Structured data entry for narrative data in a broad specialty: patient history and physical examination in pediatrics

Accelerating Food Allergy Research: Need for a Data Commons

Food allergy is a significant health problem affecting approximately 8% of children and 11% of adults in the United States. It exhibits all the characteristics of a "complex" genetic trait; therefore, it is necessary to look at very large numbers of patients, far more than exist at any single organization, to eliminate gaps in the current understanding of this complex chronic disorder. Advances may be achieved by bringing together food allergy data from large numbers of patients into a Data Commons, a secure and efficient platform for researchers, comprising standardized data, available in a common interface for download and/or analysis, in accordance with the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. Prior data commons initiatives indicate that research community consensus and support, formal food allergy ontology, data standards, an accepted platform and data management tools, an agreed upon infrastructure, and trusted governance are the foundation of any successful data commons. In this article, we will present the justification for the creation of a food allergy data commons and describe the core principles that can make it successful and sustainable.

Development of Food Allergy Data Dictionary: Toward a Food Allergy Data Commons

BACKGROUND

Food allergy (FA) data lacks a common base of terminology and hinders data exchange among institutions.

OBJECTIVE

To examine the current FA concept coverage by clinical terminologies and to develop and evaluate a Food Allergy Data Dictionary (FADD).

METHODS

Allergy/immunology templates and patient intake forms from 4 academic medical centers with expertise in FA were systematically reviewed, and in-depth discussions with a panel of FA experts were conducted to identify important FA clinical concepts and data elements. The candidate ontology was iteratively refined through a series of virtual meetings. The concepts were mapped to existing clinical terminologies manually with the ATHENA vocabulary browser. Finally, the revised dictionary document was vetted with experts across 22 academic FA centers and 3 industry partners.

RESULTS

A consensus version 1.0 FADD was finalized in November 2020. The FADD v1.0 contained 936 discrete FA concepts that were grouped into 14 categories. The categories included both FA-specific concepts, such as foods triggering reactions, and general health care categories, such as medications. Although many FA concepts are included in existing clinical terminologies, some critical concepts are missing.

CONCLUSIONS

The FADD provides a pragmatic tool that can enable improved structured coding of FA data for both research and clinical uses, as well as lay the foundation for the development of standardized FA structured data entry forms.

Think globally, act locally: Quality improvement as a catalyst for COVID-19 related care during the transitional years

The COVID-19 pandemic has posed distinctive challenges to adolescents and young adults living with spina bifida, especially those from ethic minority populations. With this public health challenge in mind, developing a customized electronic health record to leverage registry data to promote and quantify COVID-19 vaccination uptake among this population is feasible. We provide a brief description of our activities in customizing an electronic health record to track vaccination uptake among adolescents and young adults with spina bifida (AYASB); and the lessons learned, in hopeful support of those scaling-up vaccination delivery across the globe for AYASB as they transition to adult-centered care. Thus, as providers think globally and act locally, COVID-19 immunization efforts can be implemented while providing culturally appropriate transition policies and services for individuals with neurodevelopmental disabilities.

Can structured EHR data support clinical coding? A data mining approach

Structured data formats are gaining momentum in electronic health records and can be leveraged for decision support and research. Nevertheless, such structured data formats have not been explored for clinical coding, which is an essential process requiring significant manual workload in health organisations. This article explores the extent to which fully structured clinical data can support assignment of clinical codes to inpatient episodes, through a methodology that tackles high dimensionality issues, addresses the multi-label nature of coding and optimises model parameters. The methodology encompasses transformation of raw data to define a feature set, build a data matrix representation, and testing combinations of feature selection methods with machine learning models to predict code assignment. The methodology was tested with a real hospital dataset and showed varying predictive power across codes, while demonstrating the potential of leveraging structuring data to reduce workload and increase efficiency in clinical coding.

