Publisher

IJRETINAIJRETINA

Journal International Journal of RetinaInternational Journal of Retina Abstract

Background: Diabetic retinopathy (DR) is the most common microvascular complication of diabetes that can cause vision problems and blindness, posing a significant health risk and financial burden, increasing the need to effectively screen and manage diabetic eye disease. The current method of screening for diabetic eye disease relies on human experts to analyze the results. Alternatively, recent advancements in artificial intelligence (AI), especially deep learning (DL), and imaging using smartphones offer a promising solution for both patients and retinal ophthalmologists, potentially improving patient compliance and making telemedicine more efficient for DR screening.. . Purpose: To represent the accuracy of AI‑integrated process in smartphone-based DR screening and to compare the various study methods and settings used to achieve this accuracy.. . Method: Literature search on current DR screening programs was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyzes (PRISMA) framework on Google Scholar, Scopus, Web of Science, PubMed, Medline, and Embase with the most recent search updated on June 1st, 2024. Key information was extracted from the studies included: author names, journal, year of publication, country, sensitivity, specificity, positive and negative predictive values (if available), study methods, and settings.. . Result: The study identification process resulted in 9 selected studies. The performance metrics reported included intergrader/intramodality agreement, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The sensitivity of AI in detecting DR ranged from 77-100%, while specificity ranged from 61.4 - 95.5%. PPV and NPV were reported less frequently, with ranges of 48.1 - 92.92% and 91.3 - 99.46%, respectively. Intergrader agreement was within range ĸ= 0.45 – 0.91.. . Conclusion: The studies reviewed in this paper collectively represent the potential of smartphone-based integrated with AI in revolutionizing DR screening. The high sensitivity and specificity achieved by various AI algorithms, often exceeding the standards set by regulatory bodies like the FDA and ETDRS, highlight their accuracy in detecting DR and its severity levels. The accessibility and user-friendliness of smartphone-based retinal imaging further enhance the coverage of DR screening, particularly in underserved areas with limited resources and internet connectivity.

Conclusion

The studies reviewed demonstrate the potential of smartphone-based AI integration in transforming DR screening.The high sensitivity and specificity of AI algorithms, often surpassing regulatory standards, confirm their accuracy in detecting DR and its severity.Furthermore, the accessibility and ease of use of smartphone-based retinal imaging can significantly improve DR screening coverage, especially in resource-limited settings.

Future Research

Penelitian lebih lanjut perlu dilakukan untuk mengevaluasi efektivitas intervensi berbasis AI dalam mengurangi angka kebutaan akibat retinopati diabetik di berbagai populasi dan pengaturan klinis. Studi prospektif yang melibatkan jumlah peserta yang besar dan beragam secara demografis sangat penting untuk mengkonfirmasi temuan ini dan mengidentifikasi potensi bias. Selain itu, penelitian harus fokus pada pengembangan algoritma AI yang lebih akurat dan efisien, serta integrasi yang mulus dengan sistem perawatan kesehatan yang ada. Pengembangan aplikasi smartphone yang mudah digunakan dan terjangkau, yang dapat digunakan oleh tenaga kesehatan non-spesialis, juga merupakan area penelitian yang menjanjikan. Terakhir, penelitian perlu mengeksplorasi penggunaan AI untuk memprediksi risiko perkembangan retinopati diabetik pada individu dengan diabetes, memungkinkan intervensi dini dan pencegahan kehilangan penglihatan.

References

1. Evaluating the accuracy of Artificial Intelligence (AI)-integrated, Smartphone-based screening for Diabetic... doi.org/10.35479/ijretina.2025.vol008.iss001.294Evaluating the accuracy of Artificial Intelligence AI integrated Smartphone based screening for Diabetic doi 10 35479 ijretina 2025 vol008 iss001 294

Metadata

File size	675.37 KB
Pages	16
DMCA	Report