Integrating knowledge graphs into machine learning models for survival prediction and biomarker discovery in patients with non–small-cell lung cancer
Bibliographic record
Abstract
Abstract Accurate survival prediction for Non-Small Cell Lung Cancer (NSCLC) patients remains a significant challenge for the scientific and clinical community despite decades of advanced analytics. Addressing this challenge not only helps inform the critical aspects of clinical study design and biomarker discovery but also ensures that the ‘right patient’ receives the ‘right treatment’. However, survival prediction is a highly complex task, given the large number of ‘omics; and clinical features, as well as the high degree of freedom that drive patient survival. Prior knowledge could play a critical role in uncovering the complexity of a disease and understanding the driving factors affecting a patient’s survival. We introduce a methodology for incorporating prior knowledge into machine learning–based models for prediction of patient survival through Knowledge Graphs, demonstrating the advantage of such an approach for NSCLC patients. Using data from patients treated with immuno-oncologic therapies in the POPLAR (NCT01903993) and OAK (NCT02008227) clinical trials, we found that the use of knowledge graphs yielded significantly improved hazard ratios, including in the POPLAR cohort, for models based on biomarker tumor mutation burden compared with those based on knowledge graphs. Use of a model-defined mutational 10-gene signature led to significant overall survival differentiation for both trials. We provide parameterized code for incorporating knowledge graphs into survival analyses for use by the wider scientific community.
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 | 0.019 | 0.089 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.006 |
| Bibliometrics | 0.007 | 0.006 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.001 |
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".