Results of Implementation of the DigiScope for Diabetic Retinopathy Assessment in the Primary Care Environment

A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of "good", "borderline", or "poor" quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance "good" quality photographs (AUC = 0.93 (95% CI, 0.91-0.95), accuracy = 91.4% (95% CI, 90.0-92.9%), sensitivity = 93.8% (95% CI, 92.5-95.2%), specificity = 75.9% (95% CI, 69.7-82.1%) and "poor" quality photographs (AUC = 1.00 (95% CI, 0.99-1.00), accuracy = 99.1% (95% CI, 98.6-99.6%), sensitivity = 81.5% (95% CI, 70.6-93.8%), specificity = 99.7% (95% CI, 99.6-100.0%). "Borderline" quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88-0.93), accuracy = 90.6% (95% CI, 89.1-92.2%), sensitivity = 65.4% (95% CI, 56.6-72.9%), specificity = 93.4% (95% CI, 92.1-94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1-92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH.

Comparison of Telemedicine Screening of Diabetic Retinopathy by Mydriatic Smartphone-Based vs Nonmydriatic Tabletop Camera-Based Fundus Imaging

PURPOSE

To compare dilated smartphone-based imaging with a nonmydriatic, tabletop fundus camera as a teleophthalmology screening tool for diabetic retinopathy (DR).

METHODS

This was a single-institutional, cross-sectional, comparative-instrument study. Fifty-six patients at a safety-net hospital underwent teleophthalmology screening for DR using standard, nonmydriatic fundus photography with a tabletop camera (Nidek NM-1000) and dilated fundus photography using a smartphone camera with lens adapter (Paxos Scope, Verana Health). Masked graders performed standardized photo grading. Quantitative comparisons were performed employing descriptive, κ, Bland-Altman, and receiver operating characteristic analyses.

RESULTS

Posterior segment photography was of sufficient quality to grade in 89% of mydriatic smartphone-imaged eyes and in 86% of nonmydriatic tabletop camera-imaged eyes (P = .03). Using the tabletop camera as the reference to detect moderate nonproliferative DR or worse (referral-warranted DR), mydriatic smartphone-acquired photographs were found to be 82% sensitive and 96% specific. Dilated smartphone imaging detected referral-warranted DR in 3 eyes whose tabletop camera imaging did not demonstrate referral-warranted DR. Secondary masked review of medical records for the discordances in referral-warranted status from the two imaging modalities was performed, and it revealed revised sensitivity and specificity values of 95% and 98%, respectively. Overall, there was good agreement between tabletop camera and smartphone-acquired photo grades (κ = 0.91 ± 0.1, P < .001; area under the receiver operating characteristic curve = 0.99, 95% CI, 0.98-1.00).

CONCLUSIONS

Mydriatic smartphone-based imaging resulted in fewer ungradable photos compared to nonmydriatic table-top camera imaging and detected more patients with referral-warranted DR. Our study supports the use of mydriatic smartphone teleophthalmology as an alternative method to screen for DR.

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

As a third of people with diabetes mellitus (DM) will suffer the microvascular complications of diabetic retinopathy (DR) and therapeutic options can effectively prevent visual impairment, systematic screening has substantially reduced disease burden in developed countries. In an effort to tackle the rising incidence of DM, screening programmes have modernized in synchrony with technical and infrastructural advancements. Patient evaluation has shifted from face-to-face ophthalmologist-based review delivered through community grassroots to asynchronous store-and-forward modern telemedicine platforms commissioned on a nationwide scale. First pioneered with primitive 35-mm slide film retinal photography, the last decade has seen an emergence of high resolution and widefield imaging devices, which may reveal extents of DR indiscernible to the clinician but with implications of potential earlier identification. Similar progress has been seen in image analysis approaches - automated image analysis of retinal photographs of DR has evolved from qualitative feature detection to rules-based algorithms to autonomous artificial intelligence-powered classification. Such models have, relatively rapidly, been validated and are now receiving approval from health regulation authorities with deployment into the clinical sphere. In this review, we chart the evolution of global DR screening programmes since their inception highlighting major milestones in healthcare infrastructure, telemedicine approaches and imaging devices that have shaped the robust and effective frameworks recognised today. We also provide an outlook for the future of DR screening in the context of recent technological advancements with respect to their limitations in current times.

