Dataset Information

Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals.

ABSTRACT: OBJECTIVE:Phenotyping algorithms applied to electronic health record (EHR) data enable investigators to identify large cohorts for clinical and genomic research. Algorithm development is often iterative, depends on fallible investigator intuition, and is time- and labor-intensive. We developed and evaluated 4 types of phenotyping algorithms and categories of EHR information to identify hypertensive individuals and controls and provide a portable module for implementation at other sites. MATERIALS AND METHODS:We reviewed the EHRs of 631 individuals followed at Vanderbilt for hypertension status. We developed features and phenotyping algorithms of increasing complexity. Input categories included International Classification of Diseases, Ninth Revision (ICD9) codes, medications, vital signs, narrative-text search results, and Unified Medical Language System (UMLS) concepts extracted using natural language processing (NLP). We developed a module and tested portability by replicating 10 of the best-performing algorithms at the Marshfield Clinic. RESULTS:Random forests using billing codes, medications, vitals, and concepts had the best performance with a median area under the receiver operator characteristic curve (AUC) of 0.976. Normalized sums of all 4 categories also performed well (0.959 AUC). The best non-NLP algorithm combined normalized ICD9 codes, medications, and blood pressure readings with a median AUC of 0.948. Blood pressure cutoffs or ICD9 code counts alone had AUCs of 0.854 and 0.908, respectively. Marshfield Clinic results were similar. CONCLUSION:This work shows that billing codes or blood pressure readings alone yield good hypertension classification performance. However, even simple combinations of input categories improve performance. The most complex algorithms classified hypertension with excellent recall and precision.

SUBMITTER: Teixeira PL

PROVIDER: S-EPMC5201185 | biostudies-literature | 2017 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals.

Teixeira Pedro L PL Wei Wei-Qi WQ Cronin Robert M RM Mo Huan H VanHouten Jacob P JP Carroll Robert J RJ LaRose Eric E Bastarache Lisa A LA Rosenbloom S Trent ST Edwards Todd L TL Roden Dan M DM Lasko Thomas A TA Dart Richard A RA Nikolai Anne M AM Peissig Peggy L PL Denny Joshua C JC

Journal of the American Medical Informatics Association : JAMIA 20160807 1

<h4>Objective</h4>Phenotyping algorithms applied to electronic health record (EHR) data enable investigators to identify large cohorts for clinical and genomic research. Algorithm development is often iterative, depends on fallible investigator intuition, and is time- and labor-intensive. We developed and evaluated 4 types of phenotyping algorithms and categories of EHR information to identify hypertensive individuals and controls and provide a portable module for implementation at other sites.< ...[more]

PMID: 27497800

Similar Datasets

Project description:ObjectiveTo identify observational studies which used data from more than one primary care electronic health record (EHR) database, and summarise key characteristics including: objective and rationale for using multiple data sources; methods used to manage, analyse and (where applicable) combine data; and approaches used to assess and report heterogeneity between data sources.DesignA systematic review of published studies.Data sourcesPubmed and Embase databases were searched using list of named primary care EHR databases; supplementary hand searches of reference list of studies were retained after initial screening.Study selectionObservational studies published between January 2000 and May 2018 were selected, which included at least two different primary care EHR databases.Results6054 studies were identified from database and hand searches, and 109 were included in the final review, the majority published between 2014 and 2018. Included studies used 38 different primary care EHR data sources. Forty-seven studies (44%) were descriptive or methodological. Of 62 analytical studies, 22 (36%) presented separate results from each database, with no attempt to combine them; 29 (48%) combined individual patient data in a one-stage meta-analysis and 21 (34%) combined estimates from each database using two-stage meta-analysis. Discussion and exploration of heterogeneity was inconsistent across studies.ConclusionsComparing patterns and trends in different populations, or in different primary care EHR databases from the same populations, is important and a common objective for multi-database studies. When combining results from several databases using meta-analysis, provision of separate results from each database is helpful for interpretation. We found that these were often missing, particularly for studies using one-stage approaches, which also often lacked details of any statistical adjustment for heterogeneity and/or clustering. For two-stage meta-analysis, a clear rationale should be provided for choice of fixed effect and/or random effects or other models.

Project description:Accurate, real-time case identification is needed to target interventions to improve quality and outcomes for hospitalized patients with heart failure. Problem lists may be useful for case identification but are often inaccurate or incomplete. Machine-learning approaches may improve accuracy of identification but can be limited by complexity of implementation.To develop algorithms that use readily available clinical data to identify patients with heart failure while in the hospital.We performed a retrospective study of hospitalizations at an academic medical center. Hospitalizations for patients 18 years or older who were admitted after January 1, 2013, and discharged before February 28, 2015, were included. From a random 75% sample of hospitalizations, we developed 5 algorithms for heart failure identification using electronic health record data: (1) heart failure on problem list; (2) presence of at least 1 of 3 characteristics: heart failure on problem list, inpatient loop diuretic, or brain natriuretic peptide level of 500 pg/mL or higher; (3) logistic regression of 30 clinically relevant structured data elements; (4) machine-learning approach using unstructured notes; and (5) machine-learning approach using structured and unstructured data.Heart failure diagnosis based on discharge diagnosis and physician review of sampled medical records.A total of 47?119 hospitalizations were included in this study (mean [SD] age, 60.9 [18.15] years; 23 952 female [50.8%], 5258 black/African American [11.2%], and 3667 Hispanic/Latino [7.8%] patients). Of these hospitalizations, 6549 (13.9%) had a discharge diagnosis of heart failure. Inclusion of heart failure on the problem list (algorithm 1) had a sensitivity of 0.40 and a positive predictive value (PPV) of 0.96 for heart failure identification. Algorithm 2 improved sensitivity to 0.77 at the expense of a PPV of 0.64. Algorithms 3, 4, and 5 had areas under the receiver operating characteristic curves of 0.953, 0.969, and 0.974, respectively. With a PPV of 0.9, these algorithms had associated sensitivities of 0.68, 0.77, and 0.83, respectively.The problem list is insufficient for real-time identification of hospitalized patients with heart failure. The high predictive accuracy of machine learning using free text demonstrates that support of such analytics in future electronic health record systems can improve cohort identification.

Project description:BackgroundThe rarity of pediatric glomerular disease makes it difficult to identify sufficient numbers of participants for clinical trials. This leaves limited data to guide improvements in care for these patients.MethodsThe authors developed and tested an electronic health record (EHR) algorithm to identify children with glomerular disease. We used EHR data from 231 patients with glomerular disorders at a single center to develop a computerized algorithm comprising diagnosis, kidney biopsy, and transplant procedure codes. The algorithm was tested using PEDSnet, a national network of eight children's hospitals with data on >6.5 million children. Patients with three or more nephrologist encounters (n=55,560) not meeting the computable phenotype definition of glomerular disease were defined as nonglomerular cases. A reviewer blinded to case status used a standardized form to review random samples of cases (n=800) and nonglomerular cases (n=798).ResultsThe final algorithm consisted of two or more diagnosis codes from a qualifying list or one diagnosis code and a pretransplant biopsy. Performance characteristics among the population with three or more nephrology encounters were sensitivity, 96% (95% CI, 94% to 97%); specificity, 93% (95% CI, 91% to 94%); positive predictive value (PPV), 89% (95% CI, 86% to 91%); negative predictive value, 97% (95% CI, 96% to 98%); and area under the receiver operating characteristics curve, 94% (95% CI, 93% to 95%). Requiring that the sum of nephrotic syndrome diagnosis codes exceed that of glomerulonephritis codes identified children with nephrotic syndrome or biopsy-based minimal change nephropathy, FSGS, or membranous nephropathy, with 94% sensitivity and 92% PPV. The algorithm identified 6657 children with glomerular disease across PEDSnet, ≥50% of whom were seen within 18 months.ConclusionsThe authors developed an EHR-based algorithm and demonstrated that it had excellent classification accuracy across PEDSnet. This tool may enable faster identification of cohorts of pediatric patients with glomerular disease for observational or prospective studies.

Project description:BackgroundLate HIV diagnosis is detrimental both to the individual and to society. Strategies to improve early diagnosis of HIV must be a key health care priority. We examined whether nation-wide electronic registry data could be used to predict HIV status using machine learning algorithms.MethodsWe extracted individual level data from Danish registries and used algorithms to predict HIV status. We used various algorithms to train prediction models and validated these models. We calibrated the models to mimic different clinical scenarios and created confusion matrices based on the calibrated models.FindingsA total 4,384,178 individuals, including 4,350 with incident HIV, were included in the analyses. The full model that included all variables that included demographic variables and information on past medical history had the highest area under the receiver operating characteristics curves of 88·4% (95%CI: 87·5% - 89·4%) in the validation dataset. Performance measures did not differ substantially with regards to which machine learning algorithm was used. When we calibrated the models to a specificity of 99·9% (pre-exposure prophylaxis (PrEP) scenario), we found a positive predictive value (PPV) of 8·3% in the full model. When we calibrated the models to a sensitivity of 90% (screening scenario), 384 individuals would have to be tested to find one undiagnosed person with HIV.InterpretationMachine learning algorithms can learn from electronic registry data and help to predict HIV status with a fairly high level of accuracy. Integration of prediction models into clinical software systems may complement existing strategies such as indicator condition-guided HIV testing and prove useful for identifying individuals suitable for PrEP.FundingThe study was supported by funds from the Preben and Anne Simonsens Foundation, the Novo Nordisk Foundation, Rigshospitalet, Copenhagen University, the Danish AIDS Foundation, the Augustinus Foundation and the Danish Health Foundation.

