Complete surgical cytoreduction (R0 resection) is the single most important prognosticator in epithelial ovarian cancer (EOC). Explainable Artificial Intelligence (XAI) could clarify the influence of static and real-time features in the R0 resection prediction. We aimed to develop an AI-based predictive model for the R0 resection outcome, apply a methodology to explain the prediction, and evaluate the interpretability by analysing feature interactions. The retrospective cohort finally assessed 571 consecutive advanced-stage EOC patients who underwent cytoreductive surgery. An eXtreme Gradient Boosting (XGBoost) algorithm was employed to develop the predictive model including mostly patient- and surgery-specific variables. The Shapley Additive explanations (SHAP) framework was used to provide global and local explainability for the predictive model. The XGBoost accurately predicted R0 resection (area under curve [AUC] = 0.866; 95% confidence interval [CI] = 0.8–0.93). We identified “turning points” that increased the probability of complete cytoreduction including Intraoperative Mapping of Ovarian Cancer Score and Peritoneal Carcinomatosis Index < 4 and 4, patient’s age < 60 years, and largest tumour bulk < 5 cm in a surgical environment of optimized infrastructural support. We demonstrated high model accuracy for the R0 resection prediction in EOC patients and provided novel global and local feature explainability that can be used for quality control and internal audit.

(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 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.

A lack of explicit early clinical signs and effective screening measures mean that ovarian cancer (OC) often presents as advanced, incurable disease. While conventional treatment combines maximal cytoreductive surgery and platinum-based chemotherapy, patients frequently develop chemoresistance and disease recurrence. The clinical application of immune checkpoint blockade (ICB) aims to restore anti-cancer T-cell function in the tumour microenvironment (TME). Disappointingly, even though tumour infiltrating lymphocytes are associated with superior survival in OC, ICB has offered limited therapeutic benefits. Herein, we discuss specific TME features that prevent ICB from reaching its full potential, focussing in particular on the challenges created by immune, genomic and metabolic alterations. We explore both recent and current therapeutic strategies aiming to overcome these hurdles, including the synergistic effect of combination treatments with immune-based strategies and review the status quo of current clinical trials aiming to maximise the success of immunotherapy in OC.

Introduction: Accurate prediction of patient prognosis can be especially useful for the selection of best treatment protocols. Machine Learning can serve this purpose by making predictions based upon generalizable clinical patterns embedded within learning datasets. We designed a study to support the feature selection for the 2-year prognostic period and compared the performance of several Machine Learning prediction algorithms for accurate 2-year prognosis estimation in advanced-stage high grade serous ovarian cancer (HGSOC) patients. Methods: The prognosis estimation was formulated as a binary classification problem. Dataset was split into training and test cohorts with repeated random sampling until there was no significant difference (p = 0.20) between the two cohorts. A ten-fold cross-validation was applied. Various state-of-the-art supervised classifiers were used. For feature selection, in addition to the exhaustive search for the best combination of features, we used the-chi square test of independence and the MRMR method. Results: Two hundred nine patients were identified. The model's mean prediction accuracy reached 73%. We demonstrated that Support-Vector-Machine and Ensemble Subspace Discriminant algorithms outperformed Logistic Regression in accuracy indices. The probability of achieving a cancer-free state was maximised with a combination of primary cytoreduction, good performance status and maximal surgical effort (AUC 0.63). Standard chemotherapy, performance status, tumour load and residual disease were consistently predictive of the mid-term overall survival (AUC 0.63–0.66). The model recall and precision were greater than 80%. Conclusion: Machine Learning appears to be promising for accurate prognosis estimation. Appropriate feature selection is required when building an HGSOC model for 2-year prognosis prediction. We provide evidence as to what combination of prognosticators leads to the largest impact on the HGSOC 2-year prognosis.

