Related Experiment Video
Updated: Aug 5, 2026
06:55
Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Addressing Class Imbalance in Low Birth Weight Prediction: A Quantile-Based Outcome Redefinition Framework Using
Víctor Hugo Morales1, Osnamir Elias Bru-Cordero2, Antonio José Martínez-López1
1Departamento de Matemáticas y Estadística, Universidad de Córdoba, Montería 230027, Colombia.
Summary
Redefining low birth weight (LBW) using a quartile-based threshold improved predictive models for severe LBW cases. This novel approach enhances risk stratification and surveillance for better maternal and neonatal health outcomes.
Area of Science:
- Epidemiology
- Public Health
- Neonatal Medicine
Background:
- Low birth weight (LBW) is a significant global public health issue.
- Existing definitions may not adequately stratify risk within the LBW population.
- Improved predictive modeling is crucial for effective neonatal surveillance.
Purpose of the Study:
- To evaluate a quantile-based outcome redefinition for enhanced severity stratification in low birth weight (LBW) newborns.
- To improve predictive modeling and risk stratification within the LBW cohort.
- To address class imbalance in rare-event epidemiological data for maternal and neonatal health surveillance.
Main Methods:
- Analysis of deidentified SIVIGILA surveillance records (n=10,185) from Medellín, Colombia (2011-2021).
- Redefinition of the binary outcome within the LBW cohort using the first quartile (Q1=2240 g) to distinguish severe from moderate LBW.
- Comparison of logistic regression, class weighting, SMOTE, and Elastic Net models using discrimination, classification, and calibration metrics.
Main Results:
- The quantile-based redefinition significantly improved model performance.
- Key metrics increased: sensitivity (0.218 to 0.632), F1 score (0.330 to 0.496), and AUC (0.624 to 0.726).
- A sensitivity-specificity tradeoff analysis was presented for practical implementation.
Conclusions:
- Redefining the outcome variable with distribution-based thresholds is an effective strategy for mitigating class imbalance in epidemiological data.
- This approach provides a practical framework for enhancing predictive modeling in maternal and neonatal health surveillance systems.
- The proposed method improves severity stratification for low birth weight infants.
Related Concept Videos
01:17z Scores and Area Under the Curve
z scores are the standardized values obtained after converting a normal distribution into a standard normal distribution. A z score is measured in units of the standard deviation. The z score tells you how many standard deviations the value x is above (to the right of) or below (to the left of) the mean, μ. Values of x that are larger than the mean have positive z scores, and values of x that are smaller than the mean have negative z scores. If x equals the mean, then x has a z score of zero.
01:29Bias in Epidemiological Studies
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:
01:52Regression Toward the Mean
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when researchers try to extrapolate results...
01:25Strategies for Assessing and Addressing Confounding
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
01:25Statistical Methods for Analyzing Epidemiological Data
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
01:27Confounding in Epidemiological Studies
Confounding in statistical epidemiology represents a pivotal challenge, referring to the distortion in the perceived relationship between an exposure and an outcome due to the presence of a third variable, known as a confounder. This variable is associated with both the exposure and the outcome but is not a direct link in their causal chain. Its presence can lead to erroneous interpretations of the exposure's effect, either exaggerating or underestimating the true association. This phenomenon...