Adverse Health Outcomes Following Hurricane Harvey: A Comparison of Remotely-Sensed and Self-Reported Flood Exposure Estimates.

Remotely sensed inundation may help to rapidly identify areas in need of aid during and following floods. Here we evaluate the utility of daily remotely sensed flood inundation measures and estimate their congruence with self-reported home flooding and health outcomes collected via the Texas Flood Registry (TFR) following Hurricane Harvey. Daily flood inundation for 14 days following the landfall of Hurricane Harvey was acquired from FloodScan. Flood exposure, including number of days flooded and flood depth was assigned to geocoded home addresses of TFR respondents (N = 18,920 from 47 counties). Discordance between remotely-sensed flooding and self-reported home flooding was measured. Modified Poisson regression models were implemented to estimate risk ratios (RRs) for adverse health outcomes following flood exposure, controlling for potential individual level confounders. Respondents whose home was in a flooded area based on remotely-sensed data were more likely to report injury (RR = 1.5, 95% CI: 1.27-1.77), concentration problems (1.36, 95% CI: 1.25-1.49), skin rash (1.31, 95% CI: 1.15-1.48), illness (1.29, 95% CI: 1.17-1.43), headaches (1.09, 95% CI: 1.03-1.16), and runny nose (1.07, 95% CI: 1.03-1.11) compared to respondents whose home was not flooded. Effect sizes were larger when exposure was estimated using respondent-reported home flooding. Near-real time remote sensing-based flood products may help to prioritize areas in need of assistance when on the ground measures are not accessible.

Poultry Concentrated Animal-Feeding Operations on the Eastern Shore, Virginia, and Geospatial Associations with Adverse Birth Outcomes.

Concentrated animal-feeding operations (CAFOs) emit pollution into surrounding areas, and previous research has found associations with poor health outcomes. The objective of this study was to investigate if home proximity to poultry CAFOs during pregnancy is associated with adverse birth outcomes, including preterm birth (PTB) and low birth weight (LBW). This study includes births occurring on the Eastern Shore, Virginia, from 2002 to 2015 (N = 5768). A buffer model considering CAFOs within 1 km, 2 km, and 5 km of the maternal residence and an inverse distance weighted (IDW) approach were used to estimate proximity to CAFOs. Associations between proximity to poultry CAFOs and adverse birth outcomes were determined by using regression models, adjusting for available covariates. We found a -52.8 g (-95.8, -9.8) change in birthweight and a -1.51 (-2.78, -0.25) change in gestational days for the highest tertile of inverse distance to CAFOs. Infants born with a maternal residence with at least one CAFO within a 5 km buffer weighed -47 g (-94.1, -1.7) less than infants with no CAFOs within a 5 km buffer of the maternal address. More specific measures of exposure pathways via air and water should be used in future studies to refine mediators of the association found in the present study.

Estimating changes in emergency department visits associated with floods caused by Tropical Storm Imelda using satellite observations and syndromic surveillance.

BACKGROUND: Satellite observations following flooding coupled with electronic health data collected through syndromic surveillance systems (SyS) may be useful in efficiently characterizing and responding to health risks associated with flooding. RESULTS: There was a 10% (95% Confidence Interval (CI): 1%-19%) increase in asthma related ED visits and 22% (95% CI: 5%-41%) increase in insect bite related ED visits in the flooded ZCTAs compared to non-flooded ZCTAs during the flood period. One month following the floods, diarrhea related ED visits were increased by 15% (95% CI: 4%-27%) for flooded ZCTAs and children and adolescents from flooded ZCTAs had elevated risk for dehydration related ED visits. During the protracted period (2-3 months after the flood period), the risk for asthma, insect bite, and diarrhea related ED visits were elevated among the flooded ZCTAs. Effect modification by reported age, ethnicity and race was observed. CONCLUSION: Combining satellite observations with SyS data can be helpful in characterizing the location and timing of environmentally mediated adverse health outcomes, which may be useful for refining disaster resilience measures to mitigate health outcomes following flooding.

Emergency department visits associated with satellite observed flooding during and following Hurricane Harvey.

