Clinical Report: Interpretable Models for Forecasting Early-Onset Hypertension
Overview
This study introduces DSRegPSOP, a symbolic regression approach that develops interpretable models for predicting early-onset hypertension. The models demonstrate predictive performance comparable to advanced machine learning techniques while maintaining clinical interpretability.
Background
Early-onset hypertension is a significant health concern due to its association with increased cardiovascular risk. Understanding the multifactorial determinants of hypertension is crucial for early intervention and prevention strategies. The Tlalpan 2020 cohort provides a unique dataset to explore these determinants in clinically healthy adults, enhancing the potential for effective predictive modeling.
Data Highlights
No numerical data available.
Key Findings
DSRegPSOP produced interpretable mathematical models for early-onset hypertension.
The models maintained predictive performance comparable to state-of-the-art machine learning algorithms.
Key predictors of early-onset hypertension were identified through the models.
The study utilized a nested case-control design based on a 10-year prospective cohort.
Addressed class imbalance using oversampling and SMOTE-based strategies.
Clinical Implications
The development of interpretable models like DSRegPSOP can enhance clinical decision-making by providing clear insights into hypertension risk factors. These models may support early prevention strategies, pending further validation in independent cohorts.
Conclusion
DSRegPSOP offers a promising approach to hypertension risk assessment, emphasizing the need for interpretable models in clinical practice. Future validation studies are essential to confirm its utility in diverse populations.