Defining the Roles of Data Manager and Epidemiologist in Emergency Medical Teams

Medical and epidemiological documentation in disasters is pivotal: the former for recording patient care and the latter for providing real-time information to the host country. Furthermore, documentation informs post-hoc analysis to improve the effectiveness of future deployments.Although documentation is considered important and indeed integral to health care response, there are many barriers and challenges. Some of these challenges include: working without well-established standards for medical documentation; and working with international guidelines which provide minimal guidance as to how health data should be managed practically to ensure accuracy and completion. Furthermore, there is a shift in mindset in disaster contexts wherein most health care focus shifts to direct clinical care and diverts almost all attention from quality documentation.This report distinguishes between the tasks of the epidemiologist and the data manager (DM) in an emergency medical team (EMT) and discusses the importance of data collection in the specific case of an EMT deployment. While combining these roles is sometimes possible if resources are limited, it is better to separate them, as the two are quite distinct. Although there is overlap, to achieve the goals of either role, preferentially they should be carried out by two people working closely together with complementary skill sets. The main objective of this report is to provide guidance and task descriptions to EMTs and field hospitals when training, recruiting, and preparing DMs and epidemiologists to work within their teams. Clear delineation of tasks will lead to better quality data, as it commits DMs to being concerned with the provision of real-time documentation from patient arrival through to compiling daily reports. It also commits epidemiologists to providing enhanced disease surveillance; outbreak investigation; and a source of reliable and actionable information for decision makers and stakeholders in the disaster management cycle.

Does Computerized Physician Order Entry Benefit from Dynamic Structured Data Entry? A Quasi-Experimental Study

Background

With advancements in information technology, computerized physician order entry (CPOE) and electronic Medical Records (eMR), have become widely utilized in medical settings. The predominant mode of CPOE in Taiwan is free text entry (FTE). Dynamic structured data entry (DSDE) was introduced more recently, and has increasingly drawn attention from hospitals across Taiwan. This study assesses how DSDE compares to FTE for CPOE.

Methods

A quasi-experimental study was employed to investigate the time-savings, productivity, and efficiency effects of DSDE in an outpatient setting in the gynecological department of a major hospital in Taiwan. Trained female actor patients were employed in trials of both entry methods. Data were submitted to Shapiro-Wilk and Shapiro-Francia tests to assess normality, and then to paired t-tests to assess differences between DSDE and FTE.

Results

Relative to FTE, the use of DSDE resulted in an average of 97% time saved and 55% more abundant and detailed content in medical records. In addition, for each clause entry in a medical record, the time saved is 133% for DSDE compared to FTE.

Conclusion

The results suggest that DSDE is a much more efficient and productive entry method for clinicians in hospital outpatient settings. Upgrading eMR systems to the DSDE format would benefit both patients and clinicians.

Using structured data entry systems in the electronic medical record to collect clinical data for quality and research: Can we efficiently serve multiple needs for complex patients with spina bifida?

PURPOSE

The era of the electronic health record (EHR) generates the ability to systematically collect and record innumerable data for complex procedures such as videourodynamic studies (VUDS). We developed a Structured Data Entry System (SDES) that would serve as a way to better standardize VUDS for both quality improvement and research capabilities.

METHODS

A working group convened to design a SDES form for VUDS in a flow sheet format in our hospital's EHR, allowing for easy integration of the information into the clinical encounter note and for weekly export of data to clinicians in spreadsheet form.

RESULTS

Analysis of weekly VUDS data revealed that entries were missing in 3% of cells in all SDES forms completed. The availability of the data in an Excel spreadsheet allows for easy manipulation, calculation of clinical variables, and streamlined analysis in figures or graphs to identify patients at the highest risk.

CONCLUSION

Designing and implementing a SDES based on a flowsheet that can allow data to be placed seamlessly in the clinical record and to be integrated into a searchable database for quality improvement and research purposes allows one to harness the true potential of the EHR.

Generating Clinical Notes for Electronic Health Record Systems

Clinical notes summarize interactions that occur between patients and healthcare providers. With adoption of electronic health record (EHR) and computer-based documentation (CBD) systems, there is a growing emphasis on structuring clinical notes to support reusing data for subsequent tasks. However, clinical documentation remains one of the most challenging areas for EHR system development and adoption. The current manuscript describes the Vanderbilt experience with implementing clinical documentation with an EHR system. Based on their experience rolling out an EHR system that supports multiple methods for clinical documentation, the authors recommend that documentation method selection be made on the basis of clinical workflow, note content standards and usability considerations, rather than on a theoretical need for structured data.

Bridging the discursive gap between lay and medical discourse in care coordination

For older people with multiple chronic co-morbidities, strategies to coordinate care depend heavily on information exchange. We analyse the information-sharing difficulties arising from differences between patients' oral narratives and medical sense-making; and whether a modified form of 'narrative medicine' might mitigate them. We systematically compared 66 general practice patients' own narratives of their health problems and care with the contents of their clinical records. Data were collected in England during 2012-13. Patients' narratives differed from the accounts in their medical record, especially the summary, regarding mobility, falls, mental health, physical frailty and its consequences for accessing care. Parts of patients' viewpoints were never formally encoded, parts were lost when clinicians de-coded it, parts supplemented, and sometimes the whole narrative was re-framed. These discrepancies appeared to restrict the patient record's utility even for GPs for the purposes of risk stratification, case management, knowing what other care-givers were doing, and coordinating care. The findings suggest combining the encoding/decoding theory of communication with inter-subjectivity and intentionality theories as sequential, complementary elements of an explanation of how patients communicate with clinicians. A revised form of narrative medicine might mitigate the discursive gap and its consequences for care coordination.

