Predicting Surgical Outcomes and Optimizing Patients for Surgery Using AI

Abstract

Artificial intelligence (AI) platforms and machine learning (ML) algorithms provide the ability to utilize large amounts of electronically available data and leverage them to augment physicians' risk assessment and predictive abilities. These tools allow for refinement and/or reimagination of current tools aimed at predicting and optimizing outcomes in the perioperative period. In this section, we review AI and ML construction and implementation, the current state of predictive model use in surgical patients during the perioperative period, and discuss opportunities for integration into clinical care to optimize patients for surgery, improve perioperative patient care, and enable earlier detection of postoperative complications. We conclude with a discussion of limitations of AI and ML tools, along with points for consideration regarding their implementation in perioperative surgical care.

Keywords

artificial intelligence - machine learning - perioperative care - surgical outcomes

Publication History

Article published online:
12 January 2026

• References

• 1 Bhutiani N, Yousef MMG, Yousef A. et al. Automated, high-throughput platform to generate a high-reliability, comprehensive rectal cancer database. JCO Clin Cancer Inform 2024; 8: e2300219
• 2 Chen KA, Joisa CU, Stitzenberg KB. et al. Development and validation of machine learning models to predict readmission after colorectal surgery. J Gastrointest Surg 2022; 26 (11) 2342-2350
• 3 Nudel J, Bishara AM, de Geus SWL. et al. Development and validation of machine learning models to predict gastrointestinal leak and venous thromboembolism after weight loss surgery: An analysis of the MBSAQIP database. Surg Endosc 2021; 35 (01) 182-191
• 4 Shi HY, Lee KT, Lee HH. et al. Comparison of artificial neural network and logistic regression models for predicting in-hospital mortality after primary liver cancer surgery. PLoS ONE 2012; 7 (04) e35781
• 5 Lin V, Tsouchnika A, Allakhverdiiev E. et al. Training prediction models for individual risk assessment of postoperative complications after surgery for colorectal cancer. Tech Coloproctol 2022; 26 (08) 665-675
• 6 Merath K, Hyer JM, Mehta R. et al. Use of machine learning for prediction of patient risk of postoperative complications after liver, pancreatic, and colorectal surgery. J Gastrointest Surg 2020; 24 (08) 1843-1851
• 7 Riepe C, van de Water R, Winter A. et al. 90-day mortality prediction in elective visceral surgery using machine learning: A retrospective multicenter development, validation, and comparison study. Int J Surg 2025; 111 (06) 3742-3751
• 8 Agnes A, Nguyen ST, Konishi T. et al. Early postoperative prediction of complications and readmission after colorectal cancer surgery using an artificial neural network. Dis Colon Rectum 2024; 67 (10) 1341-1352
• 9 Aro R, Mäkäräinen-Uhlbäck E, Ämmälä N. et al. The impact of sarcopenia and myosteatosis on postoperative outcomes and 5-year survival in curatively operated colorectal cancer patients - A retrospective register study. Eur J Surg Oncol 2020; 46 (09) 1656-1662
• 10 O'Brien S, Kavanagh RG, Carey BW, Maher MM, O'Connor OJ, Andrews EJ. The impact of sarcopenia and myosteatosis on postoperative outcomes in patients with inflammatory bowel disease. Eur Radiol Exp 2018; 2 (01) 37
• 11 Body S, Ligthart MAP, Rahman S. et al; Wessex Research Collaborative. Sarcopenia and myosteatosis predict adverse outcomes after emergency laparotomy: A multi-center observational cohort study. Ann Surg 2022; 275 (06) 1103-1111
• 12 Irani JL, Hedrick TL, Miller TE. et al. Clinical practice guidelines for enhanced recovery after colon and rectal surgery from the American Society of Colon and Rectal Surgeons and the Society of American Gastrointestinal and Endoscopic Surgeons. Dis Colon Rectum 2023; 66 (01) 15-40
• 13 Messias BA, Botelho RV, Saad SS, Mocchetti ER, Turke KC, Waisberg J. Serum C-reactive protein is a useful marker to exclude anastomotic leakage after colorectal surgery. Sci Rep 2020; 10 (01) 1687
• 14 Yeung DE, Peterknecht E, Hajibandeh S, Hajibandeh S, Torrance AW. C-reactive protein can predict anastomotic leak in colorectal surgery: A systematic review and meta-analysis. Int J Colorectal Dis 2021; 36 (06) 1147-1162
• 15 Lucas MM, Schootman M, Laryea JA. et al. Bias in prediction models to identify patients with colorectal cancer at high risk for readmission after resection. JCO Clin Cancer Inform 2024; 8: e2300194