Background: Over 2.3 million liposuctions are performed annually with a complication rate of about 5%, including a death rate of 1 in 5,000 due to blood loss. Artificial intelligence (AI) models offer potential for improving blood loss prediction and management in these procedures, analyzing extensive data to identify risk factors and accurately estimate blood loss.

Methods: Data from 721 large-volume liposuction patients at two centers in Bogotá, Colombia, and Loja, Ecuador, between 2019 and 2023 was evaluated. Both centers followed identical perioperative protocols. The dataset was split into training (621 patients) and testing (100 patients) sets. A supervised machine learning model was trained to predict blood loss. Model's predictions were compared with clinical data using statistical validation metrics.

Results: Most patients were women (79.2%) with median values of age 37 years, weight 65 kg, height 165 cm, BMI 24.34 kg/m², volemia 3924.41 ml, infiltrated volume 5800 ml, and aspirated volume 3900 ml. Previous liposuction was noted in 32%. No significant differences were found between training and testing cohorts. The model achieved a Mean Absolute Error (MAE) of 22.09 ml, Root Mean Square Error (RMSE) of 34.13 ml, and an R² value of 0.974, indicating high predictive accuracy and excellent model fit.

Conclusions: Our study has developed and validated an accurate AI-based model to predict blood loss in large-volume liposuction, showing 94.1% accuracy. Our model enhances preoperative planning and intraoperative management, potentially reducing complications and improving outcomes.