Using health information technology to improve hypertension management

Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the Department of Veterans Affairs

Background

We developed an accurate, stakeholder-informed, automated, natural language processing (NLP) system to measure the quality of heart failure (HF) inpatient care, and explored the potential for adoption of this system within an integrated health care system.

Objective

To accurately automate a United States Department of Veterans Affairs (VA) quality measure for inpatients with HF.

Methods

We automated the HF quality measure Congestive Heart Failure Inpatient Measure 19 (CHI19) that identifies whether a given patient has left ventricular ejection fraction (LVEF) <40%, and if so, whether an angiotensin-converting enzyme inhibitor or angiotensin-receptor blocker was prescribed at discharge if there were no contraindications. We used documents from 1083 unique inpatients from eight VA medical centers to develop a reference standard (RS) to train (n=314) and test (n=769) the Congestive Heart Failure Information Extraction Framework (CHIEF). We also conducted semi-structured interviews (n=15) for stakeholder feedback on implementation of the CHIEF.

Results

The CHIEF classified each hospitalization in the test set with a sensitivity (SN) of 98.9% and positive predictive value of 98.7%, compared with an RS and SN of 98.5% for available External Peer Review Program assessments. Of the 1083 patients available for the NLP system, the CHIEF evaluated and classified 100% of cases. Stakeholders identified potential implementation facilitators and clinical uses of the CHIEF.

Conclusions

The CHIEF provided complete data for all patients in the cohort and could potentially improve the efficiency, timeliness, and utility of HF quality measurements.

Sociotechnical Challenges of Developing an Interoperable Personal Health Record: Lessons Learned

OBJECTIVES: To analyze sociotechnical issues involved in the process of developing an interoperable commercial Personal Health Record (PHR) in a hospital setting, and to create guidelines for future PHR implementations. METHODS: This qualitative study utilized observational research and semi-structured interviews with 8 members of the hospital team, as gathered over a 28 week period of developing and adapting a vendor-based PHR at Lucile Packard Children's Hospital at Stanford University. A grounded theory approach was utilized to code and analyze over 100 pages of typewritten field notes and interview transcripts. This grounded analysis allowed themes to surface during the data collection process which were subsequently explored in greater detail in the observations and interviews. RESULTS: Four major themes emerged: (1) Multidisciplinary teamwork helped team members identify crucial features of the PHR; (2) Divergent goals for the PHR existed even within the hospital team; (3) Differing organizational conceptions of the end-user between the hospital and software company differentially shaped expectations for the final product; (4) Difficulties with coordination and accountability between the hospital and software company caused major delays and expenses and strained the relationship between hospital and software vendor. CONCLUSIONS: Though commercial interoperable PHRs have great potential to improve healthcare, the process of designing and developing such systems is an inherently sociotechnical process with many complex issues and barriers. This paper offers recommendations based on the lessons learned to guide future development of such PHRs.

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

BACKGROUND

The US Veterans Administration (VA) has developed a robust and mature computational infrastructure in support of its electronic health record (EHR). Web technology offers a powerful set of tools for structuring clinical decision support (CDS) around clinical care. This paper describes informatics challenges and design issues that were confronted in the process of building three Web-based CDS systems in the context of the VA EHR.

METHODS

Over the course of several years, we implemented three Web-based CDS systems that extract patient data from the VA EHR environment to provide patient-specific CDS. These were 1) the VACS (Veterans Aging Cohort Study) Index Calculator which estimates prognosis for HIV+ patients, 2) Neuropath/CDS which assists in the medical management of patients with neuropathic pain, and 3) TRIM (Tool to Reduce Inappropriate Medications) which identifies potentially inappropriate medications in older adults and provides recommendations for improving the medication regimen.

RESULTS

The paper provides an overview of the VA EHR environment and discusses specific informatics issues/challenges that arose in the context of each of the three Web-based CDS systems. We discuss specific informatics methods and provide details of approaches that may be useful within this setting.

CONCLUSIONS

Informatics issues and challenges relating to data access and data availability arose because of the particular architecture of the national VA infrastructure and the need to link to that infrastructure from local Web-based CDS systems. Idiosyncrasies of VA patient data, especially the medication data, also posed challenges. Other issues related to specific functional needs of individual CDS systems. The goal of this paper is to describe these issues so that our experience may serve as a useful foundation to assist others who wish to build such systems in the future.

A Brief, Multifaceted, Generic Intervention to Improve Blood Pressure Control and Reduce Disparities Had Little Effect

BACKGROUND

Poor blood pressure (BP) control and racial disparities therein may be a function of clinical inertia and ineffective communication about BP care.

METHODS

We compared two different interventions (electronic medical record reminder for BP care (Reminder only, [RO]), and clinician training on BP care-related communication skills plus the reminder (Reminder + Training, [R+T]) with usual care in three primary care clinics, examining BP outcomes among 8,866 patients, and provider-patient communication and medication adherence among a subsample of 793.

RESULTS

Clinician counseling improved most at R+T. BP improved overall; R+T had a small but significantly greater reduction in diastolic BP (DBP; -1.7 mm Hg). White patients at RO experienced greater overall improvements in BP control. Site and race disparities trends suggested that disparities decreased at R+T, either stayed the same or decreased at Control; and stayed the same or increased at RO.

CONCLUSIONS

More substantial or racial/ethnically tailored interventions are needed.

A mapping analytic approach to trace development of multidisciplinary research field

Purpose

– This paper aims to provide clear domain knowledge and recent progresses on electronic healthcare (e-healthcare).

Design/methodology/approach

– In this paper, the authors use citation analysis to describe the trends of study on e-health with the help of CiteSpace II, a software for visualizing citation-based analysis. By analyzing the 2,752 publications and their citation data in ISI database, the authors proposed renewable figures and tables on ranking critical people, institutes, keywords and journals. Through the most influential articles given by CiteSpace, the authors can grasp the main direction in e-health researches. Furthermore, the authors analyzed the literature at e-health literacy as a case, to better understand the development of research viewpoints.

Findings

– Through the analysis, the authors found that e-health is a multi-disciplinary research field and the major research about it has changed. During the early stage, health information quality on the Internet dominates. Gradually, the role of information technology (IT) becomes more important. The authors also found that some researchers, recently, have proposed the effects of IT on e-health literacy which can then improve the ability to use health information on the Internet.

Research limitations/implications

– This paper has some research limitations, such as using an ISI database with most English publications. The future research may be conducted for collecting local publications data in China. It also has some implications. Based on the results, the authors claimed that IT may significantly improve people’s healthcare variance, e.g. e-health literacy. It is necessary to build new IT-based healthcare theories.

Practical implications

– This paper also has some practical implications. Practitioners and institute may easily come to know which are the hot topics, top institutes and tendencies in the e-healthcare field.

Social implications

– This paper may help practitioners to find common interests with other institutions and societies.

Originality/value

– This paper reported the status and trend of research in this field visually, and the result will help researchers to do more in-depth research in the future.

Exploring a clinically friendly web-based approach to clinical decision support linked to the electronic health record: design philosophy, prototype implementation, and framework for assessment

BACKGROUND

Computer-based clinical decision support (CDS) is an important component of the electronic health record (EHR). As an increasing amount of CDS is implemented, it will be important that this be accomplished in a fashion that assists in clinical decision making without imposing unacceptable demands and burdens upon the provider's practice.

OBJECTIVE

The objective of our study was to explore an approach that allows CDS to be clinician-friendly from a variety of perspectives, to build a prototype implementation that illustrates features of the approach, and to gain experience with a pilot framework for assessment.

METHODS

The paper first discusses the project's design philosophy and goals. It then describes a prototype implementation (Neuropath/CDS) that explores the approach in the domain of neuropathic pain and in the context of the US Veterans Administration EHR. Finally, the paper discusses a framework for assessing the approach, illustrated by a pilot assessment of Neuropath/CDS.

RESULTS

The paper describes the operation and technical design of Neuropath/CDS, as well as the results of the pilot assessment, which emphasize the four areas of focus, scope, content, and presentation.

CONCLUSIONS

The work to date has allowed us to explore various design and implementation issues relating to the approach illustrated in Neuropath/CDS, as well as the development and pilot application of a framework for assessment.

Development and validation of a clinical and computerised decision support system for management of hypertension (DSS-HTN) at a primary health care (PHC) setting

BACKGROUND

Hypertension remains the top global cause of disease burden. Decision support systems (DSS) could provide an adequate and cost-effective means to improve the management of hypertension at a primary health care (PHC) level in a developing country, nevertheless evidence on this regard is rather limited.

METHODS

Development of DSS software was based on an algorithmic approach for (a) evaluation of a hypertensive patient, (b) risk stratification (c) drug management and (d) lifestyle interventions, based on Indian guidelines for hypertension II (2007). The beta testing of DSS software involved a feedback from the end users of the system on the contents of the user interface. Software validation and piloting was done in field, wherein the virtual recommendations and advice given by the DSS were compared with two independent experts (government doctors from the non-participating PHC centers).

RESULTS

The overall percent agreement between the DSS and independent experts among 60 hypertensives on drug management was 85% (95% CI: 83.61-85.25). The kappa statistic for overall agreement for drug management was 0.659 (95% CI: 0.457-0.862) indicating a substantial degree of agreement beyond chance at an alpha fixed at 0.05 with 80% power. Receiver operator curve (ROC) showed a good accuracy for the DSS, wherein, the area under curve (AUC) was 0.848 (95% CI: 0.741-0.948). Sensitivity and specificity of the DSS were 83.33 and 85.71% respectively when compared with independent experts.

CONCLUSION

A point of care, pilot tested and validated DSS for management of hypertension has been developed in a resource constrained low and middle income setting and could contribute to improved management of hypertension at a primary health care level.

Using benefit-based tailored treatment to improve the use of antihypertensive medications

BACKGROUND

Current guidelines for prescribing antihypertensive medications focus on reaching specific blood pressure targets. We sought to determine whether antihypertensive medications could be used more effectively by a treatment strategy based on tailored estimates of cardiovascular disease events prevented.

METHODS AND RESULTS

We developed a nationally representative sample of American adults aged 30 to 85 years with no history of myocardial infarction, stroke, or severe congestive heart failure using the National Health and Nutrition Examination Survey III. We then created a simulation model to estimate the effects of 5 years of treatment with treat-to-target (treatment to specific blood pressure goals) and benefit-based tailored treatment (treatment based on estimated cardiovascular disease event reduction) approaches to antihypertensive medication management. All effect size estimates were derived directly from meta-analyses of randomized trials. We found that 55% of the overall population of 176 million Americans would be treated identically under the 2 treatment approaches. Benefit-based tailored treatment would prevent 900 000 more cardiovascular disease events and save 2.8 million more quality-adjusted life-years, despite using 6% fewer medications over 5 years. In the 45% of the population treated differently by the strategies, benefit-based tailored treatment would save 159 quality-adjusted life-years per 1000 treated versus 74 quality-adjusted life-years per 1000 treated by the treat-to-target approach. The findings were robust to sensitivity analyses.

CONCLUSIONS

We found that benefit-based tailored treatment was both more effective and required less antihypertensive medication than current guidelines based on treating to specific blood pressure goals.

Translation of hypertension treatment guidelines into practice: a review of implementation

Compared with the history of national guideline development, the science attached to implementation of guidelines is relatively new. Effectiveness of a highly evidence-based guideline, such as the 8th Joint National Committee recommendations on the treatment of high blood pressure, depends on successful translation into clinical practice. Implementation relies on several steps: clear and executable guideline language, audit and feedback attached to education of practitioners charged with carrying out the guidelines, team-based care delivery, credibility of blood pressure measurement, and measures to address therapeutic inertia and medication adherence. An evolving role of the electronic health record and patient empowerment are developments that will further promote implementation of the hypertension guideline. Further research will be needed to assess the efficacy and cost effectiveness of various implementation tools and strategies.

