Utilizing patient data from the veterans administration electronic health record to support web-based clinical decision support: informatics challenges and issues from three clinical domains

Utilizing Big Data analytics and electronic health record data in HIV prevention, treatment, and care research: a literature review

Propelled by the transformative power of modern information and communication technologies, digitalization of data, and the increasing affordability of high-performance computing, Big Data science has brought forth revolutionary advancement in many areas of business, industry, health, and medicine. The HIV research and care service community is no exception to the benefits from the availability and utilization of Big Data analytics. Electronic health record (EHR) data (e.g., administrative and billing data, electronic medical records, or other digital records of information pertinent to individual or population health) are an essential source of health and disease outcome data because of the large amount of real-world, comprehensive, and often longitudinal data, which provide a good opportunity for leveraging advanced Big Data analytics in addressing challenges in HIV prevention, treatment, and care. This review focuses on studies that apply Big Data analytics to EHR data with aims to synthesize the HIV-related issues that EHR data studies can tackle, identify challenges in the utilization of EHR data in HIV research and practice, and discuss future needs and directions that can realize the promising potential role of Big Data in ending the HIV epidemic.

Integrative approach for women with fibromyalgia in a Veterans Affairs Medical Center: An observational study

Fibromyalgia, a complex condition characterized by widespread musculoskeletal pain, presents a significant burden on individuals and healthcare systems. This observational study aims to explore the potential of an outpatient integrative care model for the management of fibromyalgia in women, focusing on personalized goals, patient education, non-pharmaceutical treatments, and lifestyle modifications. The primary objective is to assess patient satisfaction and its correlation with pain, quality of life, depression, and post-traumatic stress disorder (PTSD) symptoms. This pilot study seeks to determine the effectiveness of this model in the alleviation of fibromyalgia-related pain and the improvement of overall well-being. Twenty-five women diagnosed with fibromyalgia participated in a 14-week outpatient treatment program at a Veterans Affairs Medical Center, involving weekly patient-directed, integrative group visits and health coaching. Pre- and post-evaluation questionnaires were administered to assess patient satisfaction, patients' subjective sense of empowerment in the management of fibromyalgia, and symptom improvement (i.e., pain, quality of life, depression, and PTSD). In addition, the study evaluated the correlation of patient empowerment with symptom improvement. The integrative care model received high patient satisfaction, with a mean score of 8.04 out of 10. Significant pain reduction was observed based on the Numeric Rating Scale (n = 22, P < .001). Quality of life showed significant improvement according to the Fibromyalgia Impact Questionnaire (n = 24, P = .01). Furthermore, depression symptoms improved significantly, as assessed by Patient Health Questionnaire (n = 24, P = .04). However, there was no statistically significant change in PTSD scores (n = 22, P = .3). Patient empowerment was strongly correlated with pain reduction (n = 25, r = .78, P < .001), quality of life (n = 25, r = .57, P < .001), and improvement in depression symptoms (n = 22, r = .50, P = .004). Pairwise deletion was used for each outcome. This integrative care model demonstrated promising results in effectively managing fibromyalgia-related pain and enhancing quality of life and depression symptoms in women. This model presents a feasible and potentially effective treatment approach for fibromyalgia. Further research with larger sample sizes and control groups is warranted to validate these findings and encourage broader implementation.

Natural Language Processing-Assisted Classification Models to Confirm Monoclonal Gammopathy of Undetermined Significance and Progression in Veterans' Electronic Health Records

PURPOSE

To develop and validate natural language processing (NLP)-assisted machine learning (ML)-based classification models to confirm diagnoses of monoclonal gammopathy of undetermined significance (MGUS) and multiple myeloma (MM) from electronic health records (EHRs) in the Veterans Health Administration (VHA).

MATERIALS AND METHODS

We developed precompiled lexicons and classification rules as features for the following ML classifiers: logistic regression, random forest, and support vector machines (SVMs). These features were trained on 36,044 EHR documents from a random sample of 400 patients with at least one International Classification of Disease code for MGUS diagnosis from 1999 to 2021. The best-performing feature combination was calibrated in the validation set (17,826 documents/200 patients) and evaluated in the testing set (9,250 documents/100 patients). Model performance in diagnosis confirmation was compared with manual chart review results (gold standard) using recall, precision, accuracy, and F1 score. For patients correctly labeled as disease-positive, the difference between model-identified diagnosis dates and the gold standard was also computed.

RESULTS

In the testing set, the NLP-assisted classification model using SVMs achieved best performance in both MGUS and MM confirmation with recall/precision/accuracy/F1 of 98.8%/93.3%/93.0%/96.0% for MGUS and 100.0%/92.3%/99.0%/96.0% for MM. Dates of diagnoses matched (±45 days) with those of gold standard in 73.0% of model-confirmed MGUS and 84.6% of model-confirmed MM.

