A decision-aware framework for pre-regulatory academic early warning under resource constraints
4 affiliations
- 1Faculty of Arts and Communications, Thai Nguyen University of Information and Communication Technology
- 2School of Computer Science and AI, Duy Tan University
- 3Faculty of Information Technology, Hai Phong University
- 4Faculty of Information Technology, Thai Nguyen University of Information and Communication Technology
Abstract
Academic early-warning systems are commonly evaluated as prediction tools, although their institutional value depends on how risk estimates are translated into support decisions. We developed and retrospectively evaluated a decision-aware framework for pre-regulatory academic warning using longitudinal administrative records spanning six academic years and twelve standardised semesters at a regional public university. Condition-specific risks of violating formal academic-warning regulations were estimated using three predictive backbones and evaluated through semester-based rolling-origin testing. Calibrated probabilities were converted into support priorities using context-sensitive expected regulatory violation costs under a fixed semester-level support budget. At 20% intervention coverage, the proposed policy reduced the missed intervention rate to 0.447, compared with 0.514 for the strongest non-ERVC comparator, while increasing positive predictive value from 0.377 to 0.429. The estimated equity gap in missed intervention was smaller under ERVC (0.052 versus 0.081 for the strongest non-ERVC comparator), but the paired difference did not reach conventional statistical significance ( p=0.06 ), indicating a favourable but statistically uncertain equity pattern. These findings support evaluating early-warning systems through decision quality, resource use, and equity, while preserving human oversight and formal academic governance.
Related
- Academic treatment optimization studies in oncology and internal medicine: a risk- and burden-adapted regulatory framework for the European Union.
- Ethical Pragmatism in Healthcare Management: A Multidimensional Framework for Responsible Decision-Making Under Real-World Constraints.
- Resource allocation under uncertainty and equity constraints in Parkinson’s disease care: An econometrically grounded machine learning framework
- Explainable machine learning for breast cancer prediction in resource-constrained settings: A multi-algorithmic framework integrating shap-based transparency with clinical decision support
- LncACTdb 4.0: an updated resource of experimentally supported ceRNA interactions and multi-level regulatory networks for precision oncology
BibTeX
@article{phung2026decisionaware,
title = {{A decision-aware framework for pre-regulatory academic early warning under resource constraints}},
author = {Trung-Nghia Phung and Gia-Nhu Nguyen and Dac-Nhuong Le and The-Vinh Nguyen},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-72395-0},
url = {https://doi.org/10.1038/s41598-026-72395-0},
note = {CC BY},
}
RIS
TY - JOUR
TI - A decision-aware framework for pre-regulatory academic early warning under resource constraints
AU - Trung-Nghia Phung
AU - Gia-Nhu Nguyen
AU - Dac-Nhuong Le
AU - The-Vinh Nguyen
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-72395-0
UR - https://doi.org/10.1038/s41598-026-72395-0
AB - Academic early-warning systems are commonly evaluated as prediction tools, although their institutional value depends on how risk estimates are translated into support decisions. We developed and retrospectively evaluated a decision-aware framework for pre-regulatory academic warning using longitudinal administrative records spanning six academic years and twelve standardised semesters at a regional public university. Condition-specific risks of violating formal academic-warning regulations were estimated using three predictive backbones and evaluated through semester-based rolling-origin testing. Calibrated probabilities were converted into support priorities using context-sensitive expected regulatory violation costs under a fixed semester-level support budget. At 20% intervention coverage, the proposed policy reduced the missed intervention rate to 0.447, compared with 0.514 for the strongest non-ERVC comparator, while increasing positive predictive value from 0.377 to 0.429. The estimated equity gap in missed intervention was smaller under ERVC (0.052 versus 0.081 for the strongest non-ERVC comparator), but the paired difference did not reach conventional statistical significance ( p=0.06 ), indicating a favourable but statistically uncertain equity pattern. These findings support evaluating early-warning systems through decision quality, resource use, and equity, while preserving human oversight and formal academic governance.
SN - 2045-2322
ER -