BACKGROUND: Flooding following heavy rains precipitated by hurricanes has been shown to impact the health of people. Earth observations can be used to identify inundation extents for subsequent analysis of health risks associated with flooding at a fine spatio-temporal scale. OBJECTIVE: To evaluate emergency department (ED) visits before, during, and following flooding caused by Hurricane Harvey in 2017 in Texas. METHODS: A controlled before and after design was employed using 2016-2018 ED visits from flooded and non-flooded census tracts. ED visits between landfall of the hurricane and receding of flood waters were considered within the flood period and post-flood periods extending up to 4 months were also evaluated. Modified Poisson regression models were used to estimate adjusted rate ratios for total and cause specific ED visits. RESULTS: Flooding was associated with increased ED visits for carbon monoxide poisoning, insect bite, dehydration, hypothermia, intestinal infectious diseases, and pregnancy complications. During the month following the flood period, the risk for pregnancy complications and insect bite was still elevated in the flooded tracts. SIGNIFICANCE: Earth observations coupled with ED visits increase our understanding of the short-term health risks during and following flooding, which can be used to inform preparedness measures to mitigate adverse health outcomes and identify localities with increased health risks during and following flooding events.

A Natural Language Processing System That Links Medical Terms in Electronic Health Record Notes to Lay Definitions: System Development Using Physician Reviews.

BACKGROUND: Many health care systems now allow patients to access their electronic health record (EHR) notes online through patient portals. Medical jargon in EHR notes can confuse patients, which may interfere with potential benefits of patient access to EHR notes. OBJECTIVE: The aim of this study was to develop and evaluate the usability and content quality of NoteAid, a Web-based natural language processing system that links medical terms in EHR notes to lay definitions, that is, definitions easily understood by lay people. METHODS: NoteAid incorporates two core components: CoDeMed, a lexical resource of lay definitions for medical terms, and MedLink, a computational unit that links medical terms to lay definitions. We developed innovative computational methods, including an adapted distant supervision algorithm to prioritize medical terms important for EHR comprehension to facilitate the effort of building CoDeMed. Ten physician domain experts evaluated the user interface and content quality of NoteAid. The evaluation protocol included a cognitive walkthrough session and a postsession questionnaire. Physician feedback sessions were audio-recorded. We used standard content analysis methods to analyze qualitative data from these sessions. RESULTS: Physician feedback was mixed. Positive feedback on NoteAid included (1) Easy to use, (2) Good visual display, (3) Satisfactory system speed, and (4) Adequate lay definitions. Opportunities for improvement arising from evaluation sessions and feedback included (1) improving the display of definitions for partially matched terms, (2) including more medical terms in CoDeMed, (3) improving the handling of terms whose definitions vary depending on different contexts, and (4) standardizing the scope of definitions for medicines. On the basis of these results, we have improved NoteAid's user interface and a number of definitions, and added 4502 more definitions in CoDeMed. CONCLUSIONS: Physician evaluation yielded useful feedback for content validation and refinement of this innovative tool that has the potential to improve patient EHR comprehension and experience using patient portals. Future ongoing work will develop algorithms to handle ambiguous medical terms and test and evaluate NoteAid with patients.

Figure-associated text summarization and evaluation.

Biomedical literature incorporates millions of figures, which are a rich and important knowledge resource for biomedical researchers. Scientists need access to the figures and the knowledge they represent in order to validate research findings and to generate new hypotheses. By themselves, these figures are nearly always incomprehensible to both humans and machines and their associated texts are therefore essential for full comprehension. The associated text of a figure, however, is scattered throughout its full-text article and contains redundant information content. In this paper, we report the continued development and evaluation of several figure summarization systems, the FigSum+ systems, that automatically identify associated texts, remove redundant information, and generate a text summary for every figure in an article. Using a set of 94 annotated figures selected from 19 different journals, we conducted an intrinsic evaluation of FigSum+. We evaluate the performance by precision, recall, F1, and ROUGE scores. The best FigSum+ system is based on an unsupervised method, achieving F1 score of 0.66 and ROUGE-1 score of 0.97. The annotated data is available at figshare.com (http://figshare.com/articles/Figure_Associated_Text_Summarization_and_Evaluation/858903).

