Importance of multi-modal approaches to effectively identify cataract cases from electronic health records

Peissig, Peggy L.; Rasmussen, Luke V.; Berg, Richard L.; Linneman, James G.; McCarty, Catherine A.; Waudby, Carol; Chen, Lin; Denny, Joshua C.; Wilke, Russell A.; Pathak, Jyotishman; Carrell, David; Kho, Abel N.; Starren, Justin

doi:10.1136/amiajnl-2011-000456

Cited by 112 publications

(90 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach has led to the development of several validated algorithms to identify individuals with specific phenotypes (ie, EHR phenotyping algorithms). [22][23][24][25][26] Many of these studies have also demonstrated the ability to share EHR phenotyping algorithms among multiple institutions, 21 22 26 26a although they usually develop and validate an algorithm at one institution before implementation at other sites. In contrast, in this study, two institutions (Columbia University (CU) and Mayo Clinic (Mayo)) developed DILI EHR phenotyping algorithms separately from one another with project goals and disease case definitions informed by different organizations (eMERGE/iSAEC and DILIN, respectively).…”

Section: Introductionmentioning

confidence: 99%

A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury

Overby

Pathak

Gottesman

et al. 2013

J Am Med Inform Assoc

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury

Overby

Pathak

Gottesman

et al. 2013

J Am Med Inform Assoc

Self Cite

View full text Add to dashboard Cite

show abstract

“…Through carefully defining phenotypes, and using deployable algorithms that combine multiple sources of information in the EHR, cases and controls can be defined for association studies, such as defining age-related cataract cases and controls [1,2]. The Marshfield Personalized Medicine Research Project Biobank (Marshfield PMRP) and linked EHR, used for the study described herein, is one such resource [3].…”

Section: Introductionmentioning

confidence: 99%

Next-Generation Analysis of Cataracts: Determining Knowledge Driven Gene-Gene Interactions Using Biofilter, and Gene-Environment Interactions Using the Phenx Toolkit

et al. 2012

Self Cite

View full text Add to dashboard Cite

Investigating the association between biobank derived genomic data and the information of linked electronic health records (EHRs) is an emerging area of research for dissecting the architecture of complex human traits, where cases and controls for study are defined through the use of electronic phenotyping algorithms deployed in large EHR systems. For our study, 2580 cataract cases and 1367 controls were identified within the Marshfield Personalized Medicine Research Project (PMRP) Biobank and linked EHR, which is a member of the NHGRI-funded electronic Medical Records and Genomics (eMERGE) Network. Our goal was to explore potential gene-gene and gene-environment interactions within these data for 529,431 single nucleotide polymorphisms (SNPs) with minor allele frequency > 1%, in order to explore higher level associations with cataract risk beyond investigations of single SNP-phenotype associations. To build our SNP-SNP interaction models we utilized a prior-knowledge driven filtering method called Biofilter to minimize the multiple testing burden of exploring the vast array of interaction models possible from our extensive number of SNPs. Using the Biofilter, we developed 57,376 prior-knowledge directed SNP-SNP models to test for association with cataract status. We selected models that required 6 sources of external domain knowledge. We identified 5 statistically significant models with an interaction term with p-value < 0.05, as well as an overall model with p-value < 0.05 associated with cataract status. We also conducted gene-environment interaction analyses for all GWAS SNPs and a set of environmental factors from the PhenX Toolkit: smoking, UV exposure, and alcohol use; these environmental factors have been previously associated with the formation of cataracts. We found a total of 288 models that exhibit an interaction term with a p-value ≤ 1×10 −4 associated with cataract status. Our results show these approaches enable advanced searches for epistasis and gene-environment interactions beyond GWAS, and that the EHR based approach provides an additional source of data for seeking these advanced explanatory models of the etiology of complex disease/outcome such as cataracts.

show abstract

“…RDW data from 1979 through 2011, including diagnoses, procedures, laboratory results, observations, and medications for patients residing in a 22 ZIP Code area, were de-identified and made available for this study. The phenotypes used in this investigation were selected based on the availability of manually validated (case-control status) cohorts and include: acute myocardial infarction, acute liver failure, atrial fibrillation, cataract, congestive heart failure, dementia, type 2 diabetes, diabetic retinopathy and deep vein thrombosis [24,25,28]. The RDW was used to select training cohorts for each phenotype.…”

Section: Methodsmentioning

confidence: 99%

“…This knowledge coupled with our past phenotyping experience [28] prompted the use of ICD-9 codes as a possible surrogate to identify potential positive (POS) training examples for model building. A sampling frame of patients with at least 15–20 ICD-9 codes spanning multiple days was used to define the surrogate POS cohort.…”

Section: Methodsmentioning

confidence: 99%

Relational machine learning for electronic health record-driven phenotyping

Peissig

Costa

Caldwell

et al. 2014

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Objective Electronic health records (EHR) offer medical and pharmacogenomics research unprecedented opportunities to identify and classify patients at risk. EHRs are collections of highly inter-dependent records that include biological, anatomical, physiological, and behavioral observations. They comprise a patient’s clinical phenome, where each patient has thousands of date-stamped records distributed across many relational tables. Development of EHR computer-based phenotyping algorithms require time and medical insight from clinical experts, who most often can only review a small patient subset representative of the total EHR records, to identify phenotype features. In this research we evaluate whether relational machine learning (ML) using Inductive Logic Programming (ILP) can contribute to addressing these issues as a viable approach for EHR-based phenotyping. Methods Two relational learning ILP approaches and three well-known WEKA (Waikato Environment for Knowledge Analysis) implementations of non-relational approaches (PART, J48, and JRIP) were used to develop models for nine phenotypes. International Classification of Diseases, Ninth Revision (ICD-9) coded EHR data were used to select training cohorts for the development of each phenotypic model. Accuracy, precision, recall, F-Measure, and Area Under the Receiver Operating Characteristic (AUROC) curve statistics were measured for each phenotypic model based on independent manually verified test cohorts. A two-sided binomial distribution test (sign test) compared the five ML approaches across phenotypes for statistical significance. Results We developed an approach to automatically label training examples using ICD-9 diagnosis codes for the ML approaches being evaluated. Nine phenotypic models for each MLapproach were evaluated, resulting in better overall model performance in AUROC using ILP when compared to PART (p=0.039), J48 (p=0.003) and JRIP (p=0.003). Discussion ILP has the potential to improve phenotyping by independently delivering clinically expert interpretable rules for phenotype definitions, or intuitive phenotypes to assist experts. Conclusion Relational learning using ILP offers a viable approach to EHR-driven phenotyping.

show abstract

Importance of multi-modal approaches to effectively identify cataract cases from electronic health records

Abstract: We have demonstrated that algorithms to identify and characterize cataracts can be developed utilizing data collected via the EHR. These algorithms provide a high level of accuracy even when implemented across multiple EHRs and institutional boundaries.

Cited by 112 publications

References 31 publications

A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury

A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury

Next-Generation Analysis of Cataracts: Determining Knowledge Driven Gene-Gene Interactions Using Biofilter, and Gene-Environment Interactions Using the Phenx Toolkit

Relational machine learning for electronic health record-driven phenotyping

Contact Info

Product

Resources

About