Prerequisites to improve surgical cytoreduction in FIGO stage III/IV epithelial ovarian cancer and subsequent clinical ramifications.

BACKGROUND: No residual disease (CC 0) following cytoreductive surgery is pivotal for the prognosis of women with advanced stage epithelial ovarian cancer (EOC). Improving CC 0 resection rates without increasing morbidity and no delay in subsequent chemotherapy favors a better outcome in these women. Prerequisites to facilitate this surgical paradigm shift and subsequent ramifications need to be addressed. This quality improvement study assessed 559 women with advanced EOC who had cytoreductive surgery between January 2014 and December 2019 in our tertiary referral centre. Following implementation of the Enhanced Recovery After Surgery (ERAS) pathway and prehabilitation protocols, the surgical management paradigm in advanced EOC patients shifted towards maximal surgical effort cytoreduction in 2016. Surgical outcome parameters before, during, and after this paradigm shift were compared. The primary outcome measure was residual disease (RD). The secondary outcome parameters were postoperative morbidity, operative time (OT), length of stay (LOS) and progression-free-survival (PFS). RESULTS: R0 resection rate in patients with advanced EOC increased from 57.3% to 74.4% after the paradigm shift in surgical management whilst peri-operative morbidity and delays in adjuvant chemotherapy were unchanged. The mean OT increased from 133 + 55 min to 197 + 85 min, and postoperative high dependency/intensive care unit (HDU/ICU) admissions increased from 8.1% to 33.1%. The subsequent mean LOS increased from 7.0 + 2.6 to 8.4 + 4.9 days. The median PFS was 33 months. There was no difference for PFS in the three time frames but a trend towards improvement was observed. CONCLUSIONS: Improved CC 0 surgical cytoreduction rates without compromising morbidity in advanced EOC is achievable owing to the right conditions. Maximal effort cytoreductive surgery should solely be carried out in high output tertiary referral centres due to the associated substantial prerequisites and ramifications.

RoBERTa-Assisted Outcome Prediction in Ovarian Cancer Cytoreductive Surgery Using Operative Notes.

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.

Immune Checkpoint Inhibitors Targeting the PD-1/PD-L1 Pathway in Advanced, Recurrent Endometrial Cancer: A Scoping Review with SWOT Analysis.

Results of recent clinical trials using the immune check point inhibitors (ICI) pembrolizumab or dostarlimab with/without lenvatinib has led to their approval for specific molecular subgroups of advanced recurrent endometrial cancer (EC). Herein, we summarise the clinical data leading to this first tissue-agnostic approval. As this novel therapy is not yet available in the United Kingdom standard care setting, we explore the strengths, weaknesses, opportunities, and threats (SWOT) of ICI treatment in EC. Major databases were searched focusing on clinical trials using programmed cell death protein 1 (PD-1) and its ligand (PD-L1) ICI which ultimately contributed to anti-PD-1 approval in EC. We performed a data quality assessment, reviewing survival and safety analysis. We included 15 studies involving 1609 EC patients: 458 with mismatch repair deficiency (MMRd)/microsatellite instability-high (MSI-H) status and 1084 with mismatch repair proficiency/microsatellite stable (MMRp/MSS) status. Pembrolizumab/dostarlimab have been approved for MMRd ECs, with the addition of lenvatinib for MMRp cases in the recurrent setting. Future efforts will focus on the pathological assessment of biomarkers to determine molecular phenotypes that correlate with response or resistance to ICI in order to identify patients most likely to benefit from this treatment.

The Future of AI in Ovarian Cancer Research: The Large Language Models Perspective.

