Dataset Information

The use of Logic regression in epidemiologic studies to investigate multiple binary exposures: an example of occupation history and amyotrophic lateral sclerosis.

ABSTRACT: Investigating the joint exposure to several risk factors is becoming a key component of epidemiologic studies. Individuals are exposed to multiple factors, often simultaneously, and evaluating patterns of exposures and high-dimension interactions may allow for a better understanding of health risks at the individual level. When jointly evaluating high-dimensional exposures, common statistical methods should be integrated with machine learning techniques that may better account for complex settings. Among these, Logic regression was developed to investigate a large number of binary exposures as they relate to a given outcome. This method may be of interest in several public health settings, yet has never been presented to an epidemiologic audience. In this paper, we review and discuss Logic regression as a potential tool for epidemiological studies, using an example of occupation history (68 binary exposures of primary occupations) and amyotrophic lateral sclerosis in a population-based Danish cohort. Logic regression identifies predictors that are Boolean combinations of the original (binary) exposures, fully operating within the regression framework of interest (e.g. linear, logistic). Combinations of exposures are graphically presented as Logic trees, and techniques for selecting the best Logic model are available and of high importance. While highlighting several advantages of the method, we also discuss specific drawbacks and practical issues that should be considered when using Logic regression in population-based studies. With this paper, we encourage researchers to explore the use of machine learning techniques when evaluating large-dimensional epidemiologic data, as well as advocate the need of further methodological work in the area.

SUBMITTER: Bellavia A

PROVIDER: S-EPMC7679079 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The use of Logic regression in epidemiologic studies to investigate multiple binary exposures: an example of occupation history and amyotrophic lateral sclerosis.

Bellavia Andrea A Rotem Ran S RS Dickerson Aisha S AS Hansen Johnni J Gredal Ole O Weisskopf Marc G MG

Epidemiologic methods 20200101 1

Investigating the joint exposure to several risk factors is becoming a key component of epidemiologic studies. Individuals are exposed to multiple factors, often simultaneously, and evaluating patterns of exposures and high-dimension interactions may allow for a better understanding of health risks at the individual level. When jointly evaluating high-dimensional exposures, common statistical methods should be integrated with machine learning techniques that may better account for complex settin ...[more]

PMID: 33224709

Similar Datasets

Project description:BackgroundFactors underlying a possible excess of amyotrophic lateral sclerosis (ALS) among military veterans remain unidentified. Limitations of previous studies on this topic include reliance on ALS mortality as a surrogate for ALS incidence, low statistical power, and sparse information on military-related factors.ObjectivesWe evaluated associations between military-related factors and ALS using data from a case-control study of U.S. military veterans.MethodsFrom 2005 to 2010, we identified medical record-confirmed ALS cases via the National Registry of Veterans with ALS and controls via the Veterans Benefits Administration's Beneficiary Identification and Records Locator System database. In total, we enrolled 621 cases and 958 frequency-matched controls in the Genes and Environmental Exposures in Veterans with Amyotrophic Lateral Sclerosis study. We collected information on military service and deployments and 39 related exposures. We used unconditional logistic regression models to estimate odds ratios (ORs) and 95% confidence intervals (CIs). We used inverse probability weighting to adjust for potential bias from confounding, missing covariate data, and selection arising from a case group that disproportionately included long-term survivors and a control group that may or may not differ from U.S. military veterans at large.ResultsThe odds of ALS did not differ for veterans of the Air Force, Army, Marines, and Navy. We found higher odds of ALS for veterans whose longest deployment was World War II or the Korean War and a positive trend with total years of all deployments (OR=1.27; 95% CI: 1.06, 1.52). ALS was positively associated with exposure to herbicides for military purposes, nasopharyngeal radium, personal pesticides, exhaust from heaters or generators, high-intensity radar waves, contaminated food, explosions within one mile, herbicides in the field, mixing and application of burning agents, burning agents in the field, and Agent Orange in the field, with ORs between 1.50 and 7.75.ConclusionsAlthough our results need confirmation, they are potentially important given the large number of U.S. military veterans, and they provide clues to potential factors underlying the apparent increase of ALS in veteran populations.

Dataset Information

The use of Logic regression in epidemiologic studies to investigate multiple binary exposures: an example of occupation history and amyotrophic lateral sclerosis.

Publications

The use of Logic regression in epidemiologic studies to investigate multiple binary exposures: an example of occupation history and amyotrophic lateral sclerosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets