Diabetic ketoacidosis (DKA) is a life-threatening complication of diabetes that can lead to cerebral edema, organ failure, and even death. Traditional diagnosis depends on clinical assessment and laboratory tests, which may delay recognition and overlap with other conditions. Recent advances in artificial intelligence (AI), particularly machine learning (ML), present opportunities to improve early diagnosis, risk stratification, and management of DKA. Various ML models—such as Random Forest, K-Nearest Neighbors, XGBoost, and Long Short-Term Memory networks—have demonstrated high predictive accuracy for assessing DKA severity, prognosis, and mortality. However, many of these studies are limited by small, single-center cohorts and lack external validation. Although AI shows strong potential to transform DKA care, further standardization, validation across diverse populations, and integration into clinical workflows are required before routine adoption.

© 2025 The Author(s), licensee HBKU Press.

Article metrics loading...

/content/journals/10.5339/avi.2025.16

2025-11-03

2025-11-16

Full text loading...

/deliver/fulltext/avi/2025/2/avi.2025.16.html?itemId=/content/journals/10.5339/avi.2025.16&mimeType=html&fmt=ahah