Conversational large language model (LLM)-based chatbots utilize neural networks to process natural language. By generating highly sophisticated outputs from contextual input text, they revolutionize the access to further learning, leading to the development of new skills and personalized interactions. Although they are not developed to provide healthcare, their potential to address biomedical issues is rather unexplored. Healthcare digitalization and documentation of electronic health records is now developing into a standard practice. Developing tools to facilitate clinical review of unstructured data such as LLMs can derive clinical meaningful insights for ovarian cancer, a heterogeneous but devastating disease. Compared to standard approaches, they can host capacity to condense results and optimize analysis time. To help accelerate research in biomedical language processing and improve the validity of scientific writing, task-specific and domain-specific language models may be required. In turn, we propose a bespoke, proprietary ovarian cancer-specific natural language using solely in-domain text, whereas transfer learning drifts away from the pretrained language models to fine-tune task-specific models for all possible downstream applications. This venture will be fueled by the abundance of unstructured text information in the electronic health records resulting in ovarian cancer research ultimately reaching its linguistic home.

Development of a Novel Intra-Operative Score to Record Diseases' Anatomic Fingerprints (ANAFI Score) for the Prediction of Complete Cytoreduction in Advanced-Stage Ovarian Cancer by Using Machine Learning and Explainable Artificial Intelligence.

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.

Explaining the Elusive Nature of a Well-Defined Threshold for Blood Transfusion in Advanced Epithelial Ovarian Cancer Cytoreductive Surgery.

There is no well-defined threshold for intra-operative blood transfusion (BT) in advanced epithelial ovarian cancer (EOC) surgery. To address this, we devised a Machine Learning (ML)-driven prediction algorithm aimed at prompting and elucidating a communication alert for BT based on anticipated peri-operative events independent of existing BT policies. We analyzed data from 403 EOC patients who underwent cytoreductive surgery between 2014 and 2019. The estimated blood volume (EBV), calculated using the formula EBV = weight × 80, served for setting a 10% EBV threshold for individual intervention. Based on known estimated blood loss (EBL), we identified two distinct groups. The Receiver operating characteristic (ROC) curves revealed satisfactory results for predicting events above the established threshold (AUC 0.823, 95% CI 0.76-0.88). Operative time (OT) was the most significant factor influencing predictions. Intra-operative blood loss exceeding 10% EBV was associated with OT > 250 min, primary surgery, serous histology, performance status 0, R2 resection and surgical complexity score > 4. Certain sub-procedures including large bowel resection, stoma formation, ileocecal resection/right hemicolectomy, mesenteric resection, bladder and upper abdominal peritonectomy demonstrated clear associations with an elevated interventional risk. Our findings emphasize the importance of obtaining a rough estimate of OT in advance for precise prediction of blood requirements.

Stratification of Length of Stay Prediction following Surgical Cytoreduction in Advanced High-Grade Serous Ovarian Cancer Patients Using Artificial Intelligence; the Leeds L-AI-OS Score.

(1) Background: Length of stay (LOS) has been suggested as a marker of the effectiveness of short-term care. Artificial Intelligence (AI) technologies could help monitor hospital stays. We developed an AI-based novel predictive LOS score for advanced-stage high-grade serous ovarian cancer (HGSOC) patients following cytoreductive surgery and refined factors significantly affecting LOS. (2) Methods: Machine learning and deep learning methods using artificial neural networks (ANN) were used together with conventional logistic regression to predict continuous and binary LOS outcomes for HGSOC patients. The models were evaluated in a post-hoc internal validation set and a Graphical User Interface (GUI) was developed to demonstrate the clinical feasibility of sophisticated LOS predictions. (3) Results: For binary LOS predictions at differential time points, the accuracy ranged between 70-98%. Feature selection identified surgical complexity, pre-surgery albumin, blood loss, operative time, bowel resection with stoma formation, and severe postoperative complications (CD3-5) as independent LOS predictors. For the GUI numerical LOS score, the ANN model was a good estimator for the standard deviation of the LOS distribution by ± two days. (4) Conclusions: We demonstrated the development and application of both quantitative and qualitative AI models to predict LOS in advanced-stage EOC patients following their cytoreduction. Accurate identification of potentially modifiable factors delaying hospital discharge can further inform services performing root cause analysis of LOS.

Survival and Chemosensitivity in Advanced High Grade Serous Epithelial Ovarian Cancer Patients with and without a BRCA Germline Mutation: More Evidence for Shifting the Paradigm towards Complete Surgical Cytoreduction.

