According to new research, a low-field-of-view, cost-effective smartphone-based fundus imaging (SBFI) system may be both effective and safe in telemedicine screening for treatment-seeking retinopathy of prematurity (ROP).1
Analysis of 2 different SBFI systems suggests that one approach is not superior, but both human graders and an autonomous artificial intelligence (AI)-based system were able to refer appropriate treatment requiring ROP using SBFI photos.
“These results suggest that SBFI or other lower field-of-view camera systems can be safely and effectively used for ROP telescreening in regions where widefield digital fundus imaging (WDFI) is not available- based ROP telemedicine or in-person ophthalmoscopic screening,” wrote the investigative team, led by J. Peter Campbell, MD, MPH, Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University.1
Limited screening capacity in low- and middle-income countries has contributed to the large disease burden of ROP. The use of telemedicine with remote marking of images captured by WDFI cameras can be an effective way to improve screening in these regions by expanding the geographic reach of limited specialists. However, a major obstacle to the implementation and subsequent scaling of telemedicine programs is the high cost required to provide regions with WDFI cameras.2
Lower-cost options, including either handheld cameras or SBFI systems, have been piloted, but provide a narrower field of view than WDFI cameras and have not been tested in a real-world, operational telemedicine. that setting. SBFI systems work by combining modern smartphone cameras with standard indirect ophthalmoscopy lenses to produce an affordable, portable, noncontact fundus imaging system. For the current analysis, investigators compared a WDFI device currently deployed in an operational telemedicine program (Retcam Shuttle) with 2 similar SBFI devices (Make-In-India (MII) Retcam adapter and head-mounted Keeler Monocular Indirect Ophthalmoscope (MIO) adapter) .
Comparing the clinical diagnosis obtained using the SBFI with the WDFI in a masked manner, the investigators evaluated the efficacy of the SBFI for the detection of referral-warranted (RW)-ROP and treatment-requiring (TR)-ROP, as well as the diagnostic accuracy of grader-assigned vascular severity scores. Evaluations of routine image-based ROP screening took place in a single-center ROP teleophthalmology program in India between January 2021 – April 2022.
Two mask readers were presented with patient demographic characteristics, including birth weight and gestational age, and identified ROP diagnoses, including zone, stage, plus, and presence of aggressive ROP, and VSS (from 1 – 9) for individual eyes. Investigators calculated the sensitivity and specificity of any ROP, RW-ROP, and TR-ROP for each SBFI device relative to WDFI using Pearson χ2 test. In addition, they calculated the area under the receiver operating characteristic curve for average grader-assigned VSS compared to RW-ROP and TR-ROP.
The data set included 312 eyes from 156 infants (mean gestational age, 33.0 weeks; 75 (48%) female) included for paired analysis. Analysis indicated that sensitivity and specificity were not found to be statistically different between the 2 SBFI systems, so the results were pooled. The investigators found that SBFI devices had only moderate sensitivity for the diagnosis of more than mild ROP (59%).
As a screening tool, however, using a cutoff of at least RW-ROP detected on the device, the sensitivity for detecting TR-ROP was 100% and the specificity was 83.49% among human graders. Moreover, the data showed that the AUCs with grader-assigned VSS were 0.95 (95% CI, 0.91 – 0.99) for RW-ROP and 0.96 (95% CI, 0.93 – 0.99) for TR-ROP.
The images were preprocessed and separated into training (70%), validation (10%), and test (20%) data sets. The algorithm then assigned a diagnosis of no plus, preplus, or plus to each image. After a median diagnosis cutoff of preplus or plus, the sensitivity of detection for TR-ROP was 100% with a specificity of 53.9% and the sensitivity for RW-ROP was 83.3%, with a specificity of 56.5%, for AI-based screening.
Based on these results, SBFI systems have similar performance to each other and could potentially be used in regions where ROP telemedicine or WDFI-based in-person screening is not available. Campbell and colleagues suggested that the main advantage of SBFI systems is a significantly lower cost, as the Retcam Shuttle costs about $125,000 while the MIO system costs about $1608 and the MII Retcam system will cost around $585.
“In other words, for the cost of a single Retcam Shuttle, approximately 75 to 200 of these systems could be deployed instead for telemedicine screening, potentially dramatically increasing screening coverage,” wrote the investigators.
- Young BK, Cole ED, Shah PK, et al. Efficacy of Smartphone-Based Telescreening for Retinopathy of Prematurity With and Without Artificial Intelligence in India. JAMA Ophthalmol. Published online May 11, 2023. doi:10.1001/jamaophthalmol.2023.1466
- Patil J, Patil L, Parachuri N, et al. Smartphone based ROP (S-ROP) screening-opportunities and challenges. eye. 2020;34(9):1512-1514. doi:10.1038/s41433-020-0913-1