Development of a digital dashboard to address population-level obesity using electronic medical record data.

BackgroundPrior studies have demonstrated challenges in developing and validating claims-based algorithms that accurately predict RA disease activity.1 2 The ability to adjust for and predict RA disease activity would be...

Illustrating the patient journey through the care continuum: Leveraging structured primary care electronic medical record (EMR) data in Ontario, Canada using chronic obstructive pulmonary disease as a case study

Some hospitals have different Electronic Medical Records (EMR) systems in affect health services for patients. Electronic Medical Record data among hospitals can eliminate the process of reduplicating Electronic Medical Record data. Data sharing is still centralized and fails to provide logs and events that are trusted, secure, immutable, auditable, and decentralized. In addition, Electronic Medical Record data sharing is important to reward a hospital as a Data Owner for contributing to sharing its Electronic Medical Record data. Our paper provided an Electronic Medical Record data sharing scheme among hospitals with a blockchain solution using an Ethereum smart contract. Access to encrypted data kept on a decentralized storage platform is made possible through a re-encryption method used in conjunction with oracles. We provided the reward mechanism for each Hospital that shared their Electronic Medical Record data through rating techniques with other hospitals as Data Requesters. As a result, we improvised a proposed data-sharing scheme that is focused on Electronic Medical Record data in hospitals to solve the problem of differences in Electronic Medical Record data of patients among hospitals. We evaluated the proposed system with cost analysis and security analysis.

BackgroundAutomatic identification of notifiable diseases from electronic medical records can potentially improve the timeliness and completeness of public health surveillance. We describe the development and implementation of an algorithm for prospective surveillance of patients with acute hepatitis B using electronic medical record data.MethodsInitial algorithms were created by adapting Centers for Disease Control and Prevention diagnostic criteria for acute hepatitis B into electronic terms. The algorithms were tested by applying them to ambulatory electronic medical record data spanning 1990 to May 2006. A physician reviewer classified each case identified as acute or chronic infection. Additional criteria were added to algorithms in serial fashion to improve accuracy. The best algorithm was validated by applying it to prospective electronic medical record data from June 2006 through April 2008. Completeness of case capture was assessed by comparison with state health department records.FindingsA final algorithm including a positive hepatitis B specific test, elevated transaminases and bilirubin, absence of prior positive hepatitis B tests, and absence of an ICD9 code for chronic hepatitis B identified 112/113 patients with acute hepatitis B (sensitivity 97.4%, 95% confidence interval 94–100%; specificity 93.8%, 95% confidence interval 87–100%). Application of this algorithm to prospective electronic medical record data identified 8 cases without false positives. These included 4 patients that had not been reported to the health department. There were no known cases of acute hepatitis B missed by the algorithm.ConclusionsAn algorithm using codified electronic medical record data can reliably detect acute hepatitis B. The completeness of public health surveillance may be improved by automatically identifying notifiable diseases from electronic medical record data.

IntroductionFrailty is a complex condition that affects many aspects of patients’ wellbeing and health outcomes.ObjectivesWe used available Electronic Medical Record (EMR) and administrative data to determine definitions of frailty. We also examined whether there were differences in demographics or health conditions among those identified as frail in either the EMR or administrative data. MethodsEMR and administrative data were linked in British Columbia (BC) and Manitoba (MB) to identify those aged 65 years and older who were frail. The EMR data were obtained from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) and the administrative data (e.g. billing, hospitalizations) was obtained from Population Data BC and the Manitoba Population Research Data Repository. Sociodemographic characteristics, risk factors, prescribed medications, use and costs of healthcare are described for those identified as frail.ResultsSociodemographic and utilization differences were found among those identified as frail from the EMR compared to those in the administrative data. Among those who were >65 years, who had a record in both EMR and administrative data, 5%-8% (n=191 of 3,553, BC; n=2,396 of 29,382, MB) were identified as frail. There was a higher likelihood of being frail with increasing age and being a woman. In BC and MB, those identified as frail in both data sources have approximately twice the number of contacts with primary care (n=20 vs. n=10) and more days in hospital (n=7.2 vs. n=1.9 in BC; n=9.8 vs. n=2.8 in MB) compared to those who are not frail; 27% (BC) and 14% (MB) of those identified as frail in 2014 died in 2015. ConclusionsIdentifying frailty using EMR data is particularly challenging because many functional deficits are not routinely recorded in structured data fields. Our results suggest frailty can be captured along a continuum using both EMR and administrative data.

ObjectiveTo describe the process for linking electronic medical record (EMR) and administrative data in Alberta and examine the advantages and limitations of utilising linked data for hypertension surveillance.MethodsDe-identified EMR data...

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. 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. 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. 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.

IntroductionAutism Spectrum Disorder (ASD) is a neurodevelopmental disorder (NDD) that presents with a high degree of heterogeneity (e.g., co-occurrence of other NDDs and other co-morbid conditions), contributing to differential health system needs. Genetics are known to play an important role in ASD and may be associated with different disease trajectories.
 Objectives and ApproachIn this proof of principle project, our objective is to link >2,200 children with a confirmed diagnosis of a NDD from the Province of Ontario Neurodevelopmental (POND) Study to administrative health data and electronic medical record (EMR) data in order to identify subgroups of ASD with unique health system trajectories. POND includes detailed phenotype and whole genome sequencing (WGS) data. Identified subgroups will be characterized based on clinical phenotype and genetics. To meet this goal, consideration of WGS-specific privacy and data issues is needed to implement processes which are above and beyond traditional requirements for analyzing individual-level administrative health data.
 ResultsLinkage of WGS data with administrative health data is an emerging area of research. As such it has presented a number of initial challenges for our study of ASD. Privacy concerns surrounding the use of WGS data and rare-variant analysis are of particular importance. Practical issues required the need for analysts with expertise in administrative data, EMR data and genetic analyses, and specialized software and sufficient processing power to analyze WGS data. Transdisciplinary discussions of the scope and significance of research questions addressed through this linkage were crucial. The identification of genetic determinants of phenotypes and trajectories in ASD could support targeted early interventions; EMR linkage may inform algorithms to identify ASD in broader populations. These approaches could improve both patient outcome and family experience.
 Conclusion/ImplicationsAs the cost of genetic sequencing decreases, WGS data will become part of the routine clinical management of patients. Linkage of WGS, EMR and administrative data has tremendous potential that has largely not been realized; including population-level ASD research to improve our ability to predict long-term outcomes associated with ASD.

In hospital systems, large volumes of data are routinely collected in digital form. Advances in electronic medical record systems have created digital health data that are well coded and structured,...

BackgroundThe aim of this study was to conduct a retrospective database analysis to describe the chemotherapy treatment patterns and outcomes of patients with gastric cancer.MethodsIndividuals diagnosed with gastric cancer were identified from the IMS Oncology Database, which contains electronic medical record (EMR) data collected from a variety of community practices, and the Truven Health MarketScan® Research database, an administrative claims database. Eligible patients were 18 years of age or older and had an ICD-9 code 151.0–151.9. Patients were excluded if they had evidence of cancer within 6 months of the index diagnosis.ResultsThere were 5257 eligible patients identified in EMR data: 1982 (37.7 %) of these patients also had data regarding chemotherapy treatments. Of the 1982 patients who received first-line therapy, 42.3 %, 18.1 %, and 7.9 % went on to receive a second, third, and fourth line of chemotherapy, respectively. There were 11891 eligible patients identified in the administrative database; 5299 (44.6 %) had data regarding chemotherapy. Of those initiating chemotherapy, 2888 (54.5 %) received a second line and 1598 (30.2 %) received a third line of treatment. The average total cost of care during first-line therapy was $40,811 [standard deviation (SD) = $49,916], which was incurred over an average of 53.5 (SD = 63.4) days. A similar pattern was evident in second-line treatment (mean/SD, $26,588/$33,301) over 41.2 (SD = 55.7) days.ConclusionsCosts and duration of care received vary among gastric cancer patients in the U.S. There is a need to understand which regimens may be associated with better health outcomes and to standardize treatment as appropriate.