Background and Objectives: Approximately 10−15% of high-grade serous ovarian cancer (HGSOC) cases are related to BRCA germline mutations. Better survival rates and increased chemosensitivity are reported in patients with a BRCA 1/2 germline mutation. However, the FIGO stage and histopathological entity may have been confounding factors. This study aimed to compare chemotherapy response and survival between patients with and without a BRCA 1/2 germline mutation in advanced HGSOC receiving neoadjuvant chemotherapy (NACT). Materials and Methods: A cohort of BRCA-tested advanced HGSOC patients undergoing cytoreductive surgery following NACT was analyzed for chemotherapy response and survival. Neoadjuvant chemotherapy served as a vehicle to assess chemotherapy response on biochemical (CA125), histopathological (CRS), biological (dissemination), and surgical (residual disease) levels. Univariate and multivariate analyses for chemotherapy response and survival were utilized. Results: Thirty-nine out of 168 patients had a BRCA ½ germline mutation. No differences in histopathological chemotherapy response between the patients with and without a BRCA ½ germline mutation were observed. Survival in the groups of patients was comparable Irrespective of the BRCA status, CRS 2 and 3 (HR 7.496, 95% CI 2.523−22.27, p < 0.001 & HR 4.069, 95% CI 1.388−11.93, p = 0.011), and complete surgical cytoreduction (p = 0.017) were independent parameters for a favored overall survival. Conclusions: HGSOC patients with or without BRCA ½ germline mutations, who had cytoreductive surgery, showed comparable chemotherapy responses and subsequent survival. Irrespective of BRCA status, advanced-stage HGSOC patients have a superior prognosis with complete surgical cytoreduction and good histopathological response to chemotherapy.

Factors Predicting Surgical Effort Using Explainable Artificial Intelligence in Advanced Stage Epithelial Ovarian Cancer.

(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.

Teaching and Assessment of Medical Students During Complex Multifactorial Team-Based Tasks: The "Virtual on Call" Case Study.

Abstract: Although considerable efforts have been made to incorporate simulation-based learning (SBL) in undergraduate medical education, to date, most of the medical school curricula still focus on pure knowledge or individual assessment of objective structured clinical examination skills (OSCE). To this end, we designed a case study named "iG4 (integrated generation 4) virtual on-call (iVOC)". We aimed to simulate an on-call shift in a high-fidelity virtual hospital setting in order to assess delegates' team-based performance on tasks related to patient handovers (prioritisation, team allocation). Methods: A total of 41 clinical year medical students were split into 3 cohorts, each of which included 3 groups of 4 or 5 people. The groups consisted of a structured mix of educational and cultural backgrounds of students to achieve homogeneity. Each performing group received the handover for 5 patients in the virtual hospital and had to identify and deal with the acutely unwell ones within 15 minutes. We used TEAMTM tool to assess team-based performances. Results: The mean handover performance was 5.44/10 ± 2.24 which was the lowest across any performance marker. The overall global performance across any team was 6.64/10 ± 2.11. The first rotating team's global performance for each cycle was 6.44/10 ± 2.01, for the second 7.89/10 ± 2.09 and for the third 6.78/10 ± 1.64 (p = 0.099 between groups). Conclusion: This is one of the first reported, high-fidelity, globally reproducible SBL settings to assess the capacity of students to work as part of a multinational team, highlighting several aspects that need to be addressed during undergraduate studies. Medical schools should consider similar efforts with the aim to incorporate assessment frameworks for individual performances of students as part of a team, which can be a stepping-stone for enhancing safety in clinical practice.

Barriers to Immunotherapy in Ovarian Cancer: Metabolic, Genomic, and Immune Perturbations in the Tumour Microenvironment.

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.

The Uncertain Benefit of Adjuvant Chemotherapy in Advanced Low-Grade Serous Ovarian Cancer and the Pivotal Role of Surgical Cytoreduction.

