Design and implementation of a privacy preserving electronic health record linkage tool in Chicago

Kho, Abel N.; Cashy, John; Jackson, Kathryn; Pah, Adam R.; Goel, Satyender; Boehnke, Jörn; Humphries, John Eric; Kominers, Scott Duke; Hota, Bala; Sims, Shannon; Malin, Bradley; French, Dustin D.; Walunas, Theresa L.; Meltzer, David O.; Kaleba, Erin O.; Jones, Roderick C.; Galanter, William L.

doi:10.1093/jamia/ocv038

Cited by 97 publications

(94 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…54 One way to protect privacy while sharing PII is to use privacy-preserving data linkage Big Data and Health Disparities -Zhang et al models, which share collections of one-way hashed identifiers to align diverse datasets. 55 However, these systems require both datasets to have access to PII (or pre-hashed identifiers), and many current potential data providers may not have the ability at this time to implement such a system due to technical and cost reasons. Data de-identification can help mitigate privacy concerns.…”

Section: Challenge I: Ethics Privacy and Trustmentioning

confidence: 99%

Big Data Science: Opportunities and Challenges to Address Minority Health and Health Disparities in the 21st Century

Zhang

Pérez‐Stable²,

Bourne³

et al. 2017

Ethn Dis

163

138

View full text Add to dashboard Cite

Addressing minority health and health disparities has been a missing piece of the puzzle in Big Data science. This article focuses on three priority opportunities that Big Data science may offer to the reduction of health and health care disparities. One opportunity is to incorporate standardized information on demographic and social determinants in electronic health records in order to target ways to improve quality of care for the most disadvantaged populations over time. A second opportunity is to enhance public health surveillance by linking geographical variables and social determinants of health for geographically defined populations to clinical data and health outcomes. Third and most importantly, Big Data science may lead to a better understanding of the etiology of health disparities and understanding of minority health in order to guide intervention development. However, the promise of Big Data needs to be considered in light of significant challenges that threaten to widen health disparities. Care must be taken to incorporate diverse populations to realize the potential benefits. Specific recommendations include investing in data collection on small sample populations, building a diverse workforce pipeline for data science, actively seeking to reduce digital divides, developing novel ways to assure digital data privacy for small populations, and promoting widespread data sharing to benefit under-resourced minority-serving institutions and minority researchers. With deliberate efforts, Big Data presents a dramatic opportunity for reducing health disparities but without active engagement, it risks further widening them.Ethn.Dis;2017;27(2):95-106; doi:10.18865/ed.27.2.95.

show abstract

Section: Challenge I: Ethics Privacy and Trustmentioning

confidence: 99%

Big Data Science: Opportunities and Challenges to Address Minority Health and Health Disparities in the 21st Century

Zhang

Pérez‐Stable²,

Bourne³

et al. 2017

Ethn Dis

163

138

View full text Add to dashboard Cite

show abstract

“…Data types included demographics, diagnostic codes from inpatient, outpatient, and emergency department encounters, procedure codes, medications, laboratory measurements recorded as structured data, and vital signs data. HealthLNK investigators then, using a secure matching algorithm, 12 aggregated, de-duplicated, and de-identified the data.…”

Section: Methodsmentioning

confidence: 99%

Validity of Cardiovascular Data From Electronic Sources

Ahmad¹,

Chan²,

Rosenman³

et al. 2017

Circulation

View full text Add to dashboard Cite

Background Understanding the validity of data from electronic data research networks is critical to national research initiatives and learning healthcare systems for cardiovascular care. Our goal was to evaluate the degree of agreement of electronic data research networks compared with data collected by standardized research approaches in a cohort study. Methods We linked individual-level data from The Multi-Ethnic Study of Atherosclerosis (MESA), a community-based cohort, with HealthLNK, a 2006–2012 database of electronic health records (EHRs) from six, Chicago health systems. To evaluate the correlation and agreement of blood pressure (BP) in HealthLNK as compared with in-person MESA examinations, and BMI in HealthLNK compared with MESA, we used Pearson Correlation Coefficients and Bland-Altman plots. Using diagnoses in MESA as the criterion standard, we calculated the performance of HealthLNK for hypertension (HTN), obesity, and diabetes diagnosis using ICD-9 codes and clinical data. We also identified potential myocardial infarctions (MIs), strokes, and heart failure events in HealthLNK and compared them with adjudicated events in MESA. Results Of the 1,164 MESA participants enrolled at the Chicago Field Center, 802 (68.9%) participants had data in HealthLNK. The correlation was low for systolic BP (0.39; P<0.0001). Compared with MESA, HealthLNK overestimated systolic BP by 6.5 mmHg (95%CI: 4.2, 7.8). There was a high correlation between BMI in MESA and HealthLNK (0.94; P<0.0001). HealthLNK underestimated BMI by 0.3 kg/m2 (95%CI: −0.4, −0.1). Using ICD-9 codes and clinical data, the sensitivity and specificity of HealthLNK queries for HTN were 82.4% and 59.4%, for obesity were 73.0% and 89.8%, and for diabetes were 79.8% and 93.3%. Compared with adjudicated CVD events in MESA, the concordance rates for MI, stroke, and heart failure were, respectively, 41.7% (5/12), 61.5% (8/13), and 62.5% (10/16). Conclusions These findings illustrate the limitations and strengths of electronic data repositories compared with information collected by traditional standardized epidemiologic approaches for the ascertainment of CVD risk factors and events.

show abstract

“…The logistics, procedures and patient privacy issues have been previously described. 9 Data from 2007 – 2012 were available from Loyola, Rush, and Northwestern Universities, and the University of Chicago. Patients with diagnostic code 431 (Intracerebral hemorrhage) from the International Classification of Diseases, 9 th Ed were identified.…”

Section: Methodsmentioning

confidence: 99%