed to have nonreferable DR if there was no NPDR or mild NPDR and no ME in both eyes. Sensitivity and specificity determined by the 3 experts were estimated by comparing their individual RDR and nonreferable DR gradings before consensus against those of the other 2 experts.

The IDP consists of previously published components for image quality assessment, 19 microaneurysm and hemorrhage detection, 20 , 21 detection of exudates and cotton wool spots, 22 and a new component for detection of irregular lesions, including large hemorrhages and neovascularization.

The algorithms have all been published previously. A separate fusion algorithm, also previously published, 24 combines these analyses of individual lesions and structures, as well as the image quality. The final output of the IDP is the DR index, a dimensionless number between 0 and 1.

The DR index expresses the likelihood that the patient's images will show RDR. The IDP calculates the DR index for a single individual 2 images in less than 25 seconds on a computer equipped with a 2-core Intel i3 processor Intel Corporation.

A previous version of the IDP was evaluated in a primary care setting, with 2 images per eye. Analyses were conducted using SAS statistical software, version 9. The IDP sensitivity, specificity, positive predictive value PPV , negative predictive value NPV , and CIs were calculated at the prefixed set point.

Interobserver variability of the 3 experts was calculated with the κ statistic. Prevalence of RDR in the data set was determined from the adjudicated ICDR reference standard. We calculated the receiver operating characteristic curve for all possible set points between 0 and 1.

The area under the receiver operating characteristic curve AUC was determined using logistic regression PROC LOGISTIC and modeling the adjudicated reference standard as a function of the detection program. We calculated the expected value of the AUC that can be measured for a perfect detection program or the theoretical maximum AUC given the characteristics of the 3 readers captured by the average κ and the prevalence of disease in the population.

The primary outcome measure was IDP sensitivity and specificity for detecting RDR as measured against the adjudicated reference standard.

The set point of the IDP was fixed at 0. The study included participants and images. The mean SD age of the patients was No adverse events occurred. The 3 retinal experts graded all images from all participants. Of the participants, had RDR in the adjudicated reference standard, so the prevalence of RDR was The exact distribution of ICDR severity levels is given in Table 2.

The κ values were 0. Sensitivity of the IDP to detect RDR was The PPV was Of the participants, had true-positive, 6 had false-negative, had true-negative, and had false-positive results. The corresponding false-negative rate was 0.

No participant with a false-negative result was assigned an ICDR severity level of severe NPDR or PDR grade 3 or 4 or apparent diabetic macular edema DME by any retinal expert.

Figure 2 shows the images of all 6 participants who had false-negative results ie, were estimated by the IDP to not have RDR, whereas the consensus of the experts was that they had RDR.

The AUC C statistic against the consensus reference standard was 0. The AUC against the voted referenced standard was 0.

The estimated sensitivity and specificity of the 3 experts are given in Table 3 ; their sensitivity ranged from The theoretical maximum AUC measurable was 0. The results reveal that the IDP has high sensitivity and specificity to differentiate patients with RDR from those without RDR compared with a consensus of 3 retinal specialists.

On a practical level, the goal of a DR screening program is to identify those who need referral to an ophthalmologist for possible treatment. Individuals with no NPDR or mild NPDR and no ME have insufficient disease to require treatment and a low risk of advancing to treatment criteria within 1 year.

There is excellent evidence, therefore, that people with these levels of DR should be screened again in 1 year.

Because the sensitivity is as high as for ophthalmic screening, the number of patients requiring and referred for the expensive time of an ophthalmologist is reduced by more than half, with no diminution in the number of cases requiring attention the ophthalmologist would be required to see. A major concern of automated computer detection programs is their potential to delay diagnosis of a treatable condition.

Most of those with moderate NPDR do not progress to high-risk PDR within 1 year. Despite these false-negative results, IDP sensitivity exceeded the estimated sensitivity of any individual retinal expert: each of the retinal experts had a comparable or larger number of false-negative results.