Background: The Peritoneal Carcinomatosis Index (PCI) and the Intra-operative Mapping for Ovarian Cancer (IMO), to a lesser extent, have been universally validated in advanced-stage epithelial ovarian cancer (EOC) to describe the extent of peritoneal dissemination and are proven to be powerful predictors of the surgical outcome with an added sensitivity of assessment at laparotomy of around 70%. This leaves room for improvement because the two-dimensional anatomic scoring model fails to reflect the patient’s real anatomy, as seen by a surgeon. We hypothesized that tumor dissemination in specific anatomic locations can be more predictive of complete cytoreduction (CC0) and survival than PCI and IMO tools in EOC patients. (2) Methods: We analyzed prospectively data collected from 508 patients with FIGO-stage IIIB-IVB EOC who underwent cytoreductive surgery between January 2014 and December 2019 at a UK tertiary center. We adapted the structured ESGO ovarian cancer report to provide detailed information on the patterns of tumor dissemination (cancer anatomic fingerprints). We employed the extreme gradient boost (XGBoost) to model only the variables referring to the EOC disseminated patterns, to create an intra-operative score and judge the predictive power of the score alone for complete cytoreduction (CC0). Receiver operating characteristic (ROC) curves were then used for performance comparison between the new score and the existing PCI and IMO tools. We applied the Shapley additive explanations (SHAP) framework to support the feature selection of the narrated cancer fingerprints and provide global and local explainability. Survival analysis was performed using Kaplan–Meier curves and Cox regression. (3) Results: An intra-operative disease score was developed based on specific weights assigned to the cancer anatomic fingerprints. The scores range from 0 to 24. The XGBoost predicted CC0 resection (area under curve (AUC) = 0.88 CI = 0.854–0.913) with high accuracy. Organ-specific dissemination on the small bowel mesentery, large bowel serosa, and diaphragmatic peritoneum were the most crucial features globally. When added to the composite model, the novel score slightly enhanced its predictive value (AUC = 0.91, CI = 0.849–0.963). We identified a “turning point”, ≤5, that increased the probability of CC0. Using conventional logistic regression, the new score was superior to the PCI and IMO scores for the prediction of CC0 (AUC = 0.81 vs. 0.73 and 0.67, respectively). In multivariate Cox analysis, a 1-point increase in the new intra-operative score was associated with poorer progression-free (HR: 1.06; 95% CI: 1.03–1.09, p < 0.005) and overall survival (HR: 1.04; 95% CI: 1.01–1.07), by 4% and 6%, respectively. (4) Conclusions: The presence of cancer disseminated in specific anatomical sites, including small bowel mesentery, large bowel serosa, and diaphragmatic peritoneum, can be more predictive of CC0 and survival than the entire PCI and IMO scores. Early intra-operative assessment of these areas only may reveal whether CC0 is achievable. In contrast to the PCI and IMO scores, the novel score remains predictive of adverse survival outcomes.

Introduction: Contemporary efforts to predict surgical outcomes focus on the associations between traditional discrete surgical risk factors. We aimed to determine whether natural language processing (NLP) of unstructured operative notes improves the prediction of residual disease in women with advanced epithelial ovarian cancer (EOC) following cytoreductive surgery. Methods: Electronic Health Records were queried to identify women with advanced EOC including their operative notes. The Term Frequency – Inverse Document Frequency (TF-IDF) score was used to quantify the discrimination capacity of sequences of words (n-grams) regarding the existence of residual disease. We employed the state-of-the-art RoBERTa-based classifier to process unstructured surgical notes. Discrimination was measured using standard performance metrics. An XGBoost model was then trained on the same dataset using both discrete and engineered clinical features along with the probabilities outputted by the RoBERTa classifier. Results: The cohort consisted of 555 cases of EOC cytoreduction performed by eight surgeons between January 2014 and December 2019. Discrete word clouds weighted by n-gram TF-IDF score difference between R0 and non-R0 resection were identified. The words ‘adherent’ and ‘miliary disease’ best discriminated between the two groups. The RoBERTa model reached high evaluation metrics (AUROC .86; AUPRC .87, precision, recall, and F1 score of .77 and accuracy of .81). Equally, it outperformed models that used discrete clinical and engineered features and outplayed the performance of other state-of-the-art NLP tools. When the probabilities from the RoBERTa classifier were combined with commonly used predictors in the XGBoost model, a marginal improvement in the overall model’s performance was observed (AUROC and AUPRC of .91, with all other metrics the same). Conclusion/Implications: We applied a sui generis approach to extract information from the abundant textual surgical data and demonstrated how it can be effectively used for classification prediction, outperforming models relying on conventional structured data. State-of-art NLP applications in biomedical texts can improve modern EOC care.