Try a new search

Format these results:

Searched for:

person:sbj2002

in-biosketch:yes

Total Results:

118


Automated detection of sudden unexpected death in epilepsy risk factors in electronic medical records using natural language processing

Barbour, Kristen; Hesdorffer, Dale C; Tian, Niu; Yozawitz, Elissa G; McGoldrick, Patricia E; Wolf, Steven; McDonough, Tiffani L; Nelson, Aaron; Loddenkemper, Tobias; Basma, Natasha; Johnson, Stephen B; Grinspan, Zachary M
OBJECTIVE:Sudden unexpected death in epilepsy (SUDEP) is an important cause of mortality in epilepsy. However, there is a gap in how often providers counsel patients about SUDEP. One potential solution is to electronically prompt clinicians to provide counseling via automated detection of risk factors in electronic medical records (EMRs). We evaluated (1) the feasibility and generalizability of using regular expressions to identify risk factors in EMRs and (2) barriers to generalizability. METHODS:Data included physician notes for 3000 patients from one medical center (home) and 1000 from five additional centers (away). Through chart review, we identified three SUDEP risk factors: (1) generalized tonic-clonic seizures, (2) refractory epilepsy, and (3) epilepsy surgery candidacy. Regular expressions of risk factors were manually created with home training data, and performance was evaluated with home test and away test data. Performance was evaluated by sensitivity, positive predictive value, and F-measure. Generalizability was defined as an absolute decrease in performance by <0.10 for away versus home test data. To evaluate underlying barriers to generalizability, we identified causes of errors seen more often in away data than home data. To demonstrate how small revisions can improve generalizability, we removed three "boilerplate" standard text phrases from away notes and repeated performance. RESULTS:We observed high performance in home test data (F-measure range = 0.86-0.90), and low to high performance in away test data (F-measure range = 0.53-0.81). After removing three boilerplate phrases, away performance improved (F-measure range = 0.79-0.89) and generalizability was achieved for nearly all measures. The only significant barrier to generalizability was use of boilerplate phrases, causing 104 of 171 errors (61%) in away data. SIGNIFICANCE/CONCLUSIONS:Regular expressions are a feasible and probably a generalizable method to identify variables related to SUDEP risk. Our methods may be implemented to create large patient cohorts for research and to generate electronic prompts for SUDEP counseling.
PMID: 31111463
ISSN: 1528-1167
CID: 3935952

AMIA Board White Paper: AMIA 2017 core competencies for applied health informatics education at the master's degree level

Valenta, Annette L; Berner, Eta S; Boren, Suzanne A; Deckard, Gloria J; Eldredge, Christina; Fridsma, Douglas B; Gadd, Cynthia; Gong, Yang; Johnson, Todd; Jones, Josette; Manos, E LaVerne; Phillips, Kirk T; Roderer, Nancy K; Rosendale, Douglas; Turner, Anne M; Tusch, Guenter; Williamson, Jeffrey J; Johnson, Stephen B
This White Paper presents the foundational domains with examples of key aspects of competencies (knowledge, skills, and attitudes) that are intended for curriculum development and accreditation quality assessment for graduate (master's level) education in applied health informatics. Through a deliberative process, the AMIA Accreditation Committee refined the work of a task force of the Health Informatics Accreditation Council, establishing 10 foundational domains with accompanying example statements of knowledge, skills, and attitudes that are components of competencies by which graduates from applied health informatics programs can be assessed for competence at the time of graduation. The AMIA Accreditation Committee developed the domains for application across all the subdisciplines represented by AMIA, ranging from translational bioinformatics to clinical and public health informatics, spanning the spectrum from molecular to population levels of health and biomedicine. This document will be periodically updated, as part of the responsibility of the AMIA Accreditation Committee, through continued study, education, and surveys of market trends.
PMID: 30371862
ISSN: 1527-974x
CID: 3586582

Common terms for rare epilepsies: Synonyms, associated terms, and links to structured vocabularies

