Dataset Information

Developing a scalable FHIR-based clinical data normalization pipeline for standardizing and integrating unstructured and structured electronic health record data.

ABSTRACT:

Objective

To design, develop, and evaluate a scalable clinical data normalization pipeline for standardizing unstructured electronic health record (EHR) data leveraging the HL7 Fast Healthcare Interoperability Resources (FHIR) specification.

Methods

We established an FHIR-based clinical data normalization pipeline known as NLP2FHIR that mainly comprises: (1) a module for a core natural language processing (NLP) engine with an FHIR-based type system; (2) a module for integrating structured data; and (3) a module for content normalization. We evaluated the FHIR modeling capability focusing on core clinical resources such as Condition, Procedure, MedicationStatement (including Medication), and FamilyMemberHistory using Mayo Clinic's unstructured EHR data. We constructed a gold standard reusing annotation corpora from previous NLP projects.

Results

A total of 30 mapping rules, 62 normalization rules, and 11 NLP-specific FHIR extensions were created and implemented in the NLP2FHIR pipeline. The elements that need to integrate structured data from each clinical resource were identified. The performance of unstructured data modeling achieved F scores ranging from 0.69 to 0.99 for various FHIR element representations (0.69-0.99 for Condition; 0.75-0.84 for Procedure; 0.71-0.99 for MedicationStatement; and 0.75-0.95 for FamilyMemberHistory).

Conclusion

We demonstrated that the NLP2FHIR pipeline is feasible for modeling unstructured EHR data and integrating structured elements into the model. The outcomes of this work provide standards-based tools of clinical data normalization that is indispensable for enabling portable EHR-driven phenotyping and large-scale data analytics, as well as useful insights for future developments of the FHIR specifications with regard to handling unstructured clinical data.

SUBMITTER: Hong N

PROVIDER: S-EPMC6993992 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Developing a scalable FHIR-based clinical data normalization pipeline for standardizing and integrating unstructured and structured electronic health record data.

Hong Na N Wen Andrew A Shen Feichen F Sohn Sunghwan S Wang Chen C Liu Hongfang H Jiang Guoqian G

JAMIA open 20191018 4

<h4>Objective</h4>To design, develop, and evaluate a scalable clinical data normalization pipeline for standardizing unstructured electronic health record (EHR) data leveraging the HL7 Fast Healthcare Interoperability Resources (FHIR) specification.<h4>Methods</h4>We established an FHIR-based clinical data normalization pipeline known as NLP2FHIR that mainly comprises: (1) a module for a core natural language processing (NLP) engine with an FHIR-based type system; (2) a module for integrating st ...[more]

PMID: 32025655

Similar Datasets

Project description:BackgroundMerging disparate and heterogeneous datasets from clinical routine in a standardized and semantically enriched format to enable a multiple use of data also means incorporating unstructured data such as medical free texts. Although the extraction of structured data from texts, known as natural language processing (NLP), has been researched at least for the English language extensively, it is not enough to get a structured output in any format. NLP techniques need to be used together with clinical information standards such as openEHR to be able to reuse and exchange still unstructured data sensibly.ObjectivesThe aim of the study is to automatically extract crucial information from medical free texts and to transform this unstructured clinical data into a standardized and structured representation by designing and implementing an exemplary pipeline for the processing of pediatric medical histories.MethodsWe constructed a pipeline that allows reusing medical free texts such as pediatric medical histories in a structured and standardized way by (1) selecting and modeling appropriate openEHR archetypes as standard clinical information models, (2) defining a German dictionary with crucial text markers serving as expert knowledge base for a NLP pipeline, and (3) creating mapping rules between the NLP output and the archetypes. The approach was evaluated in a first pilot study by using 50 manually annotated medical histories from the pediatric intensive care unit of the Hannover Medical School.ResultsWe successfully reused 24 existing international archetypes to represent the most crucial elements of unstructured pediatric medical histories in a standardized form. The self-developed NLP pipeline was constructed by defining 3.055 text marker entries, 132 text events, 66 regular expressions, and a text corpus consisting of 776 entries for automatic correction of spelling mistakes. A total of 123 mapping rules were implemented to transform the extracted snippets to an openEHR-based representation to be able to store them together with other structured data in an existing openEHR-based data repository. In the first evaluation, the NLP pipeline yielded 97% precision and 94% recall.ConclusionThe use of NLP and openEHR archetypes was demonstrated as a viable approach for extracting and representing important information from pediatric medical histories in a structured and semantically enriched format. We designed a promising approach with potential to be generalized, and implemented a prototype that is extensible and reusable for other use cases concerning German medical free texts. In a long term, this will harness unstructured clinical data for further research purposes such as the design of clinical decision support systems. Together with structured data already integrated in openEHR-based representations, we aim at developing an interoperable openEHR-based application that is capable of automatically assessing a patient's risk status based on the patient's medical history at time of admission.