Automatically Detecting Acute Myocardial Infarction Events from EHR Text: A Preliminary Study.

The Worcester Heart Attack Study (WHAS) is a population-based surveillance project examining trends in the incidence, in-hospital, and long-term survival rates of acute myocardial infarction (AMI) among residents of central Massachusetts. It provides insights into various aspects of AMI. Much of the data has been assessed manually. We are developing supervised machine learning approaches to automate this process. Since the existing WHAS data cannot be used directly for an automated system, we first annotated the AMI information in electronic health records (EHR). With strict inter-annotator agreement over 0.74 and un-strict agreement over 0.9 of Cohen's κ, we annotated 105 EHR discharge summaries (135k tokens). Subsequently, we applied the state-of-the-art supervised machine-learning model, Conditional Random Fields (CRFs) for AMI detection. We explored different approaches to overcome the data sparseness challenge and our results showed that cluster-based word features achieved the highest performance.

Automatically Recognizing Medication and Adverse Event Information From Food and Drug Administration's Adverse Event Reporting System Narratives.

BACKGROUND: The Food and Drug Administration's (FDA) Adverse Event Reporting System (FAERS) is a repository of spontaneously-reported adverse drug events (ADEs) for FDA-approved prescription drugs. FAERS reports include both structured reports and unstructured narratives. The narratives often include essential information for evaluation of the severity, causality, and description of ADEs that are not present in the structured data. The timely identification of unknown toxicities of prescription drugs is an important, unsolved problem. OBJECTIVE: The objective of this study was to develop an annotated corpus of FAERS narratives and biomedical named entity tagger to automatically identify ADE related information in the FAERS narratives. METHODS: We developed an annotation guideline and annotate medication information and adverse event related entities on 122 FAERS narratives comprising approximately 23,000 word tokens. A named entity tagger using supervised machine learning approaches was built for detecting medication information and adverse event entities using various categories of features. RESULTS: The annotated corpus had an agreement of over .9 Cohen's kappa for medication and adverse event entities. The best performing tagger achieves an overall performance of 0.73 F1 score for detection of medication, adverse event and other named entities. CONCLUSIONS: In this study, we developed an annotated corpus of FAERS narratives and machine learning based models for automatically extracting medication and adverse event information from the FAERS narratives. Our study is an important step towards enriching the FAERS data for postmarketing pharmacovigilance.

Improving patients' electronic health record comprehension with NoteAid.

Allowing patients direct access to their electronic health record (EHR) notes has been shown to enhance medical understanding and may improve healthcare management and outcome. However, EHR notes contain medical terms, shortened forms, complex disease and medication names, and other domain specific jargon that make them difficult for patients to fathom. In this paper, we present a BioNLP system, NoteAid, that automatically recognizes medical concepts and links these concepts with consumer oriented, simplified definitions from external resources. We conducted a pilot evaluation for linking EHR notes through NoteAid to three external knowledge resources: MedlinePlus, the Unified Medical Language System (UMLS), and Wikipedia. Our results show that Wikipedia significantly improves EHR note readability. Preliminary analyses show that MedlinePlus and the UMLS need to improve both content readability and content coverage for consumer health information. A demonstration version of fully functional NoteAid is available at http://clinicalnotesaid.org.

Automatic discourse connective detection in biomedical text.

OBJECTIVE: Relation extraction in biomedical text mining systems has largely focused on identifying clause-level relations, but increasing sophistication demands the recognition of relations at discourse level. A first step in identifying discourse relations involves the detection of discourse connectives: words or phrases used in text to express discourse relations. In this study supervised machine-learning approaches were developed and evaluated for automatically identifying discourse connectives in biomedical text. MATERIALS AND METHODS: Two supervised machine-learning models (support vector machines and conditional random fields) were explored for identifying discourse connectives in biomedical literature. In-domain supervised machine-learning classifiers were trained on the Biomedical Discourse Relation Bank, an annotated corpus of discourse relations over 24 full-text biomedical articles (~112,000 word tokens), a subset of the GENIA corpus. Novel domain adaptation techniques were also explored to leverage the larger open-domain Penn Discourse Treebank (~1 million word tokens). The models were evaluated using the standard evaluation metrics of precision, recall and F1 scores. RESULTS AND CONCLUSION: Supervised machine-learning approaches can automatically identify discourse connectives in biomedical text, and the novel domain adaptation techniques yielded the best performance: 0.761 F1 score. A demonstration version of the fully implemented classifier BioConn is available at: http://bioconn.askhermes.org.