Grinspan, Zachary M; Tian, Niu; Yozawitz, Elissa G; McGoldrick, Patricia E; Wolf, Steven M; McDonough, Tiffani L; Nelson, Aaron; Hafeez, Baria; Johnson, Stephen B; Hesdorffer, Dale C
Identifying individuals with rare epilepsy syndromes in electronic data sources is difficult, in part because of missing codes in the International Classification of Diseases (ICD) system. Our objectives were the following: (1) to describe the representation of rare epilepsies in other medical vocabularies, to identify gaps; and (2) to compile synonyms and associated terms for rare epilepsies, to facilitate text and natural language processing tools for cohort identification and population-based surveillance. We describe the representation of 33 epilepsies in 3 vocabularies: Orphanet, SNOMED-CT, and UMLS-Metathesaurus. We compiled terms via 2 surveys, correspondence with parent advocates, and review of web resources and standard vocabularies. UMLS-Metathesaurus had entries for all 33 epilepsies, Orphanet 32, and SNOMED-CT 25. The vocabularies had redundancies and missing phenotypes. Emerging epilepsies (SCN2A-, SCN8A-, KCNQ2-, SLC13A5-, andSYNGAP-related epilepsies) were underrepresented. Survey and correspondence respondents included 160 providers, 375 caregivers, and 11 advocacy group leaders. Each epilepsy syndrome had a median of 15 (range 6-28) synonyms. Nineteen had associated terms, with a median of 4 (range 1-41). We conclude that medical vocabularies should fill gaps in representation of rare epilepsies to improve their value for epilepsy research. We encourage epilepsy researchers to use this resource to develop tools to identify individuals with rare epilepsies in electronic data sources.
PMCID:5839304
PMID: 29588993
ISSN: 2470-9239
CID: 3010882

From Sour Grapes to Low-Hanging Fruit: A Case Study Demonstrating a Practical Strategy for Natural Language Processing Portability

Johnson, Stephen B; Adekkanattu, Prakash; Campion, Thomas R; Flory, James; Pathak, Jyotishman; Patterson, Olga V; DuVall, Scott L; Major, Vincent; Aphinyanaphongs, Yindalon
Natural Language Processing (NLP) holds potential for patient care and clinical research, but a gap exists between promise and reality. While some studies have demonstrated portability of NLP systems across multiple sites, challenges remain. Strategies to mitigate these challenges can strive for complex NLP problems using advanced methods (hard-to-reach fruit), or focus on simple NLP problems using practical methods (low-hanging fruit). This paper investigates a practical strategy for NLP portability using extraction of left ventricular ejection fraction (LVEF) as a use case. We used a tool developed at the Department of Veterans Affair (VA) to extract the LVEF values from free-text echocardiograms in the MIMIC-III database. The approach showed an accuracy of 98.4%, sensitivity of 99.4%, a positive predictive value of 98.7%, and F-score of 99.0%. This experience, in which a simple NLP solution proved highly portable with excellent performance, illustrates the point that simple NLP applications may be easier to disseminate and adapt, and in the short term may prove more useful, than complex applications.
PMCID:5961788
PMID: 29888051
ISSN: 2153-4063
CID: 3154942

Ascertaining Depression Severity by Extracting Patient Health Questionnaire-9 (PHQ-9) Scores from Clinical Notes

Adekkanattu, Prakash; Sholle, Evan T; DeFerio, Joseph; Pathak, Jyotishman; Johnson, Stephen B; Campion, Thomas R
The Patient Health Questionnaire-9 (PHQ-9) is a validated instrument for assessing depression severity. While some electronic health record (EHR) systems capture PHQ-9 scores in a structured format, unstructured clinical notes remain the only source in many settings, which presents data retrieval challenges for research and clinical decision support. To address this gap, we extended the open-source Leo natural language processing (NLP) platform to extract PHQ-9 scores from clinical notes and evaluated performance using EHR data for n=123,703 patients who were prescribed antidepressants. Compared to a reference standard, the NLP method exhibited high accuracy (97%), sensitivity (98%), precision (97%), and F-score (97%). Furthermore, of patients with PHQ-9 scores identified by the NLP method, 31% (n=498) had at least one PHQ-9 score clinically indicative of major depressive disorder (MDD), but lacked a structured ICD-9/10 diagnosis code for MDD. This NLP technique may facilitate accurate identification and stratification of patients with depression.
PMCID:6371338
PMID: 30815052
ISSN: 1942-597x
CID: 4259152