Philadelphia Telemedicine Glaucoma Detection and Follow-up Study: Analysis of Unreadable Fundus Images

PURPOSE

The purpose of this study was to ascertain determinants of unreadable fundus images for participants enrolled in the Philadelphia Telemedicine Glaucoma Detection and Follow-up Study.

METHODS

Individuals were screened for glaucoma at 7 primary care practices and 4 Federally Qualified Health Centers using telemedicine. Screening (visit 1) included fundus photography, assessing family history of glaucoma, and intraocular pressure (IOP) measurements. Participants with an unreadable image in at least one eye were deemed unreadable and invited to return for a confirmatory eye examination (visit 2).

RESULTS

A total of 906 participants completed the visit 1 eye screening and 17.1% (n=155/906) were "unreadable." In the multivariable logistic regression analysis, older age, male sex, smoking, and worse visual acuity were significantly associated with an unreadable fundus image finding at the eye screening (P<0.05). Of the 89 participants who were invited for the confirmatory eye examination solely for unreadable images and attended visit 2, 58 (65.2%) were diagnosed with at least one ocular pathology. The most frequent diagnoses were cataracts (n=71; 15 visually significant, 56 nonvisually significant), glaucoma suspects (n=27), and anatomical narrow angle (n=10).

CONCLUSIONS

Understanding the causes of unreadable fundus images will foster improvements in telemedicine techniques to optimize the predictive accuracy, efficiency, and cost in ophthalmology. A high proportion of participants with unreadable images (65.2%) in our study were diagnosed with some ocular pathology, indicating that the finding of an unreadable fundus image warrants a referral for a comprehensive follow-up eye examination.

Usability testing of a smartphone-based retinal camera among first-time users in the primary care setting

Smartphone-based retinal photography is a promising method for increasing accessibility of retinal screening in the primary care and community settings. Recent work has focused on validating its use in detection of diabetic retinopathy. However, retinal imaging can be technically challenging and additional work is needed to improve ease of retinal imaging in the primary care setting. We therefore performed usability testing of a smartphone-based retinal camera, RetinaScope, among medical assistants in primary care who had never performed retinal imaging. A total of 24 medical assistants performed first-time imaging in a total of five rounds of testing, and iterative improvements to the device were made between test rounds based on the results. The time to acquire a single ~50 degree image of the posterior pole of a model eye decreased from 283 ± 60 seconds to 34 ± 17 seconds (p < 0.01) for first-time users. The time to acquire 5 overlapping images of the retina decreased from 325 ± 60 seconds to 118 ± 26 seconds (p = 0.02) for first-time users. Testing in the human eye demonstrated that a single wide-view retinal image could be captured in 65 ± 7 seconds and 5 overlapping images in 229 ± 114 seconds. Users reported high Systems Usability Scores of 86 ± 13 throughout the rounds, reflecting a high level of comfort in first-time operation of the device. Our study demonstrates that smartphone-based retinal photography has the potential to be quickly adopted among medical assistants in the primary care setting.

