Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 35 min ago
Peer-reviewedCC BY-NC 4.0Ophthalmic Research

Diagnostic Performance of Deep Learning Using Retinal Images for Detection of Chronic Kidney Disease: A Systematic Review and Meta-Analysis

  • Mehrdad Farrokhi1,2
  • Behnam Hoorshad2
  • Reza Fahimi3
  • Atousa Moghadam Fard2
  • Behnaz Dalvandi2
  • Reza Dalvandi2
  • Mahshid Esmaielzade Rostami2
  • Reza Judi Chelan4
  • Oveis Ahmadzadeh2
  • Sareh Salarinejad5
  • Ramtin Shemshadigolafzani6
  • Morteza Alipour2
3 more authors
  • Parham Rahmani2
  • Marjan Lashgari7
  • Mahya Asadalizadeh8
8 affiliations
  1. 1Department of Epidemiology, School of Public Health and Safety, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  2. 2ERIS Research Institute, Tehran, Iran
  3. 3Warwick Medical School, University of Warwick, Coventry, UK
  4. 4School of Medicine, Yasuj University of Medical Sciences, Yasuj, Iran
  5. 5Blood Transfusion Research Center, High Institute for Research and Education in Transfusion Medicine, Tehran, Iran
  6. 6Capital Medical University, Beijing, China
  7. 7Department of Anesthesiology, School of Medicine, Hamadan University of Medical Sciences, Hamadan, Iran
  8. 8Department of Biomedical Engineering, College of Engineering, University of Illinois at Chicago, Chicago, IL, USA
Read full textDOICite

Abstract

Introduction: Multiple investigations have been conducted to diagnose chronic kidney disease (CKD) from photographs of retina using deep learning models, with a wide range of diagnostic performance, which necessitates the importance of a comprehensive review. Therefore, in this meta-analysis, we estimated the detection performance of deep learning models for the diagnosis of CKD using retinal photographs.

Methods: MEDLINE, Scopus, and Web of Science were searched until 25 December 2025. Pooled estimation of heterogeneity, diagnostic parameters, and meta-regressions was performed using MetaDisc and STATA Software packages.

Results: The pooled sensitivity, specificity, and diagnostic odds ratio were 0.81 (95% CI, 0.80–0.82), 0.64 (95% CI, 0.64–0.65), and 9.15 (95% CI, 5.72–14.62), respectively. The pooled estimates of the positive and negative likelihood ratios were 2.18 (95% CI, 1.66–2.87) and 0.28 (95% CI, 0.20–0.39), respectively. The area under the summary receiver operating characteristic curve showed a discriminative performance of 0.77.

Conclusion: Deep learning based on retinal images had moderate diagnostic performance for detection of CKD. Relatively high sensitivity and modest specificity suggest that deep learning is more effective for ruling out CKD than for confirming the diagnosis that deep learning is more effective for ruling out CKD than for confirming the diagnosis. Deep learning-based retinal analysis may therefore serve as a supportive, noninvasive screening or triage tool but should not replace established diagnostic methods for CKD.

