Evaluation of an AI tool's performance in predicting primary tumors, highlighting sensitivity and positive predictive value.
Performance per category for all categories (primary tumors). Confusion matrix for primary tumors in retrospective validation cohort. Positive predictive value (PPV) for each category is indicated by the bars above and sensitivity by the bars to the right. Numbers of each predicted tumor type are shown in the boxes, with darker shading of the diagonal indicating a higher number of correctly predicted tumors (matching outside label).
No takes yet. Share an insight, caveat, or question.
Ghani et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: