Clinical code set engineering for reusing EHR data for research: A review

The reuse of electronic health records information models in the oncology domain: Studies with the bioframe framework

OBJECTIVE

The reuse of Electronic Health Records (EHR) information models (e.g., templates and archetypes) may bring various benefits, including higher standardization, integration, interoperability, increased productivity in developing EHR systems, and unlock potential Artificial Intelligence applications built on top of medical records. The literature presents recent advances in standards for modeling EHR, in Knowledge Organization Systems (KOS) and EHR data reuse. However, methods, development processes, and frameworks to improve the reuse of EHR information models are still scarce. This study proposes a software engineering framework, named BioFrame, and analyzes how the reuse of EHR information models can be improved during the development of EHR systems.

METHODS

EHR standards and KOS, including ontologies, identified from systematic reviews were considered in developing the BioFrame framework. We used the structure of the OpenEHR to model templates and archetypes, as well as its relationship to international KOS used in the oncology domain. Our framework was applied in the context of pediatric oncology. Three data entry forms concerning nutrition and one utilized during the first pediatric oncology consultations were analyzed to measure the reuse of information models.

RESULTS

There was an increase in the adherence rate to international KOS of 18% to the original forms. There was an increase in the concepts reused in all 12 scenarios analyzed, with an average reuse of 6.55% in the original forms compared to 17.1% using BioFrame, resulting in significant differences.

CONCLUSIONS

Our results point to higher reuse rates achieved due to an engineering process that provided greater adherence to EHR standards combined with semantic artifacts. This reveals the potential to develop new methods and frameworks aimed at EHR information model reuse. Additional research is needed to evaluate the impacts of the reuse of the EHR information model on interoperability, EHR data reuse, and data quality and assess the proposed framework in other health domains.

A Qualitative Study of Physicians' Views on the Reuse of Electronic Health Record Data for Secondary Analysis

Electronic health records (EHRs) have become ubiquitous in clinical practice. Given the rich biomedical data captured for a large panel of patients, secondary analysis of these data for health research is also commonplace. Yet, there are many caveats to EHR data that the researchers must be aware of, such as the accuracy of and motive for documentation, and the reason for patients' visits to the clinic. The clinician-the author of the documentation-is thus central to the correct interpretation of EHR data for research purposes. In this study, I interviewed 11 physicians in various clinical specialties to bring attention to their view on the validity of research using EHR data. Qualitative, in-depth, one-on-one interviews were conducted with practicing physicians in inpatient and outpatient medicine. Content analysis using a data-driven, inductive approach to identify themes related to challenges and opportunities in the reuse of EHR data for secondary analysis generated seven themes. Themes that reflected challenges of EHRs for research included (1) audience, (2) accuracy of data, (3) availability of data, (4) documentation practices, and (5) representativeness. Themes that reflected opportunities of EHRs for research included (6) endorsement and (7) enablers. The greatest perceived barriers reflected the intended audience of the EHR, the interpretation and meaning of the data, and the quality of the data for research purposes. Physicians generally expressed more perceived challenges than opportunities in the reuse of EHR data for research purposes; however, they remained optimistic.

Electronic health records identify timely trends in childhood mental health conditions

BACKGROUND

Electronic health records (EHRs) data provide an opportunity to collect patient information rapidly, efficiently and at scale. National collaborative research networks, such as PEDSnet, aggregate EHRs data across institutions, enabling rapid identification of pediatric disease cohorts and generating new knowledge for medical conditions. To date, aggregation of EHR data has had limited applications in advancing our understanding of mental health (MH) conditions, in part due to the limited research in clinical informatics, necessary for the translation of EHR data to child mental health research.

METHODS

In this cohort study, a comprehensive EHR-based typology was developed by an interdisciplinary team, with expertise in informatics and child and adolescent psychiatry, to query aggregated, standardized EHR data for the full spectrum of MH conditions (disorders/symptoms and exposure to adverse childhood experiences (ACEs), across 13 years (2010-2023), from 9 PEDSnet centers. Patients with and without MH disorders/symptoms (without ACEs), were compared by age, gender, race/ethnicity, insurance, and chronic physical conditions. Patients with ACEs alone were compared with those that also had MH disorders/symptoms. Prevalence estimates for patients with 1+ disorder/symptoms and for specific disorders/symptoms and exposure to ACEs were calculated, as well as risk for developing MH disorder/symptoms.

RESULTS

The EHR study data set included 7,852,081 patients < 21 years of age, of which 52.1% were male. Of this group, 1,552,726 (19.8%), without exposure to ACEs, had a lifetime MH disorders/symptoms, 56.5% being male. Annual prevalence estimates of MH disorders/symptoms (without exposure to ACEs) rose from 10.6% to 2010 to 15.1% in 2023, a 44% relative increase, peaking to 15.4% in 2019, prior to the Covid-19 pandemic. MH categories with the largest increases between 2010 and 2023 were exposure to ACEs (1.7, 95% CI 1.6-1.8), anxiety disorders (2.8, 95% CI 2.8-2.9), eating/feeding disorders (2.1, 95% CI 2.1-2.2), gender dysphoria/sexual dysfunction (43.6, 95% CI 35.8-53.0), and intentional self-harm/suicidality (3.3, 95% CI 3.2-3.5). White youths had the highest rates in most categories, except for disruptive behavior disorders, elimination disorders, psychotic disorders, and standalone symptoms which Black youths had higher rates. Median age of detection was 8.1 years (IQR 3.5-13.5) with all standalone symptoms recorded earlier than the corresponding MH disorder categories.

