A histology-based model for predicting microsatellite instability in colorectal cancers.

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.