Compliance Is Contagious: Using Informatics Methods to Measure the Spread of a Documentation Standard From a Preoperative Clinic

PURPOSE

Preoperative documentation is essential to coordinated care and has the potential for standardization, which may facilitate downstream clinical management.

DESIGN

An observational pre/post standardization design was used.

METHODS

We analyzed the implementation of a preoperative documentation standardization intervention in Vanderbilt's Preoperative Evaluation Clinic (VPEC) and its impact outside VPEC. A phased intervention consisted of clinician education with monthly feedback, followed by the development of a compliance dashboard and inclusion in Ongoing Professional Performance Evaluation system by VPEC. A follow-up survey was administered to measure the impact on clinical management.

FINDINGS

Adherence to standardization was improved with the addition of electronic feedback. Implementation of this system in the preoperative clinic had significant impact outside VPEC. Trainee status was a significant predictor of adoption of the standardized format.

CONCLUSIONS

Adoption of a preoperative documentation standard in a clinic had a positive impact on standardization practices in a perioperative system.

Tool-supported Interactive Correction and Semantic Annotation of Narrative Clinical Reports

OBJECTIVES

Our main objective is to design a method of, and supporting software for, interactive correction and semantic annotation of narrative clinical reports, which would allow for their easier and less erroneous processing outside their original context: first, by physicians unfamiliar with the original language (and possibly also the source specialty), and second, by tools requiring structured information, such as decision-support systems. Our additional goal is to gain insights into the process of narrative report creation, including the errors and ambiguities arising therein, and also into the process of report annotation by clinical terms. Finally, we also aim to provide a dataset of ground-truth transformations (specific for Czech as the source language), set up by expert physicians, which can be reused in the future for subsequent analytical studies and for training automated transformation procedures.

METHODS

A three-phase preprocessing method has been developed to support secondary use of narrative clinical reports in electronic health record. Narrative clinical reports are narrative texts of healthcare documentation often stored in electronic health records. In the first phase a narrative clinical report is tokenized. In the second phase the tokenized clinical report is normalized. The normalized clinical report is easily readable for health professionals with the knowledge of the language used in the narrative clinical report. In the third phase the normalized clinical report is enriched with extracted structured information. The final result of the third phase is a semi-structured normalized clinical report where the extracted clinical terms are matched to codebook terms. Software tools for interactive correction, expansion and semantic annotation of narrative clinical reports has been developed and the three-phase preprocessing method validated in the cardiology area.

RESULTS

The three-phase preprocessing method was validated on 49 anonymous Czech narrative clinical reports in the field of cardiology. Descriptive statistics from the database of accomplished transformations has been calculated. Two cardiologists participated in the annotation phase. The first cardiologist annotated 1500 clinical terms found in 49 narrative clinical reports to codebook terms using the classification systems ICD 10, SNOMED CT, LOINC and LEKY. The second cardiologist validated annotations of the first cardiologist. The correct clinical terms and the codebook terms have been stored in a database.

CONCLUSIONS

We extracted structured information from Czech narrative clinical reports by the proposed three-phase preprocessing method and linked it to electronic health records. The software tool, although generic, is tailored for Czech as the specific language of electronic health record pool under study. This will provide a potential etalon for porting this approach to dozens of other less-spoken languages. Structured information can support medical decision making, quality assurance tasks and further medical research.

A Novel Graphical-Oriented Framework for Capturing Data within Clinical Information Systems

One of the main challenges in the development and implementation of computerized health care systems is the physicians and nurses’ resistance, stemming in particular from the use of text based environments for the capture of their medical examination data. The purpose of the present study was to propose the basis for a graphical oriented framework which can be used to capture data for a medical examination therefore easing the data-entry using the keyboard. Following analysis of a classical general medical examination, an XML schema was designed to describe physical examinations. Based on the physical examination XML schema, XML data structures are transformed to HTML using XML transformation style sheets to create dynamic graphical user interface (GUI) widgets; user interactions with the widgets leads to the generation of sentences. The key advantages of the proposed system are: a) a reduction in the keyboard usage, b) the ability to codify the generation sentence accurately and c) an operating system platform independence. A prototype of usage of the above framework is also presented.

