An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification Bias
Objectives Computable or electronic phenotypes of patient conditions are becoming more commonplace in quality improvement and clinical research. During phenotyping algorithm validation, standard classification performance measures (i.e., sensitivity, specificity, positive predictive value...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Georg Thieme Verlag KG
2024-07-01
|
| Series: | ACI Open |
| Subjects: | |
| Online Access: | http://www.thieme-connect.de/DOI/DOI?10.1055/a-2402-5937 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850037638864568320 |
|---|---|
| author | Ajay Bhasin Sue Bielinski Abel N. Kho Nicholas Larson Laura J. Rasmussen-Torvik |
| author_facet | Ajay Bhasin Sue Bielinski Abel N. Kho Nicholas Larson Laura J. Rasmussen-Torvik |
| author_sort | Ajay Bhasin |
| collection | DOAJ |
| description |
Objectives Computable or electronic phenotypes of patient conditions are becoming more commonplace in quality improvement and clinical research. During phenotyping algorithm validation, standard classification performance measures (i.e., sensitivity, specificity, positive predictive value, negative predictive value, and accuracy) are often employed. When validation is performed on a randomly sampled patient population, direct estimates of these measures are valid. However, studies will commonly sample patients conditional on the algorithm result prior to validation, leading to a form of bias known as verification bias. |
| format | Article |
| id | doaj-art-68be6fd87fad4147b9d46b6725197f9a |
| institution | DOAJ |
| issn | 2566-9346 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | Georg Thieme Verlag KG |
| record_format | Article |
| series | ACI Open |
| spelling | doaj-art-68be6fd87fad4147b9d46b6725197f9a2025-08-20T02:56:47ZengGeorg Thieme Verlag KGACI Open2566-93462024-07-010802e89e9310.1055/a-2402-5937An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification BiasAjay Bhasin0Sue Bielinski1Abel N. Kho2Nicholas Larson3Laura J. Rasmussen-Torvik4Northwestern University Feinberg School of Medicine, Chicago, United StatesNorthwestern University Feinberg School of Medicine, Chicago, United StatesNorthwestern University Feinberg School of Medicine, Chicago, United StatesNorthwestern University Feinberg School of Medicine, Chicago, United StatesNorthwestern University Feinberg School of Medicine, Chicago, United States Objectives Computable or electronic phenotypes of patient conditions are becoming more commonplace in quality improvement and clinical research. During phenotyping algorithm validation, standard classification performance measures (i.e., sensitivity, specificity, positive predictive value, negative predictive value, and accuracy) are often employed. When validation is performed on a randomly sampled patient population, direct estimates of these measures are valid. However, studies will commonly sample patients conditional on the algorithm result prior to validation, leading to a form of bias known as verification bias.http://www.thieme-connect.de/DOI/DOI?10.1055/a-2402-5937data analysisevaluationsystem improvementstatistical methodsdata collection |
| spellingShingle | Ajay Bhasin Sue Bielinski Abel N. Kho Nicholas Larson Laura J. Rasmussen-Torvik An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification Bias ACI Open data analysis evaluation system improvement statistical methods data collection |
| title | An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification Bias |
| title_full | An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification Bias |
| title_fullStr | An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification Bias |
| title_full_unstemmed | An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification Bias |
| title_short | An Online Tool for Correcting Performance Measures of Electronic Phenotyping Algorithms for Verification Bias |
| title_sort | online tool for correcting performance measures of electronic phenotyping algorithms for verification bias |
| topic | data analysis evaluation system improvement statistical methods data collection |
| url | http://www.thieme-connect.de/DOI/DOI?10.1055/a-2402-5937 |
| work_keys_str_mv | AT ajaybhasin anonlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT suebielinski anonlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT abelnkho anonlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT nicholaslarson anonlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT laurajrasmussentorvik anonlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT ajaybhasin onlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT suebielinski onlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT abelnkho onlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT nicholaslarson onlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias AT laurajrasmussentorvik onlinetoolforcorrectingperformancemeasuresofelectronicphenotypingalgorithmsforverificationbias |