SAG-RS: Trajectory-Aware Probability Stacking with Contextual-Bandit Reliability Gating for ICD-Audited Diabetes Phenotype Identification in MIMIC-IV
- 1College of Information Science and Engineering, Hunan Women’s University, Changsha 410004, China
- 2College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
Abstract
Background: Identifying diabetes phenotypes in electronic health records is challenging when repeated admissions and diagnosis-derived variables can bias evaluation. Methods: We reconstructed an ICD-audited diabetes phenotype from MIMIC-IV v3.1 and compared LightGBM with trajectory-aware probability stacking and a conservative contextual-bandit reliability gate. Patient-level separation, out-of-fold feature generation, independent gate development, and a common upstream Base model were used. Results: On the primary held-out split (51,400 records), Full SAG-RS achieved accuracy 0.926654, F1 0.889579, AUC 0.961288, and Brier 0.059649. Across five patient-level splits, mean accuracy was 0.928021 ± 0.002217. The gate improved primary-split accuracy over Stack-only by 0.000233 (95% paired confidence interval −0.000078 to 0.000548); net corrections were positive in three of five splits. Conclusions: Trajectory-aware stacking provided most of the gain over admission-level LightGBM. The gate offered limited, variable correction rather than a demonstrated independent performance gain. Findings are restricted to retrospective internal validation; external validation and full-pipeline replication remain outstanding.
Related
- Adaptive Node Distribution via Probability Density Functions for Birkhoff Pseudospectral Trajectory Optimisation
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
- Adaptive Bandit Algorithms for Contextual Matching Markets
- HyCoSeq: Contextual Hyperbolic Representation Learning for Genomic Sequences
- The Curvature of Regret in Contextual Linear Optimization
BibTeX
@article{lv2026sagrs,
title = {{SAG-RS: Trajectory-Aware Probability Stacking with Contextual-Bandit Reliability Gating for ICD-Audited Diabetes Phenotype Identification in MIMIC-IV}},
author = {Hongchao Lv and Yineng Chen and Qingshan Ren and Shukun Liu and Xianghua Peng and Chengkai Chen and Yixin Zhang},
journal = {Mathematics},
year = {2026},
month = nov,
doi = {10.3390/math14213978},
url = {https://www.mdpi.com/2227-7390/14/21/3978},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - SAG-RS: Trajectory-Aware Probability Stacking with Contextual-Bandit Reliability Gating for ICD-Audited Diabetes Phenotype Identification in MIMIC-IV
AU - Hongchao Lv
AU - Yineng Chen
AU - Qingshan Ren
AU - Shukun Liu
AU - Xianghua Peng
AU - Chengkai Chen
AU - Yixin Zhang
PY - 2026
DA - 2026/11/01
JO - Mathematics
DO - 10.3390/math14213978
UR - https://www.mdpi.com/2227-7390/14/21/3978
AB - Background: Identifying diabetes phenotypes in electronic health records is challenging when repeated admissions and diagnosis-derived variables can bias evaluation. Methods: We reconstructed an ICD-audited diabetes phenotype from MIMIC-IV v3.1 and compared LightGBM with trajectory-aware probability stacking and a conservative contextual-bandit reliability gate. Patient-level separation, out-of-fold feature generation, independent gate development, and a common upstream Base model were used. Results: On the primary held-out split (51,400 records), Full SAG-RS achieved accuracy 0.926654, F1 0.889579, AUC 0.961288, and Brier 0.059649. Across five patient-level splits, mean accuracy was 0.928021 ± 0.002217. The gate improved primary-split accuracy over Stack-only by 0.000233 (95% paired confidence interval −0.000078 to 0.000548); net corrections were positive in three of five splits. Conclusions: Trajectory-aware stacking provided most of the gain over admission-level LightGBM. The gate offered limited, variable correction rather than a demonstrated independent performance gain. Findings are restricted to retrospective internal validation; external validation and full-pipeline replication remain outstanding.
SN - 2227-7390
ER -