A machine learning approach for predicting textbook outcome after cytoreductive surgery and hyperthermic intraperitoneal chemotherapy

Amir Ashraf Ganjouei; Fernanda Romero-Hernandez; Jaeyun Jane Wang; Ahmed Hamed; Ahmed Alaa; David Bartlett; Adnan Alseidi; Mohammad Haroon Choudry; Mohamed Adam

doi:10.1002/wjs.12184

A machine learning approach for predicting textbook outcome after cytoreductive surgery and hyperthermic intraperitoneal chemotherapy

World J Surg. 2024 Apr 23. doi: 10.1002/wjs.12184. Online ahead of print.

Authors

Affiliations

¹ Department of Surgery, University of California, San Francisco, California, USA.
² Division of Surgical Oncology, Department of Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.
³ Department of Surgery, University of Illinois at Chicago College of Medicine, Chicago, Illinois, USA.
⁴ University of California, Berkeley, California, USA.
⁵ University of California, San Francisco, California, USA.
⁶ Department of Surgery, Allegheny Health Network, Pittsburgh, Pennsylvania, USA.
⁷ Division of Surgical Oncology, Department of Surgery, University of California, San Francisco, California, USA.
⁸ Division of Surgical Oncology, Department of Surgery, UPMC Cancer Pavilion, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.

PMID: 38651936
DOI: 10.1002/wjs.12184

Abstract

Introduction: Peritoneal carcinomatosis is considered a late-stage manifestation of neoplastic diseases. Cytoreductive surgery with hyperthermic intraperitoneal chemotherapy (CRS-HIPEC) can be an effective treatment for these patients. However, the procedure is associated with significant morbidity. Our aim was to develop a machine learning model to predict the probability of achieving textbook outcome (TO) after CRS-HIPEC using only preoperatively known variables.

Methods: Adult patients with peritoneal carcinomatosis and who underwent CRS-HIPEC were included from a large, single-center, prospectively maintained dataset (2001-2020). TO was defined as a hospital length of stay ≤14 days and no postoperative adverse events including any complications, reoperation, readmission, and mortality within 90 days. Four models (logistic regression, neural network, random forest, and XGBoost) were trained, validated, and a user-friendly risk calculator was then developed.

Results: A total of 1954 CRS-HIPEC procedures for peritoneal carcinomatosis were included. Overall, 13% (n = 258) achieved TO following CRS-HIPEC procedure. XGBoost and logistic regression had the highest area under the curve (AUC) (0.76) after model optimization, followed by random forest (AUC 0.75) and neural network (AUC 0.74). The top preoperative variables associated with achieving a TO were lower peritoneal cancer index scores, not undergoing proctectomy, splenectomy, or partial colectomy and being asymptomatic from peritoneal metastases prior to surgery.

Conclusion: This is a data-driven study to predict the probability of achieving TO after CRS-HIPEC. The proposed pipeline has the potential to not only identify patients for whom surgery is not associated with prohibitive risk, but also aid surgeons in communicating this risk to patients.

Keywords: CRS‐HIPEC; machine learning; textbook outcome.