As explained in the Methods section, the IDP set point was determined before evaluating the first photograph with the expectation that it would result in a high sensitivity for the present study. Most of the disagreements among the experts that required adjudication, before consensus was reached, were around mild and moderate NPDR.

This finding is easy to understand because, for instance, an image with only a few microaneurysms is rated as mild NPDR according to the ICDR, but if an expert thought that one of these microaneurysms was actually a small hemorrhage, he or she would grade that as moderate NPDR, again following the ICDR.

Most of the IDP false-positive results were in people with moderate NPDR, which corresponds to ETDRS stages 35 through All of the IDP false-negative results had stage 35 NPDR, which has only a 4.

The IDP set point, unlike a human expert, can be set at any value between 0 and 1. At the set point of 0. At this set point, 12 people with RDR would be missed, and only people without RR would be referred unnecessarily.

A review of the images of the 12 people with missed RDR revealed that all of them had only moderate NPDR without ME.

To evaluate the efficacy of retinal photography obtained by undergraduate students using a smartphone-based device in screening and early diagnosing diabetic retinopathy DR. We carried out an open prospective study with ninety-nine diabetic patients eyes , who were submitted to an ophthalmological examination in which undergraduate students registered images of the fundus using a smartphone-based device.

At the same occasion, an experienced nurse captured fundus photographs from the same patients using a gold standard tabletop camera system Canon CR-2 Digital Non-Mydriatic Retinal Camera , with a 45º field of view. Two distinct masked specialists evaluated both forms of imaging according to the presence or absence of sings of DR and its markers of severity.

We later compared those reports to assess agreement between the two technologies. Concerning the presence or absence of DR, we found an agreement rate of As for the classification between proliferative diabetic retinopathy and non-proliferative diabetic retinopathy, we found an agreement of Regarding the degree of classification of DR, we found an agreement rate of As relating to the presence or absence of hard macular exudates, we found an agreement of The smartphone-based device showed promising accuracy in the detection of DR Diabetic retinopathy DR is one of the most important complications of Diabetes Mellitus DM and its incidence is intrinsically related to the duration of the disease and level of glycemic control.

Early diagnosis of DR allows for intervention that effectively reduces its progression to more severe states [ 1 ]. Nevertheless, ophthalmologic follow up for diabetic patients faces severe barriers deriving from the expensiveness of current diagnostic technology and its difficulties of implementation.

Patients with type 1 DM are suggested to undergo ophthalmologic evaluation at puberty or within five years of disease, whereas patients with type 2 DM should be evaluated immediately after being diagnosed.

As a consequence, telemedicine systems based on digital photographs of the fundus have become increasingly popular, as they allow for assessment of the images by a remotely located ophthalmologist.

The diagnostic accuracy of telemedicine using digital images has proven itself to be high and cost-effective in DR screening [ 3 ]. In recent years, smartphone adapters for fundus photography have been progressively developed and presented promising results when compared to the reference standards [ 7 ][ 7 ][ 7 ].

Smartphones can be used to register fundus images either serving as slit lamp adapters, as well as integrating direct or monocular indirect ophthalmoscopy settings.

Different professionals are capable of obtaining retinal fundus photographs through smartphone-based methods. Nonetheless, most of the available studies involved the participation of experienced technicians for obtaining the images [ 7 ][ 7 ][ 7 ]. In this study, images of the fundus registered through the smartphone-based device were captured by undergraduate medicine and nursery students who had no previous experience in retinal imaging.

Our aim was to assess the method when applied to a realistic scenario, where this technology would be handled by general physicians and nurses with no previous experience in eye imaging, in a context of primary healthcare. We conducted a prospective, open study, collecting data from diabetic patients eyes at the diabetic retinopathy screening clinic of Hospital das Clínicas de Ribeirão Preto HC-FMRP-USP , a high complexity general hospital in Brazil.

We included diabetic patients followed up at the hospital who were 18 years old or older and voluntarily agreed to participate in the study.

All patients had both eyes examined, except for one who had only one eye. Data from only 97 patients eyes were included in the study. Thirty-seven eyes were excluded—33 eyes were excluded due to data loss in the HC-FMRP-USP digital medical files system, 3 eyes were excluded due to the presence of cataracts, which prevented the visualization of the fundus, and 1 eye was excluded due to patient photophobia.

During their appointment for diabetic retinopathy evaluation, patients in the study underwent two types of assessments: one being standard seven field color stereoscopic photography of the fundus captured by an experienced nurse through a tabletop fundus camera Canon CR-2 Digital Non-Mydriatic Retinal Camera—demonstrated on Fig.

Five images were obtained from each eye fundus using the tabletop camera: 1 image centered on the fovea, 2 Temporal retina; 3 Nasal retina; 4 Superior retina; 5 Inferior retina. The undergraduate students who participated in the study were enrolled in the courses of Medicine or Nursery at the Ribeirão Preto Medical School University of São Paulo and had no previous experience in eye imaging of any sort.

A shows the tabletop fundus camera Canon CR-2 Digital Non-Mydriatic Retinal Camera and the corresponding color fundus picture of the posterior pole B. C shows the smartphone based device used and the corresponding color fundus image captured from the video D.

Images do not depict the same patient. All four participating students received standardized training from an experienced ophthalmologist, who presented the device and explained how to handle it, in addition to monitoring the recording of the first 10 videos.

For the smartphone-based examination, the students captured a high-definition video of the fundus, lasting around two minutes each, using a device that consisted of an iron support where a smartphone in this study, an Apple Iphone 6 ® or a Samsung Galaxy S8 ® was attached to one side and a 20 D lens was attached to the other side.

The device also had an iron adapter on the bottom that allowed its attachment to a slit lamp table. This made image acquisition easier as the patient's head remained fixed by the chin rest, facilitating handling of the camera and adjusting its focus Fig.

Nothing but the inbuilt camera software of each smartphone were used to register the images. All the included patients underwent pharmacological mydriasis prior to the exam. After posterior pole focus was obtained, recording was started and the patient was asked to look into five directions in the following order: 1 Straight ahead; 2 Temporally; 3 Nasally; 4 Superiorly and 5 Inferiorly.

Images obtained by each method were saved on cloud storage Google Drive ® in a randomized manner and organized by codes. Posteriorly, two independent masked specialists assessed each image individually and classified their findings according to the Airlie-House modified scale [ 4 ] 0—Absence of Retinopathy; 1—Minimal non-proliferative diabetic retinopathy [NPDR]; 2—Mild NPDR; 3—Moderate NPDR; 4—Severe NPDR; 5—Very severe NPDR; 6—Proliferative diabetic retinopathy PDR with no high risk signs; 7—PDR with high risk signs; 8—Advanced PDR; 9—Classification not possible and also according to the presence or absence of hard macular exudates, utilized here as a surrogate marker for diabetic macular edema.

After each individual analysis, the specialists reported the results in an online form created specifically for that purpose on Google Forms®. Both masked specialists independently evaluated and classified all images generated by the standard fundus camera and then evaluated and classified all videos generated by the smartphone-based method.

All images and videos had been completely randomized and identified only by a code, making it impossible for them to identify any patient information. In the same manner, specialist number 1 had no access to the reports produced by specialist number 2 and vice-versa.

A third specialist was asked to evaluate cases where there was disagreement between the specialists 1 and 2. Finally, we calculated the agreement rate, kappa correlation index, sensitivity, specificity and disagreement false positives and false negatives of the reports deriving from the smartphone-based method as compared to those deriving from the gold standard tabletop fundus camera system, as well as interobserver agreement between specialists for each method as further detailed ahead.