Automatic figure classification in bioscience literature.

Millions of figures appear in biomedical articles, and it is important to develop an intelligent figure search engine to return relevant figures based on user entries. In this study we report a figure classifier that automatically classifies biomedical figures into five predefined figure types: Gel-image, Image-of-thing, Graph, Model, and Mix. The classifier explored rich image features and integrated them with text features. We performed feature selection and explored different classification models, including a rule-based figure classifier, a supervised machine-learning classifier, and a multi-model classifier, the latter of which integrated the first two classifiers. Our results show that feature selection improved figure classification and the novel image features we explored were the best among image features that we have examined. Our results also show that integrating text and image features achieved better performance than using either of them individually. The best system is a multi-model classifier which combines the rule-based hierarchical classifier and a support vector machine (SVM) based classifier, achieving a 76.7% F1-score for five-type classification. We demonstrated our system at http://figureclassification.askhermes.org/.

Automatic figure ranking and user interfacing for intelligent figure search.

BACKGROUND: Figures are important experimental results that are typically reported in full-text bioscience articles. Bioscience researchers need to access figures to validate research facts and to formulate or to test novel research hypotheses. On the other hand, the sheer volume of bioscience literature has made it difficult to access figures. Therefore, we are developing an intelligent figure search engine (http://figuresearch.askhermes.org). Existing research in figure search treats each figure equally, but we introduce a novel concept of "figure ranking": figures appearing in a full-text biomedical article can be ranked by their contribution to the knowledge discovery. METHODOLOGY/FINDINGS: We empirically validated the hypothesis of figure ranking with over 100 bioscience researchers, and then developed unsupervised natural language processing (NLP) approaches to automatically rank figures. Evaluating on a collection of 202 full-text articles in which authors have ranked the figures based on importance, our best system achieved a weighted error rate of 0.2, which is significantly better than several other baseline systems we explored. We further explored a user interfacing application in which we built novel user interfaces (UIs) incorporating figure ranking, allowing bioscience researchers to efficiently access important figures. Our evaluation results show that 92% of the bioscience researchers prefer as the top two choices the user interfaces in which the most important figures are enlarged. With our automatic figure ranking NLP system, bioscience researchers preferred the UIs in which the most important figures were predicted by our NLP system than the UIs in which the most important figures were randomly assigned. In addition, our results show that there was no statistical difference in bioscience researchers' preference in the UIs generated by automatic figure ranking and UIs by human ranking annotation. CONCLUSION/SIGNIFICANCE: The evaluation results conclude that automatic figure ranking and user interfacing as we reported in this study can be fully implemented in online publishing. The novel user interface integrated with the automatic figure ranking system provides a more efficient and robust way to access scientific information in the biomedical domain, which will further enhance our existing figure search engine to better facilitate accessing figures of interest for bioscientists.

Identifying discourse connectives in biomedical text.

Discourse connectives are words or phrases that connect or relate two coherent sentences or phrases and indicate the presence of discourse relations. Automatic recognition of discourse connectives may benefit many natural language processing applications. In this pilot study, we report the development of the supervised machine-learning classifiers with conditional random fields (CRFs) for automatically identifying discourse connectives in full-text biomedical articles. Our first classifier was trained on the open-domain 1 million token Penn Discourse Tree Bank (PDTB). We performed cross validation on biomedical articles (approximately 100K word tokens) that we annotated. The results show that the classifier trained on PDTB data attained a 0.55 F1-score for identifying discourse connectives in biomedical text, while the cross-validation results in the biomedical text attained a 0.69 F1-score, a much better performance despite a much smaller training size. Our preliminary analysis suggests the existence of domain-specific features, and we speculate that domain-adaption approaches may further improve performance.