Shim SH, et al. J Gynecol Oncol. 2024 Jan;35:e66. https://doi.org/10.3802/jgo.2024.35.e66

Objective: We compared the diagnostic performance of artificial intelligence (AI) with that of a gynecologic oncologist during digital cervicography. Methods: Women with abnormal cytology who underwent cervicography between January 2019 and December 2023 were included. A gynecologic oncologist interpreted the digital cervicography and the results were compared with those of the AI system. Diagnostic performances were assessed using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic accuracy for low-grade squamous intraepithelial lesions (LSILs) and high-grade squamous intraepithelial lesions (HSILs)/cancer. Cohen’s kappa quantified agreement. Results: This study included 449 women (mean age, 41.0 years). A Cohen’s kappa of 0.511 (p < 0.0001) indicated moderate agreement between the oncologist and AI. Among 226 cases of HSILs/cancer, the oncologist’s sensitivity was 62.8%, compared to 47.8% for AI, with similar specificity (81.2% vs. 83.5%). The oncologist’s PPV and NPV were 85.0% and 56.3%, respectively, whereas AI’s were 83.1% and 48.5%, respectively. For LSILs/HSILs/cancer (n = 283), the oncologist achieved 98.2% sensitivity and 44.7% specificity, compared to AI’s 93.3% sensitivity and 46.1% specificity. Both had a similar PPV (86.9% vs. 86.6%); however, the oncologist’s NPV (87.2%) exceeded AI’s 64.8%. Diagnostic accuracy for LSILs/HSILs/cancer was 86.9% for the oncologist and 82.3% for AI, whereas for HSILs/cancer, it was 69.6% and 61.0%, respectively. Conclusions: Moderate agreement was observed between the oncologist and AI. Although AI demonstrated similar performance in diagnosing cervical lesions, the oncologist achieved higher diagnostic accuracy. AI is a complementary tool and future research should refine AI algorithms to align with clinical performance.

PurposeOvarian cancer presents significant treatment challenges due to its aggressive nature and poor response to immune checkpoint inhibitors (ICIs). The lack of standardized programmed cell death-ligand 1 (PD-L1) assays and cut-off values complicates clinical decision-making. We evaluated the concordance among commonly used PD-L1 assays and assessed changes in the expression of PD-L1 following chemotherapy.Materials and MethodsTissue samples from 29 patients with ovarian cancer were analyzed using five validated PD-L1 immunohistochemistry assays: Dako 22C3, Ventana SP263, Ventana SP142, Dako 28-8, and Ventana 22C3. PD-L1 positivity was assessed using a combined positive score (CPS), immune cell, or tumor proportion score at 1%, 5%, and 10% cut-offs. Concordance rates, including overall percent agreement and Cohen’s kappa coefficient, were analyzed. In addition, changes in the expression of PD-L1 pre- and postchemotherapy were evaluated.ResultsPositivity rates ranged from 15.8% (SP142) to 29.8% (Dako 22C3 and SP263) at the 1% CPS cut-off. SP142 consistently exhibited the lowest concordance, whereas Dako 22C3 displayed high agreement with SP263, 28-8, and Ventana 22C3. Chemotherapy increased PD-L1 positivity, with 28% of patients converting from negative to positive.ConclusionThe expression of PD-L1 in ovarian cancer varies across assays and scoring methods, emphasizing the need for standardized testing protocols. Increased PD-L1 expression post-chemotherapy underscores the importance of assessing its status at appropriate times to guide ICI therapy. Larger studies are required to validate these findings and refine clinical applications.