A CNN-BASED RETINAL IMAGE QUALITY ASSESSMENT SYSTEM FOR TELEOPHTHALMOLOGY

Oculopathy is a widespread disease among people of all ages around the world. Teleophthalmology can facilitate the ophthalmological diagnosis for less developed countries that lack medical resources. In teleophthalmology, the assessment of retinal image quality is of great importance. In this paper, we propose a no-reference retinal image assessment system based on DenseNet, a convolutional neural network architecture. This system classified fundus images into good and bad quality or five categories: adequate, just noticeable blur, inappropriate illumination, incomplete optic disc, and opacity. The proposed system was evaluated on different datasets and compared to the applications based on other two networks: VGG-16 and GoogLenet. For binary classification, the good-and-bad binary classifier achieves an AUC of 1.000, and the degradation-specified classifiers that distinguish one specified degradation versus the rest achieve AUC values of 0.972, 0.990, 0.982, 0.982 for four categories, respectively. The multi-classification based on DenseNet achieves an overall accuracy of 0.927, which is significantly higher than 0.549 and 0.757 obtained using VGG-16 and GoogLeNet, respectively. The experimental results indicate that the proposed approach produces outstanding performance in retinal image quality assessment and is worth applying in ophthalmological telemedicine applications. In addition, the proposed approach is robust to the image noise. This study fills the gap of multi-classification in retinal image quality assessment.

Combination of Global Features for the Automatic Quality Assessment of Retinal Images

Diabetic retinopathy (DR) is one of the most common causes of visual loss in developed countries. Computer-aided diagnosis systems aimed at detecting DR can reduce the workload of ophthalmologists in screening programs. Nevertheless, a large number of retinal images cannot be analyzed by physicians and automatic methods due to poor quality. Automatic retinal image quality assessment (RIQA) is needed before image analysis. The purpose of this study was to combine novel generic quality features to develop a RIQA method. Several features were calculated from retinal images to achieve this goal. Features derived from the spatial and spectral entropy-based quality (SSEQ) and the natural images quality evaluator (NIQE) methods were extracted. They were combined with novel sharpness and luminosity measures based on the continuous wavelet transform (CWT) and the hue saturation value (HSV) color model, respectively. A subset of non-redundant features was selected using the fast correlation-based filter (FCBF) method. Subsequently, a multilayer perceptron (MLP) neural network was used to obtain the quality of images from the selected features. Classification results achieved 91.46% accuracy, 92.04% sensitivity, and 87.92% specificity. Results suggest that the proposed RIQA method could be applied in a more general computer-aided diagnosis system aimed at detecting a variety of retinal pathologies such as DR and age-related macular degeneration.

Advances in Retinal Imaging and Applications in Diabetic Retinopathy Screening: A Review

Rising prevalence of diabetes worldwide has necessitated the implementation of population-based diabetic retinopathy (DR) screening programs that can perform retinal imaging and interpretation for extremely large patient cohorts in a rapid and sensitive manner while minimizing inappropriate referrals to retina specialists. While most current screening programs employ mydriatic or nonmydriatic color fundus photography and trained image graders to identify referable DR, new imaging modalities offer significant improvements in diagnostic accuracy, throughput, and affordability. Smartphone-based fundus photography, macular optical coherence tomography, ultrawide-field imaging, and artificial intelligence-based image reading address limitations of current approaches and will likely become necessary as DR becomes more prevalent. Here we review current trends in imaging for DR screening and emerging technologies that show potential for improving upon current screening approaches.

Patient-oriented mobile applications in ophthalmology

BACKGROUND

Mobile solutions will improve patient care only if they are equally valued by physicians and their patients. Although mobile applications are gaining acceptance among ophthalmologists and optometrists, little is known about their adoption among patients. Therefore, this study was designed to analyse the market for patient-oriented mobile applications in ophthalmology.

METHODS

Search engines of Google Play and App Store were utilised to find patient-oriented mobile applications. All applications were divided into seven subspecialties; dry eye, strabismus and amblyopia, macular degeneration, cataract, glaucoma, diabetic retinopathy and general ophthalmology. Subsequently, number of downloads, average patient rating, year of release and source of clinical information provided in the application were collected. Furthermore, in order to evaluate whether development of software responds to epidemiological demand, number of applications in each subspecialty was correlated with the prevalence of particular diseases.

RESULTS

Fifty-six applications that met established criteria were found. The overall number of downloads was estimated at the level of 1.5 million, whereas the weighted average rating for all applications was 4.21/5. The number of applications by subspecialty did not correlate with the prevalence of particular eye disorder. The dry eye was the most frequently downloaded and best rated subspecialty.

CONCLUSIONS

The overall number of patient-oriented applications in ophthalmology is low. Subspecialties are not equally equipped with patient-oriented mobile solutions. Furthermore, the number of applications or downloads in each subspecialty does not correlate with the number of potential users such as patients with particular eye disorders. Finally, ophthalmologists should encourage software developers to meet future demand for mobile solutions in eye disorders.

Retinal Telemedicine

PURPOSE OF REVIEW

An update and overview of the literature on current telemedicine applications in retina.

RECENT FINDINGS

The application of telemedicine to the field of Ophthalmology and Retina has been growing with advancing technologies in ophthalmic imaging. Retinal telemedicine has been most commonly applied to diabetic retinopathy and retinopathy of prematurity in adult and pediatric patients respectively. Telemedicine has the potential to alleviate the growing demand for clinical evaluation of retinal diseases. Subsequently, automated image analysis and deep learning systems may facilitate efficient processing of large, increasing numbers of images generated in telemedicine systems. Telemedicine may additionally improve access to education and standardized training through tele-education systems.

SUMMARY

Telemedicine has the potential to be utilized as a useful adjunct but not a complete replacement for physical clinical examinations. Retinal telemedicine programs should be carefully and appropriately integrated into current clinical systems.

Telemedicine and Diabetic Retinopathy: Review of Published Screening Programs

BACKGROUND

Diabetic Retinopathy (DR) is a leading cause of blindness worldwide even though successful treatments exist. Improving screening and treatment could avoid many cases of vision loss. However, due to an increasing prevalence of diabetes, traditional in-person screening for DR for every diabetic patient is not feasible. Telemedicine is one viable solution to provide high-quality and efficient screening to large number of diabetic patients.

PURPOSE

To provide a narrative review of large DR telemedicine screening programs.

METHODS

Articles were identified through a comprehensive search of the English-language literature published between 2000 and 2014. Telemedicine screening programs were included for review if they had published data on at least 150 patients and had available validation studies supporting their model. Screening programs were then categorized according to their American Telemedicine Association Validation Level.

RESULTS

Seven programs from the US and abroad were identified and included in the review. Three programs were Category 1 programs (Ophdiat, EyePacs, and Digiscope), two were Category 2 programs (Eye Check, NHS Diabetic Eye Screening Program), and two were Category 3 programs (Joslin Vision Network, Alberta Screening Program). No program was identified that claimed category 4 status. Programs ranged from community or city level programs to large nationwide programs including millions of individuals. The programs demonstrated a high level of clinical accuracy in screening for DR. There was no consensus amongst the programs regarding the need for dilation, need for stereoscopic images, or the level of training for approved image graders.

CONCLUSION

Telemedicine programs have been clinically validated and successfully implemented across the globe. They can provide a high-level of clinical accuracy for screening for DR while improving patient access in a cost-effective and scalable manner.

Tele-ophthalmology screening for proliferative diabetic retinopathy in urban primary care offices: an economic analysis

BACKGROUND AND OBJECTIVE

To determine whether tele-ophthalmology screening for proliferative diabetic retinopathy (PDR) can be cost-saving.

PATIENTS AND METHODS

Adults with diabetes presenting for routine medical care underwent non-mydriatic fundus photography with remote grading. Direct medical costs were estimated using the Medicare fee schedule in the base case, with Medicaid and commercial insurance rates used for low and high values, respectively. One-way and probabilistic sensitivity analyses were performed.

RESULTS

Of 99 participants, at least mild retinopathy was found in 24 (24.2%). Urgent consultation was recommended for eight participants (8.1%) for possible vision-threatening diabetic retinopathy, including two participants (three eyes) with PDR. In the base case, screening saved $36 per patient. A Monte Carlo simulation indicated that screening saved a median of $48 per patient.

CONCLUSION

A substantial burden of diabetic retinopathy was identified, most of which was undiagnosed. In a closed system, tele-ophthalmology screening for PDR is likely to be cost-saving across the range of scenarios explored.

