AI shows promise in diagnosing dry eye disease: Meta-analysis finds high accuracy

Artificial intelligence (AI) shows significant promise in improving the accuracy and efficiency of diagnosing dry eye disease, according to a meta-analysis of multiple studies demonstrates that AI models achieve high levels of accuracy, sensitivity, and specificity compared to traditional diagnostic methods.

Key performance metrics, including the area under the receiver operating characteristic curve, sensitivity, specificity, and overall accuracy, were evaluated across the 2838 studies.

There was a pooled estimate of diagnostic accuracy at 91.91% (95% confidence interval: 87.46-95.49) across all AI models studied. The mean values for the area under the receiver operating characteristic curve, sensitivity, and specificity were calculated at 94.1 (±5.14), 89.58 (±6.13), and 92.62 (±6.61), respectively. These metrics indicate robust performance and reliability of AI models in detecting dry eye disease compared to traditional methods.

Reference
Heidari Z, Hashemi H, Sotude D, et al. Applications of Artificial Intelligence in Diagnosis of Dry Eye Disease: A Systematic Review and Meta-Analysis. Cornea. 2024;doi: 10.1097/ICO.0000000000003626. Epub ahead of print. PMID: 38984532.