Pathomic immune biomarkers define recurrence risk in early-stage melanoma
Bibliographic record
Abstract
BACKGROUND: There is an urgent need for biomarkers in early-stage melanoma because the benefit of adjuvant immunotherapy is marginal while the toxicity is considerable. Immune surveillance is a key mechanism limiting melanoma progression, but no immune biomarkers have yet been sufficiently validated for clinical use. METHODS: We validate 3 digital pathology biomarkers, all previously trained in published cohorts and testable in formalin fixed paraffin embedded specimens, for correlation with recurrence free survival and distant metastatic free survival: (1) tumor infiltrating lymphocytes identified using artificial intelligence in digital images (eTILs), (2) nanoString melanoma immune profile (MIP), and (3) quantitative immunofluorescence of CD8+ cells. RESULTS: Three immune biomarkers were validated and found to correlate with recurrence at 36 months by receiver operating curve analysis (eTILs area under the curve [AUC] = 0.706, P = .002; MIP AUC = 0.775, P < .001; and CD8% AUC = 0.682, P = .009) and define high and low risk groups using Kaplan Meier (KM) curves within the IIA-IIID population (P = .007 for eTILs and P < .001 for MIP and CD8%) and within the difficult to treat IIB-IIIA subset (P = .005, P < .001, P < .001, respectively). Immune biomarkers enhance clinical predictors (P = .012, P < .001, P = .004), and correlate with distant metastatic recurrence (P = .031, P = .047, P = .014, respectively). Network analysis shows that stage and depth combined with pathomic immune features yields the highest correlation with recurrence (AUC = 0.875, P < .001). CONCLUSIONS: Immune biomarkers should be prospectively validated in stage II-III melanoma for the purpose of avoiding overtreatment of low-risk patients and to stratify high-risk patients for 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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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".