Germline prediction of immune checkpoint inhibitor discontinuation for immune-related adverse events
Bibliographic record
Abstract
Abstract Introduction Immune checkpoint inhibitors (ICIs) can yield remarkable clinical responses in subsets of patients with solid tumors but can also often lead to immune-related adverse events (irAEs). Predictive features of clinically severe irAEs leading to cessation of ICIs have yet to be established. Using data from 1,327 patients with lung cancer treated with ICIs between 2009 and 2022 at four academic medical centers, we evaluated the association of a germline polygenic risk score for autoimmune disease and discontinuation of ICIs due to irAEs. Methods Using Cox proportional hazards model, we assessed the association between a polygenic risk score for autoimmune disease (PRS AD ) and cessation of ICI therapy due to irAEs. All models were adjusted for age at diagnosis, sex, lung cancer histology, type of therapy, recruiting center, and the first 5 principal components. To further understand the differential effects of type of therapy and disease stage on the association between PRS AD and cessation of ICI due to irAEs, we conducted stratified logistic regression analysis by type of ICI therapy and disease stage. Results We found an association between PRS AD and ICI cessation due to irAEs (HR per SD = 1.18, 95% CI = 1.02 – 1.37, P = 0.03). This association was particularly strong in patients who had ICI cessation due to irAEs within three months of therapy initiation (HR per SD = 1.38, 95% CI = 1.08 - 1.78, P = 0.01). Individuals in the top 20th percentile of PRS AD had 7.2% ICI discontinuation for irAEs by three months, compared to 3.9% discontinuation by three months among patients in the bottom 80th percentile (log-rank P = 0.02). In addition, among patients who received combination PD-1/PD-L1 and CTLA-4 inhibitor therapy, PRS AD had an OR per SD of 1.86 (95% CI = 1.08 - 3.51, P = 0.04). Conclusions We demonstrate an association between a polygenic risk score for autoimmune disease and early ICI discontinuation for irAEs, particularly among patients treated with combination ICI therapy. Our results suggest that germline genetics may be used as an adjunctive tool for risk stratification around ICI clinical decision-making in solid tumor oncology.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 source (direct Gemma or distilled Codex), 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".