ABSTRACTObjectivesCanadians are investing heavily in electronic medical records (EMRs) to inform primary care practice improvements. The Canadian Primary Care Sentinel Surveillance Network (CPCSSN) is a national practice-based network that has enrolled more than one million patients to date. Accurate CPCSSN EMR data are essential for unbiased research about chronic disease prevention and management. The study purpose was to test the accuracy of chronic disease case definitions in EMR data from one CPCSSN site.
 ApproachThis study linked CPCSSN EMR data, hospital records, physician billing claims, prescription drug records, and population registration files for the province of Manitoba. Individuals who had at least one encounter with a CPCSSN practice between 1998 and 2012, were at least 18 years of age, and had a minimum of two years of healthcare coverage before and after the study index date were included. Separate cohorts were defined for the following chronic diseases: chronic obstructive pulmonary disease (COPD), depression, diabetes, hypertension, and osteoarthritis. Validated case definitions based on diagnoses in physician and hospital records and prescription drug data were used estimate sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and kappa of each EMR chronic disease case definition.
 ResultsMore than 74,000 individuals were included in each cohort, except for COPD which had 51,000. Approximately half of each cohort was comprised of urban residents. The average age ranged from 45.9 years for individuals with depression to 65.3 years for individuals with COPD. Hypertension had the highest prevalence (22.0%) in EMR data followed by depression (14.6%). Estimates of agreement (i.e., kappa) for EMR and administrative data ranged from 0.47 for COPD to 0.58 for diabetes. Sensitivity of the EMR data was lowest for COPD (37.4%; 95% CI 36.0-38.8) and highest for diabetes (57.6%; 95% confidence interval [CI] 56.6-58.6). PPV estimates were lowest for osteoarthritis (66.9%; 95% CI 66.0-67.8) and highest for hypertension (78.3%; 95% CI 77.7-78.9). Specificity estimates were consistently above 90% and NPV estimates were always greater than 80%. Validity estimates for the EMR case definitions were associated with demographic and comorbidity characteristics of the study cohorts.
 ConclusionsValidity of EMR data, when compared to administrative health data, for ascertaining five different chronic diseases was fair to good; it varied with the disease under investigation. Further research is needed to identify methods for improving the accuracy of chronic disease case definitions in EMR data.

Timely detection of deterioration in status for intensive care unit patients can be problematic due to variation in data availability and the necessity of integrating data from multiple sources. This can lead to opaqueness of clinical trends and failure to rescue. Automated deterioration detection using electronic medical record data can reduce the risk of failure to rescue. This review describes the automated use of electronic medical record data in identifying deterioration in intensive care unit patients. PubMed and Google Scholar were used to retrieve publications between January 1, 2006, and March 31, 2016. Six studies met inclusion criteria: intensive care unit patient focus, description of electronic medical record data use in automated patient deterioration detection, and presence of predictive, sensitivity, and/or specificity values. Detection focused on specific clinical events such as infection; data sources were electronic medical record-populated databases. Detection algorithms incorporated laboratory results, vital signs, medication orders, and respiratory therapy and radiology documentation. Positive and negative predictive values and sensitivity and specificity measures varied across studies. Three systems generated clinician alerts. Automated deterioration detection using electronic medical record data may be an important aid in caring for intensive care unit patients, but its usefulness is limited by variable electronic medical record detection approaches and performance.

