RESOLVE-IPD: High-Fidelity Individual Patient Data Reconstruction and Uncertainty-Aware Subgroup Meta-Analysis

2025-11-03

AI Summary

Existing KM curve digitization methods suffer from three key limitations: coordinate extraction errors, unrealistic assumptions of uniform censoring, and inability to reconstruct individual patient data (IPD) for subgroups from summary statistics. This paper introduces the first uncertainty-aware, subgroup-level IPD reconstruction framework. It integrates VEC-KM—enabling high-precision coordinate extraction—with CEN-KM—which corrects for non-uniform censoring—and innovatively incorporates the MAPLE algorithm to perform marginal-constrained subgroup label probability inference and evidence propagation, yielding statistically feasible multi-label sets. Evaluated on four phase III esophageal squamous cell carcinoma trials, the method significantly improves accuracy and reproducibility of treatment effect estimation in the PD-L1 low-expression subgroup. It establishes a new paradigm for IPD reconstruction in precision oncology: high-fidelity, interpretable, and quantitatively calibrated for uncertainty.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Individual patient data (IPD) from oncology trials are essential for reliable evidence synthesis but are rarely publicly available, necessitating reconstruction from published Kaplan-Meier (KM) curves. Existing reconstruction methods suffer from digitization errors, unrealistic uniform censoring assumptions, and the inability to recover subgroup-level IPD when only aggregate statistics are available. We developed RESOLVE-IPD, a unified computational framework that enables high-fidelity IPD reconstruction and uncertainty-aware subgroup meta-analysis to address these limitations. RESOLVE-IPD comprises two components. The first component, High-Fidelity IPD Reconstruction, integrates the VEC-KM and CEN-KM modules: VEC-KM extracts precise KM coordinates and explicit censoring marks from vectorized figures, minimizing digitization error, while CEN-KM corrects overlapping censor symbols and eliminates the uniform censoring assumption. The second component, Uncertainty-Aware Subgroup Recovery, employs the MAPLE (Marginal Assignment of Plausible Labels and Evidence Propagation) algorithm to infer patient-level subgroup labels consistent with published summary statistics (e.g., hazard ratio, median overall survival) when subgroup KM curves are unavailable. MAPLE generates ensembles of mathematically valid labelings, facilitating a propagating meta-analysis that quantifies and reflects uncertainty from subgroup reconstruction. RESOLVE-IPD was validated through a subgroup meta-analysis of four trials in advanced esophageal squamous cell carcinoma, focusing on the programmed death ligand 1 (PD-L1)-low population. RESOLVE-IPD enables accurate IPD reconstruction and robust, uncertainty-aware subgroup meta-analyses, strengthening the reliability and transparency of secondary evidence synthesis in precision oncology.

Problem

• Reconstructing individual patient data from oncology trial Kaplan-Meier curves
• Addressing digitization errors and unrealistic censoring assumptions in reconstruction
• Enabling subgroup meta-analysis when only aggregate statistics are available

Innovation

• Vectorized KM curve extraction minimizing digitization errors
• Censoring correction eliminating uniform censoring assumptions
• Uncertainty-aware subgroup recovery using ensemble labelings