Correlation of eTILs with recurrence free survival (RFS) in stage IIB-IIIA melanoma and use as biomarker for stratification for clinical trials.
Bibliographic record
Abstract
9567 Background: Immunotherapy is approved for resected stage IIB-IIIC, but treatment of all patients, particularly those with IIB-IIIA disease, incurs unneeded expense and toxicity. Biomarkers are urgently needed for patient stratification. Time constraints in clinical trial design have led to the adoption of recurrence free survival (RFS) as a primary endpoint in adjuvant melanoma trials. Tumor infiltrating lymphocytes (TILs) are a well-established biomarker in primary melanoma, but quantification is subjective. Electronic TILs (eTILs) are a previously published automated digital pathology tool to quantify TILs. Methods: A retrospective cohort of 194 patients with Stage II-III melanoma from Roswell Park Comprehensive Cancer Center (RPCCC, n=133) and Geisinger Medical Center (GMC, n=61) were evaluated for eTILS by blinded investigators. Patients were included based on a search of dermatopathology databases and tissue availability. Digital images of diagnostic slides were analyzed using quPath, a publicly available software. Briefly, tumor areas were selected to include infiltrating lymphocytes with minimal adjacent stroma. Color variations in H&E images were standardized, and cell types quantified utilizing a machine learning algorithm. A previously published threshold of 16.6% eTILs, calculated as lymphocytes/tumor cells x 100, was used. Patients were staged using American Joint Committee on Cancer (AJCC) guidelines, version 8. Survival was assessed using Kaplan-Meier Curves and correlation of clinic-pathologic features with survival was tested using Cox Proportional Hazards Models. Results: Of 194 patients, 56 were stage IIA, 85 were IIB-IIIA, and 53 were IIIB-D. Median follow up was 47.5 months. 103 patients had eTILs >16.6% of whom 13 (12.6%) died and 84 had eTILS <16.6% of whom 23 (27.4%) died during follow-up. HR for death from melanoma within 5 years for the high eTIL group was 0.53 (CI 0.21-0.90, p=0.024). DSS was significantly longer in the high eTIL group than the low eTIL group (p=0.0095). Among 85 stage IIB-IIIA patients, local and distant recurrence data was available for the RPCCC cohort of 68 patients. 46 of these patients had high eTILs of whom 9(19.6%) recurred and 22 had low eTILS of whom 10 (45.95%) recurred. HR for recurrence within 5 years for the high eTIL group was 0.44 (CI0.23-0.83, p=0.012). RFS was significantly longer in the high TIL group (p=0.016) as was distant metastatic recurrent survival (p= 0.0063). eTIL score correlated with RFS in a univariable Cox model (p=0.033) and added to stage and depth in a multivariable Cox model (p=0.018). Conclusions: eTILs, readily evaluable at low cost using diagnostic slides, correlate with clinical outcome in a retrospective cohort of 194 patients. eTILS should be prospectively evaluated as a biomarker to stratify early-stage melanoma patients for adjuvant clinical trials.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.010 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".