Clinical Research Informatics: Supporting the Research Study Lifecycle

Johnson, S B
Objectives: The primary goal of this review is to summarize significant developments in the field of Clinical Research Informatics (CRI) over the years 2015-2016. The secondary goal is to contribute to a deeper understanding of CRI as a field, through the development of a strategy for searching and classifying CRI publications. Methods: A search strategy was developed to query the PubMed database, using medical subject headings to both select and exclude articles, and filtering publications by date and other characteristics. A manual review classified publications using stages in the "research study lifecycle", with key stages that include study definition, participant enrollment, data management, data analysis, and results dissemination. Results: The search strategy generated 510 publications. The manual classification identified 125 publications as relevant to CRI, which were classified into seven different stages of the research lifecycle, and one additional class that pertained to multiple stages, referring to general infrastructure or standards. Important cross-cutting themes included new applications of electronic media (Internet, social media, mobile devices), standardization of data and procedures, and increased automation through the use of data mining and big data methods. Conclusions: The review revealed increased interest and support for CRI in large-scale projects across institutions, regionally, nationally, and internationally. A search strategy based on medical subject headings can find many relevant papers, but a large number of non-relevant papers need to be detected using text words which pertain to closely related fields such as computational statistics and clinical informatics. The research lifecycle was useful as a classification scheme by highlighting the relevance to the users of clinical research informatics solutions.
PMCID:6239240
PMID: 29063565
ISSN: 2364-0502
CID: 3650952

Navigation in the electronic health record: A review of the safety and usability literature

Roman, Lisette C; Ancker, Jessica S; Johnson, Stephen B; Senathirajah, Yalini
OBJECTIVE:Inefficient navigation in electronic health records has been shown to increase users' cognitive load, which may increase potential for errors, reduce efficiency, and increase fatigue. However, navigation has received insufficient recognition and attention in the electronic health record (EHR) literature as an independent construct and contributor to overall usability. Our aims in this literature review were to (1) assess the prevalence of navigation-related topics within the EHR usability and safety research literature, (2) categorize types of navigation actions within the EHR, (3) capture relationships between these navigation actions and usability principles, and (4) collect terms and concepts related to EHR navigation. Our goal was to improve access to navigation-related research in usability. MATERIALS AND METHODS:We applied scoping literature review search methods with the assistance of a reference librarian to identify articles published since 1996 that reported evaluation of the usability or safety of an EHR user interface via user test, analytic methods, or inspection methods. The 4336 references collected from MEDLINE, EMBASE, Engineering Village, and expert referrals were de-duplicated and screened for relevance, and navigation-related concepts were abstracted from the 21 articles eligible for review using a standard abstraction form. RESULTS:Of the 21 eligible articles, 20 (95%) mentioned navigation in results and discussion of usability evaluations. Navigation between pages of the EHR was the more frequently documented type of navigation (86%) compared to navigation within a single page (14%). Navigation actions (e.g., scrolling through a medication list) were frequently linked to specific usability heuristic violations, among which flexibility and efficiency of use, recognition rather than recall, and error prevention were most common. DISCUSSION:Discussion of navigation was prevalent in results across all types of evaluation methods among the articles reviewed. Navigating between multiple screens was frequently identified as a usability barrier. The lack of standard terminology created some challenges to identifying and comparing articles. CONCLUSION:We observed that usability researchers are frequently capturing navigation-related issues even in articles that did not explicitly state navigation as a focus. Capturing and synthesizing the literature on navigation is challenging because of the lack of uniform vocabulary. Navigation is a potential target for normative recommendations for improved interaction design for safer systems. Future research in this domain, including development of normative recommendations for usability design and evaluation, will be facilitated by development of a standard terminology for describing EHR navigation.
PMID: 28088527
ISSN: 1532-0480
CID: 3586562

