Identifying predictors of overall survival among patients with TMB-low metastatic cancer treated with immune checkpoint inhibitors
Bibliographic record
Abstract
BACKGROUND: Immune checkpoint inhibitors (ICIs) have significantly advanced cancer therapy, yet their efficacy in tumors with low tumor mutational burden (TMB) remains suboptimal. In this study, we aimed to elucidate the impact of somatic mutations on overall survival (OS) in TMB-low patients treated with ICIs and to explore the potential for personalized treatment selection through machine learning. METHODS: We conducted a comprehensive analysis of 1172 TMB-low (TMB < 10 mutations per megabase) patients with cancer receiving ICIs, examining the association between specific gene mutations and OS. Additionally, we developed a decision tree model (DTM) to predict OS based on clinical features and tumor mutational profiles. RESULTS: Our findings reveal that mutations in DAXX, HLA-A, H3C2, IGF1R, CTNNB1, SMARCA4, KMT2D, and TP53 are significantly associated with poorer survival outcomes in the multivariate analysis. Remarkably, for renal cell carcinoma (RCC) patients, VHL mutations predicted improved OS following ICI even when adjusted for age, sex, and microsatellite instability (MSI) status in both multivariate analysis and the DTM model. CONCLUSIONS: These results reinforce the prevailing notion that TMB alone does not predict ICI response, highlighting the critical role of individual gene mutations in TMB-low tumors under ICI therapy. Furthermore, our study demonstrates the promise of machine learning models in optimizing ICI treatment decisions, paving the way for more precise and effective therapeutic strategies in this patient population.
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 | 0.000 | 0.000 |
| 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 | 0.001 |
| 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".