In our center, adjuvant chemotherapy is routinely offered in high-grade serous ovarian cancer (HGSOC) patients but less commonly as a standard treatment in low-grade serous ovarian cancer (LGSOC) patients. This study evaluates the efficacy of this paradigm by analysing survival outcomes and by comparing the influence of different clinical and surgical characteristics between women with advanced LGSOC (n = 37) and advanced HGSOC (n = 300). Multivariate analysis was used to identify independent prognostic features for survival in LGSOC and HGSOC. Adjuvant chemotherapy was given in 99.7% of HGSOC patients versus in 27% of LGSOC (p < 0.0001). The LGSOC patients had greater surgical complexity scores (p < 0.0001), more frequent postoperative ICU/HDU admissions (p = 0.0002), and higher peri-/post-operative morbidity (p < 0.0001) compared to the HGSOC patients. The 5-year OS and progression-free survival (PFS) was 30% and 13% for HGSOC versus 57% and 21.6% for LGSOC, p = 0.016 and p = 0.044, respectively. Surgical complexity (HR 5.3, 95%CI 1.2-22.8, p = 0.024) and complete cytoreduction (HR 62.4, 95% CI 6.8-567.9, p < 0.001) were independent prognostic features for OS in LGSOC. This study demonstrates no clear significant survival advantage of chemotherapy in LGSOC. It highlights the substantial survival benefit of dynamic multi-visceral surgery to achieve complete cytoreduction as the primary treatment for LGSOC patients.

Feature Selection is Critical for 2-Year Prognosis in Advanced Stage High Grade Serous Ovarian Cancer by Using Machine Learning.

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.

Breast Cancer Patients at Increased Risk of Developing Type II Endometrial Cancer: Relative and Absolute Risk Estimation and Implications for Counseling.

Introduction Breast cancer (BC) is a recognized risk factor for endometrial cancer (EC). Emerging literature indicates that it confers a higher risk of type II EC (T2EC) than type I EC (T1EC). Although some surgeons offer a prophylactic hysterectomy to BC patients referred for risk-reducing bilateral salpingo-oophorectomy, insufficient evidence prevents this from being the standard practice. We aimed to quantify their absolute risk and relative risk (RR) of developing both EC subtypes and identify a higher-risk group that could be considered for prophylactic hysterectomy. Methodology This retrospective service evaluation compared patients diagnosed with BC between 2008 and 2014, who subsequently developed EC within 10 years to those who did not. Absolute risk and RR were calculated using the numbers of regional BC and EC cases within this group, alongside 2009 UK female population and EC incidence statistics. Binary logistic regression generated adjusted odds ratios (ORs) for patient- and disease-specific variables. Results A total of 45 BC patients developed EC, 24 had T1EC and 21 had T2EC. Their RR of developing EC was greater than that of the general population (RR: 12.44, p < 0.0001). Notably, this was higher for T2EC (RR: 33.96, p < 0.001) than T1EC (RR: 8.63, p < 0.0001). Nonetheless, the absolute risk remained low. Tamoxifen exposure was significantly more prevalent among T2EC patients (adjusted OR: 79.61, p = 0.003). Increased age at BC diagnosis was associated with T1EC (adjusted OR: 1.10, p = 0.043) and T2EC (adjusted OR: 1.13, p = 0.03). Neither smoking status nor family history of BC was significantly associated with any outcome. Conclusion Women with BC were more likely to develop T2EC than T1EC, and although the absolute risk was low, the cumulative risk was substantial enough to warrant vigilance. Tamoxifen exposure was significantly predictive of EC, particularly T2EC, and might facilitate risk estimation. Older women at BC diagnosis who receive tamoxifen treatment should be screened and closely monitored for EC. However, given the limitations of normal screening methods for the detection of T2EC, counseling for a prophylactic hysterectomy should also be considered. Clarification of the menopausal status will help make more meaningful recommendations.

Machine Learning-Based Risk Prediction of Critical Care Unit Admission for Advanced Stage High Grade Serous Ovarian Cancer Patients Undergoing Cytoreductive Surgery: The Leeds-Natal Score.

