Effect of Using Artificial Intelligence in the Prediction and Initial Assessment of Chronic Kidney Disease: A Systematic Review and Meta-analysis

Background and aim: The present research aims to evaluate the effect of using artificial intelligence in the prediction and initial assessment of chronic kidney disease. Material and methods: In the present study, the researchers searched the international databases Cochrane, Embase, and MEDLINE (PubMed and Ovid) for keywords related to the study objectives. Considering that recent data is significant with the advancement of artificial intelligence, the search was limited to the last five years, between January 2019 and January 2025. The effect size was used with the random-effects model and REML methods of 95% confidence intervals (CI). Meta-analysis was performed using Stata (as of version 17). Results: The Area Under the Curve and accuracy of artificial intelligence in the prediction and initial assessment of chronic kidney disease was 90% (ES 0.90 95% CI; 0.28, 1.52) and 87% (ES 0.87 95% CI; 0.25, 1.49), respectively. Conclusions: Based on the meta-analysis of the present study, artificial intelligence models could be highly effective in the early ancillary diagnosis of chronic kidney disease.