Danielle Vicus

Background: Folate receptor alpha (FRα), commonly expressed in epithelial ovarian cancers, is a clinically actionable biomarker following approval of the antibody–drug conjugate mirvetuximab soravtansine (MIRV). Pivotal trials showed that high FRα expression predicts MIRV benefit, creating the need for standardized testing to ensure timely, equitable access. Methods: To address the need for guidance on FRα testing, the Society of Gynecologic Oncology of Canada convened a multidisciplinary Expert Panel to review the evidence and integrate Canadian clinical, pathology, laboratory, and patient perspectives. Consensus recommendations were developed through structured evidence review, expert discussion, iterative revision, and patient partner input. Results: The panel issued recommendations on the clinical role and timing of FRα testing, tissue requirements, assay selection and validation, interpretation and reporting standards, laboratory quality assurance, reimbursement, and equitable access. It is recommended that FRα testing be available to all patients with epithelial ovarian cancer, with results available no later than platinum-resistant disease, using a validated assay, preferably the Ventana FOLR1 RxDx assay or an appropriately validated laboratory-developed test. Standardized synoptic reporting, participation in external quality assurance programs, and clear patient communication were deemed essential. Conclusions: These recommendations aim to promote integrated, equitable, standardized FRα testing across Canada and support timely identification of patients eligible for FRα-directed therapy, clinical trial enrollment, and future biomarker-driven treatment strategies.

Surgical site infections (SSIs) occur in 10–15% of patients and are linked to up to 29% of delays in starting adjuvant treatment. This study assessed the association between SSIs in patients with ovarian and uterine cancer and their impact on time to adjuvant therapy and oncologic outcomes. Patients who underwent surgery from 1 January 2015 to 30 September 2017 were included, using institutional National Surgical Quality Improvement Program (NSQIP) data and chart reviews. Among 371 patients (median follow-up 4.1 years), 243 (65.5%) received adjuvant treatment. The median time to start was 39 days for chemotherapy, 61 days for radiotherapy, and 42 days for combined therapy (p < 0.001). Patients with ovarian cancer began treatment sooner than those with uterine cancer (39 vs. 52 days, p < 0.001), but no significant difference was observed between those with or without SSIs. In 238 patients with uterine cancer, those with SSIs had a twofold higher recurrence risk (HR 1.97, p = 0.022) and over threefold lower overall survival (HR 3.45, p = 0.018). Multivariable analysis showed that surgical route and disease stage were independent predictors; SSI was not an independent factor. No survival difference related to SSIs was found in patients with ovarian cancer. Further research is needed to clarify the impact of SSIs on treatment timing and recurrence.

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.

Objective To review the literature on machine learning in endometrial cancer, report the most commonly used algorithms, and compare performance with traditional prediction models. Methods This is a systematic review of the literature from January 1985 to March 2021 on the use of machine learning in endometrial cancer. An extensive search of electronic databases was conducted. Four independent reviewers screened studies initially by title then full text. Quality was assessed using the MINORS (Methodological Index for Non-Randomized Studies) criteria. P values were derived using the Pearson’s Χ² test in JMP 15.0. Results Among 4295 articles screened, 30 studies on machine learning in endometrial cancer were included. The most frequent applications were in patient datasets (33.3%, n=10), pre-operative diagnostics (30%, n=9), genomics (23.3%, n=7), and serum biomarkers (13.3%, n=4). The most commonly used models were neural networks (n=10, 33.3%) and support vector machine (n=6, 20%). The number of publications on machine learning in endometrial cancer increased from 1 in 2010 to 29 in 2021.Eight studies compared machine learning with traditional statistics. Among patient dataset studies, two machine learning models (20%) performed similarly to logistic regression (accuracy: 0.85 vs 0.82, p=0.16). Machine learning algorithms performed similarly to detect endometrial cancer based on MRI (accuracy: 0.87 vs 0.82, p=0.24) while outperforming traditional methods in predicting extra-uterine disease in one serum biomarker study (accuracy: 0.81 vs 0.61). For survival outcomes, one study compared machine learning with Kaplan-Meier and reported no difference in concordance index (83.8% vs 83.1%). Conclusion Although machine learning is an innovative and emerging technology, performance is similar to that of traditional regression models in endometrial cancer. More studies are needed to assess its role in endometrial cancer. PROSPERO registration number CRD42021269565.

Minimally invasive surgery for the treatment of macroscopic cervical cancer leads to worse oncologic outcomes than with open surgery. Preoperative conization may mitigate the risk of surgical approach. Our objective was to describe the oncologic outcomes in cases of cervical cancer initially treated with conization, and subsequently found to have no residual cervical cancer after hysterectomy performed via open and minimally invasive approaches. This was a retrospective cohort study of surgically treated cervical cancer at 11 Canadian institutions from 2007 to 2017. Cases initially treated with cervical conization and subsequent hysterectomy, with no residual disease on hysterectomy specimen were included. They were subdivided according to minimally invasive (laparoscopic/robotic (MIS) or laparoscopically assisted vaginal/vaginal hysterectomy (LVH)), or abdominal (AH). Recurrence free survival (RFS) and overall survival (OS) were estimated using Kaplan–Meier analysis. Chi-square and log-rank tests were used to compare between cohorts. Within the total cohort, 238/1696 (14%) had no residual disease on hysterectomy specimen (122 MIS, 103 AH, and 13 VLH). The majority of cases in the cohort were FIGO 2018 stage IB1 (43.7%) and underwent a radical hysterectomy (81.9%). There was no statistical difference between stage, histology, and radical vs simple hysterectomy between the abdominal and minimally invasive groups. There were no significant differences in RFS (5-year: MIS/LVH 97.7%, AH 95.8%, p = 0.23) or OS (5-year: MIS/VLH 98.9%, AH 97.4%, p = 0.10), although event-rates were low. There were only two recurrences. In this large study including only patients with no residual cervical cancer on hysterectomy specimen, no significant differences in survival were seen by surgical approach. This may be due to the small number of events or due to no actual difference between the groups. Further studies are warranted.