Development and validation of the PEPPER framework (Prenatal Exposure PubMed ParsER) with applications to food additives

Abstract

BackgroundGlobally, 36% of deaths among children can be attributed to environmental factors. However, no comprehensive list of environmental exposures exists. We seek to address this gap by developing a literature-mining algorithm to catalog prenatal environmental exposures.MethodsWe designed a framework called PEPPER Prenatal Exposure PubMed ParsER to a) catalog prenatal exposures studied in the literature and b) identify study type. Using PubMed Central, PEPPER classifies article type (methodology, systematic review) and catalogs prenatal exposures. We coupled PEPPER with the FDA’s food additive database to form a master set of exposures.ResultsWe found that of 31 764 prenatal exposure studies only 53.0% were methodology studies. PEPPER consists of 219 prenatal exposures, including a common set of 43 exposures. PEPPER captured prenatal exposures from 56.4% of methodology studies (9492/16 832 studies). Two raters independently reviewed 50 randomly selected articles and annotated presence of exposures and study methodology type. Error rates for PEPPER’s exposure assignment ranged from 0.56% to 1.30% depending on the rater. Evaluation of the study type assignment showed agreement ranging from 96% to 100% (kappa = 0.909, p < .001). Using a gold-standard set of relevant prenatal exposure studies, PEPPER achieved a recall of 94.4%.ConclusionsUsing curated exposures and food additives; PEPPER provides the first comprehensive list of 219 prenatal exposures studied in methodology papers. On average, 1.45 exposures were investigated per study. PEPPER successfully distinguished article type for all prenatal studies allowing literature gaps to be easily identified.

Applied Veterinary Informatics: Development of a Semantic and Domain-Specific Method to Construct a Canine Data Repository

“…Understanding the origins of disease, including both environmental 1 and genetic etiologies requires the use of good and validated models. Dogs are useful models for studying several canine and human diseases 2,3 , including cardiovascular diseases 4 , and various cancers 5 .…”

Mining Early Life Risk and Resiliency Factors and Their Influences in Human Populations from PubMed: A Machine Learning Approach to Discover DOHaD Evidence

“…Across clinical and academic settings, text mining strategies are emerging as a means to meet the growing need to remain up to date on the increasingly vast amount of research published across many scientific and clinical fields [17,19]. To date, there has only been one other study exploring machine learning techniques in the prenatal environmental exposures context, which mainly explored extracting and grouping studies based on methodology type [20]. Our study thus contributes another aspect to this field by introducing a proof-of-concept model for collating and discriminating studies based on specific topics within the DOHaD landscape.…”