CONCLUSION

An NLP-assisted classification model can reliably confirm MGUS and MM diagnoses and dates and extract laboratory results using automated interpretation of EHR data. This algorithm has the potential to be adapted to other disease areas in VHA EHR system.

Advancing Health Equity in Neurologic Disorders and Stroke: Stakeholder Insights Into Health Disparities, Research Gaps, and Potential Interventions

OBJECTIVES

The purpose of this study was to analyze the National Institute of Neurological Disorders and Stroke (NINDS) Request for Information (RFI) input from the public-including health care providers, researchers, patients, patient advocates, caregivers, advocacy organizations, professional societies, and private and academic stakeholders with an interest in health disparities (HDs) in neurologic disease. RFI questions were structured to solicit input on what stakeholders believe are neurologic disease HD research priorities, drivers of health inequity, and potential interventions. Furthermore, these stakeholder insights were examined within the context of contemporary scientific literature and research frameworks on health equity and health disparities.

BACKGROUND

The NINDS published a RFI from March 31 to July 15, 2020. The RFI analysis presented here is part of a larger strategic planning process aimed to guide future NINDS efforts in neurologic disorder health equity (HE) research and training. The public commented on facilitators of HDs, populations that experience HDs (HDPs), potential interventions, and research opportunities related to HDs in neurologic disease and/or care in the United States across the lifespan. Responses were analyzed using qualitative methodology. Frequently suggested interventions were thematically clustered using the interpretive phenomenological analysis methodology and are presented in this article to provide a stakeholder-identified roadmap for advancing HE.

RESULTS

Respondents identified socioecological factors as driving HDs in 89% of determinants reported. Stakeholder-reported HD determinants and subsequent interventions could be classified into the following conceptual categories: HDP neurospecialty care access, innovative HDP engagement and research inclusion strategies, and development of a well-trained clinician-scientist HD workforce. Clustering of the feedback from patient and patient-adjacent respondents (i.e., caretakers and patient advocates) highlighted the prevalence of patient-provider interpersonal factors and limited resources driving access-to-care barriers among their sentiments.

DISCUSSION

Respondent sentiments suggest prioritization of social determinants of health (SDOH) research, shifting away from the common target of biological and behavioral themes addressed in the existing body of HE research provided by the stakeholder. Overall, respondents suggest focusing research prioritization on access to care, engagement across the HE research and care landscape, and HE workforce development.

Impact of Clopidogrel on Clinical Outcomes in Patients with Staphylococcus aureus Bacteremia: a National Retrospective Cohort Study

Activated platelets have known antimicrobial activity against Staphylococcus aureus. Accelerated clearance of platelets induced by S. aureus can result in thrombocytopenia and increased mortality in patients. Recent studies suggest that P2Y12 inhibition protects platelets from accelerated clearance. We therefore evaluated the effect of P2Y12 inhibition on clinical outcomes in patients with S. aureus bacteremia across a large national cohort. Our retrospective cohort (2010 to 2018) included patients admitted to Veterans Affairs (VA) hospitals with blood cultures positive for S. aureus and treated with standard-of-care antibiotics. Employing propensity score-matched Cox proportional hazards regression models, we compared clinical outcomes in patients treated with clopidogrel for at least the 30 days prior to admission and continuing for at least 5 days after admission to patients without any P2Y12 inhibitor use in the year preceding admission. Mortality was significantly lower among clopidogrel users than P2Y12 inhibitor nonusers (n = 147 propensity score-matched pairs): the inpatient mortality hazard ratio (HR) was 0.11 (95% confidence interval [CI], 0.01 to 0.86), and 30-day mortality HR was 0.43 (95% CI, 0.19 to 0.98). There were no differences in 30-day readmission, 30-day S. aureus reinfection, microbiological clearance, or thrombocytopenia. Clopidogrel use at the time of infection reduced in-hospital mortality by 89% and 30-day mortality by 57% among a cohort of patients with S. aureus bacteremia. These results support the need to further study the use of P2Y12 inhibitors as adjunctive therapy in S. aureus bloodstream infections.

Enriching limited information on rare diseases from heterogeneous networks for drug repositioning

Background

The historical data of rare disease is very scarce in reality, so how to perform drug repositioning for the rare disease is a great challenge. Most existing methods of drug repositioning for the rare disease usually neglect father–son information, so it is extremely difficult to predict drugs for the rare disease.