CONCLUSIONS

These results support EHRs' capability in capturing the full spectrum of MH disorders/symptoms and exposure to ACEs, identifying the proportion of patients and groups at risk, and detecting trends throughout a 13-year period that included the Covid-19 pandemic. Standardized EHR data, which capture MH conditions is critical for health systems to examine past and current trends for future surveillance. Our publicly available EHR-mental health typology codes can be used in other studies to further advance research in this area.

Translating and evaluating historic phenotyping algorithms using SNOMED CT

OBJECTIVE

Patient phenotype definitions based on terminologies are required for the computational use of electronic health records. Within UK primary care research databases, such definitions have typically been represented as flat lists of Read terms, but Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) (a widely employed international reference terminology) enables the use of relationships between concepts, which could facilitate the phenotyping process. We implemented SNOMED CT-based phenotyping approaches and investigated their performance in the CPRD Aurum primary care database.

MATERIALS AND METHODS

We developed SNOMED CT phenotype definitions for 3 exemplar diseases: diabetes mellitus, asthma, and heart failure, using 3 methods: "primary" (primary concept and its descendants), "extended" (primary concept, descendants, and additional relations), and "value set" (based on text searches of term descriptions). We also derived SNOMED CT codelists in a semiautomated manner for 276 disease phenotypes used in a study of health across the lifecourse. Cohorts selected using each codelist were compared to "gold standard" manually curated Read codelists in a sample of 500 000 patients from CPRD Aurum.

RESULTS

SNOMED CT codelists selected a similar set of patients to Read, with F1 scores exceeding 0.93, and age and sex distributions were similar. The "value set" and "extended" codelists had slightly greater recall but lower precision than "primary" codelists. We were able to represent 257 of the 276 phenotypes by a single concept hierarchy, and for 135 phenotypes, the F1 score was greater than 0.9.

CONCLUSIONS

SNOMED CT provides an efficient way to define disease phenotypes, resulting in similar patient populations to manually curated codelists.

Computational drug repurposing based on electronic health records: a scoping review

Computational drug repurposing methods adapt Artificial intelligence (AI) algorithms for the discovery of new applications of approved or investigational drugs. Among the heterogeneous datasets, electronic health records (EHRs) datasets provide rich longitudinal and pathophysiological data that facilitate the generation and validation of drug repurposing. Here, we present an appraisal of recently published research on computational drug repurposing utilizing the EHR. Thirty-three research articles, retrieved from Embase, Medline, Scopus, and Web of Science between January 2000 and January 2022, were included in the final review. Four themes, (1) publication venue, (2) data types and sources, (3) method for data processing and prediction, and (4) targeted disease, validation, and released tools were presented. The review summarized the contribution of EHR used in drug repurposing as well as revealed that the utilization is hindered by the validation, accessibility, and understanding of EHRs. These findings can support researchers in the utilization of medical data resources and the development of computational methods for drug repurposing.

Establishing a National Cardiovascular Disease Surveillance System in the United States Using Electronic Health Record Data: Key Strengths and Limitations

Cardiovascular disease surveillance involves quantifying the evolving population-level burden of cardiovascular outcomes and risk factors as a data-driven initial step followed by the implementation of interventional strategies designed to alleviate this burden in the target population. Despite widespread acknowledgement of its potential value, a national surveillance system dedicated specifically to cardiovascular disease does not currently exist in the United States. Routinely collected health care data such as from electronic health records (EHRs) are a possible means of achieving national surveillance. Accordingly, this article elaborates on some key strengths and limitations of using EHR data for establishing a national cardiovascular disease surveillance system. Key strengths discussed include the: (1) ubiquity of EHRs and consequent ability to create a more "national" surveillance system, (2) existence of a common data infrastructure underlying the health care enterprise with respect to data domains and the nomenclature by which these data are expressed, (3) longitudinal length and detail that define EHR data when individuals repeatedly patronize a health care organization, and (4) breadth of outcomes capable of being surveilled with EHRs. Key limitations discussed include the: (1) incomplete ascertainment of health information related to health care-seeking behavior and the disconnect of health care data generated at separate health care organizations, (2) suspect data quality resulting from the default information-gathering processes within the clinical enterprise, (3) questionable ability to surveil patients through EHRs in the absence of documented interactions, and (4) the challenge in interpreting temporal trends in health metrics, which can be obscured by changing clinical and administrative processes.

Curating a longitudinal research resource using linked primary care EHR data-a UK Biobank case study

Primary care EHR data are often of clinical importance to cohort studies however they require careful handling. Challenges include determining the periods during which EHR data were collected. Participants are typically censored when they deregister from a medical practice, however, cohort studies wish to follow participants longitudinally including those that change practice. Using UK Biobank as an exemplar, we developed methodology to infer continuous periods of data collection and maximize follow-up in longitudinal studies. This resulted in longer follow-up for around 40% of participants with multiple registration records (mean increase of 3.8 years from the first study visit). The approach did not sacrifice phenotyping accuracy when comparing agreement between self-reported and EHR data. A diabetes mellitus case study illustrates how the algorithm supports longitudinal study design and provides further validation. We use UK Biobank data, however, the tools provided can be used for other conditions and studies with minimal alteration.

Development of Prediction Models for Unplanned Hospital Readmission within 30 Days Based on Common Data Model: A Feasibility Study

Background  Unplanned hospital readmission after discharge reflects low satisfaction and reliability in care and the possibility of potential medical accidents, and is thus indicative of the quality of patient care and the appropriateness of discharge plans.

Objectives  The purpose of this study was to develop and validate prediction models for all-cause unplanned hospital readmissions within 30 days of discharge, based on a common data model (CDM), which can be applied to multiple institutions for efficient readmission management.

Methods  Retrospective patient-level prediction models were developed based on clinical data of two tertiary general university hospitals converted into a CDM developed by Observational Medical Outcomes Partnership. Machine learning classification models based on the LASSO logistic regression model, decision tree, AdaBoost, random forest, and gradient boosting machine (GBM) were developed and tested by manipulating a set of CDM variables. An internal 10-fold cross-validation was performed on the target data of the model. To examine its transportability, the model was externally validated. Verification indicators helped evaluate the model performance based on the values of area under the curve (AUC).

Results  Based on the time interval for outcome prediction, it was confirmed that the prediction model targeting the variables obtained within 30 days of discharge was the most efficient (AUC of 82.75). The external validation showed that the model is transferable, with the combination of various clinical covariates. Above all, the prediction model based on the GBM showed the highest AUC performance of 84.14 ± 0.015 for the Seoul National University Hospital cohort, yielding in 78.33 in external validation.

Conclusions  This study showed that readmission prediction models developed using machine-learning techniques and CDM can be a useful tool to compare two hospitals in terms of patient-data features.

Deriving Weight from Big Data: A Comparison of Body Weight Measurement Cleaning Algorithms (Preprint)

Background

Patient body weight is a frequently used measure in biomedical studies, yet there are no standard methods for processing and cleaning weight data. Conflicting documentation on constructing body weight measurements presents challenges for research and program evaluation.

Objective

In this study, we aim to describe and compare methods for extracting and cleaning weight data from electronic health record databases to develop guidelines for standardized approaches that promote reproducibility.

Methods

We conducted a systematic review of studies published from 2008 to 2018 that used Veterans Health Administration electronic health record weight data and documented the algorithms for constructing patient weight. We applied these algorithms to a cohort of veterans with at least one primary care visit in 2016. The resulting weight measures were compared at the patient and site levels.

Results

We identified 496 studies and included 62 (12.5%) that used weight as an outcome. Approximately 48% (27/62) included a replicable algorithm. Algorithms varied from cutoffs of implausible weights to complex models using measures within patients over time. We found differences in the number of weight values after applying the algorithms (71,961/1,175,995, 6.12% to 1,175,177/1,175,995, 99.93% of raw data) but little difference in average weights across methods (93.3, SD 21.0 kg to 94.8, SD 21.8 kg). The percentage of patients with at least 5% weight loss over 1 year ranged from 9.37% (4933/52,642) to 13.99% (3355/23,987).

Conclusions

Contrasting algorithms provide similar results and, in some cases, the results are not different from using raw, unprocessed data despite algorithm complexity. Studies using point estimates of weight may benefit from a simple cleaning rule based on cutoffs of implausible values; however, research questions involving weight trajectories and other, more complex scenarios may benefit from a more nuanced algorithm that considers all available weight data.

Use of standardized terminologies in clinical practice: A scoping review

AIM

To explore the use and impact of standardized terminologies (STs) within nursing and midwifery practice.

INTRODUCTION

The standardization of clinical documentation creates a potential to optimize patient care and safety. Nurses and midwives, who represent the largest proportion of the healthcare workforce worldwide, have been using nursing-specific and multidisciplinary STs within electronic health records (EHRs) for decades. However, little is known regarding ST use and impact within clinical practice.

METHODS

A scoping review of the literature was conducted (2019) across PubMed, CINAHL, Embase and CENTRAL in collaboration with the Five Country Nursing and Midwifery Digital Leadership Group (DLG). Identified studies (n = 3547) were reviewed against a number of agreed criterion, and data were extracted from included studies. Studies were categorized and findings were reviewed by the DLG.

RESULTS

One hundred and eighty three studies met the inclusion criteria. These were conducted across 25 different countries and in various healthcare settings, utilising mainly nursing-specific (most commonly NANDA-I, NIC, NOC and the Omaha System) and less frequently local, multidisciplinary or medical STs (e.g., ICD). Within the studies, STs were evaluated in terms of Measurement properties, Usability, Documentation quality, Patient care, Knowledge generation, and Education (pre and post registration). As well as the ST content, the impact of the ST on practice depended on the healthcare setting, patient cohort, nursing experience, provision of education and support in using the ST, and usability of EHRs.

CONCLUSION

Employment of STs in clinical practice has the capability to improve communication, quality of care and interoperability, as well as facilitate value-based healthcare and knowledge generation. However, employment of several different STs and study heterogeneity renders it difficult to aggregate and generalize findings.

Coding Systems for Clinical Decision Support: Theoretical and Real-World Comparative Analysis

Background

Effective clinical decision support systems require accurate translation of practice recommendations into machine-readable artifacts; developing code sets that represent clinical concepts are an important step in this process. Many clinical coding systems are currently used in electronic health records, and it is unclear whether all of these systems are capable of efficiently representing the clinical concepts required in executing clinical decision support systems.

Objective

The aim of this study was to evaluate which clinical coding systems are capable of efficiently representing clinical concepts that are necessary for translating artifacts into executable code for clinical decision support systems.

Methods

Two methods were used to evaluate a set of clinical coding systems. In a theoretical approach, we extracted all the clinical concepts from 3 preventive care recommendations and constructed a series of code sets containing codes from a single clinical coding system. In a practical approach using data from a real-world setting, we studied the content of 1890 code sets used in an internationally available clinical decision support system and compared the usage of various clinical coding systems.

Results

SNOMED CT and ICD-10 (International Classification of Diseases, Tenth Revision) proved to be the most accurate clinical coding systems for most concepts in our theoretical evaluation. In our practical evaluation, we found that International Classification of Diseases (Tenth Revision) was most often used to construct code sets. Some coding systems were very accurate in representing specific types of clinical concepts, for example, LOINC (Logical Observation Identifiers Names and Codes) for investigation results and ATC (Anatomical Therapeutic Chemical Classification) for drugs.

Conclusions

No single coding system seems to fulfill all the needs for representing clinical concepts for clinical decision support systems. Comprehensiveness of the coding systems seems to be offset by complexity and forms a barrier to usability for code set construction. Clinical vocabularies mapped to multiple clinical coding systems could facilitate clinical code set construction.

Diagnosis of physical and mental health conditions in primary care during the COVID-19 pandemic: a retrospective cohort study

BACKGROUND

To date, research on the indirect impact of the COVID-19 pandemic on the health of the population and the health-care system is scarce. We aimed to investigate the indirect effect of the COVID-19 pandemic on general practice health-care usage, and the subsequent diagnoses of common physical and mental health conditions in a deprived UK population.

METHODS

We did a retrospective cohort study using routinely collected primary care data that was recorded in the Salford Integrated Record between Jan 1, 2010, and May 31, 2020. We extracted the weekly number of clinical codes entered into patient records overall, and for six high-level categories: symptoms and observations, diagnoses, prescriptions, operations and procedures, laboratory tests, and other diagnostic procedures. Negative binomial regression models were applied to monthly counts of first diagnoses of common conditions (common mental health problems, cardiovascular and cerebrovascular disease, type 2 diabetes, and cancer), and corresponding first prescriptions of medications indicative of these conditions. We used these models to predict the expected numbers of first diagnoses and first prescriptions between March 1 and May 31, 2020, which were then compared with the observed numbers for the same time period.

FINDINGS

Between March 1 and May 31, 2020, 1073 first diagnoses of common mental health problems were reported compared with 2147 expected cases (95% CI 1821 to 2489) based on preceding years, representing a 50·0% reduction (95% CI 41·1 to 56·9). Compared with expected numbers, 456 fewer diagnoses of circulatory system diseases (43·3% reduction, 95% CI 29·6 to 53·5), and 135 fewer type 2 diabetes diagnoses (49·0% reduction, 23·8 to 63·1) were observed. The number of first prescriptions of associated medications was also lower than expected for the same time period. However, the gap between observed and expected cancer diagnoses (31 fewer; 16·0% reduction, -18·1 to 36·6) during this time period was not statistically significant.

INTERPRETATION

In this deprived urban population, diagnoses of common conditions decreased substantially between March and May 2020, suggesting a large number of patients have undiagnosed conditions. A rebound in future workload could be imminent as COVID-19 restrictions ease and patients with undiagnosed conditions or delayed diagnosis present to primary and secondary health-care services. Such services should prioritise the diagnosis and treatment of these patients to mitigate potential indirect harms to protect public health.

FUNDING

National Institute of Health Research.

Conceptual Design, Implementation, and Evaluation of Generic and Standard-Compliant Data Transfer into Electronic Health Records

Objectives  The objective of this study is the conceptual design, implementation and evaluation of a system for generic, standard-compliant data transfer into electronic health records (EHRs). This includes patient data from clinical research and medical care that has been semantically annotated and enhanced with metadata. The implementation is based on the single-source approach. Technical and clinical feasibilities, as well as cost-benefit efficiency, were investigated in everyday clinical practice.

Methods  Münster University Hospital is a tertiary care hospital with 1,457 beds and 10,823 staff who treated 548,110 patients in 2018. Single-source metadata architecture transformation (SMA:T) was implemented as an extension to the EHR system. This architecture uses Model Driven Software Development (MDSD) to generate documentation forms according to the Clinical Data Interchange Standards Consortium (CDISC) operational data model (ODM). Clinical data are stored in ODM format in the EHR system database. Documentation forms are based on Google's Material Design Standard. SMA:T was used at a total of five clinics and one administrative department in the period from March 1, 2018 until March 31, 2019 in everyday clinical practice.

Results  The technical and clinical feasibility of SMA:T was demonstrated in the course of the study. Seventeen documentation forms including 373 data items were created with SMA:T. Those were created for 2,484 patients by 283 users in everyday clinical practice. A total of 121 documentation forms were examined retrospectively. The Constructive cost model (COCOMO II) was used to calculate cost and time savings. The form development mean time was reduced by 83.4% from 3,357 to 557 hours. Average costs per form went down from EUR 953 to 158.

Conclusion  Automated generic transfer of standard-compliant data and metadata into EHRs is technically and clinically feasible, cost efficient, and a useful method to establish comprehensive and semantically annotated clinical documentation. Savings of time and personnel resources are possible.

Machine intelligence in healthcare-perspectives on trustworthiness, explainability, usability, and transparency

Machine Intelligence (MI) is rapidly becoming an important approach across biomedical discovery, clinical research, medical diagnostics/devices, and precision medicine. Such tools can uncover new possibilities for researchers, physicians, and patients, allowing them to make more informed decisions and achieve better outcomes. When deployed in healthcare settings, these approaches have the potential to enhance efficiency and effectiveness of the health research and care ecosystem, and ultimately improve quality of patient care. In response to the increased use of MI in healthcare, and issues associated when applying such approaches to clinical care settings, the National Institutes of Health (NIH) and National Center for Advancing Translational Sciences (NCATS) co-hosted a Machine Intelligence in Healthcare workshop with the National Cancer Institute (NCI) and the National Institute of Biomedical Imaging and Bioengineering (NIBIB) on 12 July 2019. Speakers and attendees included researchers, clinicians and patients/ patient advocates, with representation from industry, academia, and federal agencies. A number of issues were addressed, including: data quality and quantity; access and use of electronic health records (EHRs); transparency and explainability of the system in contrast to the entire clinical workflow; and the impact of bias on system outputs, among other topics. This whitepaper reports on key issues associated with MI specific to applications in the healthcare field, identifies areas of improvement for MI systems in the context of healthcare, and proposes avenues and solutions for these issues, with the aim of surfacing key areas that, if appropriately addressed, could accelerate progress in the field effectively, transparently, and ethically.

