Pezzuto, Federica

Importance Tumor-infiltrating lymphocytes (TILs) are a provocative biomarker in melanoma, influencing diagnosis, prognosis, and immunotherapy outcomes; however, traditional pathologist-read TIL assessment on hematoxylin and eosin–stained slides is prone to interobserver variability, leading to inconsistent clinical decisions. Therefore, development of newer TIL scoring approaches that produce more reliable and consistent readouts is important. Objective To evaluate the analytical and clinical validity of a machine learning algorithm for TIL quantification in melanoma compared with traditional pathologist-read methods. Design, Setting, and Participants This multioperator, global, multi-institutional prognostic study compared TIL scoring reproducibility between traditional pathologist-read methods and an artificial intelligence (AI)-driven approach. The study was conducted using retrospective cohorts of patients with melanoma between January 2022 and June 2023 across 45 institutions, with tissue evaluated by participants from academic, clinical, and research institutions. Participants were selected to ensure diverse expertise and professional backgrounds. Main Outcomes and Measures Intraclass correlation coefficient (ICC) values were calculated for the manual and AI-assisted arms using log-transformed data. Kendall W values were calculated for Clark scores (brisk = 3, nonbrisk = 2, and sparse = 1). Reliabilities of ICC and W values were classified as moderate (0.40-0.60), good (0.61-0.80), or excellent (>0.80). AI TIL measurements were dichotomized using the 16.6 and median cutoffs. Univariable and multivariable Cox regression analyses assessed the prognostic value of TIL scores adjusted for clinicopathologic variables. Results There were 111 patients with melanoma in the independent testing cohort (median [range] age at diagnosis, 61.0 [25.0-87.0] years; 56 [50.5%] male) who contributed melanoma whole tissue sections. A total of 98 participants evaluated TILs on 60 hematoxylin and eosin–stained melanoma tissue sections. All 40 participants in the manual arm were pathologists, while the AI-assisted arm included 11 pathologists and 47 nonpathologists (scientists). The AI algorithm demonstrated superior reproducibility, with ICCs higher than 0.90 for all machine learning TIL variables, significantly outperforming manual assessments (ICC, 0.61 for AI-derived stromal TILs vs Kendall W , 0.44 for manual Clark TIL scoring). AI-based TIL scores showed prognostic associations with patient outcomes (n = 111) using the median cutoff approach with a hazard ratio (HR) of 0.45 (95% CI, 0.26-0.80; P = .005), and using the cutoff of 16.6, with an HR of 0.56 (95% CI, 0.32-0.98; P = .04). Conclusions and Relevance In this prognostic study of TIL quantification in melanoma, the AI algorithm demonstrated superior reproducibility and prognostic associations compared with traditional methods. Although the retrospective nature of the cohorts limits demonstration of clinical utility, the publicly available dataset and open-source AI tool offer a foundation for future validation and integration into melanoma management.

Abstract Accumulating evidence suggests dysregulated immune checkpoint (IC) signaling can exacerbate COVID-19 severity, but the role of these molecules in the pathogenesis of fatal COVID-19-related diffuse alveolar damage (DAD) remains elusive. Understanding how IC proteins influence acute lung injury due to COVID-19 can provide insights into potential therapeutic strategies to modulate immune responses and improve patient outcomes. Here, in a single-center autopsy cohort, we determined the cellular localization of ICs in lung tissue from cases of fatal COVID-19, DAD-comparators, and non-fibrotic controls by using immunohistochemistry, and investigated their association with clinical outcomes. We expanded our findings by performing analyses of publicly available single-cell RNA sequencing datasets from patients with fatal COVID-19 and non-fibrotic controls. We demonstrated the presence of protein-protein interaction networks of ICs in the lung cellular niche by performing transcriptomic profiling of lung tissue-derived RNA counts from patients with fatal COVID-19. Further, we leveraged data from the largest international, multi-center COVID-19 autopsy cohort and validated that, among patients with fatal COVID-19, those with higher PD-L1/CD274 expression in lung endothelial cells had more rapid clinical deterioration. Lastly, in a cohort of individuals with early COVID-19, IC plasma protein levels were elevated in those with persistent SARS-CoV-2 RNAemia and adverse clinical outcomes. Collectively, our data provide unique pathological insights into the role of IC dysregulation and differential disease severity in COVID-19.