Method

In this paper, we focus on father–son information mining for the rare disease. We propose GRU-Cooperation-Attention-Network (GCAN) to predict drugs for the rare disease. We construct two heterogeneous networks for information enhancement, one network contains the father-nodes of the rare disease and the other network contains the son-nodes information. To bridge two heterogeneous networks, we set a mapping to connect them. What’s more, we use the biased random walk mechanism to collect the information smoothly from two heterogeneous networks, and employ a cooperation attention mechanism to enhance repositioning ability of the network.

Result

Comparing with traditional methods, GCAN makes full use of father–son information. The experimental results on real drug data from hospitals show that GCAN outperforms state-of-the-art machine learning methods for drug repositioning.

Conclusion

The performance of GCAN for drug repositioning is mainly limited by the insufficient scale and poor quality of the data. In future research work, we will focus on how to utilize more data such as drug molecule information and protein molecule information for the drug repositioning of the rare disease.

A minimum data set of user profile or electronic health record for chemical warfare victims' recommender system

Background:

There are many people who are suffering from a variety of physical and mental illnesses due to the chemical attacks. There are various technologies such as recommender systems that can identify the main concerns related to health and make efforts to address them. To design and develop a recommender system, preparation of data source of this system should be considered. The aim of this study was to determine the minimum data set for user profile or user's electronic health record in chemical warfare victims’ recommender system.

Methods:

This applied descriptive, cross-sectional study which was conducted in 2017. A questionnaire was developed by the authors from the data elements that were collected using the data extraction form from the studied sources. Content validity of the questionnaire was confirmed by using the experts. Test–retest method was used to determine the reliability of the questionnaire. The reliability of the questionnaire with Cronbach's alpha coefficient was confirmed as 84%. The questionnaire were submitted for related experts based on Delphi method by email or in person. Data resulting from the Delphi technique with descriptive statistics methods in SPSS software were analyzed.

Results:

Forty-seven nonclinical data elements and 181 clinical data elements were classified.

Conclusion:

Determining minimum data set of user profile or electronic health record in the recommender system for chemical warfare victims helps the health authorities to implement the recommender system which demonstrates chemical warfare victims’ needs.

What You Need to Know Before Implementing a Clinical Research Data Warehouse: Comparative Review of Integrated Data Repositories in Health Care Institutions

Background

Integrated data repositories (IDRs), also referred to as clinical data warehouses, are platforms used for the integration of several data sources through specialized analytical tools that facilitate data processing and analysis. IDRs offer several opportunities for clinical data reuse, and the number of institutions implementing an IDR has grown steadily in the past decade.

Objective

The architectural choices of major IDRs are highly diverse and determining their differences can be overwhelming. This review aims to explore the underlying models and common features of IDRs, provide a high-level overview for those entering the field, and propose a set of guiding principles for small- to medium-sized health institutions embarking on IDR implementation.

Methods

We reviewed manuscripts published in peer-reviewed scientific literature between 2008 and 2020, and selected those that specifically describe IDR architectures. Of 255 shortlisted articles, we found 34 articles describing 29 different architectures. The different IDRs were analyzed for common features and classified according to their data processing and integration solution choices.

Results

Despite common trends in the selection of standard terminologies and data models, the IDRs examined showed heterogeneity in the underlying architecture design. We identified 4 common architecture models that use different approaches for data processing and integration. These different approaches were driven by a variety of features such as data sources, whether the IDR was for a single institution or a collaborative project, the intended primary data user, and purpose (research-only or including clinical or operational decision making).

Conclusions

IDR implementations are diverse and complex undertakings, which benefit from being preceded by an evaluation of requirements and definition of scope in the early planning stage. Factors such as data source diversity and intended users of the IDR influence data flow and synchronization, both of which are crucial factors in IDR architecture planning.

sig2db: a Workflow for Processing Natural Language from Prescription Instructions for Clinical Data Warehouses

We present sig2db as an open-source solution for clinical data warehouses desiring to process natural language from prescription instructions, often referred to as "sigs". In electronic prescribing, the sig is typically an unstructured text field intended to capture all requirements for medication administration. The sig captures certain fields that the structured data may lack such as days supply, time of day, or meal-time considerations. Our open-source software package facilitates the workflow needed to process sigs into a structured format usable by clinical data warehouses. Our solution focuses on extracting concepts from prescriptions in order to understand the intended semantics by leveraging known natural language processing tools. We demonstrate the utility of concept extraction from sigs and present our findings in processing 1023 unique sigs from 5.7 million unique prescriptions.

