ONCOPRE: A new chemotherapy benefit prediction model to assist treatment decision making.
Bibliographic record
Abstract
126 Background: Clinical decision support tools (CDSTs) can help physicians make complex treatment decisions and inform care. For colon cancer, CDSTs such as Adjuvant! Online and Numeracy were widely used to estimate the effects of adjuvant treatment and guide conversations with patients. Existing CDSTs, however, do not consider more contemporary predictive and prognostic factors, such as microsatellite instability (MSI), BRAF mutational status, or the presence of additional high risk clinical or pathological features (HRFs), in their assessment of outcomes. Current CDSTs are also not optimized for handheld devices. Methods: We developed ONCOPRE, which is an adjuvant chemotherapy benefit calculator for colon cancer that addresses the limitations of current CDSTs. Based on a comprehensive review of epidemiological data and results of landmark trials, ONCOPRE was devised to predict 5 year colon cancer recurrence and death. To validate ONCOPRE, we compared its predictions with those generated by existing CDSTs as well as real-world data from 7 tertiary cancer centers across Canada. Results: ONCOPRE is able to predict 5-year DFS and OS of patients with colon cancer based on age, sex, TNM status, and contemporary risk factors such as MSI status, BRAF mutations, and other HRFs. ONCOPRE’s predictions compare favorably with real-world data and predictions from other CDSTs. ONCOPRE’s predictions are typically more optimistic than historical outcomes, and this likely reflects the fact that current day colon cancer patients experience better prognosis with the use of modern therapy and improved supportive care. These attributes make ONCOPRE a potentially new benchmark among CDSTs that can reliably predict colon cancer outcomes. Conclusions: ONCOPRE ( http://www.oncopre.com/ ) represents a new CDST that can assist in adjuvant treatment decision-making and patient counseling. We make the case that the next generation of CDSTs in oncology must take into account more contemporary clinical, biochemical, and genetic risk factors since these elements significantly affect outcomes. The ONCOPRE platform serves as a potential model on which to develop prediction tools for other forms of cancers.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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".