Calculations were performed using the numerical calculation software GNU Octave®. Participants had a mean age of Self-declared racial demographic was of Enrolled patients had a previous diagnosis of type 1 DM in Regarding the presence or absence of DR, agreement between the two independent evaluators of the images Interobserver from the smartphone-based device was As for the gold standard fundus photograph, interobserver agreement was Considering reports from the first evaluator Intraobserver 1 , analysis of the smartphone-based device in comparison with the gold standard obtained the agreement of: Considering reports from the second evaluator Intraobserver 2 , smartphone-based device compared to the gold standard showed an agreement of These data are depicted in Tables 2 and 3.

Concerning the classification between proliferative diabetic retinopathy and non-proliferative diabetic retinopathy, interobserver agreement of the images from the smartphone-based device was Intraobserver 1: smartphone-based device analysis compared to gold standard images demonstrated agreement: Intraobserver 2: analysis of the smartphone-based device in comparison with the gold standard images showed agreement: These data are shown in Tables 2 and 4.

For the analysis of the classification of severity of DR, when specialists differed by only one class, we considered only the most severe classification. In this case, interobserver agreement found in the images of the smartphone-based device was In the gold standard images, interobserver agreement was Intraobserver 1: agreement of the reports obtained by the smartphone-based images in comparison with those coming from the gold standard was Intraobserver 2: agreement of the reports obtained by the smartphone-based images in comparison with those coming from the gold standard was Considering a tolerance of up to two classes of divergence, agreement found in the interobserver comparison of the images obtained by the smartphone-based device was Interobserver comparison of the images obtained by the gold standard was Considering the presence or absence of hard macular exudates, agreement of the reports obtained by the smartphone-based images in comparison with those coming from the gold standard was In order to obtain a final analysis between the two methods, results from the two specialists were merged.

On reports from both the smartphone-based and the conventional tabletop camera methods, when the classification attributed by the specialists was consensual in their analysis, the data was kept; when there was no consensus, a third independent masked specialist assessed and assigned the final analysis.

As for the classification between proliferative diabetic retinopathy and nonproliferative diabetic retinopathy, final agreement between the images from the smartphone-based device and those from the gold standard was Regarding the classification of severity of DR, to obtain a final result, when the specialists differed by only 1 class, the most severe classification was assigned, when they differed by up to 2 classes, a third independent masked specialist performed the analysis and attributed the final classification Tables 2 and 5.

Therefore, agreement of the reports obtained by the smartphone-based images in comparison with those coming from the gold standard was Our study was able to verify that retinal images obtained by undergraduate students using a smartphone-based device showed satisfactory performance when compared to the reference standard for the diagnosis of DR.

Recent studies suggest that the diagnostic accuracy of telemedicine using digital images in DR is, in general, high. The high sensitivity of its detection of any clinical level of DR indicates that telemedicine could be widely used for DR screening [ 3 ].

Portable devices for eye fundus image acquisition have shown high levels of agreement with traditional tabletop retinal cameras for the detection and follow-up of DR [ 7 ]. However, the latter tend to perform better compared to smartphone-based devices like the one reported in this study.

Russo et al. Summary of the comparative results for grading of diabetic retinopathy severity and grade of diabetic macular oedema is depicted in Table 1. Sixteen patients Four patients 6.

Five patients had hazy media in one or other eye and found it difficult to achieve sharp focus. Due to senile ptosis, 7 patients Two patients 3. The procedure was not comfortable to 4 patients 6.

They needed reassurance and assistance to retract their eyelids. It was challenging for 1 patient 1. One patient had cervical spondylosis and found it difficult to move his neck for positioning the camera.

Centred image could not be obtained in one patient with 3rd nerve palsy. Comparative photographs of participant 1 showing images captured using selfie fundus imaging 1A, 1B , by technician using the same handheld fundus camera 1C, 1D and standard desktop fundus camera 1E, 1F.

Comparative photographs of participant 2 showing images captured using selfie fundus imaging 2A, 2B , by technician using the same handheld fundus camera 2C, 2D and standard desktop fundus camera 2E, 2F. Diabetic retinopathy is a severe sight threatening complication of diabetes mellitus and has become the most common cause of blindness in middle aged adults, in several countries [ 13 ].

