RESUMO
(1) Background: Surgical cytoreduction for epithelial ovarian cancer (EOC) is a complex procedure. Encompassed within the performance skills to achieve surgical precision, intra-operative surgical decision-making remains a core feature. The use of eXplainable Artificial Intelligence (XAI) could potentially interpret the influence of human factors on the surgical effort for the cytoreductive outcome in question; (2) Methods: The retrospective cohort study evaluated 560 consecutive EOC patients who underwent cytoreductive surgery between January 2014 and December 2019 in a single public institution. The eXtreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN) algorithms were employed to develop the predictive model, including patient- and operation-specific features, and novel features reflecting human factors in surgical heuristics. The precision, recall, F1 score, and area under curve (AUC) were compared between both training algorithms. The SHapley Additive exPlanations (SHAP) framework was used to provide global and local explainability for the predictive model; (3) Results: A surgical complexity score (SCS) cut-off value of five was calculated using a Receiver Operator Characteristic (ROC) curve, above which the probability of incomplete cytoreduction was more likely (area under the curve [AUC] = 0.644; 95% confidence interval [CI] = 0.598−0.69; sensitivity and specificity 34.1%, 86.5%, respectively; p = 0.000). The XGBoost outperformed the DNN assessment for the prediction of the above threshold surgical effort outcome (AUC = 0.77; 95% [CI] 0.69−0.85; p < 0.05 vs. AUC 0.739; 95% [CI] 0.655−0.823; p < 0.95). We identified "turning points" that demonstrated a clear preference towards above the given cut-off level of surgical effort; in consultant surgeons with <12 years of experience, age <53 years old, who, when attempting primary cytoreductive surgery, recorded the presence of ascites, an Intraoperative Mapping of Ovarian Cancer score >4, and a Peritoneal Carcinomatosis Index >7, in a surgical environment with the optimization of infrastructural support. (4) Conclusions: Using XAI, we explain how intra-operative decisions may consider human factors during EOC cytoreduction alongside factual knowledge, to maximize the magnitude of the selected trade-off in effort. XAI techniques are critical for a better understanding of Artificial Intelligence frameworks, and to enhance their incorporation in medical applications.
RESUMO
OBJECTIVE: We investigated the learning curve for a monodisciplinary surgical team consisting of gynecologic oncologists performing cytoreductive surgery for advanced ovarian cancer, involving high-complexity procedures with bowel resection and upper abdominal surgery. METHODS: We investigated 271 consecutive patients with ovarian, fallopian tube, and peritoneal carcinoma undergoing cytoreductive surgery for stage III/IV disease. All operations were performed by a team consisting of only gynecologic oncologists. Patients were classified into 2 groups depending on the surgical complexity score (a cumulative score based on complexity and number of procedures performed). Learning curves for patients with moderate (4-7, 63 patients) and high scores (8-18, 208 patients) were evaluated using cumulative sum (CUSUM) analysis of operative time, total blood loss, and perioperative complications. RESULTS: Operative time and total blood loss showed a learning curve. The CUSUM curve for operative time peaked at the 28th and 51st case in the moderate- and high-score groups, respectively. The CUSUM curve for total blood loss peaked at the 16th and 55th case in the moderate- and high-score groups, respectively. The CUSUM curve for complications (Clavien-Dindo ≥ IIIb) showed a downward slope after the 6th case in the high-score group and remained within the acceptable range throughout the study. CONCLUSION: Proficiency in performing high-complexity surgery was achieved after approximately 50 cases and this number is greater than the number of cases required to perform moderate-complexity surgery. Acceptable rates of severe perioperative complications were observed even during the initial learning period in cases of high-complexity surgery.