Performance evaluation of a prescription medication image classification model: an observational cohort
Abstract Technology assistance of pharmacist verification tasks through the use of machine intelligence has the potential to detect dangerous and costly pharmacy dispensing errors. National Drug Codes (NDC) are unique numeric identifiers of prescription drug products for the United States Food and D...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2021-07-01
|
Series: | npj Digital Medicine |
Online Access: | https://doi.org/10.1038/s41746-021-00483-8 |
_version_ | 1797428113305501696 |
---|---|
author | Corey A. Lester Jiazhao Li Yuting Ding Brigid Rowell Jessie ‘Xi’ Yang Raed Al Kontar |
author_facet | Corey A. Lester Jiazhao Li Yuting Ding Brigid Rowell Jessie ‘Xi’ Yang Raed Al Kontar |
author_sort | Corey A. Lester |
collection | DOAJ |
description | Abstract Technology assistance of pharmacist verification tasks through the use of machine intelligence has the potential to detect dangerous and costly pharmacy dispensing errors. National Drug Codes (NDC) are unique numeric identifiers of prescription drug products for the United States Food and Drug Administration. The physical form of the medication, often tablets and capsules, captures the unique features of the NDC product to help ensure patients receive the same medication product inside their prescription bottle as is found on the label from a pharmacy. We report and evaluate using an automated check to predict the shape, color, and NDC for images showing a pile of pills inside a prescription bottle. In a test set containing 65,274 images of 345 NDC classes, overall macro-average precision was 98.5%. Patterns of incorrect NDC predictions based on similar colors, shapes, and imprints of pills were identified and recommendations to improve the model are provided. |
first_indexed | 2024-03-09T08:54:28Z |
format | Article |
id | doaj.art-b13be2ddb1b343bc98c265391a61b6bd |
institution | Directory Open Access Journal |
issn | 2398-6352 |
language | English |
last_indexed | 2024-03-09T08:54:28Z |
publishDate | 2021-07-01 |
publisher | Nature Portfolio |
record_format | Article |
series | npj Digital Medicine |
spelling | doaj.art-b13be2ddb1b343bc98c265391a61b6bd2023-12-02T13:37:28ZengNature Portfolionpj Digital Medicine2398-63522021-07-01411810.1038/s41746-021-00483-8Performance evaluation of a prescription medication image classification model: an observational cohortCorey A. Lester0Jiazhao Li1Yuting Ding2Brigid Rowell3Jessie ‘Xi’ Yang4Raed Al Kontar5Department of Clinical Pharmacy, College of Pharmacy, University of MichiganSchool of Information, University of MichiganDepartment of Clinical Pharmacy, College of Pharmacy, University of MichiganDepartment of Clinical Pharmacy, College of Pharmacy, University of MichiganDepartment of Industrial and Operations Engineering, College of Engineering, University of MichiganDepartment of Industrial and Operations Engineering, College of Engineering, University of MichiganAbstract Technology assistance of pharmacist verification tasks through the use of machine intelligence has the potential to detect dangerous and costly pharmacy dispensing errors. National Drug Codes (NDC) are unique numeric identifiers of prescription drug products for the United States Food and Drug Administration. The physical form of the medication, often tablets and capsules, captures the unique features of the NDC product to help ensure patients receive the same medication product inside their prescription bottle as is found on the label from a pharmacy. We report and evaluate using an automated check to predict the shape, color, and NDC for images showing a pile of pills inside a prescription bottle. In a test set containing 65,274 images of 345 NDC classes, overall macro-average precision was 98.5%. Patterns of incorrect NDC predictions based on similar colors, shapes, and imprints of pills were identified and recommendations to improve the model are provided.https://doi.org/10.1038/s41746-021-00483-8 |
spellingShingle | Corey A. Lester Jiazhao Li Yuting Ding Brigid Rowell Jessie ‘Xi’ Yang Raed Al Kontar Performance evaluation of a prescription medication image classification model: an observational cohort npj Digital Medicine |
title | Performance evaluation of a prescription medication image classification model: an observational cohort |
title_full | Performance evaluation of a prescription medication image classification model: an observational cohort |
title_fullStr | Performance evaluation of a prescription medication image classification model: an observational cohort |
title_full_unstemmed | Performance evaluation of a prescription medication image classification model: an observational cohort |
title_short | Performance evaluation of a prescription medication image classification model: an observational cohort |
title_sort | performance evaluation of a prescription medication image classification model an observational cohort |
url | https://doi.org/10.1038/s41746-021-00483-8 |
work_keys_str_mv | AT coreyalester performanceevaluationofaprescriptionmedicationimageclassificationmodelanobservationalcohort AT jiazhaoli performanceevaluationofaprescriptionmedicationimageclassificationmodelanobservationalcohort AT yutingding performanceevaluationofaprescriptionmedicationimageclassificationmodelanobservationalcohort AT brigidrowell performanceevaluationofaprescriptionmedicationimageclassificationmodelanobservationalcohort AT jessiexiyang performanceevaluationofaprescriptionmedicationimageclassificationmodelanobservationalcohort AT raedalkontar performanceevaluationofaprescriptionmedicationimageclassificationmodelanobservationalcohort |