Project description:BackgroundInterventional studies are the fundamental method for obtaining answers to clinical questions. However, these studies are sometimes difficult to conduct because of insufficient financial or human resources or the rarity of the disease in question. One means of addressing these issues is to conduct a non-interventional observational study using electronic health record (EHR) databases as the data source, although how best to evaluate the suitability of an EHR database when planning a study remains to be clarified. The aim of the present study is to identify and characterize the data sources that have been used for conducting non-interventional observational studies in Japan and propose a flow diagram to help researchers determine the most appropriate EHR database for their study goals.MethodsWe compiled a list of published articles reporting observational studies conducted in Japan by searching PubMed for relevant articles published in the last 3 years and by searching database providers' publication lists related to studies using their databases. For each article, we reviewed the abstract and/or full text to obtain information about data source, target disease or therapeutic area, number of patients, and study design (prospective or retrospective). We then characterized the identified EHR databases.ResultsIn Japan, non-interventional observational studies have been mostly conducted using data stored locally at individual medical institutions (663/1511) or collected from several collaborating medical institutions (315/1511). Whereas the studies conducted with large-scale integrated databases (330/1511) were mostly retrospective (73.6%), 27.5% of the single-center studies, 47.6% of the multi-center studies, and 73.7% of the post-marketing surveillance studies, identified in the present study, were conducted prospectively. We used our findings to develop an assessment flow diagram to assist researchers in evaluating and choosing the most suitable EHR database for their study goals.ConclusionsOur analysis revealed that the non-interventional observational studies were conducted using data stored local at individual medical institutions or collected from collaborating medical institutions in Japan. Disease registries, disease databases, and large-scale databases would enable researchers to conduct studies with large sample sizes to provide robust data from which strong inferences could be drawn.

Project description:ObjectivesRecent sepsis studies have defined patients as "infected" using a combination of culture and antibiotic orders rather than billing data. However, the accuracy of these definitions is unclear. We aimed to compare the accuracy of different established criteria for identifying infected patients using detailed chart review.DesignRetrospective observational study.SettingSix hospitals from three health systems in Illinois.PatientsAdult admissions with blood culture or antibiotic orders, or Angus International Classification of Diseases infection codes and death were eligible for study inclusion as potentially infected patients. Nine-hundred to 1,000 of these admissions were randomly selected from each health system for chart review, and a proportional number of patients who did not meet chart review eligibility criteria were also included and deemed not infected.InterventionsNone.Measurements and main resultsThe accuracy of published billing code criteria by Angus et al and electronic health record criteria by Rhee et al and Seymour et al (Sepsis-3) was determined using the manual chart review results as the gold standard. A total of 5,215 patients were included, with 2,874 encounters analyzed via chart review and a proportional 2,341 added who did not meet chart review eligibility criteria. In the study cohort, 27.5% of admissions had at least one infection. This was most similar to the percentage of admissions with blood culture orders (26.8%), Angus infection criteria (28.7%), and the Sepsis-3 criteria (30.4%). Sepsis-3 criteria was the most sensitive (81%), followed by Angus (77%) and Rhee (52%), while Rhee (97%) and Angus (90%) were more specific than the Sepsis-3 criteria (89%). Results were similar for patients with organ dysfunction during their admission.ConclusionsPublished criteria have a wide range of accuracy for identifying infected patients, with the Sepsis-3 criteria being the most sensitive and Rhee criteria being the most specific. These findings have important implications for studies investigating the burden of sepsis on a local and national level.

Project description:ImportanceComparisons of antimicrobial use among hospitals are difficult to interpret owing to variations in patient case mix. Risk-adjustment strategies incorporating larger numbers of variables haves been proposed as a method to improve comparisons for antimicrobial stewardship assessments.ObjectiveTo evaluate whether variables of varying complexity and feasibility of measurement, derived retrospectively from the electronic health records, accurately identify inpatient antimicrobial use.Design, setting, and participantsRetrospective cohort study, using a 2-stage random forests machine learning modeling analysis of electronic health record data. Data were split into training and testing sets to measure model performance using area under the curve and absolute error. All adult and pediatric inpatient encounters from October 1, 2015, to September 30, 2017, at 2 community hospitals and 1 academic medical center in the Duke University Health System were analyzed. A total of 204 candidate variables were categorized into 4 tiers based on feasibility of measurement from the electronic health records.Main outcomes and measuresAntimicrobial exposure was measured at the encounter level in 2 ways: binary (ever or never) and number of days of therapy. Analyses were stratified by age (pediatric or adult), unit type, and antibiotic group.ResultsThe data set included 170 294 encounters and 204 candidate variables from 3 hospitals during the 3-year study period. Antimicrobial exposure occurred in 80 190 encounters (47%); 64 998 (38%) received 1 to 6 days of therapy, and 15 192 (9%) received 7 or more days of therapy. Two-stage models identified antimicrobial use with high fidelity (mean area under the curve, 0.85; mean absolute error, 1.0 days of therapy). Addition of more complex variables increased accuracy, with largest improvements occurring with inclusion of diagnosis information. Accuracy varied based on location and antibiotic group. Models underestimated the number of days of therapy of encounters with long lengths of stay.Conclusions and relevanceModels using variables derived from electronic health records identified antimicrobial exposure accurately. Future risk-adjustment strategies incorporating encounter-level information may make comparisons of antimicrobial use more meaningful for hospital antimicrobial stewardship assessments.

Dataset Information

Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals.

Publications

Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets