An artificial intelligence-designed predictive calculator of conversion from minimally invasive to open colectomy in colon cancer

Abstract

AbstractMinimally invasive surgery is safe and effective in colorectal cancer. Conversion to open surgery may be associated with adverse effects on treatment outcomes. This study aimed to assess risk factors of conversion from minimally invasive to open colectomy for colon cancer and impact of conversion on short-term and survival outcomes. This case–control study included colon cancer patients undergoing minimally invasive colectomy from the National Cancer Database (2015–2019). Logistic regression analyses were conducted to determine independent predictors of conversion from laparoscopic and robotic colectomy to open surgery. 26,546 patients (mean age: 66.9 ± 13.1 years) were included. Laparoscopic and robotic colectomies were performed in 79.1% and 20.9% of patients, respectively, with a 10.6% conversion rate. Independent predictors of conversion were male sex (OR: 1.19, p = 0.014), left-sided cancer (OR: 1.35, p < 0.001), tumor size (OR: 1, p = 0.047), stage II (OR: 1.25, p = 0.007) and stage III (OR: 1.47, p < 0.001) disease, undifferentiated carcinomas (OR: 1.93, p = 0.002), subtotal (OR: 1.25, p = 0.011) and total (OR: 2.06, p < 0.001) colectomy, resection of contiguous organs (OR: 1.9, p < 0.001), and robotic colectomy (OR: 0.501, p < 0.001). Conversion was associated with higher 30- and 90-day mortality and unplanned readmission, longer hospital stay, and shorter overall survival (59.8 vs 65.3 months, p < 0.001). Male patients, patients with bulky, high-grade, advanced-stage, and left-sided colon cancers, and patients undergoing extended resections are at increased risk of conversion from minimally invasive to open colectomy. The robotic platform was associated with reduced odds of conversion. However, surgeons’ technical skills and criteria for conversion could not be assessed.