Related

  1. From underdiagnosis to scalable screening: Applications of artificial intelligence for vertebral compression fracture detection – a systematic review and meta-analysis of diagnostic performance
    Hsuan-Yu Chen, Linjun Yang, Gwen Wilson +4
    Osteoporosis and sarcopeniaPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
  2. Diagnostic performance of deep learning models using ultrasound for preoperative axillary nodal status in breast cancer: a systematic review and meta-analysis
    Tianxin Liu, Xiaowu Yuan, Jinli Wang +8
    Frontiers in OncologyPeer-reviewedCC BY 4.0Full textOncologyCrossrefDOAJ
  3. Detection and Risk Prediction of Diabetes Related Kidney Disease Using Retinal Images: A Systematic Review and Meta-Analysis.
    Samuel Ato Gyasi Otabir, Teketo Kassaw Tegegne, Paul Nderitu +6
    Journal of diabetesPeer-reviewedCC BYFull textMedical imaging & radiologyEurope PMC
  4. Deep Learning Optimizes the Diagnostic Performance of Coronary Computed Tomography Angiography in Heavily Calcified Coronary Plaques: A Chinese Multicenter Study
    Chunyan Shi, Chengjin Yu, Bin Zhang +10
    Reviews in cardiovascular medicinePeer-reviewedCC BYFull textCardiovascular medicineEurope PMC
  5. Diagnostic Performance of a Deep Learning Model Using Phonocardiogram and Single‐Lead ECG Signals for Detecting Moderate‐or‐Greater Aortic Stenosis: Multicenter External Validation
    Shumpei Saito, Masanobu Ishii, Shimpei Ogawa +21
    Clinical cardiologyPeer-reviewedCC BYFull textCardiovascular medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{farrokhi2026diagnostic,
  title = {{Diagnostic Performance of Deep Learning Using Retinal Images for Detection of Chronic Kidney Disease: A Systematic Review and Meta-Analysis}},
  author = {Mehrdad Farrokhi and Behnam Hoorshad and Reza Fahimi and Atousa Moghadam Fard and Behnaz Dalvandi and Reza Dalvandi and Mahshid Esmaielzade Rostami and Reza Judi Chelan and Oveis Ahmadzadeh and Sareh Salarinejad and Ramtin Shemshadigolafzani and Morteza Alipour and Parham Rahmani and Marjan Lashgari and Mahya Asadalizadeh},
  journal = {Ophthalmic Research},
  year = {2026},
  month = aug,
  doi = {10.1159/ore/aedag003},
  url = {https://doi.org/10.1159/ore/aedag003},
  note = {CC BY-NC 4.0},
}
RIS
TY  - JOUR
TI  - Diagnostic Performance of Deep Learning Using Retinal Images for Detection of Chronic Kidney Disease: A Systematic Review and Meta-Analysis
AU  - Mehrdad Farrokhi
AU  - Behnam Hoorshad
AU  - Reza Fahimi
AU  - Atousa Moghadam Fard
AU  - Behnaz Dalvandi
AU  - Reza Dalvandi
AU  - Mahshid Esmaielzade Rostami
AU  - Reza Judi Chelan
AU  - Oveis Ahmadzadeh
AU  - Sareh Salarinejad
AU  - Ramtin Shemshadigolafzani
AU  - Morteza Alipour
AU  - Parham Rahmani
AU  - Marjan Lashgari
AU  - Mahya Asadalizadeh
PY  - 2026
DA  - 2026/08/26
JO  - Ophthalmic Research
DO  - 10.1159/ore/aedag003
UR  - https://doi.org/10.1159/ore/aedag003
AB  - Introduction: Multiple investigations have been conducted to diagnose chronic kidney disease (CKD) from photographs of retina using deep learning models, with a wide range of diagnostic performance, which necessitates the importance of a comprehensive review. Therefore, in this meta-analysis, we estimated the detection performance of deep learning models for the diagnosis of CKD using retinal photographs.  Methods: MEDLINE, Scopus, and Web of Science were searched until 25 December 2025. Pooled estimation of heterogeneity, diagnostic parameters, and meta-regressions was performed using MetaDisc and STATA Software packages.  Results: The pooled sensitivity, specificity, and diagnostic odds ratio were 0.81 (95% CI, 0.80–0.82), 0.64 (95% CI, 0.64–0.65), and 9.15 (95% CI, 5.72–14.62), respectively. The pooled estimates of the positive and negative likelihood ratios were 2.18 (95% CI, 1.66–2.87) and 0.28 (95% CI, 0.20–0.39), respectively. The area under the summary receiver operating characteristic curve showed a discriminative performance of 0.77.  Conclusion: Deep learning based on retinal images had moderate diagnostic performance for detection of CKD. Relatively high sensitivity and modest specificity suggest that deep learning is more effective for ruling out CKD than for confirming the diagnosis that deep learning is more effective for ruling out CKD than for confirming the diagnosis. Deep learning-based retinal analysis may therefore serve as a supportive, noninvasive screening or triage tool but should not replace established diagnostic methods for CKD.
SN  - 0030-3747
SN  - 1423-0259
ER  -