A Histology-Based Model for Predicting Microsatellite Instability in Colorectal Cancers
Bibliographic record
Abstract
Identifying colorectal cancers (CRCs) with high levels of microsatellite instability (MSI-H) is clinically important. MSI-H is a positive prognostic marker for CRC, a predictive marker for resistance to standard 5-fluorouracil-based adjuvant chemotherapy, and an important feature for identifying individuals and families with Lynch syndrome. Our aim was to compare and improve upon the existing predictive pathology models for MSI-H CRCs. We tested 2 existing models used to predict MSI-H tumors, (1) Revised Bethesda Guidelines and (2) MsPath, in our population-based cohort of CRCs diagnosed less than 75 years from Newfoundland (N=710). We also scored additional histologic features not described in the other models. From this analysis, we developed a model for the prediction of MSI-H CRCs; Pathologic Role in Determination of Instability in Colorectal Tumors (PREDICT). An independent pathologist validated this model in a second cohort of all CRCs (N=276). Tumor histology was a better predictor of MSI status than was personal and family history of cancer. MsPath identified MSI-H CRCs with a sensitivity of 92.1% and a specificity of 37.8%, whereas the Revised Bethesda Guidelines had a sensitivity of 81.3% and a specificity of 39.5%. PREDICT included some new histology features, including peritumoral lymphocytic reaction and increased proportion of plasma cells in the tumor stroma. PREDICT was superior to both existing models in the development cohort with a sensitivity of 97.4% and a specificity of 53.9%. In the validation cohort, sensitivity was 96.9% and specificity 76.6%. We conclude that PREDICT is a good predictor of MSI-H CRC.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".