Validation of acute exacerbation of chronic obstructive pulmonary disease (COPD) recording in electronic health records: a systematic review protocol

INTRODUCTION

Many patients with chronic obstructive pulmonary disease (COPD) experience a sustained worsening in symptoms termed an acute exacerbation (AECOPD). AECOPDs impact on patients' quality of life and lung function, are costly to health services and are an important topic for research. Electronic health records (EHR) are increasingly being used to study AECOPD, requiring accurate detection of AECOPD in EHRs to ensure generalisable results. The aim of this protocol is to provide an overview of studies that validate AECOPD definitions used in EHRs and administrative claims databases.

METHODS AND ANALYSIS

Medline and Embase will be searched for terms related to COPD exacerbation, EHRs and validation. All studies published between 1 January 1990 and 30 September 2019 written in English that validate AECOPD in EHRs and administrative claims databases will be considered.

INCLUSION CRITERIA

EHR data must be routinely collected; the AECOPD detection algorithm must be compared against a reference standard; and a measure of validity must be calculable. Two independent reviewers will screen articles for inclusion, extract study details and assess risk of bias using QUADAS-2. Disagreements will be resolved by consensus or arbitration by a third reviewer. This protocol has been developed in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols checklist.

ETHICS AND DISSEMINATION

This will be a review of previously published literature therefore no ethical approval is required. Results from this review will be published in a peer-reviewed journal. The results can be used in future research to identify occurrences of AECOPD.

PROSPERO REGISTRATION NUMBER

CRD42019130863.

UK phenomics platform for developing and validating electronic health record phenotypes: CALIBER

OBJECTIVE

Electronic health records (EHRs) are a rich source of information on human diseases, but the information is variably structured, fragmented, curated using different coding systems, and collected for purposes other than medical research. We describe an approach for developing, validating, and sharing reproducible phenotypes from national structured EHR in the United Kingdom with applications for translational research.

MATERIALS AND METHODS

We implemented a rule-based phenotyping framework, with up to 6 approaches of validation. We applied our framework to a sample of 15 million individuals in a national EHR data source (population-based primary care, all ages) linked to hospitalization and death records in England. Data comprised continuous measurements (for example, blood pressure; medication information; coded diagnoses, symptoms, procedures, and referrals), recorded using 5 controlled clinical terminologies: (1) read (primary care, subset of SNOMED-CT [Systematized Nomenclature of Medicine Clinical Terms]), (2) International Classification of Diseases-Ninth Revision and Tenth Revision (secondary care diagnoses and cause of mortality), (3) Office of Population Censuses and Surveys Classification of Surgical Operations and Procedures, Fourth Revision (hospital surgical procedures), and (4) DM+D prescription codes.

RESULTS

Using the CALIBER phenotyping framework, we created algorithms for 51 diseases, syndromes, biomarkers, and lifestyle risk factors and provide up to 6 validation approaches. The EHR phenotypes are curated in the open-access CALIBER Portal (https://www.caliberresearch.org/portal) and have been used by 40 national and international research groups in 60 peer-reviewed publications.

CONCLUSIONS

We describe a UK EHR phenomics approach within the CALIBER EHR data platform with initial evidence of validity and use, as an important step toward international use of UK EHR data for health research.

Quality improvement of prescribing safety: a pilot study in primary care using UK electronic health records

Background

Quality improvement (QI) is a priority for general practice, and GPs are expected to participate in and provide evidence of QI activity. There is growing interest in harnessing the potential of electronic health records (EHR) to improve patient care by supporting practices to find cases that could benefit from a medicines review.

Aim

To develop scalable and reproducible prescribing safety reports using patient-level EHR data.

Design and setting

UK general practices that contribute de-identified patient data to the Clinical Practice Research Datalink (CPRD).

Method

A scoping phase used stakeholder consultations to identify primary care QI needs and potential indicators. QI reports containing real data were sent to 12 pilot practices that used Vision GP software and had expressed interest. The scale-up phase involved automating production and distribution of reports to all contributing practices that used both Vision and EMIS software systems. Benchmarking reports with patient-level case review lists for two prescribing safety indicators were sent to 457 practices in December 2017 following the initial scale-up (Figure 2).

Results

Two indicators were selected from the Royal College of General Practitioners Patient Safety Toolkit following stakeholder consultations for the pilot phase involving 12 GP practices. Pilot phase interviews showed that reports were used to review individual patient care, implement wider QI actions in the practice, and for appraisal and revalidation.

Conclusion

Electronic health record data can be used to provide standardised, reproducible reports that can be delivered at scale with minimal resource requirements. These can be used in a national QI initiative that impacts directly on patient care.

Chronic obstructive pulmonary disease exacerbation episodes derived from electronic health record data validated using clinical trial data

Purpose

To validate an algorithm for acute exacerbations of chronic obstructive pulmonary disease (AECOPD) episodes derived in an electronic health record (EHR) database, against AECOPD episodes collected in a randomized clinical trial using an electronic case report form (eCRF).

Methods

We analyzed two data sources from the Salford Lung Study in COPD: trial eCRF and the Salford Integrated Record, a linked primary‐secondary routine care EHR database of all patients in Salford. For trial participants, AECOPD episodes reported in eCRF were compared with algorithmically derived moderate/severe AECOPD episodes identified in EHR. Episode characteristics (frequency, duration), sensitivity, and positive predictive value (PPV) were calculated. A match between eCRF and EHR episodes was defined as at least 1‐day overlap.

Results

In the primary effectiveness analysis population (n = 2269), 3791 EHR episodes (mean [SD] length: 15.1 [3.59] days; range: 14‐54) and 4403 moderate/severe AECOPD eCRF episodes (mean length: 13.8 [16.20] days; range: 1‐372) were identified. eCRF episodes exceeding 28 days were usually broken up into shorter episodes in the EHR. Sensitivity was 63.6% and PPV 71.1%, where concordance was defined as at least 1‐day overlap.

Conclusions

The EHR algorithm performance was acceptable, indicating that EHR‐derived AECOPD episodes may provide an efficient, valid method of data collection. Comparing EHR‐derived AECOPD episodes with those collected by eCRF resulted in slightly fewer episodes, and eCRF episodes of extreme lengths were poorly captured in EHR. Analysis of routinely collected EHR data may be reasonable when relative, rather than absolute, rates of AECOPD are relevant for stakeholders' decision making.

Variation in Laboratory Test Naming Conventions in EHRs Within and Between Hospitals: A Nationwide Longitudinal Study

BACKGROUND

Electronic health records provide clinically rich data for research and quality improvement work. However, the data are often unstructured text, may be inconsistently recorded and extracted into centralized databases, making them difficult to use for research.

OBJECTIVES

We sought to quantify the variation in how key laboratory measures are recorded in the Department of Veterans Affairs (VA) Corporate Data Warehouse (CDW) across hospitals and over time. We included 6 laboratory tests commonly drawn within the first 24 hours of hospital admission (albumin, bilirubin, creatinine, hemoglobin, sodium, white blood cell count) from fiscal years 2005-2015.

RESULTS

We assessed laboratory test capture for 5,454,411 acute hospital admissions at 121 sites across the VA. The mapping of standardized laboratory nomenclature (Logical Observation Identifiers Names and Codes, LOINCs) to test results in CDW varied within hospital by laboratory test. The relationship between LOINCs and laboratory test names improved over time; by FY2015, 109 (95.6%) hospitals had >90% of the 6 laboratory tests mapped to an appropriate LOINC. All fields used to classify test results are provided in an Appendix (Supplemental Digital Content 1, http://links.lww.com/MLR/B635).

CONCLUSIONS

The use of electronic health record data for research requires assessing data consistency and quality. Using laboratory test results requires the use of both unstructured text fields and the identification of appropriate LOINCs. When using data from multiple facilities, the results should be carefully examined by facility and over time to maximize the capture of data fields.

Code sets for respiratory symptoms in electronic health records research: a systematic review protocol

INTRODUCTION

Asthma and chronic obstructive pulmonary disease (COPD) are common respiratory conditions, which result in significant morbidity worldwide. These conditions are associated with a range of non-specific symptoms, which in themselves are a target for health research. Such research is increasingly being conducted using electronic health records (EHRs), but computable phenotype definitions, in the form of code sets or code lists, are required to extract structured data from these large routine databases in a systematic and reproducible way. The aim of this protocol is to specify a systematic review to identify code sets for respiratory symptoms in EHRs research.

METHODS AND ANALYSIS

MEDLINE and Embase databases will be searched using terms relating to EHRs, respiratory symptoms and use of code sets. The search will cover all English-language studies in these databases between January 1990 and December 2017. Two reviewers will independently screen identified studies for inclusion, and key data will be extracted into a uniform table, facilitating cross-comparison of codes used. Disagreements between the reviewers will be adjudicated by a third reviewer. This protocol has been produced in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocol guidelines.

ETHICS AND DISSEMINATION

As a review of previously published studies, no ethical approval is required. The results of this review will be submitted to a peer-reviewed journal for publication and can be used in future research into respiratory symptoms that uses electronic healthcare databases.

PROSPERO REGISTRATION NUMBER

CRD42018100830.

Term sets: A transparent and reproducible representation of clinical code sets

OBJECTIVE

Clinical code sets are vital to research using routinely-collected electronic healthcare data. Existing code set engineering methods pose significant limitations when considering reproducible research. To improve the transparency and reusability of research, these code sets must abide by FAIR principles; this is not currently happening. We propose 'term sets', an equivalent alternative to code sets that are findable, accessible, interoperable and reusable.

MATERIALS AND METHODS

We describe a new code set representation, consisting of natural language inclusion and exclusion terms (term sets), and explain its relationship to code sets. We formally prove that any code set has a corresponding term set. We demonstrate utility by searching for recently published code sets, representing them as term sets, and reporting on the number of inclusion and exclusion terms compared with the size of the code set.

RESULTS

Thirty-one code sets from 20 papers covering diverse disease domains were converted into term sets. The term sets were on average 74% the size of their equivalent original code set. Four term sets were larger due to deficiencies in the original code sets.

DISCUSSION

Term sets can concisely represent any code set. This may reduce barriers for examining and reusing code sets, which may accelerate research using healthcare databases. We have developed open-source software that supports researchers using term sets.

CONCLUSION

Term sets are independent of clinical code terminologies and therefore: enable reproducible research; are resistant to terminology changes; and are less error-prone as they are shorter than the equivalent code set.

Health records as the basis of clinical coding: Is the quality adequate? A qualitative study of medical coders' perceptions

BACKGROUND

Health records are the basis of clinical coding. In Portugal, relevant diagnoses and procedures are abstracted and categorised using an internationally accepted classification system and the resulting codes, together with the administrative data, are then grouped into diagnosis-related groups (DRGs). Hospital reimbursement is partially calculated from the DRGs. Moreover, the administrative database generated with these data is widely used in research and epidemiology, among other purposes.

OBJECTIVE

To explore the perceptions of medical coders (medical doctors) regarding possible problems with health records that may affect the quality of coded data.

METHOD

A qualitative design using four focus groups sessions with 10 medical coders was undertaken between October and November 2017. The convenience sample was obtained from four public hospitals in Portugal. Questions related to problems with the coding process were developed from the literature and authors' expertise. The focus groups sessions were taped, transcribed and analysed to elicit themes.

RESULTS

There are several problems, identified by the focus groups, in health records that influence the coded data: the lack of or unclear documented information; the variability in diagnosis description; "copy & paste"; and the lack of solutions to solve these problems.

CONCLUSION AND IMPLICATIONS

The use of standards in health records, audits and physician awareness could increase the quality of health records, contributing to improvements in the quality of coded data, and in the fulfilment of its purposes (e.g. more accurate payments and more reliable research).

Artificial intelligence and machine learning | applications in musculoskeletal physiotherapy

INTRODUCTION

Artificial intelligence (AI) is a field of mathematical engineering which has potential to enhance healthcare through new care delivery strategies, informed decision making and facilitation of patient engagement. Machine learning (ML) is a form of narrow artificial intelligence which can be used to automate decision making and make predictions based upon patient data.

PURPOSE

This review outlines key applications of supervised and unsupervised machine learning in musculoskeletal medicine; such as diagnostic imaging, patient measurement data, and clinical decision support. The current literature base is examined to identify areas where ML performs equal to or more accurately than human levels.

IMPLICATIONS

Potential is apparent for intelligent machines to enhance various areas of physiotherapy practice through automization of tasks which involve data analysis, classification and prediction. Changes to service provision through applications of ML, should encourage physiotherapists to increase their awareness of and experiences with emerging technologies. Data literacy should be a component of professional development plans to assist physiotherapists in the application of ML and the preparation of information technology systems to use these techniques.

The internal validation of weight and weight change coding using weight measurement data within the UK primary care Electronic Health Record

PURPOSE

To use recorded weight values to internally validate weight status and weight change coding in the primary care Electronic Health Record (EHR).

PATIENTS AND METHODS

We included adult patients with weight-related Read codes recorded in the UK's Clinical Practice Research Datalink EHR between 2000 and 2017. Weight status codes were compared to weight values recorded on the same day and positive predictive values (PPVs) were calculated for commonly used codes. Weight change codes were validated using three methods: the percentage (%) difference in kilograms at the time of the code and 1) the previous weight measurement, 2) the weight predicted using linear regression, and 3) the historic mean weight. Weight change codes were validated if estimates were consistent across two out of three methods.

RESULTS

A total of 8,108,481 weight codes were recorded in 1,000,002 patients' EHR. Twice as many were recorded in females (n=5,208,593, 64%). The mean body mass index for "overweight" codes ranged from 31.9 kg/m2 to 46.9 kg/m2 and from 17.4 kg/m2 to 19.2 kg/m2 for "underweight" codes. PPVs for the most commonly used weight status codes ranged from 81.3% (80%-82.5%) to 99.3% (99.2%-99.4%). Across the estimation methods, and using only validated weight change codes, mean weight loss ranged from - 5.2% (SD 5.8%) to -7.9% (SD 7.3%) and mean weight gain from 4.2 % (SD 5.5%) to 7.9 % (SD 8.2%). The previous and predicted weight methods were most consistent.

CONCLUSION

We have developed an internationally applicable methodology to internally validate weight-related EHR coding by using available weight measurement data. We demonstrate the UK Read codes that can be confidently used to classify weight status and weight change in the absence of weight values. We provide the first evidence from primary care that a Read code for unexpected weight loss represents a mean loss of ≥ 5 % in a 6-month period, which was broadly consistent across age groups and gender.

Driving Type 2 Diabetes Risk Scores into Clinical Practice: Performance Analysis in Hospital Settings

Electronic health records and computational modelling have paved the way for the development of Type 2 Diabetes risk scores to identify subjects at high risk. Unfortunately, few risk scores have been externally validated, and their performance can be compromised when routine clinical data is used. The aim of this study was to assess the performance of well-established risk scores for Type 2 Diabetes using routinely collected clinical data and to quantify their impact on the decision making process of endocrinologists. We tested six risk models that have been validated in external cohorts, as opposed to model development, on electronic health records collected from 2008-2015 from a population of 10,730 subjects. Unavailable or missing data in electronic health records was imputed using an existing validated Bayesian Network. Risk scores were assessed on the basis of statistical performance to differentiate between subjects who developed diabetes and those who did not. Eight endocrinologists provided clinical recommendations based on the risk score output. Due to inaccuracies and discrepancies regarding the exact date of Type 2 Diabetes onset, 76 subjects from the initial population were eligible for the study. Risk scores were useful for identifying subjects who developed diabetes (Framingham risk score yielded a c-statistic of 85%), however, our findings suggest that electronic health records are not prepared to massively use this type of risk scores. Use of a Bayesian Network was key for completion of the risk estimation and did not affect the risk score calculation (p > 0.05). Risk score estimation did not have a significant effect on the clinical recommendation except for starting pharmacological treatment (p = 0.004) and dietary counselling (p = 0.039). Despite their potential use, electronic health records should be carefully analyzed before the massive use of Type 2 Diabetes risk scores for the identification of high-risk subjects, and subsequent targeting of preventive actions.

Processing of Electronic Medical Records for Health Services Research in an Academic Medical Center: Methods and Validation

Background

Electronic medical records (EMRs) contain a wealth of information that can support data-driven decision making in health care policy design and service planning. Although research using EMRs has become increasingly prevalent, challenges such as coding inconsistency, data validity, and lack of suitable measures in important domains still hinder the progress.

Objective

The objective of this study was to design a structured way to process records in administrative EMR systems for health services research and assess validity in selected areas.

Methods

On the basis of a local hospital EMR system in Singapore, we developed a structured framework for EMR data processing, including standardization and phenotyping of diagnosis codes, construction of cohort with multilevel views, and generation of variables and proxy measures to supplement primary data. Disease complexity was estimated by Charlson Comorbidity Index (CCI) and Polypharmacy Score (PPS), whereas socioeconomic status (SES) was estimated by housing type. Validity of modified diagnosis codes and derived measures were investigated.

Results

Visit-level (N=7,778,761) and patient-level records (n=549,109) were generated. The International Classification of Diseases, Tenth Revision, Australian Modification (ICD-10-AM) codes were standardized to the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) with a mapping rate of 87.1%. In all, 97.4% of the ICD-9-CM codes were phenotyped successfully using Clinical Classification Software by Agency for Healthcare Research and Quality. Diagnosis codes that underwent modification (truncation or zero addition) in standardization and phenotyping procedures had the modification validated by physicians, with validity rates of more than 90%. Disease complexity measures (CCI and PPS) and SES were found to be valid and robust after a correlation analysis and a multivariate regression analysis. CCI and PPS were correlated with each other and positively correlated with health care utilization measures. Larger housing type was associated with lower government subsidies received, suggesting association with higher SES. Profile of constructed cohorts showed differences in disease prevalence, disease complexity, and health care utilization in those aged above 65 years and those aged 65 years or younger.

Conclusions

The framework proposed in this study would be useful for other researchers working with EMR data for health services research. Further analyses would be needed to better understand differences observed in the cohorts.

SMASH! The Salford medication safety dashboard

BACKGROUND

Patient safety is vital to well-functioning health systems. A key component is safe prescribing, particularly in primary care where most medications are prescribed. Previous research demonstrated that the number of patients exposed to potentially hazardous prescribing can be reduced by interrogating the electronic health record (EHR) database of general practices and providing feedback to general practitioners in a pharmacist-led intervention. We aimed to develop and roll out an online dashboard application that delivers this audit and feedback intervention in a continuous fashion.

METHOD

Based on initial system requirements we designed the dashboard's user interface over 3 iterations with 6 general practitioners (GPs), 7 pharmacists and a member of the public. Prescribing safety indicators from previous work were implemented in the dashboard. Pharmacists were trained to use the intervention and deliver it to general practices.

RESULTS

A web-based electronic dashboard was developed and linked to shared care records in Salford, UK. The completed dashboard was deployed in all but one (n=43) general practices in the region. By November 2017, 36 pharmacists had been trained in delivering the intervention to practices. There were 135 registered users of the dashboard, with an average of 91 user sessions a week.

CONCLUSION

We have developed and successfully rolled out of a complex, pharmacist-led dashboard intervention in Salford, UK. System usage statistics indicate broad and sustained uptake of the intervention. The use of systems that provide regularly updated audit information may be an important contributor towards medication safety in primary care.

Validation of an algorithm that determines stroke diagnostic code accuracy in a Japanese hospital-based cancer registry using electronic medical records

BACKGROUND

This study aimed to validate an algorithm that determines stroke diagnostic code accuracy, in a hospital-based cancer registry, using electronic medical records (EMRs) in Japan.

METHODS

The subjects were 27,932 patients enrolled in the hospital-based cancer registry of Osaka University Hospital, between January 1, 2007 and December 31, 2015. The ICD-10 (international classification of diseases, 10th revision) diagnostic codes for stroke were extracted from the EMR database. Specifically, subarachnoid hemorrhage (I60); intracerebral hemorrhage (I61); cerebral infarction (I63); and other transient cerebral ischemic attacks and related syndromes and transient cerebral ischemic attack (unspecified) (G458 and G459), respectively. Diagnostic codes, both "definite" and "suspected," and brain imaging information were extracted from the database. We set the algorithm with the combination of the diagnostic code and/or the brain imaging information, and manually reviewed the presence or absence of the acute cerebrovascular disease with medical charts.

RESULTS

A total of 2654 diagnostic codes, 1991 "definite" and 663 "suspected," were identified. After excluding duplicates, the numbers of "definite" and "suspected" diagnostic codes were 912 and 228, respectively. The proportion of the presence of the disease in the "definite" diagnostic code was 22%; this raised 51% with the combination of the diagnostic code and the use of brain imaging information. When adding the interval of when brain imaging was performed (within 30 days and within 1 day) to the diagnostic code, the proportion increased to 84% and 90%, respectively. In the algorithm of "definite" diagnostic code, history of stroke was the most common in the diagnostic code, but in the algorithm of "definite" diagnostic code and the use of brain imaging within 1 day, stroke mimics was the most frequent.

CONCLUSIONS

Combining the diagnostic code and clinical examination improved the proportion of the presence of disease in the diagnostic code and achieved appropriate accuracy for research. Clinical research using EMRs require outcome validation prior to conducting a study.