Reducing cardiovascular disease risk in medically underserved urban and rural communities

OBJECTIVES

The aim of this study is to evaluate methods for lowering cardiovascular disease (CVD) risk in asymptomatic urban and rural underserved subjects.

BACKGROUND

Medically underserved populations are at increased CVD risk, and systems to lower CVD risk are needed. Nurse management (NM) and telemedicine (T) systems may provide low-cost solutions for this care.

METHODS

We randomized 465 subjects without overt CVD, with Framingham CVD risk >10% to NM with 4 visits over 1 year, or NM plus T to facilitate weight, blood pressure (BP), and physical activity reporting. The study goal was to reduce CVD risk by 5%.

RESULTS

Three hundred eighty-eight subjects completed the study. Cardiovascular disease risk fell by ≥ 5% in 32% of the NM group and 26% of the T group (P, nonsignificant). In hyperlipidemic subjects, total cholesterol decreased (NM -21.9 ± 39.4, T -22.7 ± 41.3 mg/dL) significantly. In subjects with grade II hypertension (systolic BP ≥ 160 mm Hg, 24% of subjects), both NM and T groups had a similar BP response (average study BP: NM 147.4 ± 17.5, T 145.3. ± 18.4, P is nonsignificant), and for those with grade I hypertension (37% of subjects), T had a lower average study BP compared to NM (NM 140.4 ± 16.9, T 134.6 ± 15.0, P = .058). In subjects at high risk (Framingham score ≥ 20%), risk fell 6.0% ± 9.9%; in subjects at intermediate risk (Framingham score ≥ 10, < 20), risk fell 1.3% ± 4.5% (P < .001 compared to high-risk subjects). Medication adherence was similar in both high- and intermediate-risk subjects.

CONCLUSIONS

In 2 underserved populations, CVD risk was reduced by a nurse intervention; T did not add to the risk improvement. Reductions in BP and blood lipids occurred in both high- and intermediate-risk subjects with greatest reductions noted in the high-risk subjects. Frequent communication using a nurse intervention contributes to improved CVD risk in asymptomatic, underserved subjects with increased CVD risk. Telemedicine did not change the effectiveness of the nurse intervention.

The effectiveness of computerized clinical guidelines in the process of care: a systematic review

BACKGROUND

Clinical practice guidelines have been developed aiming to improve the quality of care. The implementation of the computerized clinical guidelines (CCG) has been supported by the development of computerized clinical decision support systems.This systematic review assesses the impact of CCG on the process of care compared with non-computerized clinical guidelines.

METHODS

Specific features of CCG were studied through an extensive search of scientific literature, querying electronic databases: Pubmed/Medline, Embase and Cochrane Controlled Trials Register. A multivariable logistic regression was carried out to evaluate the association of CCG's features with positive effect on the process of care.

RESULTS

Forty-five articles were selected. The logistic model showed that Automatic provision of recommendation in electronic version as part of clinician workflow (Odds Ratio [OR]= 17.5; 95% confidence interval [CI]: 1.6-193.7) and Publication Year (OR = 6.7; 95%CI: 1.3-34.3) were statistically significant predictors.

CONCLUSIONS

From the research that has been carried out, we can conclude that after implementation of CCG significant improvements in process of care are shown. Our findings also suggest clinicians, managers and other health care decision makers which features of CCG might improve the structure of computerized system.

Implementing evidence-based patient self-management programs in the Veterans Health Administration: perspectives on delivery system design considerations

While many patient self-management (PSM) programs have been developed and evaluated for effectiveness, less effort has been devoted to translating and systematically delivering PSM in primary and specialty care. Therefore, the purpose of this paper is to review delivery system design considerations for implementing self-management programs in practice. As lessons are learned about implementing PSM programs in Veterans Health Administration (VHA), resource allocation by healthcare organization for formatting PSM programs, providing patient access, facilitating PSM, and incorporating support tools to foster PSM among its consumers can be refined and tailored. Redesigning the system to deliver and support PSM will be important as implementation researchers translate evidence based PSM practices into routine care and evaluate its impact on the health-related quality of life of veterans living with chronic disease.