Project description:BackgroundEfficient triage in emergency departments (EDs) is critical for timely and appropriate care. Traditional triage systems primarily rely on structured data, but the increasing availability of unstructured data, such as clinical notes, presents an opportunity to enhance predictive models for assessing emergency severity and to explore associations between patient characteristics and severity outcomes. This study aimed to evaluate the effectiveness of combining structured and unstructured data to predict emergency severity more accurately.MethodsData from the 2021 National Hospital Ambulatory Medical Care Survey (NHAMCS) for adult ED patients were used. Emergency severity was categorized into urgent (scores 1-3) and non-urgent (scores 4-5) based on the Emergency Severity Index. Unstructured data, including chief complaints and reasons for visit, were processed using a Bidirectional Encoder Representations from Transformers (BERT) model. Structured data included patient demographics and clinical information. Four machine learning models-Logistic Regression, Random Forest, Gradient Boosting, and Extreme Gradient Boosting-were applied to three data configurations: structured data only, unstructured data only, and combined data. A mean probability model was also created by averaging the predicted probabilities from the structured and unstructured models.ResultsThe study included 8,716 adult patients, of whom 74.6% were classified as urgent. Association analysis revealed significant predictors of emergency severity, including older age (OR = 2.13 for patients 65 +), higher heart rate (OR = 1.56 for heart rates > 90 bpm), and specific chronic conditions such as chronic kidney disease (OR = 2.28) and coronary artery disease (OR = 2.55). Gradient Boosting with combined data demonstrated the highest performance, achieving an area under the curve (AUC) of 0.789, an accuracy of 0.726, and a precision of 0.892. The mean probability model also showed improvements over structured-only models.ConclusionsCombining structured and unstructured data improved the prediction of emergency severity in ED patients, highlighting the potential for enhanced triage systems. Integrating text data into predictive models can provide more accurate and nuanced severity assessments, improving resource allocation and patient outcomes. Further research should focus on real-time application and validation in diverse clinical settings.

Project description:BackgroundEnvironmental exposures such as airborne pollutant exposures and socio-economic indicators are increasingly recognized as important to consider when conducting clinical research using electronic health record (EHR) data or other sources of clinical data such as survey data. While numerous public sources of geospatial and spatiotemporal data are available to support such research, the data are challenging to work with due to inconsistencies in file formats and spatiotemporal resolutions, computational challenges with large file sizes, and a lack of tools for patient- or subject-level data integration.ResultsWe developed FHIR PIT (HL7® Fast Healthcare Interoperability Resources Patient data Integration Tool) as an open-source, modular, data-integration software pipeline that consumes EHR data in FHIR® format and integrates the data at the level of the patient or subject with environmental exposures data of varying spatiotemporal resolutions and file formats. We applied FHIR PIT to generate "integrated feature tables" containing patient- or subject-level EHR data integrated with environmental exposures data on two cohorts: one on patients with asthma and related common pulmonary disorders; and a second on patients with primary ciliary dyskinesia and related rare pulmonary disorders. The data were then exposed via the open Integrated Clinical and Environmental Exposures Service, which was then queried to explore relationships between exposures to two representative airborne pollutants (particulate matter and ozone) and annual emergency department or inpatient visits for respiratory issues. We found that hospitalizations for respiratory issues were more common among patients exposed to relatively high levels of particulate matter and ozone and were higher overall among patients with primary ciliary dyskinesia than among patients with asthma.ConclusionsOur manuscript describes a major release of FHIR PIT v1.0 and includes a technical demonstration use case and a clinical application on the use of FHIR PIT to support research on environmental exposures and health outcomes related to asthma and primary ciliary dyskinesia. For application of the tool to common data models (CDMs) other than FHIR, we offer open-source conversion tools to map from the PCORnet, i2b2, and OMOP CDMs to FHIR.

Project description:IntroductionKeloids are lesions characterized by the growth of dense fibrous tissue extending beyond original wound boundaries. Research into the natural history of keloids and potential differences by sociodemographic factors in the USA is limited. This real-world, retrospective cohort study aimed to characterize a population of patients with keloids compared with matched dermatology and general cohorts.MethodsPatients with ≥ 2 International Classification of Diseases codes for keloid ≥ 30 days apart and a confirmed keloid diagnosis from clinical notes enrolled in the OM1 Real-World Data Cloud between 1 January 2013 and 18 March 2022 were age- and sex-matched 1:1:1 to patients without keloids who visited dermatologists ("dermatology cohort") and those who did not ("general cohort"). Results are presented using descriptive statistics and analysis stratified by cohort, race, ethnicity, household income, and education.ResultsOverall, 24,453 patients with keloids were matched to 23,936 dermatology and 24,088 general patients. A numerically higher proportion of patients with keloids were Asian or Black. Among available data for patients with keloids, 67.7% had 1 keloid lesion, and 68.3% had keloids sized 0.5 to < 3 cm. Black patients tended to have larger keloids. Asian and Black patients more frequently had > 1 keloid than did white patients (30.6% vs. 32.5% vs. 20.5%). Among all patients with keloids who had available data, 56.4% had major keloid severity, with major severity more frequent in Black patients. Progression was not significantly associated with race, ethnicity, income, or education level; 29%, 25%, and 20% of the dermatology, keloid, and general cohorts were in the highest income bracket (≥ US$75,000). The proportion of patients with income below the federal poverty line (< US$22,000) and patterns of education level were similar across cohorts.ConclusionA large population of patients in the USA with keloids was identified and characterized using structured/unstructured sources. A numerically higher proportion of patients with keloids were non-white; Black patients had larger, more severe keloids at diagnosis.

Dataset Information

Developing a scalable FHIR-based clinical data normalization pipeline for standardizing and integrating unstructured and structured electronic health record data.

Objective

Methods

Results

Conclusion

Publications

Developing a scalable FHIR-based clinical data normalization pipeline for standardizing and integrating unstructured and structured electronic health record data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets