Osman, Iman

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.

Background Management of immune-related adverse events (irAEs) is important as they cause treatment interruption or discontinuation, more often seen with combination immune checkpoint inhibitor (ICI) therapy. Here, we retrospectively evaluated the safety and effectiveness of anti-interleukin-6 receptor (anti-IL-6R) as therapy for irAEs. Methods We performed a retrospective multicenter study evaluating patients diagnosed with de novo irAEs or flare of pre-existing autoimmune disease following ICI and were treated with anti-IL-6R. Our objectives were to assess the improvement of irAEs as well as the overall tumor response rate (ORR) before and after anti-IL-6R treatment. Results We identified a total of 92 patients who received therapeutic anti-IL-6R antibodies (tocilizumab or sarilumab). Median age was 61 years, 63% were men, 69% received anti-programmed cell death protein-1 (PD-1) antibodies alone, and 26% patients were treated with the combination of anti-cytotoxic T lymphocyte antigen-4 and anti-PD-1 antibodies. Cancer types were primarily melanoma (46%), genitourinary cancer (35%), and lung cancer (8%). Indications for using anti-IL-6R antibodies included inflammatory arthritis (73%), hepatitis/cholangitis (7%), myositis/myocarditis/myasthenia gravis (5%), polymyalgia rheumatica (4%), and one patient each with autoimmune scleroderma, nephritis, colitis, pneumonitis and central nervous system vasculitis. Notably, 88% of patients had received corticosteroids, and 36% received other disease-modifying antirheumatic drugs (DMARDs) as first-line therapies, but without adequate improvement. After initiation of anti-IL-6R (as first-line or post-corticosteroids and DMARDs), 73% of patients showed resolution or change to ≤grade 1 of irAEs after a median of 2.0 months from initiation of anti-IL-6R therapy. Six patients (7%) stopped anti-IL-6R due to adverse events. Of 70 evaluable patients by RECIST (Response Evaluation Criteria in Solid Tumors) V.1.1 criteria; the ORR was 66% prior versus 66% after anti-IL-6R (95% CI, 54% to 77%), with 8% higher complete response rate. Of 34 evaluable patients with melanoma, the ORR was 56% prior and increased to 68% after anti-IL-6R (p=0.04). Conclusion Targeting IL-6R could be an effective approach to treat several irAE types without hindering antitumor immunity. This study supports ongoing clinical trials evaluating the safety and efficacy of tocilizumab (anti-IL-6R antibody) in combination with ICIs ( NCT04940299 , NCT03999749 ).