Dataset Information

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation.

ABSTRACT: BACKGROUND:Widespread adoption of electronic health records has enabled the secondary use of electronic health record data for clinical research and health care delivery. Natural language processing techniques have shown promise in their capability to extract the information embedded in unstructured clinical data, and information retrieval techniques provide flexible and scalable solutions that can augment natural language processing systems for retrieving and ranking relevant records. OBJECTIVE:In this paper, we present the implementation of a cohort retrieval system that can execute textual cohort selection queries on both structured data and unstructured text-Cohort Retrieval Enhanced by Analysis of Text from Electronic Health Records (CREATE). METHODS:CREATE is a proof-of-concept system that leverages a combination of structured queries and information retrieval techniques on natural language processing results to improve cohort retrieval performance using the Observational Medical Outcomes Partnership Common Data Model to enhance model portability. The natural language processing component was used to extract common data model concepts from textual queries. We designed a hierarchical index to support the common data model concept search utilizing information retrieval techniques and frameworks. RESULTS:Our case study on 5 cohort identification queries, evaluated using the precision at 5 information retrieval metric at both the patient-level and document-level, demonstrates that CREATE achieves a mean precision at 5 of 0.90, which outperforms systems using only structured data or only unstructured text with mean precision at 5 values of 0.54 and 0.74, respectively. CONCLUSIONS:The implementation and evaluation of Mayo Clinic Biobank data demonstrated that CREATE outperforms cohort retrieval systems that only use one of either structured data or unstructured text in complex textual cohort queries.

SUBMITTER: Liu S

PROVIDER: S-EPMC7576539 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation.

Liu Sijia S Wang Yanshan Y Wen Andrew A Wang Liwei L Hong Na N Shen Feichen F Bedrick Steven S Hersh William W Liu Hongfang H

JMIR medical informatics 20201006 10

<h4>Background</h4>Widespread adoption of electronic health records has enabled the secondary use of electronic health record data for clinical research and health care delivery. Natural language processing techniques have shown promise in their capability to extract the information embedded in unstructured clinical data, and information retrieval techniques provide flexible and scalable solutions that can augment natural language processing systems for retrieving and ranking relevant records.<h ...[more]

PMID: 33021486

Similar Datasets

Project description:BackgroundElectronic health records (EHRs, such as those created by an anesthesia management system) generate a large amount of data that can notably be reused for clinical audits and scientific research. The sharing of these data and tools is generally affected by the lack of system interoperability. To overcome these issues, Observational Health Data Sciences and Informatics (OHDSI) developed the Observational Medical Outcomes Partnership (OMOP) common data model (CDM) to standardize EHR data and promote large-scale observational and longitudinal research. Anesthesia data have not previously been mapped into the OMOP CDM.ObjectiveThe primary objective was to transform anesthesia data into the OMOP CDM. The secondary objective was to provide vocabularies, queries, and dashboards that might promote the exploitation and sharing of anesthesia data through the CDM.MethodsUsing our local anesthesia data warehouse, a group of 5 experts from 5 different medical centers identified local concepts related to anesthesia. The concepts were then matched with standard concepts in the OHDSI vocabularies. We performed structural mapping between the design of our local anesthesia data warehouse and the OMOP CDM tables and fields. To validate the implementation of anesthesia data into the OMOP CDM, we developed a set of queries and dashboards.ResultsWe identified 522 concepts related to anesthesia care. They were classified as demographics, units, measurements, operating room steps, drugs, periods of interest, and features. After semantic mapping, 353 (67.7%) of these anesthesia concepts were mapped to OHDSI concepts. Further, 169 (32.3%) concepts related to periods and features were added to the OHDSI vocabularies. Then, 8 OMOP CDM tables were implemented with anesthesia data and 2 new tables (EPISODE and FEATURE) were added to store secondarily computed data. We integrated data from 5,72,609 operations and provided the code for a set of 8 queries and 4 dashboards related to anesthesia care.ConclusionsGeneric data concerning demographics, drugs, units, measurements, and operating room steps were already available in OHDSI vocabularies. However, most of the intraoperative concepts (the duration of specific steps, an episode of hypotension, etc) were not present in OHDSI vocabularies. The OMOP mapping provided here enables anesthesia data reuse.

