Abstract 3344: The 31-gene expression profile identifies patients at risk of developing early distant metastases and can guide risk-appropriate surveillance strategies
Bibliographic record
Abstract
Abstract Introduction: Up to 20% of patients with stage I-II cutaneous melanoma (CM) will develop distant metastases (DMs), with the most frequent DM sites being the liver, lungs, bone, and brain. Although patients who develop DM have poor prognosis, trials of new immunotherapies in patients with DM have reported 5-year survival rates as high as 50%. Critically, early detection of DM, when tumor burden is lower, tends to lead to better treatment responses. Thus, it is important to identify patients at the highest risk of developing DM so clinicians can recommend risk-appropriate surveillance and treatment plans. We previously assessed the ability of the 31-gene expression profile (31-GEP) to predict CNS metastases, and here we expand our analysis to assess 31-GEP risk prediction for DMs to the lung, liver, and bone. Methods: We conducted a retrospective analysis of patients with stage I-II CM clinically tested with the 31-GEP from 2013-2017 (n=1, 661). Differences in DM rates between groups were assessed with Chi-squared test. Survival estimates (DM-free survival, DMFS) were estimated using Kaplan-Meier and compared using the log-rank test. (*, p<0.05; **, p<0.001). Results: Among patients with stage I-II CM, a total of 90 DMs developed in 67 (4.0%) patients to the liver (n=48), lung (n=22), and/or bone (n=20). A higher percentage of patients with Class 2B than Class 1A developed DM to the liver (7.4% vs. 1.2%, **), lung (4.5% vs. 0.6%, **), and bone (3.0% vs. 0.8%, *). A 31-GEP Class 2B result was associated with significantly lower 5-year DMFS than Class 1B/2A or Class 1A for liver (91.7%, 92.2%, vs. 98.9%, **), lung (95.0%, 97.6%, vs. 99.4%, **), and bone (96.4%, 98.0%, vs. 99.2%, *). Of those with DM, the median time to develop DM (Class 1A, 1B/2A, vs. 2B) was 2.43, 2.22, vs. 2.27 years for liver; 1.74, 3.20, vs. 1.10 years for lung; and 3.2, 2.05, vs. 1.30 years for bone. Conclusion: Among patients with stage I-II CM, a greater percentage of those with a Class 2B 31-GEP developed DM at all studied sites, and 5-year DMFS was significantly lower for those with a Class 2B result. Thus, including 31-GEP testing with AJCC staging can allow clinicians to identify patients at higher risk of DM and recommend risk-appropriate surveillance modalities and frequency for early detection and treatment of DM. Citation Format: Merve Hasanov, Elshad Hasanov, David Pariser, Sonia Morgan-Linnell, Samuel Dierks, Brian Martin, Abel Jarell. The 31-gene expression profile identifies patients at risk of developing early distant metastases and can guide risk-appropriate surveillance strategies [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 3344.
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".