Limits...
A knowledge-based, automated method for phenotyping in the EHR using only clinical pathology reports.

Yahi A, Tatonetti NP - AMIA Jt Summits Transl Sci Proc (2015)

Bottom Line: Central to this goal is, EHR-phenotyping, also known as cohort identification, which remains a significant challenge.We present Ontology-driven Reports-based Phenotyping from Unique Signatures (ORPheUS), an automated approach to EHR-phenotyping.To do this we identify unique signatures of abnormal clinical pathology reports that correspond to pre-defined medical terms from biomedical ontologies.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Informatics, Department of Systems Biology, Department of Medicine, Columbia University, New York, NY, USA.

ABSTRACT
The secondary use of electronic health records (EHR) represents unprecedented opportunities for biomedical discovery. Central to this goal is, EHR-phenotyping, also known as cohort identification, which remains a significant challenge. Complex phenotypes often require multivariate and multi-scale analyses, ultimately leading to manually created phenotype definitions. We present Ontology-driven Reports-based Phenotyping from Unique Signatures (ORPheUS), an automated approach to EHR-phenotyping. To do this we identify unique signatures of abnormal clinical pathology reports that correspond to pre-defined medical terms from biomedical ontologies. By using only the clinical pathology, or "lab", reports we are able to mitigate clinical biases enabling researchers to explore other dimensions of the EHR. We used ORPheUS to generate signatures for 858 diseases and validated against reference cohorts for Type 2 Diabetes Mellitus (T2DM) and Atrial Fibrillation (AF). Our results suggest that our approach, using solely clinical pathology reports, is an effective as a primary screening tool for automated clinical phenotyping.

No MeSH data available.


Related in: MedlinePlus

(a) Congenital heart disease and (b) Myocardial infarction signatures in Atrial Fibrillation patients
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4525265&req=5

f2-2090751: (a) Congenital heart disease and (b) Myocardial infarction signatures in Atrial Fibrillation patients

Mentions: We also explored the cohorts of 80,163 patients with Atrial Fibrillation and evaluated the signatures of two of AF’s known comorbidities: myocardial infarction19, and congenital heart disease20. We observed an interesting precision for Congenital Heart Disease (Figure 2.a.) reaching a plateau around 80% from 10 distinct ATs. Myocardial Infarction (Figure 2.b.) presented a better precision, needing only 6 distinct ATs to reach 80%. However, despite a better initial recall, we witnessed a faster drop in sensitivity for the myocardial infarction signature than the congenital heart disease one. Finally, we observed that for 10 distinct ATs the predicted set of patients was so small that the precision fell to zero.


A knowledge-based, automated method for phenotyping in the EHR using only clinical pathology reports.

Yahi A, Tatonetti NP - AMIA Jt Summits Transl Sci Proc (2015)

(a) Congenital heart disease and (b) Myocardial infarction signatures in Atrial Fibrillation patients
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4525265&req=5

f2-2090751: (a) Congenital heart disease and (b) Myocardial infarction signatures in Atrial Fibrillation patients
Mentions: We also explored the cohorts of 80,163 patients with Atrial Fibrillation and evaluated the signatures of two of AF’s known comorbidities: myocardial infarction19, and congenital heart disease20. We observed an interesting precision for Congenital Heart Disease (Figure 2.a.) reaching a plateau around 80% from 10 distinct ATs. Myocardial Infarction (Figure 2.b.) presented a better precision, needing only 6 distinct ATs to reach 80%. However, despite a better initial recall, we witnessed a faster drop in sensitivity for the myocardial infarction signature than the congenital heart disease one. Finally, we observed that for 10 distinct ATs the predicted set of patients was so small that the precision fell to zero.

Bottom Line: Central to this goal is, EHR-phenotyping, also known as cohort identification, which remains a significant challenge.We present Ontology-driven Reports-based Phenotyping from Unique Signatures (ORPheUS), an automated approach to EHR-phenotyping.To do this we identify unique signatures of abnormal clinical pathology reports that correspond to pre-defined medical terms from biomedical ontologies.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Informatics, Department of Systems Biology, Department of Medicine, Columbia University, New York, NY, USA.

ABSTRACT
The secondary use of electronic health records (EHR) represents unprecedented opportunities for biomedical discovery. Central to this goal is, EHR-phenotyping, also known as cohort identification, which remains a significant challenge. Complex phenotypes often require multivariate and multi-scale analyses, ultimately leading to manually created phenotype definitions. We present Ontology-driven Reports-based Phenotyping from Unique Signatures (ORPheUS), an automated approach to EHR-phenotyping. To do this we identify unique signatures of abnormal clinical pathology reports that correspond to pre-defined medical terms from biomedical ontologies. By using only the clinical pathology, or "lab", reports we are able to mitigate clinical biases enabling researchers to explore other dimensions of the EHR. We used ORPheUS to generate signatures for 858 diseases and validated against reference cohorts for Type 2 Diabetes Mellitus (T2DM) and Atrial Fibrillation (AF). Our results suggest that our approach, using solely clinical pathology reports, is an effective as a primary screening tool for automated clinical phenotyping.

No MeSH data available.


Related in: MedlinePlus