Pulse.

a daily field guide to health research that matters

◆ Console

‹ Tue · 14 Jul 2026
Near-term implementable finding

Machine Learning for Predicting Ki-67 Expression in Renal Tumors: A Systematic Review And Meta-Analysis.

Machine learning models reliably predict tumor growth rates from imaging alone, potentially allowing doctors to grade kidney cancers without biopsies.

This systematic review and meta-analysis evaluates the aggregate diagnostic performance of machine learning models predicting Ki-67 proliferative index in renal tumors from imaging, finding collectively strong performance that supports the concept of non-invasive imaging-based tumor grading. The findings support prospective validation of ML-based Ki-67 prediction as a clinical tool that could inform treatment decisions without requiring biopsy.

What the study was

Study design
Systematic review and meta-analysis
Population
Renal tumor patients undergoing imaging for Ki-67 proliferative index assessment
Category
Diagnostics
Maturity
Validated
Journal
Academic radiology

Why it surfaced

Meta-analysis of ML-based Ki-67 prediction from imaging consolidates evidence for a clinically actionable non-invasive alternative to biopsy-based tumor grading in renal cancer.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.