There is a significant lead time between onset of diabetes and the development of retinopathy, and in addition, highly efficacious therapy to prevent visual disability is available.

The focus of screening is to detect retinopathy before it has progressed to a stage wherein therapy becomes ineffective or less efficacious. A high percentage of success in screening translates to lower visual morbidity and hence to reduced health costs and improved health economics.

The situation is even more alarming in low-middle income countries [ 14 , 15 , 16 ]. Several approaches to diabetic retinopathy screening have been explored and used in practice [ 17 ]. Broadly, these can be categorized into methods based on ophthalmoscopy and those based on photography.

The former methods are subjective and so have a wide margin of specificity and sensitivity based on the amount of training. The latter is objective, has high sensitivity and specificity but is technology and cost intensive. Despite these limitations, grading of images captured using fundus cameras is considered the most efficient method for the management of diabetic retinopathy.

Ninety of the selfie images obtained by the patients themselves were of good quality and appropriately centred on the retina. disc macula and both the vascular arcades. Though there were some initial challenges, a good proportion of patients When compared with images captured using a standard fundus camera, SFI had a sensitivity of For the identification of DMO, the sensitivity of SFI was The quality of SFI was also highly comparable to the photographs taken by the trained specialist on the same device.

An important necessity with SFI using the currently available smartphone camera is the need for pupillary dilatation. This may bring to question the safety of having diabetic patients themselves dilate their pupils.

Other minor obstacles to SFI include severe senile ptosis, dermatochalasis, deeply set eyeball, senile tremor, cervical spondylosis, senile fatigue, frozen shoulder, and few others.

As anticipated, the presence of hazy media is an impediment to image capture with all cameras and so it is with SFI also. However, the inability to capture retinal images using SFI should be construed as the presence of significant cataract, posterior capsular opacification, corneal opacity, asteroid hyalosis or even vitreous haemorrhage and urgent ophthalmology consultation becomes inevitable.

The patient can then save the images and tele-consult with the ophthalmologist for further guidance. This approach would overcome barriers like poor access to healthcare, travel cost and distance, busy schedule, lack of caretaker etc. If individuals do not have access to smartphones, SFI may be made available at other public facilities like post offices, banks etc.

as it is not heavily dependent on costly infrastructure. When amalgamated with the burgeoning field of machine learning and AI, we are optimistic that SFI may have the potential to improve the success of diabetic retinopathy screening programmes of all countries. In addition, during situations like a highly contagious and dangerous pandemic, SFI may help to sustain timely screening efforts for diabetic retinopathy.

Some limitations of the study include the hospital-based recruitment of participants, limited sample size, evaluation with only one out of the several commercially available fundus cameras, need for initial tutoring of patients using a training video and necessity of pupillary dilatation.

Though the need for pupillary dilatation seems like a drawback, the benefits of successful screening would outweigh the associated low risk of elevated intraocular pressure [ 19 ].

To conclude, the present study highlights the feasibility of bringing SFI to the forefront of diabetic retinopathy screening. To the best of our knowledge, this is the first study undertaken with selfie fundus imaging to screen diabetic patients for retinopathy.

With greater penetrance, advances, and availability of mobile technology, including camera resolution and specific health-related apps, we believe that SFI would positively impact success of diabetic retinopathy screening programs, both in normal circumstances as well as situations like the ongoing COVID infection.

Fundus imaging by trained specialist was used for grading and screening for diabetic retinopathy. Selfie Fundus Imaging SFI , which is taking photo of the retina by the patient themselves can improve screening by overcoming the barrier of accessibility and affordability, more so in the era of pandemic.

Saeedi P, Petersohn I, Salpea P, Malanda B, Karuranga S, Unwin N, et al. Global and regional diabetes prevalence estimates for and projections for and Results from the International Diabetes Federation Diabetes Atlas, 9th edition.

Diabetes Res Clin Pract. Article Google Scholar. World Health Organization. Prevention of Blindness from Diabetes Mellitus: Report of WHO Consultation in Geneva, Switzerland; Scanlon PH. Update on screening for sight-threatening diabetic retinopathy.

Ophthalmic Res. Schoenfeld ER, Greene JM, Wu SY, Leske MC. Patterns of adherence to diabetes vision care guidelines: baseline findings from the Diabetic Retinopathy Awareness Program. Article CAS Google Scholar.

Squirrell DM, Talbot JF. Screening for diabetic retinopathy. J R Soc Med. Harding SP, Broadbent DM, Neoh C, White MC, Vora J. Sensitivity and specificity of photography and direct ophthalmoscopy in screening for sight threatening eye disease: the Liverpool Diabetic Eye Study.

Kalm H, Egertsen R, Blohmé G. Non-stereo fundus photography as a screening procedure for diabetic retinopathy among patients with type II diabetes. Acta Ophthalmologica. Garg S, Davis RM. Diabetic retinopathy screening update.

Clin Diabetes. Rajalakshmi R, Arulmalar S, Usha M, Prathiba V, Kareemuddin KS, Anjana RM, et al. Validation of smartphone based retinal photography for diabetic retinopathy screening.

PLoS ONE. Venkatesh P, Kumar S, Tandon N, Takkar B. Selfie fundus imaging: innovative approach to retinopathy screening. Nat Med J Ind. Wong TY, Lanzetta P, Bandello F, Eldem B, Navarro R, Lövestam-Adrian M. Current concepts and modalities for monitoring the fellow eye in neovascular age-related macular degeneration: an expert panel consensus.

International Council of Ophthalmology. Guidelines for diabetic eye care. International Council of Ophthalmology; Cheung N, Mitchell P, Wong TY.

Diabetic retinopathy. Wong TY, Sabanayagam C. Strategies to tackle the global burden of diabetic retinopathy: from epidemiology to artificial intelligence. Huang OS, Tay WT, Ong PG, Sabanayagam C, Cheng CY, Tan GS, et al. Prevalence and determinants of undiagnosed diabetic retinopathy and vision-threatening retinopathy in a multiethnic Asian cohort: the Singapore Epidemiology of Eye Diseases SEED study.

Br J Ophthalmol. Verma L, Elankumaran P, Prakash G, Venkatesh P, Tewari Hem K. Awareness of diabetic retinopathy among diabetics.

However, the latter tend to perform better compared to smartphone-based devices like the one reported in this study. Russo et al. The study reported substantial agreement between the methods, with sensitivity and specificity of 0.

Toy et al. In the same study, the authors recommended that it would be interesting to compare a smartphone-based device with a tabletop fundus camera, the gold standard for diagnosing DR. In the present study, we found a sensitivity of 0.

We attribute the lower values of sensitivity and specificity in the present study to the fact that the users of the smartphone-based fundus camera were not used to fundus photography, while in the previous studies smartphone-based ophthalmoscopy was performed by a retina specialist [ 8 , 9 ].

In their study, Williams et al. stated that there is level I evidence that single-field fundus photography with interpretation by trained readers can serve as a screening tool to identify patients with diabetic retinopathy for referral for ophthalmologic evaluation and treatment, but it is not a substitute for a comprehensive eye examination [ 11 ].

Ryan ME et al. reported that photographs from smartphones assisted by 20 diopters lenses had a low rate of unclassifiable images, and most of them had at least satisfactory quality. Kappa was 0. Our study, regarding the presence or absence of DR, showed a Kappa of 0.

The smartphone was less sensitive than non-mydriatic photography in detecting the presence of DR at any degree. However, the two methods were similar in detecting vision threatening stages of the disease.

Although both methods have shown robust specificity, smartphone-based teleophthalmology screening represents a much lower cost of implementation, and could be particularly useful as a tool that allows for detection of the disease in patients who may not have proper access to eye care [ 12 ].

