Maurice Perol | Searcharxiv

arXiv2026

Multimodality Stacking with Blockwise missing values and application to the PIONeeR biomarkers study for prediction of resistance to immunotherapy

Integrating multimodal datasets in clinical oncology is frequently hindered by high dimensionality and blockwise missingness, where entire data sources are unavailable for specific patient subsets. Standard survival models often struggle with these gaps, leading to biased results or patient exclusion. We introduce Multimodality Stacking with Blockwise missing values (MSB), a late-fusion framework for survival analysis that independently models modality-specific features before aggregating predictions via a cross-validated stacking meta-learner. MSB was validated on the PIONeeR study (n=443 patients, 378 biomarkers across eight heterogeneous sources) to predict progression-free survival in advanced non-small cell lung cancer patients receiving immunotherapy. MSB yielded higher predictive performance (C-index) than baseline algorithms. Improvements varied by baseline strength: linear models showed a 15.9% increase (p<0.001 for the Wilcoxon signed-rank test), random survival forests gained 5.4% (p=0.002), and gradient boosting methods improved by 2.1% (p=0.030). Beyond discrimination, MSB reduced the generalization gap (train-test difference in 5 folds cross-validation repeated 3 times: 0.055 vs 0.380 for linear models). Permutation importance analysis identified routine laboratory markers, clinical features, and PD-L1 expression as primary predictive drivers. Missing block indicators showed negligible importance, suggesting the model learned from biomarker values rather than data availability patterns. MSB provides a statistically validated framework for multimodal survival prediction with blockwise missingness. By enabling systematic biomarker evaluation without requiring complete data, MSB offers a practical tool for predictive modeling in biomedical research, pending external validation. Implementation is available at https://github.com/MohamedBoussena/MSB under Inria license.

stat.AP↗

arXiv2025

Methodological Advances and Challenges in Indirect Treatment Comparisons: A Review of International Guidelines and HAS TC Case Studies

To evaluate methodological challenges and regulatory considerations of indirect treatment comparisons (ITCs) with the analysis of international health technology assessment guidelines and French Transparency Committee (TC) decisions. We conducted a pragmatic review of ITC guidelines from major health technology assessment (HTA) bodies and multistakeholder organizations. Then, we analyzed TC opinions published between 2021-2023. We extracted data on ITC methodology, therapeutic areas, acceptability, and limitations expressed by the TC. The targeted review of the main guidelines showed mainly agreements between HTA bodies and multistakeholder organizations, with some specificities. 138 TC opinions containing 195 ITCs were analyzed. Only 13.3% of these ITCs influenced TC decision-making. ITCs were more frequently accepted in genetic diseases (34.4%) compared to oncology (10.0%) and autoimmune diseases (11.1%). Methods using individual patient data showed higher acceptance rates (23.1%) than network meta-analyses (4.2%). Main limitations included heterogeneity/bias risk (59%), lack of data (48%), statistical methodology issues (29%), study design concerns (27%), small sample size (25%), and outcome definition variability (20%). When ITCs were the primary source of evidence, the proportion of important clinical benefit was lower (60.9% vs. 73.4%) than when randomized controlled trials were available. While ITCs are increasingly submitted, particularly where direct evidence is impractical, their influence on reimbursement decisions remains limited. There is a need for clear and accessible guides so manufacturers can produce clearer and more robust ITCs that follow regulatory guidelines, from the planning phase to execution.

stat.ME↗