JAMIA Open最新文献

Objective: This article describes a scalable, performant, sustainable global network of electronic health record data for biomedical and clinical research.

Materials and methods: TriNetX has created a technology platform characterized by a conservative security and governance model that facilitates collaboration and cooperation between industry participants, such as pharmaceutical companies and contract research organizations, and academic and community-based healthcare organizations (HCOs). HCOs participate on the network in return for access to a suite of analytics capabilities, large networks of de-identified data, and more sponsored trial opportunities. Industry participants provide the financial resources to support, expand, and improve the technology platform in return for access to network data, which provides increased efficiencies in clinical trial design and deployment.

Results: TriNetX is a growing global network, expanding from 55 HCOs and 7 countries in 2017 to over 220 HCOs and 30 countries in 2022. Over 19 000 sponsored clinical trial opportunities have been initiated through the TriNetX network. There have been over 350 peer-reviewed scientific publications based on the network's data.

Conclusions: The continued growth of the TriNetX network and its yield of clinical trial collaborations and published studies indicates that this academic-industry structure is a safe, proven, sustainable path for building and maintaining research-centric data networks.

Objective: Our objective is to assess the accuracy of the COVID-19 vaccination status within the electronic health record (EHR) for a panel of patients in a primary care practice when manual queries of the state immunization databases are required to access outside immunization records.

Materials and methods: This study evaluated COVID-19 vaccination status of adult primary care patients within a university-based health system EHR by manually querying the Kansas and Missouri Immunization Information Systems.

Results: A manual query of the local Immunization Information Systems for 4114 adult patients with "unknown" vaccination status showed 44% of the patients were previously vaccinated. Attempts to assess the comprehensiveness of the Immunization Information Systems were hampered by incomplete documentation in the chart and poor response to patient outreach.

Conclusions: When the interface between the patient chart and the local Immunization Information System depends on a manual query for the transfer of data, the COVID-19 vaccination status for a panel of patients is often inaccurate.

Objectives: The use of electronic health record (EHR)-embedded child abuse clinical decision support (CA-CDS) may help decrease morbidity from child maltreatment. We previously reported on the development of CA-CDS in Epic and Allscripts. The objective of this study was to implement CA-CDS into Epic and Allscripts and determine its effects on identification, evaluation, and reporting of suspected child maltreatment.

Materials and methods: After a preimplementation period, CA-CDS was implemented at University of Wisconsin (Epic) and Northwell Health (Allscripts). Providers were surveyed before the go-live and 4 months later. Outcomes included the proportion of children who triggered the CA-CDS system, had a positive Child Abuse Screen (CAS) and/or were reported to Child Protective Services (CPS).

Results: At University of Wisconsin (UW), 3.5% of children in the implementation period triggered the system. The CAS was positive in 1.8% of children. The proportion of children reported to CPS increased from 0.6% to 0.9%. There was rapid uptake of the abuse order set.At Northwell Health (NW), 1.9% of children in the implementation period triggered the system. The CAS was positive in 1% of children. The child abuse order set was rarely used. Preimplementation, providers at both sites were similar in desire to have CA-CDS system and perception of CDS in general. After implementation, UW providers had a positive perception of the CA-CDS system, while NW providers had a negative perception.

Discussion: CA-CDS was able to be implemented in 2 different EHRs with differing effects on clinical care and provider feedback. At UW, the site with higher uptake of the CA-CDS system, the proportion of children who triggered the system and the rate of positive CAS was similar to previous studies and there was an increase in the proportion of cases of suspected abuse identified as measured by reports to CPS. Our data demonstrate how local environment, end-users' opinions, and limitations in the EHR platform can impact the success of implementation.

Conclusions: When disseminating CA-CDS into different hospital systems and different EHRs, it is critical to recognize how limitations in the functionality of the EHR can impact the success of implementation. The importance of collecting, interpreting, and responding to provider feedback is of critical importance particularly with CDS related to child maltreatment.

Objectives: Studies that combine medical record and primary data are typically conducted in a small number of health care facilities (HCFs) covering a limited catchment area; however, depending on the study objectives, validity may be improved by recruiting a more expansive sample of patients receiving care across multiple HCFs. We evaluate the feasibility of a novel protocol to obtain patient medical records from multiple HCFs using a broad representative sampling frame.

Materials and methods: In a prospective cohort study on HIV pre-exposure prophylaxis utilization, primary data were collected from a representative sample of community-dwelling participants; voluntary authorization was obtained to access participants' medical records from the HCF at which they were receiving care. Medical record procurement procedures were documented for later analysis.

Results: The cohort consisted of 460 participants receiving care from 122 HCFs; 81 participants were lost to follow-up resulting in 379 requests for medical records submitted to HCFs, and a total of 343 medical records were obtained (91% response rate). Less than 20% of the medical records received were in electronic form. On average, the cost of medical record acquisition was $120 USD per medical record.

Conclusions: Obtaining medical record data on research participants receiving care across multiple HCFs was feasible, but time-consuming and resulted in appreciable missing data. Researchers combining primary data with medical record data should select a sampling and data collection approach that optimizes study validity while weighing the potential benefits (more representative sample; inclusion of HCF-level predictors) and drawbacks (cost, missing data) of obtaining medical records from multiple HCFs.

Objective: When correcting for the "class imbalance" problem in medical data, the effects of resampling applied on classifier algorithms remain unclear. We examined the effect on performance over several combinations of classifiers and resampling ratios.

Materials and methods: Multiple classification algorithms were trained on 7 resampled datasets: no correction, random undersampling, 4 ratios of Synthetic Minority Oversampling Technique (SMOTE), and random oversampling with the Adaptive Synthetic algorithm (ADASYN). Performance was evaluated in Area Under the Curve (AUC), precision, recall, Brier score, and calibration metrics. A case study on prediction modeling for 30-day unplanned readmissions in previously admitted Urology patients was presented.

Results: For most algorithms, using resampled data showed a significant increase in AUC and precision, ranging from 0.74 (CI: 0.69-0.79) to 0.93 (CI: 0.92-0.94), and 0.35 (CI: 0.12-0.58) to 0.86 (CI: 0.81-0.92) respectively. All classification algorithms showed significant increases in recall, and significant decreases in Brier score with distorted calibration overestimating positives.

Discussion: Imbalance correction resulted in an overall improved performance, yet poorly calibrated models. There can still be clinical utility due to a strong discriminating performance, specifically when predicting only low and high risk cases is clinically more relevant.

Conclusion: Resampling data resulted in increased performances in classification algorithms, yet produced an overestimation of positive predictions. Based on the findings from our case study, a thoughtful predefinition of the clinical prediction task may guide the use of resampling techniques in future studies aiming to improve clinical decision support tools.

Objectives: To assess whether a fall-prevention clinical decision support (CDS) approach using electronic analytics that stimulates risk-targeted interventions is associated with reduced rates of falls and injurious falls.

Materials and methods: The CDS intervention included a machine-learning prediction algorithm, individual risk-factor identification, and guideline-based prevention recommendations. After a 5-month plan-do-study-act quality improvement initiative, the CDS intervention was implemented at an academic tertiary hospital and compared with the usual care using a pretest (lasting 24 months and involving 23 498 patients) and posttest (lasting 13 months and involving 17 341 patients) design in six nursing units. Primary and secondary outcomes were the rates of falls and injurious falls per 1000 hospital days, respectively. Outcome measurements were tested using a priori Poisson regression and adjusted with patient-level covariates. Subgroup analyses were conducted according to age.

Results: The age distribution, sex, hospital and unit lengths of stay, number of secondary diagnoses, fall history, condition at admission, and overall fall rate per 1000 hospital days did not differ significantly between the intervention and control periods before (1.88 vs 2.05, respectively, P = .1764) or after adjusting for demographics. The injurious-falls rate per 1000 hospital days decreased significantly before (0.68 vs 0.45, P = .0171) and after (rate difference = -0.64, P = .0212) adjusting for demographics. The differences in injury rates were greater among patients aged at least 65 years.

Conclusions: This study suggests that a well-designed CDS intervention employing electronic analytics was associated with a decrease in fall-related injuries. The benefits from this intervention were greater in elderly patients aged at least 65 years.

Trial registration: This study was conducted as part of a more extensive study registered with the Clinical Research Information Service (CRIS) (KCT0005378).

Background: Electronic health records and many legacy systems contain rich longitudinal data that can be used for research; however, they typically are not readily available.

Materials and methods: At Kaiser Permanente Southern California (KPSC), a research data warehouse (RDW) has been developed and maintained since the late 1990s and widely extended in 2006, aggregating and standardizing data collected from internal and a few external sources. This article provides a high-level overview of the RDW and discusses challenges common to data warehouses or repositories for research use. To demonstrate the application of the data, we report the volume, patient characteristics, and age-adjusted prevalence of selected medical conditions and utilization rates of selected medical procedures.

Results: A total of 105 million person-years of health plan enrollment was recorded in the RDW between 1981 and 2018, with most healthcare utilization data available since early or middle 1990s. Among active enrollees on December 31, 2018, 15% were ≥65 years of age, 33.9% were non-Hispanic white, 43.3% Hispanic, 11.0% Asian, and 8.4% African American, and 34.4% of children (2-17 years old) and 72.1% of adults (≥18 years old) were overweight or obese. The age-adjusted prevalence of asthma, atrial fibrillation, diabetes mellitus, hypercholesteremia, and hypertension increased between 2001 and 2018. Hospitalization and Emergency Department (ED) visit rates appeared lower, and office visit rates seemed higher at KPSC compared to the reported US averages.

Discussion and conclusion: Although the RDW is unique to KPSC, its methodologies and experience may provide useful insights for researchers of other healthcare systems worldwide in the era of big data analysis.

Objective: Electronic health records (EHRs) within the United States increasingly include sexual orientation and gender identity (SOGI) fields. We assess how well SOGI fields, along with International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10) codes and medication records, identify gender-expansive patients.

Materials and methods: The study used a data set of all patients that had in-person inpatient or outpatient encounters at an academic medical center in a rural state between December 1, 2018 and February 17, 2022. Chart review was performed for all patients meeting at least one of the following criteria: differences between legal sex, sex assigned at birth, and gender identity (excluding blank fields) in the EHR SOGI fields; ICD-10 codes related to gender dysphoria or unspecified endocrine disorder; prescription for estradiol or testosterone suggesting use of gender-affirming hormones.

Results: Out of 123 441 total unique patients with in-person encounters, we identified a total of 2236 patients identifying as gender-expansive, with 1506 taking gender-affirming hormones. SOGI field differences or ICD-10 codes related to gender dysphoria or both were found in 2219 of 2236 (99.2%) patients who identify as gender-expansive, and 1500 of 1506 (99.6%) taking gender-affirming hormones. For the gender-expansive population, assigned female at birth was more common in the 12-29 year age range, while assigned male at birth was more common for those 40 years and older.

Conclusions: SOGI fields and ICD-10 codes identify a high percentage of gender-expansive patients at an academic medical center.

Objectives: Introduce the CDS-Sandbox, a cloud-based virtual machine created to facilitate Clinical Decision Support (CDS) developers and implementers in the use of FHIR- and CQL-based open-source tools and technologies for building and testing CDS artifacts.

Materials and methods: The CDS-Sandbox includes components that enable workflows for authoring and testing CDS artifacts. Two workshops at the 2020 and 2021 AMIA Annual Symposia were conducted to demonstrate the use of the open-source CDS tools.

Results: The CDS-Sandbox successfully integrated the use of open-source CDS tools. Both workshops were well attended. Participants demonstrated use and understanding of the workshop materials and provided positive feedback after the workshops.

Discussion: The CDS-Sandbox and publicly available tutorial materials facilitated an understanding of the leading-edge open-source CDS infrastructure components.

Conclusion: The CDS-Sandbox supports integrated use of the key CDS open-source tools that may be used to introduce CDS concepts and practice to the clinical informatics community.

Objective: To develop the architecture for a clinical decision support system (CDSS) linked to the electronic health record (EHR) using the tools provided by Research Electronic Data Capture (REDCap) to assess medication appropriateness in older adults with polypharmacy.

Materials and methods: The tools available in REDCap were used to create the architecture for replicating a previously developed stand-alone system while overcoming its limitations.

Results: The architecture consists of data input forms, drug- and disease-mapper, rules engine, and report generator. The input forms integrate medication and health condition data from the EHR with patient assessment data. The rules engine evaluates medication appropriateness through rules built through a series of drop-down menus. The rules generate output, which are a set of recommendations to the clinician.

Discussion and conclusion: This architecture successfully replicates the stand-alone CDSS while addressing its limitations. It is compatible with several EHRs, easily shared among the large community using REDCap, and readily modifiable.