Personalized risk prediction for event‐free survival at 24 months in patients with diffuse large B‐cell lymphoma
Bibliographic record
Abstract
We recently defined event-free survival at 24 months (EFS24) as a clinically relevant outcome for patients with DLBCL. Patients who fail EFS24 have very poor overall survival, while those who achieve EFS24 have a subsequent overall survival equivalent to that of the age- and sex-matched general population. Here, we develop and validate a clinical risk calculator (IPI24) for EFS24. Model building was performed on a discovery dataset of 1,348 patients with DLBCL and treated with anthracycline-based immunochemotherapy. A multivariable model containing age, Ann Arbor stage, normalized serum LDH, ALC, ECOG performance status, bulky disease, and sex was identified. The model was then applied to an independent validation dataset of 1,177 DLBCL patients. The IPI24 score estimates the probability of failing to achieve the EFS24 endpoint for an individual patient. The IPI24 model showed superior discriminatory ability (c-statistic = 0.671) in the validation dataset compared to the IPI (c-statistic = 0.649) or the NCCN-IPI (c-statistic = 0.657). After recalibration of the model on the combined dataset, the median predicted probability of failing to achieve EFS24 was 36% (range, 12-88%), and the IPI24 showed an EFS24 gradient in all IPI groups. The IPI24 also identified a significant percentage of patients with high risk disease, with over 20% of patients having a 50% or higher risk of failing to achieve EFS24. The IPI24 provides an individual patient level probability of achieving the clinically relevant EFS24 endpoint. It can be used via electronic apps.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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 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".