Achieving complete surgical cytoreduction in advanced stage high grade serous ovarian cancer (HGSOC) patients warrants an availability of Critical Care Unit (CCU) beds. Machine Learning (ML) could be helpful in monitoring CCU admissions to improve standards of care. We aimed to improve the accuracy of predicting CCU admission in HGSOC patients by ML algorithms and developed an ML-based predictive score. A cohort of 291 advanced stage HGSOC patients with fully curated data was selected. Several linear and non-linear distances, and quadratic discriminant ML methods, were employed to derive prediction information for CCU admission. When all the variables were included in the model, the prediction accuracies were higher for linear discriminant (0.90) and quadratic discriminant (0.93) methods compared with conventional logistic regression (0.84). Feature selection identified pre-treatment albumin, surgical complexity score, estimated blood loss, operative time, and bowel resection with stoma as the most significant prediction features. The real-time prediction accuracy of the Graphical User Interface CCU calculator reached 95%. Limited, potentially modifiable, mostly intra-operative factors contributing to CCU admission were identified and suggest areas for targeted interventions. The accurate quantification of CCU admission patterns is critical information when counseling patients about peri-operative risks related to their cytoreductive surgery.

Predicting complete cytoreduction for advanced ovarian cancer patients using nearest-neighbor models.

BACKGROUND: The foundation of modern ovarian cancer care is cytoreductive surgery to remove all macroscopic disease (R0). Identification of R0 resection patients may help individualise treatment. Machine learning and AI have been shown to be effective systems for classification and prediction. For a disease as heterogenous as ovarian cancer, they could potentially outperform conventional predictive algorithms for routine clinical use. We investigated the performance of an AI system, the k-nearest neighbor (k-NN) classifier, to predict R0, comparing it with logistic regression. Patients diagnosed with advanced stage, high grade serous ovarian, tubal and primary peritoneal cancer, undergoing surgical cytoreduction from 2015 to 2019, was selected from the ovarian database. Performance variables included age, BMI, Charlson Comorbidity Index, timing of surgery, surgical complexity and disease score. The k-NN algorithm classified R0 vs non-R0 patients using 3-20 nearest neighbors. Prediction accuracy was estimated as percentage of observations in the training set correctly classified. RESULTS: 154 patients were identified, with mean age of 64.4 + 10.5 yrs., BMI of 27.2 + 5.8 and mean SCS of 3 + 1 (1-8). Complete and optimal cytoreduction was achieved in 62 and 88% patients. The mean predictive accuracy was 66%. R0 resection prediction of true negatives was as high as 90% using k = 20 neighbors. CONCLUSIONS: The k-NN algorithm is a promising and versatile tool for R0 resection prediction. It slightly outperforms logistic regression and is expected to improve accuracy with data expansion.

5-Flouorouracil Is an Attractive Medical Treatment in Women With Vaginal Intraepithelial Neoplasia: A Meta-Analysis.

OBJECTIVE: In the absence of standard guidelines, the management of vaginal intraepithelial neoplasia (VaIN) remains a field of debate. The aim of this systematic review and meta-analysis was to ascertain the 5-flouorouracil (5-FU) effectiveness in this context. MATERIALS AND METHODS: A literature search was conducted throughout the PubMed, EMBASE, SCOPUS, ClinicalTrials.gov, and Cochrane Databases for relevant studies. We computed the summary proportions of women treated for VaIN with 5-FU for the outcomes of complete response and recurrence by random-effects meta-analysis. We also performed a subgroup analysis by computing the summary proportions for complete response among women with high-grade VaIN, persistent disease, and recurrence respectively. RESULTS: Fourteen observational studies reporting on 358 women included in the study. The study quality was moderate. The summary proportions of women who had complete response after the first 5-FU course were 82.18% (95% CI = 69.80%-88.82%). The summary proportions of women who recurred were 16.42% (95% CI = 7.39%-28.14%). The summary proportions of women with complete response in the high-grade VaIN, persistent disease, and recurrence subgroups were 77.53% (95% CI = 59.90%-91.15%), 53.92% (95% CI = 34.62%-72.61%), and 72.32% (95% CI = 48.12%-91.05%), respectively. CONCLUSIONS: This is the first meta-analysis to date to provide a convincing overview of 5-FU efficacy on the VaIN treatment. Albeit a medium risk of bias warrants some caution with interpretation of the results, 5-FU can be an attractive alternative to surgery, especially among young women with multifocal and recurrent disease.