Examining the value of electronic health records on labor and delivery

OBJECTIVE

The objective of the study was to evaluate the impact of an electronic health record (EHR) on documentation completeness and patient care in a labor and delivery unit.

STUDY DESIGN

We conducted a pre- and postintervention study to compare documentation quality and workflow before and after EHR implementation. Documentation was compared using chi(2) and Fisher's exact tests. Objective observers measured workflow activities across all shifts before and after EHR implementation and activities were compared using Kruskal-Wallis tests and analysis of covariance.

RESULTS

Paper admission records were significantly more likely to miss key clinical information such as chief complaints (contractions, membrane status, bleeding, fetal movement, 10-64% vs 2-5%; P < .0001) and prenatal laboratory results and history (Varicella, group B Streptococcus, human immunodeficiency virus, 26-66% vs 1-16%, P < .0001). Both direct patient care and computer activities increased after EHR implementation (2 vs 12 and 12 vs 17 activities/shift, respectively, P < .0001).

CONCLUSION

The introduction of an obstetric EHR improved documentation completeness without reducing direct patient care.

BioEMR: an integrative framework for cancer research with multiple genomic technologies

The rapid development of omic technologies facilitate cancer researchers to apply multiple genomic technologies simultaneously. In fact, the complex nature of cancer biology is the reason why we need tools for data integration. Given the complexity of managing multiple technologies and dataset formats, several projects have been introduced including cancer Biomedical Informatics Grid (caGRID) and the Biomedical Research Institute Domain Group (BRIDG) with limited applicability. We introduce an object-oriented data model, Cancer Genomics Object Model (CaGe-OM) for multiple genomics data and Xperanto-CaGe, a web-based application using CaGe-OM with hybrid object-relational mapping technique. The hybrid approach uses objectrelational mapping which is extended to include dynamic structure by using Entity-Attribute-Value (EAV) model. CaGe-OM and Xperanto-CaGe are an attempt to establish a comprehensive framework for integrated storage and interpretation of clinical and multiple genomics data and to facilitate model-level integration of other newly emerging data types. A pilot implementation for the integrated clinical, histo-pathological and genomic information systems is introduced.

Is OpenSDE an alternative for dedicated medical research databases? An example in coronary surgery

BACKGROUND

When using a conventional relational database approach to collect and query data in the context of specific clinical studies, a study with a new data set usually requires the design of a new database and entry forms. OpenSDE (SDE = Structured Data Entry) is intended to provide a flexible and intuitive way to create databases and entry forms for the collection of data in a structured format. This study illustrates the use of OpenSDE as a potential alternative to a conventional approach with respect to data modelling, database creation, data entry, and data extraction.

METHODS

A database and entry forms are created using OpenSDE and MSAccess to support collection of coronary surgery data, based on the Adult Cardiac Surgery Data Set of the Society of Thoracic Surgeons. Data of 52 cases are entered and nine different queries are designed, and executed on both databases.

RESULTS

Design of the data model and the creation of entry forms were experienced as more intuitive and less labor intensive with OpenSDE. Both resulting databases provided sufficient expressiveness to accommodate the data set. Data entry was more flexible with OpenSDE. Queries produced equal and correct results with comparable effort.

CONCLUSION

For prospective studies involving well-defined and straight forward data sets, OpenSDE deserves to be considered as an alternative to the conventional approach.

Do registro ao indicador: gestão da produção da informação assistencial nos hospitais

A valorização da utilização de indicadores assistenciais no monitoramento do desempenho dos sistemas de serviços de saúde cresceu de forma significativa nas últimas décadas. A expansão do Sistema Único de Saúde/SUS e do Sistema de Saúde Suplementar, e as formas de gestão adotadas estimularam o uso de indicadores na avaliação do desempenho, qualidade e segurança nos hospitais, sendo propostos sistemas de indicadores. Não houve uma correspondente preocupação com as condições de produção dos dados e informações para esses indicadores nos serviços de saúde. O artigo discute algumas das condições necessárias para a qualidade nos indicadores para a gestão da assistência nos hospitais: uma cultura de valorização da informação clínica, administrativa e de pesquisa, compartilhada por todos, e a adequada gestão dos registros clínicos, estatísticas hospitalares e sistemas de informações hospitalares. Não existem propostas prontas para a gestão da informação nos hospitais, fazendo-se necessário desenvolver uma capacidade institucional de incorporar e utilizar, na forma mais adequada para cada instituição e contexto, competências e recursos materiais e humanos diversificados, para que a gestão da informação se transforme em um processo dinâmico e parte da gestão do serviço como um todo.