Our primary aim was to characterize the level of medication use across age-groups by examining electronic medical record data for a large number of patients receiving care in primary care clinics. A secondary aim was to identify factors associated with higher levels of medication use or polypharmacy. We conducted a retrospective query of electronic medical record data from a clinical data warehouse, evaluating 114 012 patients seen in primary care clinics at least once in the previous 6 months. Medication use was evaluated in 3 different categories: level 1 (0-4 medications), level 2 (5-9 medications), and level 3 (≥ 10 medications). Multivariate analysis was used to analyze different patient demographics and comorbidities for association with level of medication use. At ages 18 to 24 years, 15% (male) to 23% (female) of patients were taking greater than 5 medications, a trend that continued to increase with older cohorts. Female patients were more likely to have level 2 (odds ratio [OR] = 1.76) and level 3 (OR = 2.73) use compared with men. Level 2 and level 3 use was associated with other patient characteristics, including number of patient encounters (level 2 OR = 2.99; level 3 OR = 8.08 for >7 encounters) and common chronic conditions such as chronic pain (level 2 OR = 2.56; level 3 OR = 6.40), diabetes (level 2 OR = 2.4; level 3 OR = 4.61), heart disease (level 2 OR = 1.99; level 3 OR = 3.65), hypertension (level 2 OR = 2.27; level 3 OR = 2.87), and dyslipidemia (level 2 OR = 1.82; level 3 OR = 2.12). Electronic medical record data may be an important tool for providing more comprehensive information regarding medication usage. Medication usage assessed by electronic medical records, even among the youngest cohort, appears to be greater than other sources of medication usage indicate. Higher levels of medication use were associated with a number of factors, including gender, body mass index, number of patient encounters, and comorbid conditions.

The objective of this study was to evaluate the incremental predictive power of electronic medical record (EMR) data, relative to the information available in more easily accessible and standardized insurance claims data. Using both EMR and Claims data, we predicted outcomes for 118,510 patients with 144,966 hospitalizations in 8 hospitals, using widely used prediction models. We use cross-validation to prevent overfitting and tested predictive performance on separate data that were not used for model training. We predict 4 binary outcomes: length of stay (≥7 d), death during the index admission, 30-day readmission, and 1-year mortality. We achieve nearly the same prediction accuracy using both EMR and claims data relative to using claims data alone in predicting 30-day readmissions [area under the receiver operating characteristic curve (AUC): 0.698 vs. 0.711; positive predictive value (PPV) at top 10% of predicted risk: 37.2% vs. 35.7%], and 1-year mortality (AUC: 0.902 vs. 0.912; PPV: 64.6% vs. 57.6%). EMR data, especially from the first 2 days of the index admission, substantially improved prediction of length of stay (AUC: 0.786 vs. 0.837; PPV: 58.9% vs. 55.5%) and inpatient mortality (AUC: 0.897 vs. 0.950; PPV: 24.3% vs. 14.0%). Results were similar for sensitivity, specificity, and negative predictive value across alternative cutoffs and for using alternative types of predictive models. EMR data are useful in predicting short-term outcomes. However, their incremental value for predicting longer-term outcomes is smaller. Therefore, for interventions that are based on long-term predictions, using more broadly available claims data is equally effective.

Social networks have been used in the study of outbreaks of infectious diseases, including in small group settings such as individual hospitals. Collecting the data needed to create such networks, however, can be time consuming, costly, and error prone. We sought to create a social network of hospital inpatients using electronic medical record (EMR) data already collected for other purposes, for use in simulating outbreaks of nosocomial infections. We used the EMR data warehouse of a tertiary academic hospital to model contact among inpatients. Patient-to-patient contact due to shared rooms was inferred from admission-discharge-transfer data, and contact with healthcare workers was inferred from clinical documents. Contacts were used to generate a social network, which was then used to conduct probabilistic simulations of nosocomial outbreaks of methicillin-resistant Staphylococcus aureus and influenza. Simulations of infection transmission across the network reflected the staffing and patient flow practices of the hospital. Simulations modeling patient isolation, increased hand hygiene, and staff vaccination showed a decrease in the spread of infection. We developed a method of generating a social network of hospital inpatients from EMR data. This method allows the derivation of networks that reflect the local hospital environment, obviate the need for simulated or manually collected data, and can be updated in near real time. Inpatient social networks represent a novel secondary use of EMR data, and can be used to simulate nosocomial infections. Future work should focus on prospective validation of the simulations, and adapting such networks to other tasks.