AI Insight
Researchers developed POETIC-AI, a digital platform that integrates and analyzes diverse data types from the POETIC breast cancer clinical trial, which tested hormone therapy before and after surgery. The system uses a graph-based structure to link patient information, tissue samples, laboratory tests, and imaging data while preserving their relationships and clinical context. Testing the platform with Ki67 proliferation markers, they confirmed treatment effects and revealed differences between pathologist assessments and automated image analysis methods, demonstrating how maintaining connections between data types and tissue images enables more thorough exploration of clinical trial results.
Why it matters
This approach addresses a critical challenge in modern cancer research where trials generate multiple data types that are typically analyzed in isolation. By preserving the connections between molecular measurements, images, and clinical outcomes, the platform enables more reproducible research and could accelerate the development of biomarkers that better predict treatment responses in breast cancer patients.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Biologically rich clinical trials generate heterogeneous datasets whose relationships and clinical context must be preserved. Here we present the POETIC-AI environment, a trial-centric digital environment for integrating, analysing, and exploring multimodal data from POETIC, a randomised phase III trial of peri-operative aromatase inhibition in hormone receptor-positive breast cancer (NCT02338310). We implemented a graph-based ontology linking patients, treatments, sampling timepoints, specimens, assays, images, spatial regions, and derived measurements; and designed code-based and graphical analytical workflows. Using proliferation as a test case, we reproduced POETIC’s established reduction in Ki67% and examined variation underlying sample-level measurements. In response-enriched cohorts, mean Ki67% decreased while relative variation among pathologist-assessed fields increased (paired Wilcoxon, P < 0.0001). Pathologist-assessed Ki67% correlated strongly with an 18-gene transcriptomic proliferation signature (r = 0.834), and both decreased significantly during treatment (P < 0.0001). An annotation-free pixel-wise Ki67 H-score showed weaker correlations and a similar but non-significant reduction (r = 0.327-0.472; P = 0.15), highlighting differences between tumour-focused and whole-section image quantification. Digital pathology and spatial molecular measurements remained linked to their source images and annotated tissue regions, enabling exploration within their morphological and spatial context using bespoke interactive applications. POETIC-AI demonstrates how the structure, provenance, and tissue context of evolving multimodal clinical-trial data can be preserved within a connected research environment, supporting reproducible analyses and the laying the groundwork for future development of biologically interpretable computational biomarkers.