Synchrotron- and focal plane array-based Fourier-transform infrared spectroscopy differentiates the basalis and functionalis epithelial endometrial regions and identifies putative stem cell regions of human endometrial glands.

The cyclical process of regeneration of the endometrium suggests that it may contain a cell population that can provide daughter cells with high proliferative potential. These cell lineages are clinically significant as they may represent clonogenic cells that may also be involved in tumourigenesis as well as endometriotic lesion development. To determine whether the putative stem cell location within human uterine tissue can be derived using vibrational spectroscopy techniques, normal endometrial tissue was interrogated by two spectroscopic techniques. Paraffin-embedded uterine tissues containing endometrial glands were sectioned to 10-µm-thick parallel tissue sections and were floated onto BaF2 slides for synchrotron radiation-based Fourier-transform infrared (SR-FTIR) microspectroscopy and globar focal plane array-based FTIR spectroscopy. Different spectral characteristics were identified depending on the location of the glands examined. The resulting infrared spectra were subjected to multivariate analysis to determine associated biophysical differences along the length of longitudinal and crosscut gland sections. Comparison of the epithelial cellular layer of transverse gland sections revealed alterations indicating the presence of putative transient-amplifying-like cells in the basalis and mitotic cells in the functionalis. SR-FTIR microspectroscopy of the base of the endometrial glands identified the location where putative stem cells may reside at the same time pointing towards νsPO2- in DNA and RNA, nucleic acids and amide I and II vibrations as major discriminating factors. This study supports the view that vibration spectroscopy technologies are a powerful adjunct to our understanding of the stem cell biology of endometrial tissue. Graphical abstract ᅟ.

An imaging dataset of cervical cells using scanning near-field optical microscopy coupled to an infrared free electron laser.

Using a scanning near-field optical microscope coupled to an infrared free electron laser (SNOM-IR-FEL) in low-resolution transmission mode, we collected chemical data from whole cervical cells obtained from 5 pre-menopausal, non-pregnant women of reproductive age, and cytologically classified as normal or with different grades of cervical cell dyskaryosis. Imaging data are complemented by demography. All samples were collected before any treatment. Spectra were also collected using attenuated total reflection, Fourier-transform (ATR-FTIR) spectroscopy, to investigate the differences between the two techniques. Results of this pilot study suggests SNOM-IR-FEL may be able to distinguish cervical abnormalities based upon changes in the chemical profiles for each grade of dyskaryosis at designated wavelengths associated with DNA, Amide I/II, and lipids. The novel data sets are the first collected using SNOM-IR-FEL in transmission mode at the ALICE facility (UK), and obtained using whole cells as opposed to tissue sections, thus providing an 'intact' chemical profile. These data sets are suited to complementing future work on image analysis, and/or applying the newly developed algorithm to other datasets collected using the SNOM-IR-FEL approach.

Tracking the Impact of Excisional Cervical Treatment on the Cervix using Biospectroscopy.

Local excisional treatment for cervical intra-epithelial neoplasia (CIN) is linked to significant adverse sequelae including preterm birth, with cone depth and radicality of treatment correlating to the frequency and severity of adverse events. Attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy can detect underlying cervical disease more accurately than conventional cytology. The chemical profile of cells pre- and post-treatment may differ as a result of altered biochemical processes due to excision, or treatment of the disease. Since pre-treatment cervical length varies amongst women, the percentage of cervix excised may correlate more accurately to risk than absolute dimensions. We show that treatment for CIN significantly alters the biochemistry of the cervix, compared with women who have not had treatment; this is due to the removal of cervical tissue rather than the removal of the disease. However, the spectra do not seem to correlate to the cone depth or proportion of cervical length excised. Future research should aim to explore the impact of treatment in a larger cohort.