Using Machine Learning to Predict TP53 Mutation Status and Aggressiveness of Prostate Cancer from Routine Histology Images

Despite years of progress, we still lack reliable tools to predict the aggressiveness of tumors, including in the case of prostate cancer. Biomarkers have been developed, but they often suffer from poor accuracy if used alone due to tumor heterogeneity. Nevertheless, some mutations, notably TP53 mutations, are highly correlated with pro-gression. In their work in this issue of Cancer Research, Pizurica and colleagues implemented a machine learning-based model applied to routine histology and trained with prior information on TP53 mutation status. Their model output provides a quantitative predic-tion of TP53 mutation status while having a strong correlation with aggressiveness, showing promise as a prognostic in silico biomarker. See related article by Pizurica et al., p. 2970

Automated summary

Despite progress, reliable tools for predicting tumor aggressiveness, including prostate cancer, are still lacking. Biomarkers have poor accuracy when used alone due to tumor heterogeneity. However, TP53 mutations are highly correlated with progression.