Advanced ovarian cancer and cytoreductive surgery: Independent validation of a risk-calculator for perioperative adverse events

Prediction of Clavien Dindo Classification ≥ Grade III Complications After Epithelial Ovarian Cancer Surgery Using Machine Learning Methods

Background and Objectives: Ovarian cancer surgery requires multiple radical resections with a high risk of complications. The aim of this single-centre, retrospective study was to determine the best method for predicting Clavien-Dindo grade ≥ III complications using machine learning techniques. Material and Methods: The study included 179 patients who underwent surgery at the gynaecological oncology department of Antalya Training and Research Hospital between January 2015 and December 2020. The data were randomly split into training set n = 134 (75%) and test set n = 45 (25%). We used 49 predictors to develop the best algorithm. Mean absolute error, root mean squared error, correlation coefficients, Mathew's correlation coefficient, and F1 score were used to determine the best performing algorithm. Cohens' kappa value was evaluated to analyse the consistency of the model with real data. The relationship between these predicted values and the actual values were then summarised using a confusion matrix. True positive (TP) rate, False positive (FP) rate, precision, recall, and Area under the curve (AUC) values were evaluated to demonstrate clinical usability and classification skills. Results: 139 patients (77.65%) had no morbidity or grade I-II CDC morbidity, while 40 patients (22.35%) had grade III or higher CDC morbidity. BayesNet was found to be the most effective prediction model. No dominant parameter was observed in the Bayesian net importance matrix plot. The true positive (TP) rate was 76%, false positive (FP) rate was 15.6%, recall rate (sensitivity) was 76.9%, and overall accuracy was 82.2% A receiver operating characteristic (ROC) analysis was performed to estimate CDC grade ≥ III. AUC was 0.863 with a statistical significance of p < 0.001, indicating a high degree of accuracy. Conclusions: The Bayesian network model achieved the highest accuracy compared to all other models in predicting CDC Grade ≥ III complications following epithelial ovarian cancer surgery.

Predicting Response to Treatment and Survival in Advanced Ovarian Cancer Using Machine Learning and Radiomics: A Systematic Review

Background and Objective: Machine learning and radiomics (ML/RM) are gaining interest in ovarian cancer (OC) but only a few studies have used these methods to predict treatment response. The objective of this study was to review the literature on the applications of ML/RM in OC assessments, specifically focusing on studies describing algorithms to predict treatment response and survival. Methods: This is a systematic review of the published literature from January 1985 to December 2023 on the use of ML/RM in OC An extensive search of electronic library databases was conducted. Two independent reviewers screened the articles initially by title then by full text. Quality was assessed using the MINORS criteria. p-values were generated using the Pearson's Chi-squared (x2) test to compare the performances of ML/RM models with traditional statistics. Results: Of the 5576 screened articles, 225 studies were included. Between 2021 and 2023, 49 studies were published, highlighting the rapidly growing interest in ML/RM. Median-quality scores using the MINORS scale were similar between studies published between 1985-2021 and 2021-2023 (both 8). Neural Networks (22.6%) and LASSO (15.3%) were the most common ML/RM algorithms in OC. Among these studies, 13 focused specifically on prediction of treatment response using radiomics. A total of 5113 patients were analyzed. The most common algorithms were Random Forest (4/13) followed by Neural Networks (3/13) and Support Vectors (3/13). Radiomic analysis was used to predict response to neoadjuvant chemotherapy in seven studies, with a median AUC of 0.77 (range 0.72-0.93), while the median AUC was 0.82 (range 0.77-0.89) in the six studies assessing the prediction of optimal or complete cytoreduction. Median model accuracy reported in 7/13 studies was 73% (range 66-98%). Additionally, four studies investigated the use of ML/RM for survival prediction for OC. The XGBoost model had 80.9% accuracy in predicting 5-year survival compared to linear regression, which achieved 79% accuracy. The Random Forest model has 93.7% accuracy in predicting 12-month progression-free survival, compared to 82% for linear regression. Conclusions: In conclusion, we found that the use of ML/RM algorithms is becoming a more frequent method to predict responses to treatment of OC. These models should be validated in a prospective multicenter trial prior to integration into clinical use.

Assessment of the American College of Surgeons Surgical Risk Calculator (ACS-SRC) for Prediction of Early Postoperative Complications in Patients Undergoing Cytoreductive Surgery for Ovarian Peritoneal Carcinomatosis

Ovarian cancer (OC) is diagnosed at a locally advanced stage in two-thirds of cases. The first line of treatment consists of cytoreductive surgery (CRS) combined with neoadjuvant and/or adjuvant chemotherapy. However, CRS can be associated with high rates of postoperative complications (POCs), and detection of fragile patients at high risk of POCs is important. The American College of Surgeons Surgical Risk Calculator (ACS-SRC) provides a predictive model for early POCs (30 days) for any given surgical procedure. This study aimed to evaluate the performance of the ACS-SRC in predicting the occurrence of early POCs for patients undergoing CRS for OC. This was a retrospective study that included patients undergoing CRS for advanced OC between January 2010 and December 2022. Early POCs were reviewed, and the rate of POCs was compared with those predicted by the ACS-SRC to evaluate its accuracy (i.e., discrimination and calibration). A total of 218 patients were included, 112 of whom underwent extensive surgery/resection. A total of 94 complications were recorded. This cohort demonstrated correct calibration of the ACS-SRC for the prediction of surgical site infection, readmission, and the need for nursing care post-discharge (NCPD; transfer to revalidation center or need for nursing care at home). Using both the discrimination and calibration methods, the score only predicted NCPD. In this study, the ACS-SRC was shown to be of little value for patients undergoing cytoreductive surgery for ovarian peritoneal carcinomatosis, as it only accurately predicted NCPD.

New Insights into the Assessment of Peri-Operative Risk in Women Undergoing Surgery for Gynecological Neoplasms: A Call for a New Tool

Existing tools for predicting postoperative complications in women undergoing surgery for gynecological neoplasms are evaluated in this narrative review. Although surgery is a very efficient therapy for gynecological tumors, it is not devoid of the possibility of negative postoperative outcomes. Widely used tools at present, such as the Surgical Apgar Score and the Modified Frailty Index, fail to consider the complex characteristics of gynecological malignancies and their related risk factors. A thorough search of the PubMed database was conducted for our review, specifically targeting studies that investigate several aspects impacting postoperative outcomes, including nutritional status, obesity, albumin levels, sodium levels, fluid management, and psychological well-being. Research has shown that both malnutrition and obesity have a substantial impact on postoperative mortality and morbidity. Diminished sodium and albumin levels together with compromised psychological well-being can serve as reliable indicators of negative consequences. The role of appropriate fluid management in enhancing patient recovery was also investigated. The evidence indicates that although current mechanisms are useful, they have limitations in terms of their range and do not thoroughly address these recently identified risk factors. Therefore, there is a need for a new, more comprehensive tool that combines these developing elements to more accurately forecast postoperative problems and enhance patient results in gynecological oncology. This paper highlights the need to create such a tool to improve clinical practice and the treatment of patients.

Predictive value of the Adult Comorbidity Evaluation 27 on adverse surgical outcomes and survival in elderly with advanced epithelial ovarian cancer undergoing cytoreductive surgery

OBJECTIVE

We aimed to evaluate the ability of Adult Comorbidity Evaluation 27 (ACE-27) to predict perioperative outcomes and survival in elderly women with advanced epithelial ovarian cancer (AEOC) undergoing cytoreductive surgery.

METHODS

We collected patients with AEOC in our hospital between January 1, 2012 and January 1, 2021. Patients younger than 65 years old or those with non-epithelial ovarian cancer were excluded. ACE-27 was applied retrospectively to assess comorbidities in the selected patients, who were then classified into two groups based on their ACE-27 scores: low ACE-27 score group (none to mild) and high ACE-27 score group (moderate to severe).

RESULTS

A total of 222 elderly women with AEOC were included, of whom 164 patients accepted debulking surgery. Among those who have undergone surgery, Clavien-Dindo grade III + perioperative complications or unintended intensive care unit (ICU) admission occurred more often in patients of high ACE-27 score group, with statistically significant difference (odds ratio [OR]: 4.21, 95% confidence interval [CI], 1.28-14.35, p = 0.018). Further stratified analyses by age, BMI, FIGO stage and pathology also prove that OS of patients graded severe was shorter than patients graded none to moderate in cohort of age < 70, BMI < 25 kg/m2, FIGO III stage and pathology of serous, respectively. Kaplan-Meier survival curves analyzed by log-rank test showed that the overall survival (OS) of patients with severe comorbidities were shorter than with none to moderate (HR 3.25, 95%CI 1.55-6.79, p = 0.002).

CONCLUSIONS

Our findings demonstrate the ability of ACE-27 to predict grade III + perioperative complications or unintended ICU admission and survival in elderly patients with AEOC. This highlights the possibility for ACE-27 to play an instrumental role in identifying AEOC patients who are more susceptible to adverse surgical outcomes and have a poor survival rate and assisting in decisions regarding treatment.

Impact of postoperative morbidity on outcomes in patients with advanced epithelial ovarian cancer undergoing intestinal surgery at the time of primary or interval cytoreductive surgery: A Memorial Sloan Kettering Cancer Center Team Ovary study

OBJECTIVE

To assess the impact of short-term postoperative complications on oncologic outcomes for patients with epithelial ovarian cancer undergoing primary cytoreductive surgery (PCS) or interval cytoreductive surgery (ICS) with intestinal resection.

METHODS

A retrospective chart review was performed for patients with ovarian cancer who underwent PCS or ICS with at least one intestinal resection at our institution from 1/1/2015 to 12/31/2020. Progression-free survival (PFS) and overall survival (OS) were analyzed for the PCS and ICS cohorts separately. Short-term complications within 30 days of surgery (surgical secondary events [SSEs]) were graded by a validated institutional SSE system.

RESULTS

Among 437 patients who underwent intestinal resections during PCS (n = 289) or ICS (n = 148), 183 (42%) had one, 180 (41%) had two, and 74 (17%) had three intestinal resections. Six (1.4%) of 437 patients experienced an anastomotic leak postoperatively. There were no perioperative deaths. There was no difference in PFS and OS for patients who underwent PCS with any SSE vs. no SSE within 30 days of surgery (HR, 1.05; 95% CI: 0.76-1.47; p = 0.75 and HR, 0.79; 95% CI: 0.49-1.26; p = 0.32, respectively). There was no difference in PFS and OS for patients who underwent ICS with any SSE vs. no SSE within 30 days of surgery (HR, 1.43; 95% CI: 0.99-2.07; p = 0.055 and HR. 1.18; 95% CI: 0.72-1.93; p = 0.52, respectively.

CONCLUSION

Short-term postoperative morbidity for patients who underwent intestinal surgery during primary surgical management for advanced ovarian cancer did not impact oncologic outcomes.

Predicting Neoadjuvant Chemotherapy Response and High-Grade Serous Ovarian Cancer From CT Images in Ovarian Cancer with Multitask Deep Learning: A Multicenter Study

RATIONALE AND OBJECTIVES

Accurate prediction neoadjuvant chemotherapy (NACT) response in ovarian cancer (OC) is essential for personalized medicine. We aimed to develop and validate a deep learning (DL) model based on pretreatment contrast-enhanced CT (CECT) images for predicting NACT responses and classifying high-grade serous ovarian cancer (HGSOC) to identify patients who may benefit from NACT.

MATERIALS AND METHODS

This multicenter study, which contained both retrospective and prospective studies, included consecutive OC patients (n = 757) from three hospitals. Using WHO RECIST 1.1 for the reference standard, a total of 587 women with 1761 images were included in the training and validation sets, 67 women with 201 images were included in the prospective sets, and 103 women with 309 images were included in the external sets. A multitask DL model based on the multiperiod CT image was developed to predict NACT response and HGSOC.

RESULTS

Logistic regression analysis showed that peritoneal invasion, retinal invasion, and inguinal lymph node metastasis were independent predictors. The DL achieved promising segmentation performances with DICEmean= 0.83 (range: 0.78-0.87). For predicting NACT response, the DL model combined with clinical risk factors obtained area under the receiver operating characteristic curve (AUCs) of 0.87 (0.83-0.89), 0.88 (0.86-0.91), 0.86 (0.82-0.89), and 0.79 (0.75-0.82) in the training, validation, prospective, and external sets, respectively. The AUCs were 0.91 (0.87-0.94), 0.89 (0.86-0.91), 0.80 (0.76-0.84), and 0.80 (0.75-0.85) in four sets in HGSOC classification.