Project description:BackgroundThe Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) has been implemented on various claims and electronic health record (EHR) databases, but has not been applied to a hospital transactional database. This study addresses the implementation of the OMOP CDM on the U.S. Premier Hospital database.MethodsWe designed and implemented an extract, transform, load (ETL) process to convert the Premier hospital database into the OMOP CDM. Standard charge codes in Premier were mapped between the OMOP version 4.0 Vocabulary and standard charge descriptions. Visit logic was added to impute the visit dates. We tested the conversion by replicating a published study using the raw and transformed databases. The Premier hospital database was compared to a claims database, in regard to prevalence of disease.FindingsThe data transformed into the CDM resulted in 1% of the data being discarded due to data errors in the raw data. A total of 91.4% of Premier standard charge codes were mapped successfully to a standard vocabulary. The results of the replication study resulted in a similar distribution of patient characteristics. The comparison to the claims data yields notable similarities and differences amongst conditions represented in both databases.DiscussionThe transformation of the Premier database into the OMOP CDM version 4.0 adds value in conducting analyses due to successful mapping of the drugs and procedures. The addition of visit logic gives ordinality to drugs and procedures that wasn't present prior to the transformation. Comparing conditions in Premier against a claims database can provide an understanding about Premier's potential use in pharmacoepidemiology studies that are traditionally conducted via claims databases.Conclusion and next stepsThe conversion of the Premier database into the OMOP CDM 4.0 was completed successfully. The next steps include refinement of vocabularies and mappings and continual maintenance of the transformed CDM.

Project description:OBJECTIVE:The use of electronic medical record (EMR) data is necessary to improve clinical research efficiency. However, it is not easy to identify patients who meet research eligibility criteria and collect the necessary information from EMRs because the data collection process must integrate various techniques, including the development of a data warehouse and translation of eligibility criteria into computable criteria. This research aimed to demonstrate an electronic medical records retrieval system (ERS) and an example of a hospital-based cohort study that identified both patients and exposure with an ERS. We also evaluated the feasibility and usefulness of the method. DESIGN:The system was developed and evaluated. PARTICIPANTS:In total, 800 000 cases of clinical information stored in EMRs at our hospital were used. PRIMARY AND SECONDARY OUTCOME MEASURES:The feasibility and usefulness of the ERS, the method to convert text from eligible criteria to computable criteria, and a confirmation method to increase research data accuracy. RESULTS:To comprehensively and efficiently collect information from patients participating in clinical research, we developed an ERS. To create the ERS database, we designed a multidimensional data model optimised for patient identification. We also devised practical methods to translate narrative eligibility criteria into computable parameters. We applied the system to an actual hospital-based cohort study performed at our hospital and converted the test results into computable criteria. Based on this information, we identified eligible patients and extracted data necessary for confirmation by our investigators and for statistical analyses with our ERS. CONCLUSIONS:We propose a pragmatic methodology to identify patients from EMRs who meet clinical research eligibility criteria. Our ERS allowed for the efficient collection of information on the eligibility of a given patient, reduced the labour required from the investigators and improved the reliability of the results.

Project description:BackgroundNational classifications and terminologies already routinely used for documentation within patient care settings enable the unambiguous representation of clinical information. However, the diversity of different vocabularies across health care institutions and countries is a barrier to achieving semantic interoperability and exchanging data across sites. The Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) enables the standardization of structure and medical terminology. It allows the mapping of national vocabularies into so-called standard concepts, representing normative expressions for international analyses and research. Within our project "Hybrid Quality Indicators Using Machine Learning Methods" (Hybrid-QI), we aim to harmonize source codes used in German claims data vocabularies that are currently unavailable in the OMOP CDM.ObjectiveThis study aims to increase the coverage of German vocabularies in the OMOP CDM. We aim to completely transform the source codes used in German claims data into the OMOP CDM without data loss and make German claims data usable for OMOP CDM-based research.MethodsTo prepare the missing German vocabularies for the OMOP CDM, we defined a vocabulary preparation approach consisting of the identification of all codes of the corresponding vocabularies, their assembly into machine-readable tables, and the translation of German designations into English. Furthermore, we used 2 proposed approaches for OMOP-compliant vocabulary preparation: the mapping to standard concepts using the Observational Health Data Sciences and Informatics (OHDSI) tool Usagi and the preparation of new 2-billion concepts (ie, concept_id >2 billion). Finally, we evaluated the prepared vocabularies regarding completeness and correctness using synthetic German claims data and calculated the coverage of German claims data vocabularies in the OMOP CDM.ResultsOur vocabulary preparation approach was able to map 3 missing German vocabularies to standard concepts and prepare 8 vocabularies as new 2-billion concepts. The completeness evaluation showed that the prepared vocabularies cover 44.3% (3288/7417) of the source codes contained in German claims data. The correctness evaluation revealed that the specified validity periods in the OMOP CDM are compliant for the majority (705,531/706,032, 99.9%) of source codes and associated dates in German claims data. The calculation of the vocabulary coverage showed a noticeable decrease of missing vocabularies from 55% (11/20) to 10% (2/20) due to our preparation approach.ConclusionsBy preparing 10 vocabularies, we showed that our approach is applicable to any type of vocabulary used in a source data set. The prepared vocabularies are currently limited to German vocabularies, which can only be used in national OMOP CDM research projects, because the mapping of new 2-billion concepts to standard concepts is missing. To participate in international OHDSI network studies with German claims data, future work is required to map the prepared 2-billion concepts to standard concepts.

Dataset Information

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation.

Publications

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets