Desiderata for computable representations of electronic health records-driven phenotype algorithms

Mo, Huan; Thompson, William K.; Rasmussen, Luke V.; Pacheco, Jennifer A.; Jiang, Guoqian; Kiefer, Richard C.; Zhu, Qian; Xu, Jie; Montague, Enid; Carrell, David; Lingren, Todd; Mentch, Frank; Ni, Yizhao; Wehbe, Firas; Peissig, Peggy L.; Tromp, Gerard; Larson, Eric B.; Chute, Christopher G.; Pathak, Jyotishman; Denny, Joshua C.; Speltz, Peter; Kho, Abel N.; Jarvik, Gail P.; Bejan, Cosmin Adrian; Williams, Marc S.; Borthwick, Kenneth M.; Kitchner, Terrie; Roden, Dan M.; Harris, Paul A.

doi:10.1093/jamia/ocv112

Cited by 104 publications

(88 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…19,20 Each data source poses unique challenges, and use of multiple data sources often improves performance. 21 Billing code-based phenotyping methods have variable performance with estimates for cardiovascular and stroke risk factors ranging from 0.55 to 0.95 positive predictive value (PPV).…”

Section: Background and Significancementioning

confidence: 99%

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

Teixeira

Wei

Cronin

et al. 2016

Journal of the American Medical Informatics Association

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Background and Significancementioning

confidence: 99%

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

Teixeira

Wei

Cronin

et al. 2016

Journal of the American Medical Informatics Association

Self Cite

View full text Add to dashboard Cite

show abstract

“…Controlling for co-morbid conditions in multi-variable modeling will similarly be negatively impacted by missing clinical EHR terms. Defining clinical phenotypes more completely with rule-based intensional value sets leveraging SNOMED CT's hierarchical structure advances the feasibility and reliability of pragmatic clinical studies and Learning Health System cycles conducted with EHR data produced during normal clinical care [27][28][29].…”

Section: Clinical Phenotyping For Clinical-translational Studies Usinmentioning

confidence: 99%

“…EHRs have "local codes" that can hamper implementation, but increasingly these are mapped to standard terminology codes to achieve interoperability with other EHRs as organizations participate in HIEs [27]. To accelerated implementation, we propose that specialty guideline and eCQM writing committees include a medical informaticist (as either a consultant or a formal member of the writing group representing a clinical informatics specialty society).…”

Section: Authoring Practice Guidelines and Ecqms For Streamlined Implmentioning

confidence: 99%

SNOMED CT Concept Hierarchies for Computable Clinical Phenotypes From Electronic Health Record Data: Comparison of Intensional Versus Extensional Value Sets (Preprint)

Chu¹,

Kannan²,

Basit³

et al. 2018

Preprint

View full text Add to dashboard Cite

Background: Defining clinical phenotypes from EHR-derived data proves crucial for clinical decision support, population health endeavors, and translational research. EHR diagnoses now commonly draw from a finely-grained clinical terminologyeither native SNOMED CT, or a vendor-supplied terminology mapped to SNOMED CT concepts as the standard for EHR interoperability. Accordingly, electronic clinical quality measures (eCQMs) increasingly define clinical phenotypes with SNOMED CT value sets. The work of creating and maintaining list-based value sets proves daunting, as does vetting that their contents accurately represent the clinicallyintended condition. Objective: To compare an intensional (concept hierarchy-based) vs. extensional (list-based) value set approach to defining clinical phenotypes using SNOMED CT encoded data from EHRs, by evaluating value set conciseness, time to create, and completeness. Methods: Starting from published CMS 2018 high-priority eCQMs, we selected ten clinical conditions referenced by those eCQMs. For each, the published SNOMED CT list-based (extensional) value set was downloaded from the Value Set Authority Center (VSAC). Ten corresponding SNOMED CT hierarchy-based intensional value sets for the same conditions were identified within our EHR. From each hierarchybased intensional value set, an exactly equivalent full extensional value set was derived enumerating all included descendant SNOMED CT concepts. Comparisons were then made between (a) (VSAC) downloaded list-based (extensional) value sets, (b) corresponding hierarchy-based intensional value sets for the same conditions, and (c) derived list-based (extensional) value sets exactly equivalent to the hierarchy-based intensional value sets. Value set conciseness was assessed by the number of SNOMED CT concepts needed for definition. Time to construct the value sets for local use was measured. Value set completeness was assessed by comparing contents of the downloaded extensional vs. intensional value sets. Two measures of content completeness were made: for individual SNOMED CT concepts, and for the mapped diagnosis clinical terms available for selection within the EHR by clinicians. Results: The 10 hierarchy-based intensional value sets proved far simpler and faster to construct than exactly equivalent derived extensional value set lists, requiring a median 3 vs. 78 concepts to define, and 5 vs. 37 min to build. The hierarchy-based intensional value sets also proved more complete: in comparison, the 10 downloaded 2018 extensional value sets contained a median of just 35% of the intensional value sets' SNOMED CT concepts and 65% of mapped EHR clinical terms. Conclusions: In the EHR era, defining conditions preferentially should employ SNOMED CT concept hierarchy-based (intensional) value sets, rather than 1 extensional lists. By doing so, clinical guideline and eCQM authors can more readily engage specialists in vetting condition subtypes to include and exclude, and streamline broad EHR implementation of condition-specific ...

show abstract

“…We evaluated the ability of openEHR for providing computable representations of EHR phenotyping algorithms using the desiderata defined by Mo and colleagues [7]. In their work, the authors reviewed a series of EHR phenotyping algorithms which were developed as part of the Electronic Medical Records and Genomics (eMERGE) consortium [8], a national consortium of U.S. medical research institutions that combine DNA repositories with hospital EHR data in approximately 55,000 patients.…”

Section: Desiderata For Computable Representationsmentioning

confidence: 99%

Evaluating OpenEHR for Storing Computable Representations of Electronic Health Record Phenotyping Algorithms

Papež

Denaxas

Hemingway

2017

2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS)

View full text Add to dashboard Cite

Abstract-Electronic Health Records (EHR) are data generated during routine clinical care. EHR offer researchers unprecedented phenotypic breadth and depth and have the potential to accelerate the pace of precision medicine at scale. A main EHR use-case is creating phenotyping algorithms to define disease status, onset and severity. Currently, no common machine-readable standard exists for defining phenotyping algorithms which often are stored in human-readable formats. As a result, the translation of algorithms to implementation code is challenging and sharing across the scientific community is problematic. In this paper, we evaluate openEHR, a formal EHR data specification, for computable representations of EHR phenotyping algorithms.

show abstract

Desiderata for computable representations of electronic health records-driven phenotype algorithms

Cited by 104 publications

References 93 publications

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

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

SNOMED CT Concept Hierarchies for Computable Clinical Phenotypes From Electronic Health Record Data: Comparison of Intensional Versus Extensional Value Sets (Preprint)

Evaluating OpenEHR for Storing Computable Representations of Electronic Health Record Phenotyping Algorithms

Contact Info

Product

Resources

About