Design Process and Utilization of a Novel Clinical Decision Support System for Neuropathic Pain in Primary Care: Mixed Methods Observational Study

Background

Computerized clinical decision support systems (CDSSs) have emerged as an approach to improve compliance of clinicians with clinical practice guidelines (CPGs). Research utilizing CDSS has primarily been conducted in clinical contexts with clear diagnostic criteria such as diabetes and cardiovascular diseases. In contrast, research on CDSS for pain management and more specifically neuropathic pain has been limited. A CDSS for neuropathic pain has the potential to enhance patient care as the challenge of diagnosing and treating neuropathic pain often leads to tension in clinician-patient relationships.

Objective

The aim of this study was to design and evaluate a CDSS aimed at improving the adherence of interprofessional primary care clinicians to CPG for managing neuropathic pain.

Methods

Recommendations from the Canadian CPGs informed the decision pathways. The development of the CDSS format and function involved participation of multiple stakeholders and end users in needs assessment and usability testing. Clinicians, including family medicine physicians, residents, and nurse practitioners, in three academic teaching clinics were trained in the use of the CDSS. Evaluation over one year included the measurement of utilization of the CDSS; change in reported awareness, agreement, and adoption of CPG recommendations; and change in the observed adherence to CPG recommendations.

Results

The usability testing of the CDSS was highly successful in the prototype environment. Deployment in the clinical setting was partially complete by the time of the study, with some limitations in the planned functionality. The study population had a high level of awareness, agreement, and adoption of guideline recommendations before implementation of CDSS. Nevertheless, there was a small and statistically significant improvement in the mean awareness and adoption scores over the year of observation (P=.01 for mean awareness scores at 6 and 12 months compared with baseline, for mean adoption scores at 6 months compared with baseline, and for mean adoption scores at 12 months). Documenting significant findings related to diagnosis of neuropathic pain increased significantly. Clinicians accessed CPG information more frequently than they utilized data entry functions. Nurse practitioners and first year family medicine trainees had higher utilization than physicians.

Conclusions

We observed a small increase in the adherence to CPG recommendations for managing neuropathic pain. Clinicians utilized the CDSS more as a source of knowledge and as a training tool than as an ongoing dynamic decision support.

Calculating maximum morphine equivalent daily dose from prescription directions for use in the electronic health record: a case report

To demonstrate a process of calculating the maximum potential morphine milligram equivalent daily dose (MEDD) based on the prescription Sig for use in quality improvement initiatives. To calculate an opioid prescription’s maximum potential Sig-MEDD, we developed SQL code to determine a prescription’s maximum units/day using discrete field data and text-parsing in the prescription instructions. We validated the derived units/day calculation using 3000 Sigs, then compared the Sig-MEDD calculation against the Epic-MEDD calculator. Of the 101 782 outpatient opioid prescriptions ordered over 1 year, 80% used discrete-field Sigs, 7% used free-text Sigs, and 3% used both types. We determined units/day and calculated a Sig-MEDD for 98.3% of all the prescriptions, 99.99% of discrete-Sig prescriptions, and 81.5% of free-text-Sig prescriptions. Analyzing opioid prescription Sigs to determine a maximum potential Sig-MEDD provides greater insight into a patient’s risk for opioid exposure.

Automated safety event monitoring using electronic medical records in a clinical trial setting: Validation study using the VA NEPHRON-D trial

Background/Aims:

Electronic medical records are now frequently used for capturing patient-level data in clinical trials. Within the Veterans Affairs health care system, electronic medical record data have been widely used in clinical trials to assess eligibility, facilitate referrals for recruitment, and conduct follow-up and safety monitoring. Despite the potential for increased efficiency in using electronic medical records to capture safety data via a centralized algorithm, it is important to evaluate the integrity and accuracy of electronic medical record–captured data. To this end, this investigation assesses data collection, both for general and study-specific safety endpoints, by comparing electronic medical record–based safety monitoring versus safety data collected during the course of the Veterans Affairs Nephropathy in Diabetes (VA NEPHRON-D) clinical trial.

Methods:

The VA NEPHRON-D study was a multicenter, double-blind, randomized clinical trial designed to compare the effect of combination therapy (losartan plus lisinopril) versus monotherapy (losartan) on the progression of kidney disease in individuals with diabetes and proteinuria. The trial’s safety outcomes included serious adverse events, hyperkalemia, and acute kidney injury. A subset of the participants (~62%, n = 895) enrolled in the trial’s long-term follow-up sub-study and consented to electronic medical record data collection. We applied an automated algorithm to search and capture safety data using the VA Corporate Data Warehouse which houses electronic medical record data. Using study safety data reported during the trial as the gold standard, we evaluated the sensitivity and precision of electronic medical record–based safety data and related treatment effects.