Furthermore, considering that artificial intelligence AI systems are currently being developed and gradually implanted worldwide [ 13 , 14 ], it is plausible to assume that the portability of smartphone-generated images could, in a near future, act synergistically with the power of AI in order to amplify access to eye care.

In line with the other studies in literature Russo et al. and Toy et al. High cost and low availability of eye examination, especially when requiring in-site experts, represent an important limitation for DR screening. Fundus images taken through a smartphone-based method by undergraduate students, here adopted as surrogates for professionals with no previous experience in eye imaging, may favor early diagnosis and severity classification of DR.

Implementation of this method in primary healthcare settings such as the basic care units of Brazil's public health system could allow for broader detection and timely referral for intervention in a large population of underserved diabetic patients.

All data generated in this study, including the images obtained through both the analysed method and the gold standard, were saved on private cloud storage Google Drive ® for patient safety and privacy. We kindly request any interested parts to contact the authors directly for obtaining access to the database when applicable.

Klein R, Klein BEK. Epidemiology of eye disease in diabetes. In: Flynn HW Jr, Smiddy WE, editors. Diabetes and ocular Disease: past, present, and future therapies. Cham: The foundation of the American Academy of Ophthalmology; Google Scholar.

World Health Organization. Tool for the assessment of diabetic retinopathy and diabetes management systems. Genebra: WHO; Shi L, Wu H, Dong J, Jiang K, Lu X, Shi J. Telemedicine for detecting diabetic retinopathy: a systematic review and meta-analysis. Br J Ophthalmol. Article PubMed Google Scholar.

Early Treatment Diabetic Retinopathy Study Research Group. Grading diabetic retinopathy from stereoscopic color fundus photographs—an extension of the modified Airlie House classification. ETDRS report number Article Google Scholar. Sociedade Brasileira de Diabetes. Diretrizes da Sociedade Brasileira de Diabetes — São Paulo, SP: A.

Farmacêutica, Fong S, Aiello LP, Gardner TW, King GL, et al. Diabetic retinopathy. Diabetes Care. Hilgert GR, Trevizan E, de Souza JM. Uso de retinógrafo portátil como ferramenta no rastreamento de retinopatia diabética. Rev Bras Oftalmol. Russo A, Morescalchi F, Costagliola C, Delcassi L, Semeraro F.

Comparison of smartphone ophthalmoscopy with slit-lamp biomicroscopy for grading diabetic retinopathy. Am J Ophthalmol. e1 Epub Nov 7 PMID: Toy BC, Myung DJ, He L, et al.

Smartphone-based dilated fundus photography and near visual acuity testing as inexpensive screening tools to detect referral warranted diabetic eye disease.

Bolster NM, Giardini ME, Bastawrous A. The diabetic retinopathy screening workflow: potential for smartphone imaging. J Diabetes Sci Technol. Williams GA, Scott IU, Haller JA, Maguire AM, Marcus D, McDonald HR. Single-field fundus photography for diabetic retinopathy screening.

Ryan ME, Rajalakshmi R, Prathiba V, Anjana RM, Ranjani H, Narayan KMV, et al. Comparison among methods of retinopathy assessment CAMRA study. Abràmoff MD, Lavin PT, Birch M, et al. Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices.

NPJ Digit Med. Vedula SS, Tsou BC, Sikder S. Artificial intelligence in clinical practice is here—now what? JAMA Ophthalmol. Download references. We thank Dr. Igor F. Teodoro and Dr.

Carlos Augusto S. Borges for their contributions in the development of this study. Daniel Ferraz for the reviews. The project received financial support from FAEPA Foundation for the Support of Teaching, Research and Service of the University Hospital - FMRP-USP. Division of Ophthalmology, Ribeirão Preto Medical School, University of São Paulo, , Bandeirantes Ave, Ribeirão Preto, SP, , Brazil.