CONCLUSION

The multitask DL model developed using multiperiod CT images exhibited a promising performance for predicting NACT response and HGSOC with OC, which could provide valuable information for individualized treatment.

The KORE-INNOVATION trial, a prospective controlled multi-site clinical study to implement and assess the effects of an innovative peri-operative care pathway for patients with ovarian cancer: rationale, methods and trial design

BACKGROUND

Advanced ovarian cancer is managed by extensive surgery, which could be associated with high morbidity. A personalized pre-habilitation strategy combined with an 'enhanced recovery after surgery' (ERAS) pathway may decrease post-operative morbidity.

PRIMARY OBJECTIVE

To analyze the effects of a combined multi-modal pre-habilitation and ERAS strategy on severe post-operative morbidity for patients with ovarian cancer (primary diagnosis or first recurrence) undergoing cytoreductive surgery.

STUDY HYPOTHESIS

A personalized multi-modal pre-habilitation algorithm entailing a physical fitness intervention, nutritional and psycho-oncological support, completed by an ERAS pathway, reduces post-operative morbidity.

TRIAL DESIGN

This is a prospective, controlled, non-randomized, open, interventional two-center clinical study. Endpoints will be compared with a three-fold control: (a) historic control group (data from institutional ovarian cancer databases); (b) prospective control group (assessed before implementing the intervention); and (c) matched health insurance controls.

INCLUSION CRITERIA

Patients with ovarian, fallopian, or primary peritoneal cancer undergoing primary surgical treatment (primary ovarian cancer or first recurrence) can be included. The intervention group receives an additional multi-level study treatment: (1) standardized frailty assessment followed by (2) a personalized tri-modal pre-habilitation program and (3) peri-operative care according to an ERAS pathway.

EXCLUSION CRITERIA

Inoperable disease or neoadjuvant chemotherapy, simultaneous diagnosis of simultaneous primary tumors, in case of interference with the overall prognosis (except for breast cancer); dementia or other conditions that impair compliance or prognosis.

PRIMARY ENDPOINT

Reduction of severe post-operative complications (according to Clavien- Dindo Classification (CDC) III-V) within 30 days after surgery.

SAMPLE SIZE

Intervention group (n=414, of which approximately 20% insure with the participating health insurance); historic control group (n=198); prospective control group (n=50), health insurance controls (for those intervention patients who are members of the participating health insurance).

ESTIMATED DATES FOR COMPLETING ACCRUAL AND PRESENTING RESULTS

The intervention phase started in December 2021 and will continue until June 2023. As of March 2023, 280 patients have been enrolled in the intervention group. The expected completion of the entire study is September 2024.

TRIAL REGISTRATION

NCT05256576.

Validation of a risk-based algorithm to reduce poor operative outcomes after complex surgery for ovarian cancer

OBJECTIVE

We developed an algorithm that identifies patients at high risk of morbidity/mortality after cytoreductive surgery for advanced ovarian cancer. We have previously shown that the Mayo triage algorithm reduces operative mortality internally, followed by validation using an external low complexity national dataset. However, validation in a higher complexity surgical setting is required before widespread acceptance of this approach, and this was the goal of our study.

METHODS

We included patients who underwent debulking surgery (including primary or interval debulking surgery) for stage IIIC/IV ovarian cancer between October 2011 and November 2019 (SCORPION trial patients until May 2016 and non-trial patients thereafter) at Fondazione Policlinico A Gemelli, Italy. Using the algorithm, we classified patients as either high-risk or triage-appropriate and compared 30-day grade 3+ complications and 90-day mortality using a χ2 test or Fisher's exact test.

RESULTS

A total of 625 patients were included. The mean age was 58.7±11.4 years, 73.6% (n=460) were stage IIIC, and 63.0% (n=394) underwent primary debulking surgery. Surgical complexity was intermediate or high in 82.6% (n=516) of patients (95.7% (n=377) for primary surgery and 60.2% (n=139) for interval surgery), and 20.3% (n=127) were classified as high-risk. When compared with triage-appropriate patients, high-risk patients had (1) a threefold higher rate of 90-day mortality (6.3% vs 2.0%, p=0.02); (2) a higher likelihood of 90-day mortality following a grade 3+ complication (25.9% vs 10.0%, p=0.05); and (3) comparable rates of grade 3+ complications (21.3% vs 16.1%, p=0.17).