Results:

The sensitivity of the electronic medical record–based safety for hospitalizations was 65.3% without non-VA hospitalization events and 92.3% with the non-VA hospitalization events included. The sensitivity was only 54.3% for acute kidney injury and 87.3% for hyperkalemia. The precision of electronic medical record–based safety data was 89.4%, 38%, and 63.2% for hospitalization, acute kidney injury, and hyperkalemia, respectively. Relative treatment differences under the study and electronic medical record settings were 15% and 3% for hospitalization, 123% and 29% for acute kidney injury, and 238% and 140% for hyperkalemia, respectively.

Conclusion:

The accuracy of using automated electronic medical record safety data depends on the events of interest. Identification of all-cause hospitalizations would be reliable if search methods could, in addition to VA hospitalizations, also capture non-VA hospitalizations. However, hospitalization is different from a cause-specific serious adverse event that could be more sensitive to treatment effects. In addition, some study-specific safety events were not easily identified using the electronic medical records. This limits the effectiveness of the automated central database search for purposes of safety monitoring. Hence, this data captured approach should be carefully considered when implementing endpoint data collection in future pragmatic trials.

Advances in Sharing Multi-sourced Health Data on Decision Support Science 2016-2017

INTRODUCTION

 Clinical decision support science is expanding to include integration from broader and more varied data sources, diverse platforms and delivery modalities, and is responding to emerging regulatory guidelines and increased interest from industry.

OBJECTIVE

 Evaluate key advances and challenges of accessing, sharing, and managing data from multiple sources for development and implementation of Clinical Decision Support (CDS) systems in 2016-2017.

METHODS

 Assessment of literature and scientific conference proceedings, current and pending policy development, and review of commercial applications nationally and internationally.

RESULTS

 CDS research is approaching multiple landmark points driven by commercialization interests, emerging regulatory policy, and increased public awareness. However, the availability of patient-related "Big Data" sources from genomics and mobile health, expanded privacy considerations, applications of service-based computational techniques and tools, the emergence of "app" ecosystems, and evolving patient-centric approaches reflect the distributed, complex, and uneven maturity of the CDS landscape. Nonetheless, the field of CDS is yet to mature. The lack of standards and CDS-specific policies from regulatory bodies that address the privacy and safety concerns of data and knowledge sharing to support CDS development may continue to slow down the broad CDS adoption within and across institutions.

CONCLUSION

 Partnerships with Electronic Health Record and commercial CDS vendors, policy makers, standards development agencies, clinicians, and patients are needed to see CDS deployed in the evolving learning health system.

Excess Clinical Comorbidity Among HIV-Infected Patients Accessing Primary Care in US Community Health Centers

OBJECTIVES

As the life expectancy of people infected with human immunodeficiency virus (HIV) infection has increased, the spectrum of illness has evolved. We evaluated whether people living with HIV accessing primary care in US community health centers had higher morbidity compared with HIV-uninfected patients receiving care at the same sites.

METHODS

We compared data from electronic health records for 12 837 HIV-infected and 227 012 HIV-uninfected patients to evaluate the relative prevalence of diabetes mellitus, hypertension, chronic kidney disease, dyslipidemia, and malignancies by HIV serostatus. We used multivariable logistic regression to evaluate differences. Participants were patients aged ≥18 who were followed for ≥3 years (from January 2006 to December 2016) in 1 of 17 community health centers belonging to the Community Health Applied Research Network.

RESULTS

Nearly two-thirds of HIV-infected and HIV-uninfected patients lived in poverty. Compared with HIV-uninfected patients, HIV-infected patients were significantly more likely to be diagnosed and/or treated for diabetes (odds ratio [OR] = 1.18; 95% confidence interval [CI], 1.22-1.41), hypertension (OR = 1.38; 95% CI, 1.31-1.46), dyslipidemia (OR = 2.30; 95% CI, 2.17-2.43), chronic kidney disease (OR = 4.75; 95% CI, 4.23-5.34), lymphomas (OR = 4.02; 95% CI, 2.86-5.67), cancers related to human papillomavirus (OR = 5.05; 95% CI, 3.77-6.78), or other cancers (OR = 1.25; 95% CI, 1.10-1.42). The prevalence of stroke was higher among HIV-infected patients (OR = 1.32; 95% CI, 1.06-1.63) than among HIV-uninfected patients, but the prevalence of myocardial infarction or coronary artery disease did not differ between the 2 groups.

CONCLUSIONS

As HIV-infected patients live longer, the increasing burden of noncommunicable diseases may complicate their clinical management, requiring primary care providers to be trained in chronic disease management for this population.