Jéssica Deponti Gobbi, João Pedro Romero Braga, Moises M. Lucena, Victor C. Department of Applied Mathematics and Statistics, University of São Paulo, São Carlos, Brazil. Department of Ophthalmology, National University Hospital, Singapore, Singapore.

You can also search for this author in PubMed Google Scholar. RJ was the primary contributor to research design.

JG, VB, JB and MM were responsible for research execution and data acquisition. RJ, DF, MF, and VK were the primary contributors to data analysis and interpretation. Manuscript was prepared by RJ, JB, VB, MM, JG, with critical revisions provided by RJ, DF and VK. Correspondence to Rodrigo Jorge.

Every volunteer received clear explanations about the involved procedures and filled in a declaration of informed consent prior to their participation. Sponsors had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution 4. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material.

If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. Reprints and permissions.

Gobbi, J. et al. Efficacy of smartphone-based retinal photography by undergraduate students in screening and early diagnosing diabetic retinopathy.

Int J Retin Vitr 8 , 35 Download citation. Received : 04 March Accepted : 23 May Published : 07 June Anyone you share the following link with will be able to read this content:.

Sorry, a shareable link is not currently available for this article. Provided by the Springer Nature SharedIt content-sharing initiative. Skip to main content. Search all BMC articles Search.

Download PDF. Original article Open access Published: 07 June Efficacy of smartphone-based retinal photography by undergraduate students in screening and early diagnosing diabetic retinopathy Jéssica Deponti Gobbi 1 , João Pedro Romero Braga 1 , Moises M.

Lucena 1 , Victor C. Bellanda 1 , Miguel V. Abstract Background To evaluate the efficacy of retinal photography obtained by undergraduate students using a smartphone-based device in screening and early diagnosing diabetic retinopathy DR.

Methods We carried out an open prospective study with ninety-nine diabetic patients eyes , who were submitted to an ophthalmological examination in which undergraduate students registered images of the fundus using a smartphone-based device.

Results Concerning the presence or absence of DR, we found an agreement rate of Conclusion The smartphone-based device showed promising accuracy in the detection of DR Background: Diabetic retinopathy DR is one of the most important complications of Diabetes Mellitus DM and its incidence is intrinsically related to the duration of the disease and level of glycemic control.

Materials and methods Patients and ethics We conducted a prospective, open study, collecting data from diabetic patients eyes at the diabetic retinopathy screening clinic of Hospital das Clínicas de Ribeirão Preto HC-FMRP-USP , a high complexity general hospital in Brazil.

Ophthalmological evaluation During their appointment for diabetic retinopathy evaluation, patients in the study underwent two types of assessments: one being standard seven field color stereoscopic photography of the fundus captured by an experienced nurse through a tabletop fundus camera Canon CR-2 Digital Non-Mydriatic Retinal Camera—demonstrated on Fig.

Our goal is not to disrupt your current process, but to supplement it with easy-to-use, simple technology that helps you improve patient outcomes and increase your quality compliance measures. Want to have a conversation around how IRIS can work with your workflow?

Get in touch with our team today to schedule a free demo. IRIS is designed to go live in as little as 90 days. To get started, schedule a free demo with the IRIS team today. Get more information about IRIS today.

Contact form 7 Mailchimp extension by Renzo Johnson - Web Developer. Eliminating Blindness, One Retinal Screening at a Time. SCHEDULE A DEMO.

The IRIS Solution Any healthcare organization can perform a retinal screening with IRIS. Platform Compatible, easy-to-use software that integrates with your workflow. LEARN MORE. Service Consistent communication to ensure your long-term success.

GET STARTED. Get started See how easy it is to close care gaps with IRIS. GET A DEMO. We go wherever your diabetic patients are. Federally Qualified HeaLth Centers. Saving eyesight has to be a priority.

IRIS makes it easy. Learn with IRIS Stay updated with our latest resources. Frequently Asked Questions Have questions? We've got the answers.

Healthcare is changing. Need help?