CONCLUSION

The evidence-based triage algorithm identifies patients at high risk of morbidity/mortality after cytoreductive surgery. Triage high-risk patients are poor candidates for surgery when complex surgery is required. This algorithm has been validated in heterogeneous settings (internal, national, and international) and degree of surgical complexity. Risk-based decision making should be standard of care when planning surgery for patients with advanced ovarian cancer, whether primary or interval surgery.

Integrated prediction model of patient factors, resectability scores and surgical complexity to predict cytoreductive outcome and guide treatment plan in advanced ovarian cancer

OBJECTIVE

To report performance of an integrated predictive model (IPM) algorithm based on patient factors, surgical resectability and surgical complexity to predict outcome of primary cytoreductive surgery (PCS) and guide treatment plan in patients with advanced epithelial ovarian cancer (AEOC).

METHODS

Patients with AEOC between October 2018 and October 2020 were enrolled into a dedicated AEOC program and decision for PCS or neoadjuvant chemotherapy (NACT) was based on multidisciplinary consensus. Data of unresectable stage IVb, patient factors (PF), surgical resectability scores (SRS) and surgical complexity scores (SCS) was prospectively documented. An integrated prediction model (IPM) was developed to predict outcome of optimal (RD < 1 cm) cytoreduction. Retrospective analysis was performed to assess the performance of the IPM. Cut-offs were selected using the Youden Index.

RESULTS

Of 185 eligible patients, 81 underwent PCS and 104 were treated with NACT. Patients undergoing PCS had significantly lower median PF (0 vs 2, p < 0.01), SRS (2 vs 4, p < 0.01) and pre-operative SCS (6 vs 8.5, p = 0.01) compared to NACT. In patients undergoing PCS, 88% had optimal cytoreduction and 34.5% had grade 3-4 post-operative complications. A model triaging patients with unresectable Stage IVb, PF > 2, SRS > 5 and SCS > 9 to NACT had 85% sensitivity, 75% specificity and 85% accuracy for outcome of optimal cytoreduction. Our model would have improved triage of 3/10 sub-optimally cytoreduced patients to NACT. For outcome of no-gross residual disease (RD = 0 mm) using the same cut-offs sensitivity and specificity were 85% and 76% respectively.

CONCLUSION

The 4-step IPM algorithm had high sensitivity and specificity for optimal cytoreduction with acceptable morbidity without delay to adjuvant therapy. This algorithm may be used to triage patients to PCS or NACT once it is further validated.

Applying low coverage whole genome sequencing to detect malignant ovarian mass

To evaluate whether low coverage whole genome sequencing is suitable for the detection of malignant pelvic mass and compare its diagnostic value with traditional tumor markers. We enrolled 63 patients with a pelvic mass suspicious for ovarian malignancy. Each patient underwent low coverage whole genome sequencing (LCWGS) and traditional tumor markers test. The pelvic masses were finally confirmed via pathological examination. The copy number variants (CNVs) of whole genome were detected and the Stouffers Z-scores for each CNV was extracted. The risk of malignancy (RM) of each suspicious sample was calculated based on the CNV counts and Z-scores, which was subsequently compared with ovarian cancer markers CA125 and HE4, and the risk of ovarian malignancy algorithm (ROMA). Receiver Operating Characteristic Curve (ROC) were used to access the diagnostic value of variables. As confirmed by pathological diagnosis, 44 (70%) patients with malignancy and 19 patients with benign mass were identified. Our results showed that CA125 and HE4, the CNV, the mean of Z-scores (Zmean), the max of Z-scores (Zmax), the RM and the ROMA were significantly different between patients with malignant and benign masses. The area under curve (AUC) of CA125, HE4, CNV, Zmax, and Zmean was 0.775, 0.866, 0.786, 0.685 and 0.725 respectively. ROMA and RM showed similar AUC (0.876 and 0.837), but differed in sensitivity and specificity. In the validation cohort, the AUC of RM was higher than traditional serum markers. In conclusion, we develop a LCWGS based method for the identification of pelvic mass of suspicious ovarian cancer. LCWGS shows accurate result and could be complementary with the existing diagnostic methods.