Fully automated diabetic retinopathy screening using morphological component analysis

Diabetic retinopathy is the major cause of blindness in the world. It has been shown that early diagnosis can play a major role in prevention of visual loss and blindness. This diagnosis can be made through regular screening and timely treatment. Besides, automation of this process can significantly reduce the work of ophthalmologists and alleviate inter and intra observer variability. This paper provides a fully automated diabetic retinopathy screening system with the ability of retinal image quality assessment. The novelty of the proposed method lies in the use of Morphological Component Analysis (MCA) algorithm to discriminate between normal and pathological retinal structures. To this end, first a pre-screening algorithm is used to assess the quality of retinal images. If the quality of the image is not satisfactory, it is examined by an ophthalmologist and must be recaptured if necessary. Otherwise, the image is processed for diabetic retinopathy detection. In this stage, normal and pathological structures of the retinal image are separated by MCA algorithm. Finally, the normal and abnormal retinal images are distinguished by statistical features of the retinal lesions. Our proposed system achieved 92.01% sensitivity and 95.45% specificity on the Messidor dataset which is a remarkable result in comparison with previous work.

Diabetes eye screening in urban settings serving minority populations: detection of diabetic retinopathy and other ocular findings using telemedicine

IMPORTANCE

The use of a nonmydriatic camera for retinal imaging combined with the remote evaluation of images at a telemedicine reading center has been advanced as a strategy for diabetic retinopathy (DR) screening, particularly among patients with diabetes mellitus from ethnic/racial minority populations with low utilization of eye care.

OBJECTIVE

To examine the rate and types of DR identified through a telemedicine screening program using a nonmydriatic camera, as well as the rate of other ocular findings.

DESIGN, SETTING, AND PARTICIPANTS

A cross-sectional study (Innovative Network for Sight [INSIGHT]) was conducted at 4 urban clinic or pharmacy settings in the United States serving predominantly ethnic/racial minority and uninsured persons with diabetes. Participants included persons aged 18 years or older who had type 1 or 2 diabetes mellitus and presented to the community-based settings.

MAIN OUTCOMES AND MEASURES

The percentage of DR detection, including type of DR, and the percentage of detection of other ocular findings.

RESULTS

A total of 1894 persons participated in the INSIGHT screening program across sites, with 21.7% having DR in at least 1 eye. The most common type of DR was background DR, which was present in 94.1% of all participants with DR. Almost half (44.2%) of the sample screened had ocular findings other than DR; 30.7% of the other ocular findings were cataract.

CONCLUSIONS AND RELEVANCE

In a DR telemedicine screening program in urban clinic or pharmacy settings in the United States serving predominantly ethnic/racial minority populations, DR was identified on screening in approximately 1 in 5 persons with diabetes. The vast majority of DR was background, indicating high public health potential for intervention in the earliest phases of DR when treatment can prevent vision loss. Other ocular conditions were detected at a high rate, a collateral benefit of DR screening programs that may be underappreciated.

Telemedicine for evaluation of retinopathy of prematurity

Retinopathy of prematurity (ROP) remains a significant threat to vision for extremely premature infants despite the availability of therapeutic modalities capable, in most cases, of managing this disorder. It has been shown in many controlled trials that application of therapies at the appropriate time is essential to successful outcomes in premature infants affected by ROP. Bedside binocular indirect ophthalmoscopy has been the standard technique for diagnosis and monitoring of ROP in these patients. However, implementation of routine use of this screening method for at-risk premature infants has presented challenges within our existing care systems, including relative local scarcity of qualified ophthalmologist examiners in some locations and the remote location of some NICUs. Modern technology, including the development of wide-angle ocular digital fundus photography, coupled with the ability to send digital images electronically to remote locations, has led to the development of telemedicine-based remote digital fundus imaging (RDFI-TM) evaluation techniques. These techniques have the potential to allow the diagnosis and monitoring of ROP to occur in lieu of the necessity for some repeated on-site examinations in NICUs. This report reviews the currently available literature on RDFI-TM evaluations for ROP and outlines pertinent practical and risk management considerations that should be used when including RDFI-TM in any new or existing ROP care structure.

