Automated Verification of Phenotypes using PubMed

Bridges, Ryan; Henderson, Jette; Ho, Joyce C.; Wallace, Byron C.; Ghosh, Joydeep

doi:10.1145/2975167.2985844

Cited by 2 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was observed in PheKnow-Cloud that the lift increases exponentially with the size of the co-occurrence set [1]. This is consistent with equation 2.…”

Section: Methodssupporting

confidence: 84%

“…This subset is identical to the one used in the original evaluation of Pheknow-Cloud (see [1] for more details regarding the construction of the dataset). We limit this subset to articles with MeSH terms, which results in a corpus of articles that comprises 7.85% of the PMC OA subset (94,673/1,206,506).…”

Section: Resultsmentioning

confidence: 99%

“…PIVET is an improvement on a recently introduced prototype tool called PheKnow-Cloud [1]. PheKnow-Cloud, which earned the Distinguished Paper Award at the 2017 AMIA Joint Summits, demonstrated that the medical expertise contained in PubMed articles could be harnessed to build evidence sets for the clinical validity of candidate phenotypes.…”

Section: Introductionmentioning

confidence: 99%

“…Phenotype evaluation via co-occurrence analysis of online articles was first introduced by Bridges et al [1]. Henderson and colleagues improved on the evaluation framework and developed a prototype tool implementing the approach called PheKnow-Cloud, which provided a Web interface for researchers and clinicians to interact with the technology [27].…”

Section: Introductionmentioning

confidence: 99%

“…Each phenotype consists of medical terms, which we refer to as phenotypic items, that are assumed to have been generated by an automatic high-throughput phenotyping process. PheKnow-Cloud builds evidence sets for batches of phenotypes based on co-occurrence analysis of the PubMed corpus (see [1,27] for details).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature

Henderson

et al. 2018

J Med Internet Res

Self Cite

View full text Add to dashboard Cite

BackgroundResearchers are developing methods to automatically extract clinically relevant and useful patient characteristics from raw healthcare datasets. These characteristics, often capturing essential properties of patients with common medical conditions, are called computational phenotypes. Being generated by automated or semiautomated, data-driven methods, such potential phenotypes need to be validated as clinically meaningful (or not) before they are acceptable for use in decision making.ObjectiveThe objective of this study was to present Phenotype Instance Verification and Evaluation Tool (PIVET), a framework that uses co-occurrence analysis on an online corpus of publically available medical journal articles to build clinical relevance evidence sets for user-supplied phenotypes. PIVET adopts a conceptual framework similar to the pioneering prototype tool PheKnow-Cloud that was developed for the phenotype validation task. PIVET completely refactors each part of the PheKnow-Cloud pipeline to deliver vast improvements in speed without sacrificing the quality of the insights PheKnow-Cloud achieved.MethodsPIVET leverages indexing in NoSQL databases to efficiently generate evidence sets. Specifically, PIVET uses a succinct representation of the phenotypes that corresponds to the index on the corpus database and an optimized co-occurrence algorithm inspired by the Aho-Corasick algorithm. We compare PIVET’s phenotype representation with PheKnow-Cloud’s by using PheKnow-Cloud’s experimental setup. In PIVET’s framework, we also introduce a statistical model trained on domain expert–verified phenotypes to automatically classify phenotypes as clinically relevant or not. Additionally, we show how the classification model can be used to examine user-supplied phenotypes in an online, rather than batch, manner.ResultsPIVET maintains the discriminative power of PheKnow-Cloud in terms of identifying clinically relevant phenotypes for the same corpus with which PheKnow-Cloud was originally developed, but PIVET’s analysis is an order of magnitude faster than that of PheKnow-Cloud. Not only is PIVET much faster, it can be scaled to a larger corpus and still retain speed. We evaluated multiple classification models on top of the PIVET framework and found ridge regression to perform best, realizing an average F1 score of 0.91 when predicting clinically relevant phenotypes.ConclusionsOur study shows that PIVET improves on the most notable existing computational tool for phenotype validation in terms of speed and automation and is comparable in terms of accuracy.

show abstract

“…It was observed in PheKnow-Cloud that the lift increases exponentially with the size of the co-occurrence set [1]. This is consistent with equation 2.…”

Section: Methodssupporting

confidence: 84%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature

Henderson

et al. 2018

J Med Internet Res

Self Cite

View full text Add to dashboard Cite

show abstract

Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature (Preprint)

Henderson¹,

Ke²,

Ho³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

BACKGROUND Researchers are developing methods to automatically extract clinically relevant and useful patient characteristics from raw healthcare datasets. These characteristics, often capturing essential properties of patients with common medical conditions, are called computational phenotypes. Being generated by automated or semiautomated, data-driven methods, such potential phenotypes need to be validated as clinically meaningful (or not) before they are acceptable for use in decision making. OBJECTIVE The objective of this study was to present Phenotype Instance Verification and Evaluation Tool (PIVET), a framework that uses co-occurrence analysis on an online corpus of publically available medical journal articles to build clinical relevance evidence sets for user-supplied phenotypes. PIVET adopts a conceptual framework similar to the pioneering prototype tool PheKnow-Cloud that was developed for the phenotype validation task. PIVET completely refactors each part of the PheKnow-Cloud pipeline to deliver vast improvements in speed without sacrificing the quality of the insights PheKnow-Cloud achieved. METHODS PIVET leverages indexing in NoSQL databases to efficiently generate evidence sets. Specifically, PIVET uses a succinct representation of the phenotypes that corresponds to the index on the corpus database and an optimized co-occurrence algorithm inspired by the Aho-Corasick algorithm. We compare PIVET’s phenotype representation with PheKnow-Cloud’s by using PheKnow-Cloud’s experimental setup. In PIVET’s framework, we also introduce a statistical model trained on domain expert–verified phenotypes to automatically classify phenotypes as clinically relevant or not. Additionally, we show how the classification model can be used to examine user-supplied phenotypes in an online, rather than batch, manner. RESULTS PIVET maintains the discriminative power of PheKnow-Cloud in terms of identifying clinically relevant phenotypes for the same corpus with which PheKnow-Cloud was originally developed, but PIVET’s analysis is an order of magnitude faster than that of PheKnow-Cloud. Not only is PIVET much faster, it can be scaled to a larger corpus and still retain speed. We evaluated multiple classification models on top of the PIVET framework and found ridge regression to perform best, realizing an average F1 score of 0.91 when predicting clinically relevant phenotypes. CONCLUSIONS Our study shows that PIVET improves on the most notable existing computational tool for phenotype validation in terms of speed and automation and is comparable in terms of accuracy.

show abstract

Automated Verification of Phenotypes using PubMed

Cited by 2 publications

References 16 publications

Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature

Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature

Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature (Preprint)

Contact Info

Product

Resources

About