TY - JOUR
T1 - The Use of Machine Learning for Predicting Complications of Free-Flap Head and Neck Reconstruction
AU - Asaad, Malke
AU - Lu, Sheng Chieh
AU - Hassan, Abbas M.
AU - Kambhampati, Praneeth
AU - Mitchell, David
AU - Chang, Edward I.
AU - Yu, Peirong
AU - Hanasono, Matthew M.
AU - Sidey-Gibbons, C.
N1 - Funding Information:
This research has been supported not financially by “European Reference Network for Rare Kidney Disease, ERKNet”. This ERN is partly co-funded by the European Union within the framework of the Third Health Programme “ERN- 2016 – Framework Partnership Agreement 2017–2021”.
Publisher Copyright:
© 2023, Society of Surgical Oncology.
PY - 2023/4
Y1 - 2023/4
N2 - Background: Machine learning has been increasingly used for surgical outcome prediction, yet applications in head and neck reconstruction are not well-described. In this study, we developed and evaluated the performance of ML algorithms in predicting postoperative complications in head and neck free-flap reconstruction. Methods: We conducted a comprehensive review of patients who underwent microvascular head and neck reconstruction between January 2005 and December 2018. Data were used to develop and evaluate nine supervised ML algorithms in predicting overall complications, major recipient-site complication, and total flap loss. Results: We identified 4000 patients who met inclusion criteria. Overall, 33.7% of patients experienced a complication, 26.5% experienced a major recipient-site complication, and 1.7% suffered total flap loss. The k-nearest neighbors algorithm demonstrated the best overall performance for predicting any complication (AUROC = 0.61, sensitivity = 0.60). Regularized regression had the best performance for predicting major recipient-site complications (AUROC = 0.68, sensitivity = 0.66), and decision trees were the best predictors of total flap loss (AUROC = 0.66, sensitivity = 0.50). Conclusions: ML accurately identified patients at risk of experiencing postsurgical complications, including total flap loss. Predictions from ML models may provide insight in the perioperative setting and facilitate shared decision making.
AB - Background: Machine learning has been increasingly used for surgical outcome prediction, yet applications in head and neck reconstruction are not well-described. In this study, we developed and evaluated the performance of ML algorithms in predicting postoperative complications in head and neck free-flap reconstruction. Methods: We conducted a comprehensive review of patients who underwent microvascular head and neck reconstruction between January 2005 and December 2018. Data were used to develop and evaluate nine supervised ML algorithms in predicting overall complications, major recipient-site complication, and total flap loss. Results: We identified 4000 patients who met inclusion criteria. Overall, 33.7% of patients experienced a complication, 26.5% experienced a major recipient-site complication, and 1.7% suffered total flap loss. The k-nearest neighbors algorithm demonstrated the best overall performance for predicting any complication (AUROC = 0.61, sensitivity = 0.60). Regularized regression had the best performance for predicting major recipient-site complications (AUROC = 0.68, sensitivity = 0.66), and decision trees were the best predictors of total flap loss (AUROC = 0.66, sensitivity = 0.50). Conclusions: ML accurately identified patients at risk of experiencing postsurgical complications, including total flap loss. Predictions from ML models may provide insight in the perioperative setting and facilitate shared decision making.
UR - http://www.scopus.com/inward/record.url?scp=85147117402&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85147117402&partnerID=8YFLogxK
U2 - 10.1245/s10434-022-13053-3
DO - 10.1245/s10434-022-13053-3
M3 - Article
C2 - 36719569
AN - SCOPUS:85147117402
SN - 1068-9265
VL - 30
SP - 2343
EP - 2352
JO - Annals of surgical oncology
JF - Annals of surgical oncology
IS - 4
ER -