What question did this study set out to answer?

The aim is to estimate exposure-response associations using output from machine learning models to derive odds ratios.

February 19, 2026Scientific Reports0 citationsOpen Access

Estimating the odds ratio from the output scores of machine learning models: possibilities and limitations

RNRonit Nirel NBNaor BaumanHebrew University of Jerusalem EMEfrat MorinHebrew University of Jerusalem

Key Points

The aim is to estimate exposure-response associations using output from machine learning models to derive odds ratios.
Developed eight hybrid estimators for odds ratios based on classifier output and logistic regression adjustment.
Suggested two estimators utilizing partial dependence functions.
Applied these methods on outputs from logistic regression, random forest, and gradient boosting models in two case studies.
87% of the gradient boosting estimates fell within the logistic regression 95% confidence interval.
For random forest, estimates varied significantly: 0%, 60%, and 13% within the CI for respiratory, cardiovascular, and infant data, respectively.
Gradient boosting-based confidence intervals for uncalibrated estimates were 13-59% narrower than those from logistic regression.

Abstract

Estimation of exposure-response association is central to epidemiologic research. Although the advantages of machine learning (ML) techniques for modeling complex relationships are well-recognized, their use in epidemiologic studies are limited mainly because they do not provide direct estimates of associations, such as odds ratios (ORs). We suggest eight hybrid estimators of the OR that are functions of the output from a classifier, or their probability-calibrated form, multiplied by an adjustment factor that is 'borrowed' from logistic regression (LR). We also suggest two estimators based on partial dependence functions. We applied these estimators to output from LR, random forest (RF) and gradient boosting (GB) models for investigating associations between (1) temperature and respiratory or cardiovascular admissions and (2) prenatal exposure to temperature and overweight among infants. Most (87%) of the estimates produced by GB were within the LR 95% CI, but for RF the results were mixed: 0%, 60% and 13% of the estimates were within this CI for the Respiratory, Cardiovascular and Infants data, respectively. Additionally, GB-based CIs for the uncalibrated estimates were narrower by 13-59% compared to the LR CIs. These findings may enhance the integration between ML and epidemiologic research by providing interpretable results.

Demander à l'IA

Bookmark

View Full Paper

Cite This Study

Nirel et al. (Mon,) studied this question.

synapsesocial.com/papers/6996a80aecb39a600b3ee590 https://doi.org/https://doi.org/10.1038/s41598-026-38150-1

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

Demander à l'IA

Bookmark

View Full Paper