Telemedicine and ocular health in diabetes mellitus

Teleretinal/teleophthalmological programs that use existing health information technology infrastructure solutions for people with diabetes increase access to and adherence to appropriate eye care. Teleophthalmological studies indicate that the single act of patients viewing their own retinal images improves self-management behaviour and clinical outcomes. In some settings this can be done at lower cost and with improved visual outcomes compared with standard eye care. Cost-effective and sustainable teleretinal surveillance for detection of diabetic retinopathy requires a combination of an inexpensive portable device for taking low light-level retinal images without the use of pharmacological dilation of the pupil and a computer-assisted methodology for rapidly detecting and diagnosing diabetic retinopathy. A more holistic telehealth-care paradigm augmented with the use of health information technology, medical devices, mobile phone and mobile health applications and software applications to improve health-care co-ordination, self-care management and education can significantly impact a broad range of health outcomes, including prevention of diabetes-associated visual loss. This approach will require a collaborative, transformational, patient-centred health-care program that integrates data from medical record systems with remote monitoring of data and a longitudinal health record. This includes data associated with social media applications and personal mobile health technology and should support continuous interactions between the patient, health-care team and the patient's social environment. Taken together, this system will deliver contextually and temporally relevant decision support to patients to facilitate their well-being and to reduce the risk of diabetic complications.

Accuracy and reliability of telemedicine for diagnosis of cytomegalovirus retinitis

PURPOSE

To determine the feasibility of remote diagnostic screening for cytomegalovirus (CMV) retinitis among HIV patients in northern Thailand.

DESIGN

Prospective, observational cross-sectional study.

METHODS

One hundred eighty-two eyes from 94 consecutive patients with HIV seen in 2008 and 2009 at a tertiary university-based medical center were photographed using a digital retinal camera. Individual and composite images were uploaded to a secure web site. Three expert graders accessed the electronic images and graded each image for signs of CMV retinitis. Results of remote expert grading were compared with on-site patient examination by local expert ophthalmologists.

RESULTS

On-site ophthalmologists diagnosed CMV retinitis in 89 (48.9%) of 182 eyes. Trained ophthalmic photographers obtained digital retinal images for all 182 eyes. As compared with the on-site examinations, the sensitivity for detecting CMV retinitis by remote readers using composite retinal images ranged from 89% to 91%. The specificity for detecting CMV retinitis by remote readers ranged from 85% to 88%. Intrarater reliability was high, with each grader achieving a κ value of 0.93. Interrater reliability among the 3 graders also was high, with a κ value of 0.86.

CONCLUSIONS

Remote diagnostic screening for CMV retinitis among HIV-positive patients may prove to be a valuable tool in countries where the burden of HIV exceeds the capacity of the local eye care providers to screen for ocular opportunistic infections.

Implementation and first-year screening results of an ocular telehealth system for diabetic retinopathy in China

BACKGROUND

To describe implementation and first-year screening results of the first Chinese telehealth system for diabetic retinopathy (DR) - the Beixinjing Community Diabetic Retinopathy Telehealth system (BCDRT).

METHODS

BCDRT implementation was based on the acquisition of adequate digital retinographs, secure digital transmission, storage and retrieval of participants' data and reader-generated medical reports. Local diabetic residents meeting inclusion criteria were enrolled into the BCDRT system beginning in 2009. Participants recommended for further in-person examination with ophthalmologists were followed, and the consistencies in diagnoses between BCDRT and ophthalmologists for DR or macular edema were calculated.

RESULTS

A total of 471 diabetic residents participated in BCDRT screening in 2009. The proportions of total DR, proliferative DR, and diabetic macular edema were 24.42% (115 patients), 2.12% (10 patients) and 6.47% (24 patients), respectively: 56 patients consulted ophthalmologists for further in-person retinal examination with funduscopy after pupil dilation. High rates of consistency between BCDRT screening and ophthalmologists were observed for macular edema (Kappa = 0.81), moderate or severe non-proliferative DR grade (Kappa = 0.92), and other DR grades (Kappa = 1). A total of 456 (96.82%) patients were willing to participate in the next BCDRT screening.

CONCLUSIONS

BCDRT was a reliable and valid system for DR screening, and offers the potential to increase DR annual screening rates in local residents.

Ocular telehealth initiatives in diabetic retinopathy

Diabetic retinopathy (DR) is a common complication of diabetes mellitus and a leading cause of new-onset vision loss in adults worldwide. Current medical and surgical evidence-based care, including laser photocoagulation, is effective in preserving vision. This care is most effective prior to the onset of ocular or visual symptoms, but many diabetic persons do not receive the recommended annual eye examination for the evaluation of the retina for level of DR. With diabetes incidence and prevalence increasing at epidemic rates and the prediction that 370 million people worldwide will have diabetes by the year 2030, human and fiscal resources will be unable to meet the visual needs with current acute care methods. Appropriate and validated telemedicine programs for DR hold the promise of both enrolling patients into appropriate eye care programs and, more importantly, providing more effective, high-quality diabetes eye care based on current and developing technology.

The INCA system: a further step towards a telemedical artificial pancreas

Biomedical engineering research efforts have accomplished another level of a "technological solution" for diabetes: an artificial pancreas to be used by patients and supervised by healthcare professionals at any time and place. Reliability of continuous glucose monitoring, availability of real-time programmable insulin pumps, and validation of safe and efficient control algorithms are critical components for achieving that goal. Nevertheless, the development and integration of these new technologies within a telemedicine system can be the basis of a future artificial pancreas. This paper introduces the concept, design, and evaluation of the "intelligent control assistant for diabetes, INCA" system. INCA is a personal digital assistant (PDA)-based personal smart assistant to provide patients with closed-loop control strategies (personal and remote loop), based on a real-time continuous glucose sensor (Guardian RT, Medtronic), an insulin pump (D-TRON, Disetronic Medical Systems), and a mobile general packet radio service (GPRS)-based telemedicine communication system. Patient therapeutic decision making is supervised by doctors through a multiaccess telemedicine central server that provides to diabetics and doctors a Web-based access to continuous glucose monitoring and insulin infusion data. The INCA system has been technically and clinically evaluated in two randomized and crossover clinical trials showing an improvement on glycaemic control of diabetic patients.

OPHDIAT: a telemedical network screening system for diabetic retinopathy in the Ile-de-France

OBJECTIVE

International and national guidelines recommend an annual funduscopic examination for all diabetic patients, but such annual fundus examinations are not sufficiently performed in France. Non-mydriatic fundus photography is a valid method of evaluation for diabetic retinopathy (DR) and a viable alternative to ophthalmoscopy. After two pilot studies demonstrated the feasibility of telemedical screening for diabetic retinopathy in both hospital and primary-care settings, we developed a regional telemedical network, OPHDIAT, designed to facilitate access to regular annual evaluations of patients with diabetes while saving medical time.

MATERIALS AND METHODS

OPHDIAT comprises peripheral screening centres equipped with non-mydriatic cameras, where fundus photographs are taken by technicians linked by telemedicine to a reference centre, where ophthalmologists grade the images. Currently in the Ile-de-France region, 16 screening centres are linked through a central server to an ophthalmologic reading centre and includes 11 centres located in the diabetes departments of 11 hospitals, one diabetic retinopathy screening centre located in northern Paris, three in healthcare centres and one in a prison.

RESULTS

During the 28-month evaluation period, 15,307 DR screening examinations were performed. Retinal photographs of at least one eye could not be graded in 1332 patients (9.7%) and diabetic retinopathy was detected in 3350 patients (23.4%). After the screening examination, 3478 patients (25.2%) were referred to an ophthalmologist for either DR, cataract and/or non-gradable photographs.

CONCLUSION

Fundus photography combined with telemedicine has the potential to improve the regular annual evaluation for diabetic retinopathy. The organization of the network around a central reading centre serves to guarantee quality control.