Secondary Use of Patients' Electronic Records (SUPER): An Approach for Meeting Specific Data Needs of Clinical and Translational Researchers

Sholle, Evan T; Kabariti, Joseph; Johnson, Stephen B; Leonard, John P; Pathak, Jyotishman; Varughese, Vinay I; Cole, Curtis L; Campion, Thomas R
Academic medical centers commonly approach secondary use of electronic health record (EHR) data by implementing centralized clinical data warehouses (CDWs). However, CDWs require extensive resources to model data dimensions and harmonize clinical terminology, which can hinder effective support of the specific and varied data needs of investigators. We hypothesized that an approach that aggregates raw data from source systems, ignores initial modeling typical of CDWs, and transforms raw data for specific research purposes would meet investigator needs. The approach has successfully enabled multiple tools that provide utility to the institutional research enterprise. To our knowledge, this is the first complete description of a methodology for electronic patient data acquisition and provisioning that ignores data harmonization at the time of initial storage in favor of downstream transformation to address specific research questions and applications.
PMCID:5977622
PMID: 29854228
ISSN: 1942-597x
CID: 3586572

Data management in clinical research: Synthesizing stakeholder perspectives

Johnson, Stephen B; Farach, Frank J; Pelphrey, Kevin; Rozenblit, Leon
OBJECTIVE:This study assesses data management needs in clinical research from the perspectives of researchers, software analysts and developers. MATERIALS AND METHODS/METHODS:This is a mixed-methods study that employs sublanguage analysis in an innovative manner to link the assessments. We performed content analysis using sublanguage theory on transcribed interviews conducted with researchers at four universities. A business analyst independently extracted potential software features from the transcriptions, which were translated into the sublanguage. This common sublanguage was then used to create survey questions for researchers, analysts and developers about the desirability and difficulty of features. Results were synthesized using the common sublanguage to compare stakeholder perceptions with the original content analysis. RESULTS:Individual researchers exhibited significant diversity of perspectives that did not correlate by role or site. Researchers had mixed feelings about their technologies, and sought improvements in integration, interoperability and interaction as well as engaging with study participants. Researchers and analysts agreed that data integration has higher desirability and mobile technology has lower desirability but disagreed on the desirability of data validation rules. Developers agreed that data integration and validation are the most difficult to implement. DISCUSSION/CONCLUSIONS:Researchers perceive tasks related to study execution, analysis and quality control as highly strategic, in contrast with tactical tasks related to data manipulation. Researchers have only partial technologic support for analysis and quality control, and poor support for study execution. CONCLUSION/CONCLUSIONS:Software for data integration and validation appears critical to support clinical research, but may be expensive to implement. Features to support study workflow, collaboration and engagement have been underappreciated, but may prove to be easy successes. Software developers should consider the strategic goals of researchers with regard to the overall coordination of research projects and teams, workflow connecting data collection with analysis and processes for improving data quality.
PMID: 26925516
ISSN: 1532-0480
CID: 3586552

Integrating an Informationist Into Graduate Education: Case Study With Preliminary Results

Tmanova, Lyubov L; Ancker, Jessica S; Johnson, Stephen B
An informationist taught, consulted, and mentored graduate students enrolled in a graduate research project course in Health Informatics. An observational cohort study was conducted to determine the effect of an early (first term) and continued (subsequent term) exposure of course-integrated instruction, individual consultations, information resource mentoring, and educational collaboration partnership on the development of information literacy, research skills, and integrative competencies in graduate students. Student progress was assessed by survey, class performance, and faculty feedback. The course-integrated lectures, consultations, mentoring, and educational partnership between the informationist and academic advisors increased the students' course performance, information literacy, and research skills in graduate students.
PMID: 26211791
ISSN: 1540-9597
CID: 3586542