Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201645308> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3201645308 abstract "Abstract Background: Issuing of correct prescriptions is a foundation of patient safety. Medication errors represent one of the most important problems in health care, with ‘look-alike and sound-alike’ (LASA) being the lead error. Existing solutions to prevent LASA still have their limitations. Deep learning techniques have revolutionized identification classifiers in many fields. In search of better image-based solutions for blister package identification problem, this study using a baseline deep learning drug identification (DLDI) aims to understand how identification confusion of look-alike images by human occurs through the cognitive counterpart of deep learning solutions and thereof to suggest further solutions to approach them. Methods: We collected images of 250 types of blister-packaged drug from the Out-Patient Department (OPD) of a medical center for identification. The deep learning framework of You Only Look Once (YOLO) was adopted for implementation of the proposed deep learning. The commonly-used F1 score, defined by precision and recall for large numbers of identification tests, was used as the performance criterion. This study trained and compared the proposed models based on images of either the front-side or back-side of blister-packaged drugs. Results: Our results showed that the total training time for the front-side model and back-side model was 5 hours 34 minutes and 7 hours 42 minutes, respectively. The F1 score of the back-side model (95.99%) was better than that of the front-side model (93.72%). Conclusions: In conclusion, this study constructed a deep learning-based model for blister-packaged drug identification, with an accuracy greater than 90%. This model outperformed identification using conventional computer vision solutions, and could assist pharmacists in identifying drugs while preventing medication errors caused by look-alike blister packages. By integration into existing prescription systems in hospitals, the results of this study indicated that using this model, drugs dispensed could be verified in order to achieve automated prescription and dispensing." @default.
- W3201645308 created "2021-09-27" @default.
- W3201645308 creator A5003381147 @default.
- W3201645308 creator A5009767964 @default.
- W3201645308 creator A5010175511 @default.
- W3201645308 creator A5015424581 @default.
- W3201645308 creator A5051610584 @default.
- W3201645308 date "2020-03-10" @default.
- W3201645308 modified "2023-10-16" @default.
- W3201645308 title "A Drug Identification Model developed using Deep Learning Technologies: Experience of a Medical Center in Taiwan" @default.
- W3201645308 cites W1508648488 @default.
- W3201645308 cites W2031235037 @default.
- W3201645308 cites W2033310064 @default.
- W3201645308 cites W2112796928 @default.
- W3201645308 cites W2131067223 @default.
- W3201645308 cites W2205303542 @default.
- W3201645308 cites W2234315266 @default.
- W3201645308 cites W2329986310 @default.
- W3201645308 cites W2555375657 @default.
- W3201645308 cites W2561981131 @default.
- W3201645308 cites W2580657852 @default.
- W3201645308 cites W2600602195 @default.
- W3201645308 cites W2618530766 @default.
- W3201645308 cites W2756120902 @default.
- W3201645308 cites W2760147458 @default.
- W3201645308 cites W2768138179 @default.
- W3201645308 cites W2769523360 @default.
- W3201645308 cites W2915583118 @default.
- W3201645308 cites W2916833112 @default.
- W3201645308 cites W2923682152 @default.
- W3201645308 cites W2940242941 @default.
- W3201645308 cites W2940542247 @default.
- W3201645308 cites W2942407711 @default.
- W3201645308 cites W4362203250 @default.
- W3201645308 cites W639708223 @default.
- W3201645308 doi "https://doi.org/10.21203/rs.2.16857/v2" @default.
- W3201645308 hasPublicationYear "2020" @default.
- W3201645308 type Work @default.
- W3201645308 sameAs 3201645308 @default.
- W3201645308 citedByCount "0" @default.
- W3201645308 crossrefType "posted-content" @default.
- W3201645308 hasAuthorship W3201645308A5003381147 @default.
- W3201645308 hasAuthorship W3201645308A5009767964 @default.
- W3201645308 hasAuthorship W3201645308A5010175511 @default.
- W3201645308 hasAuthorship W3201645308A5015424581 @default.
- W3201645308 hasAuthorship W3201645308A5051610584 @default.
- W3201645308 hasBestOaLocation W32016453081 @default.
- W3201645308 hasConcept C108583219 @default.
- W3201645308 hasConcept C11171543 @default.
- W3201645308 hasConcept C116834253 @default.
- W3201645308 hasConcept C119857082 @default.
- W3201645308 hasConcept C154945302 @default.
- W3201645308 hasConcept C15744967 @default.
- W3201645308 hasConcept C2781140086 @default.
- W3201645308 hasConcept C41008148 @default.
- W3201645308 hasConcept C59822182 @default.
- W3201645308 hasConcept C71924100 @default.
- W3201645308 hasConcept C86803240 @default.
- W3201645308 hasConceptScore W3201645308C108583219 @default.
- W3201645308 hasConceptScore W3201645308C11171543 @default.
- W3201645308 hasConceptScore W3201645308C116834253 @default.
- W3201645308 hasConceptScore W3201645308C119857082 @default.
- W3201645308 hasConceptScore W3201645308C154945302 @default.
- W3201645308 hasConceptScore W3201645308C15744967 @default.
- W3201645308 hasConceptScore W3201645308C2781140086 @default.
- W3201645308 hasConceptScore W3201645308C41008148 @default.
- W3201645308 hasConceptScore W3201645308C59822182 @default.
- W3201645308 hasConceptScore W3201645308C71924100 @default.
- W3201645308 hasConceptScore W3201645308C86803240 @default.
- W3201645308 hasLocation W32016453081 @default.
- W3201645308 hasLocation W32016453082 @default.
- W3201645308 hasLocation W32016453083 @default.
- W3201645308 hasOpenAccess W3201645308 @default.
- W3201645308 hasPrimaryLocation W32016453081 @default.
- W3201645308 hasRelatedWork W2922457425 @default.
- W3201645308 hasRelatedWork W2991087447 @default.
- W3201645308 hasRelatedWork W3007495838 @default.
- W3201645308 hasRelatedWork W3014300295 @default.
- W3201645308 hasRelatedWork W3079760979 @default.
- W3201645308 hasRelatedWork W3159901390 @default.
- W3201645308 hasRelatedWork W3164822677 @default.
- W3201645308 hasRelatedWork W4223943233 @default.
- W3201645308 hasRelatedWork W4250304930 @default.
- W3201645308 hasRelatedWork W4299487748 @default.
- W3201645308 isParatext "false" @default.
- W3201645308 isRetracted "false" @default.
- W3201645308 magId "3201645308" @default.
- W3201645308 workType "article" @default.