PU-Boost: ATwo-StageReliable-Sample Reconstruction Positive-Unlabeled Learning Framework for Screening Undiagnosed Hypertension
- 1University of Arizona
Abstract
In hypertension screening, previously diagnosed cases provide reliable positive labels, whereas individuals without a prior diagnosis comprise both undiagnosed hypertensive and non-hypertensive individuals, creating a canonical positive-unlabeled (PU) learning setting. We propose PU-Boost, a two-stage reliable-sample reconstruction framework that uses only readily obtainable demographic, behavioral, medical-history, and anthropometric variables. During training, only previously diagnosed hypertension cases are treated as labeled positives (P), while all remaining individuals are treated as unlabeled (U); no additional reference labels are supplied to the two-stage reconstruction procedure. Elastic Net first provides a global ranking of P versus U, after which a random forest refines the uncertain region and highly ambiguous observations are rejected. XGBoost is then trained on the reconstructed class-balanced pseudo-labeled sample. In the independent test set, PU-Boost achieved a sensitivity of 0.817 and a balanced accuracy of 0.682, the highest observed values among the compared models. It produced 729 false negatives, 41.1% fewer than standard XGBoost, although specificity decreased to 0.547. SHAP analysis indicated that established hypertension-related features, including age, body mass index, waist circumference, and family history, contributed strongly to model output. PU-Boost therefore provides a statistically motivated framework for reducing missed cases when screening for undiagnosed hypertension under incomplete diagnostic labeling.
Related
- Regional Disparities in Undiagnosed Hypertension Among South Asian Adults in the Bay Area and Central Valley: The PRANA Heart Study
- Measurement error adjusted prevalence of undiagnosed hypertension in England: A cross-sectional study
- Cervical Scrofula Revealing Miliary Tuberculosis and Previously Undiagnosed Advanced HIV: A Case Report
- Severe Intraoperative Airway Leak Revealing Undiagnosed Mounier‐Kuhn Syndrome in an Elderly Patient
- ICD-Coded Versus Undiagnosed Acute Kidney Injury in the Atherosclerosis Risk in Communities (ARIC) Study
BibTeX
@misc{wu2026puboost,
title = {{PU-Boost: ATwo-StageReliable-Sample Reconstruction Positive-Unlabeled Learning Framework for Screening Undiagnosed Hypertension}},
author = {H. Wu and L. Shi and H. Yang and B. Li and Q. Wang and Z. Zhan and L. Guo},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.04.26364708},
url = {https://www.medrxiv.org/content/10.64898/2026.10.04.26364708v1},
note = {CC BY-ND},
}
RIS
TY - UNPB
TI - PU-Boost: ATwo-StageReliable-Sample Reconstruction Positive-Unlabeled Learning Framework for Screening Undiagnosed Hypertension
AU - H. Wu
AU - L. Shi
AU - H. Yang
AU - B. Li
AU - Q. Wang
AU - Z. Zhan
AU - L. Guo
PY - 2026
DA - 2026/10/04
PB - medRxiv
DO - 10.64898/2026.10.04.26364708
UR - https://www.medrxiv.org/content/10.64898/2026.10.04.26364708v1
AB - In hypertension screening, previously diagnosed cases provide reliable positive labels, whereas individuals without a prior diagnosis comprise both undiagnosed hypertensive and non-hypertensive individuals, creating a canonical positive-unlabeled (PU) learning setting. We propose PU-Boost, a two-stage reliable-sample reconstruction framework that uses only readily obtainable demographic, behavioral, medical-history, and anthropometric variables. During training, only previously diagnosed hypertension cases are treated as labeled positives (P), while all remaining individuals are treated as unlabeled (U); no additional reference labels are supplied to the two-stage reconstruction procedure. Elastic Net first provides a global ranking of P versus U, after which a random forest refines the uncertain region and highly ambiguous observations are rejected. XGBoost is then trained on the reconstructed class-balanced pseudo-labeled sample. In the independent test set, PU-Boost achieved a sensitivity of 0.817 and a balanced accuracy of 0.682, the highest observed values among the compared models. It produced 729 false negatives, 41.1% fewer than standard XGBoost, although specificity decreased to 0.547. SHAP analysis indicated that established hypertension-related features, including age, body mass index, waist circumference, and family history, contributed strongly to model output. PU-Boost therefore provides a statistically motivated framework for reducing missed cases when screening for undiagnosed hypertension under incomplete diagnostic labeling.
ER -