Extracting Biomedical Terms from Postpartum Depression Online Health Communities.

Online health communities play a vital role in supporting patients by connecting them to people with similar health conditions, thereby enabling interactions that may be distinct from those with their healthcare providers. Online health support groups can provide social support for people experiencing clinical conditions such as postpartum depression (PPD). In this paper, we describe our creation of a dataset of annotated PPD discussion forums and a preliminary assessment of topics that are discussed on the forums. Our approach leverages the capabilities of MetaMapLite (MMLite) and the Human Phenotype Ontology (HPO) concept recognition software to identify biomedical terms from BabyCenter.com online health communities. A data extraction pipeline wherein text from discussion forums on the topic of PPD is scraped and structured for annotation by the MMLite and HPO. The final corpus includes 10,584 posts with their all associated comments. Our analysis of the performance of MMLite to annotate biomedical terms relevant to PPD indicated a precision of 86.7%, recall of 81.3%, and AUC of 0.714. We propose a data model illustrating the main topics discussed among PPD forum users. Topics include: exposures, phenotypes, health conditions, behaviors, and timing. This resource has potential to enable investigating previously unexplored experiences with PPD.

Finding Understudied Disorders Potentially Associated with Maternal Morbidity and Mortality.

Objective Clinical research literature focuses primarily on the most common causes of maternal morbidity and mortality (MMM). We explore sections of the discharge summaries of pregnant or postpartum women admitted to an intensive care unit (ICU) to identify associated disorders and mine the literature to identify knowledge gaps in clinical research. Methods Data for the study were discharge summaries in the MIMIC (Medical Information Mart for Intensive Care) database. We extracted a control cohort to study if there is a difference in comorbidities between pregnant and not pregnant patients with similar reasons for admission. We identified comorbidities of the Unified Medical Language System (UMLS) semantic types disease or syndrome, Mental or behavioral dysfunction, and injury, or poisoning. We used Entrez programming utilities (E-utilities) to query PubMed ® . Results We identified 246 pregnant and postpartum patients. A control group of 587 not pregnancy related admissions matched on age and admit diagnosis. We found overlap of 24.3% discharge diagnoses between the two groups, and 7.5% of the codes exclusively in the pregnancy group. We identified 33 disease mentions not included in the most common reported causes of MMM. Conclusion Our results demonstrate that clinical text provides additional comorbidities associated with maternal complications that need further clinical research.

Mining the literature for genes associated with placenta-mediated maternal diseases.

Automated literature analysis could significantly speed up understanding of the role of the placenta and the impact of its development and functions on the health of the mother and the child. To facilitate automatic extraction of information about placenta-mediated disorders from the literature, we manually annotated genes and proteins, the associated diseases, and the functions and processes involved in the development and function of placenta in a collection of PubMed/MEDLINE abstracts. We developed three baseline approaches to finding sentences containing this information: one based on supervised machine learning (ML) and two based on distant supervision: 1) using automated detection of named entities and 2) using MeSH. We compare the performance of several well-known supervised ML algorithms and identify two approaches, Support Vector Machines (SVM) and Generalized Linear Models (GLM), which yield up to 98% recall precision and F1 score. We demonstrate that distant supervision approaches could be used at the expense of missing up to 15% of relevant documents.

Automatic Classification of Structured Product Labels for Pregnancy Risk Drug Categories, a Machine Learning Approach.

With regular expressions and manual review, 18,342 FDA-approved drug product labels were processed to determine if the five standard pregnancy drug risk categories were mentioned in the label. After excluding 81 drugs with multiple-risk categories, 83% of the labels had a risk category within the text and 17% labels did not. We trained a Sequential Minimal Optimization algorithm on the labels containing pregnancy risk information segmented into standard document sections. For the evaluation of the classifier on the testing set, we used the Micromedex drug risk categories. The precautions section had the best performance for assigning drug risk categories, achieving Accuracy 0.79, Precision 0.66, Recall 0.64 and F1 measure 0.65. Missing pregnancy risk categories could be suggested using machine learning algorithms trained on the existing publicly available pregnancy risk information.

A bottom-up approach to MEDLINE indexing recommendations.

MEDLINE indexing performed by the US National Library of Medicine staff describes the essence of a biomedical publication in about 14 Medical Subject Headings (MeSH). Since 2002, this task is assisted by the Medical Text Indexer (MTI) program. We present a bottom-up approach to MEDLINE indexing in which the abstract is searched for indicators for a specific MeSH recommendation in a two-step process. Supervised machine learning combined with triage rules improves sensitivity of recommendations while keeping the number of recommended terms relatively small. Improvement in recommendations observed in this work warrants further exploration of this approach to MTI recommendations on a larger set of MeSH headings.

Investigating drug classes in biomedical terminologies from the perspective of clinical decision support.

OBJECTIVES: To assess whether 1) the necessary drug classes and 2) the necessary drug-class membership relations are represented in biomedical terminologies in order to support clinical decision regarding drug-drug interactions. METHODS: In order to investigate drug classes and drug-class membership in clinical terminologies, we start by establishing a reference list of these entities. Then, we map drugs and classes to the UMLS, where we investigate their relations. RESULTS: 186 (83%) of the 223 names for drug classes mapped to the UMLS. The single best source is SNOMED CT with 75%. 140 (89%) of the 157 drug-membership relations were found in the UMLS. CONCLUSIONS: One important category of drug classes missing from all clinical terminologies is related to drug metabolism by the Cytochrome P450 enzyme family.