Liposuction is among the most common cosmetic procedures globally, with over 2.3 million performed annually. Despite its popularity, the procedure carries notable risks, including a 5% overall complication rate and a rare but serious risk of death from blood loss, occurring in roughly 1 in 5,000 cases. Artificial intelligence (AI) offers a promising approach to enhance patient safety by analyzing complex clinical data to identify risk factors and estimate expected blood loss more precisely than traditional methods.
In this study, researchers led by Mauricio E. Perez Pachon analyzed data from 721 patients undergoing large-volume liposuction at two centers in Bogotá, Colombia, and Loja, Ecuador, between 2019 and 2023. Both centers followed identical perioperative protocols. The dataset was divided into a training set of 621 patients and a testing set of 100 patients. A supervised machine learning model was developed to predict blood loss, and its predictions were compared with actual clinical measurements using standard statistical validation metrics.
The key findings of the study were as follows:
- The patient cohort was predominantly female (79.2%) with a median age of 37 years.
- Median weight was 65 kg, median height 165 cm, and median body mass index 24.34 kg/m².
- Median volemia was 3,924 mL, median infiltrated volume 5,800 mL, and median aspirated volume 3,900 mL.
- About 32% of patients had undergone previous liposuction.
- No significant differences were observed between the training and testing cohorts, supporting model reliability.
- The AI model achieved a mean absolute error of 22.09 mL, a root mean square error of 34.13 mL, and an R² value of 0.974.
- Overall predictive accuracy of the model was 94.1%.
- Accurate blood loss prediction can enhance preoperative planning and intraoperative management.
- Surgeons can better anticipate transfusion needs and optimize patient safety, potentially reducing complications in high-volume liposuction.
Looking ahead, the researchers emphasized the model’s potential to transform surgical practice. Validating the AI system could redefine safe limits for lipoaspirate volumes, moving beyond anecdotal guidance or reliance solely on expert experience. The platform also lays the foundation for more comprehensive AI algorithms that could predict patient-specific risks in other aesthetic and surgical procedures, enabling clinicians to implement targeted strategies to mitigate complications.
"The study presents a major step forward in leveraging AI to enhance safety in cosmetic surgery. By integrating predictive analytics into surgical planning, the model supports smarter, more personalized care. Ongoing research and application across diverse populations and surgical settings could further refine accuracy, paving the way for safer, more efficient liposuction procedures and potentially benefiting other surgical disciplines," the authors concluded.
Reference:
Perez Pachon, Mauricio E. MD1,2; Santaella, Jose T. MD3,4; Oñate, Carlos MD5,6; Oñate, Daniel MD5,6; De Freitas, Jonathan MD7; Borras Osorio, Mariana MD1,6; Hoyos, Alfredo E. MD1,6. Artificial Intelligence–Driven Blood Loss Prediction in Large-Volume Liposuction: Enhancing Precision and Patient Safety. Plastic and Reconstructive Surgery 157(1):p 63e-70e, January 2026. | DOI: 10.1097/PRS.0000000000012240
Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.
NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.