Giulia Parpinel

The Use of Artificial Intelligence for Complete Cytoreduction Prediction in Epithelial Ovarian Cancer: A Narrative Review

Introduction In patients affected by epithelial ovarian cancer (EOC) complete cytoreduction (CC) has been associated with higher survival outcomes. Artificial intelligence (AI) systems have proved clinical benefice in different areas of healthcare. Objective To systematically assemble and analyze the available literature on the use of AI in patients affected by EOC to evaluate its applicability to predict CC compared to traditional statistics. Material and Methods Data search was carried out through PubMed, Scopus, Ovid MEDLINE, Cochrane Library, EMBASE, international congresses and clinical trials. The main search terms were: Artificial Intelligence AND surgery/cytoreduction AND ovarian cancer. Two authors independently performed the search by October 2022 and evaluated the eligibility criteria. Studies were included when data about Artificial Intelligence and methodological data were detailed. Results A total of 1899 cases were analyzed. Survival data were reported in 2 articles: 92% of 5-years overall survival (OS) and 73% of 2-years OS. The median area under the curve (AUC) resulted 0,62. The model accuracy for surgical resection reported in two articles reported was 77,7% and 65,8% respectively while the median AUC was 0,81. On average 8 variables were inserted in the algorithms. The most used parameters were age and Ca125. Discussion AI revealed greater accuracy compared against the logistic regression models data. Survival predictive accuracy and AUC were lower for advanced ovarian cancers. One study analyzed the importance of factors predicting CC in recurrent epithelial ovarian cancer and disease free interval, retroperitoneal recurrence, residual disease at primary surgery and stage represented the main influencing factors. Surgical Complexity Scores resulted to be more useful in the algorithms than pre-operating imaging. Conclusion AI showed better prognostic accuracy if compared to conventional algorithms. However further studies are needed to compare the impact of different AI methods and variables and to provide survival informations.

Prognostic and predictive value of combined HE-4 and CA-125 biomarkers during chemotherapy in patients with epithelial ovarian cancer

Introduction: At present there is no predictive value univocally associated with the success of chemotherapy. Biomarkers produced by ovarian cancer (HE4 and Ca125) could have a good prognostic significance. The aim of this study is to prove the ability of biomarkers to identify patients with the highest risk of non-optimal response during the chemotherapy, and to predict which patients will most likely develop recurrence of disease. Methods: We analyzed 78 patients with epithelial ovarian cancers who underwent surgery in the biennium 2016–2017. All the patients underwent chemotherapy after surgery or interval debulking surgery following neoadjuvant therapy. Serum levels of HE4 and Ca125 were measured at diagnosis and at each cycle of chemotherapy. We established the degree of response to the treatment by computed tomography scan, and the patients were followed up (median: 10 months). The parameters of progression-free survival and disease-free survival were related to serum levels of biomarkers. Results: Both CA125 and HE4 values became negative at the fourth cycle in the patients with good response to chemotherapy. HE4 increased earlier than Ca125. The parameters that best correlated with a long progression-free survival were: negativization of the marker after the third cycle of chemotherapy (HE4: odds ratio (OR) 5.5; Ca125: OR 9.1) and biomarker serum levels lower than the mean value in the affected population at the time of diagnosis (HE4: OR 3.4; Ca125: OR 3.7). Conclusions: We can conclude that the monitoring of HE4 and Ca125 during chemotherapy, especially at the third cycle, is recommended, because their variation is a good prognostic factor.

Survival after sentinel lymph node biopsy for early cervical cancers: a systematic review and meta-analysis

Sentinel lymph node biopsy represents an alternative to pelvic lymphadenectomy for lymph node staging of early-stage cervical carcinoma, but prospective evidence on long-term oncological safety of sentinel lymph node biopsy alone versus pelvic lymphadenectomy is missing. To investigate, with this meta-analysis, the impact of sentinel lymph node biopsy alone versus pelvic lymphadenectomy on survival for patients with early-stage cervical cancer. A systematic literature review was performed. We excluded studies in which pelvic lymphadenectomy was systematically performed after every sentinel lymph node biopsy, including only articles where pelvic lymphadenectomy was performed because sentinel lymph node biopsy was not conclusive. A meta-analysis was carried out combining 5-year disease-free survival and overall survival rates with a random and fixed effect model. Heterogeneity was tested using the Cochran Χ The search of databases and registers found 927 items and six articles (two retrospective and four prospective). The median time of follow-up was 34.8 months (range 13-53). Overall common effect disease-free survival was 98% while random effect disease-free survival was 94%. Overall heterogeneity was 77%. A subgroup analysis was applied, dividing studies into one group including sentinel lymph node biopsy negative data only (common effect disease-free survival 91%; random effect disease-free survival 90%), and one group with a negative and positive sentinel lymph node biopsy (common effect disease-free survival 98%; random effect disease-free survival 96%). In the analysis of overall survival, positive and negative sentinel lymph node biopsy cases were examined together (common and random effect overall survival 99%). Ultrastaging did not affect disease-free survival (common and random effect disease-free survival 92% in the ultrastaging group vs common effect disease-free survival 99% and random effect disease-free survival 96% in the non-ultrastaging group). Both 5-year disease-free survival and overall survival rate after sentinel lymph node biopsy alone are higher than 90% and do not differ from pelvic lymphadenectomy survival data. Ultrastaging did not impact survival.