Image-based identification and DEA-based optimization modeling of antibiotic packaging using unsupervised learning techniques
PLOS One · 27.07.2026 · 21 (7) · e0354277
DOI: 10.1371/journal.pone.0354277 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 27.07.2026. Verfasst von Phakdee Sukpornsawan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Pharmaceutical Sciences, Burapha University, Chonburi, Thailand. Hauptthemen laut MEDLINE: Anti-Bacterial Agents, Drug Packaging, Unsupervised Machine Learning, Image Processing, Computer-Assisted. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Council of Thailand.
Abstract (Originalsprache)
Background
Ensuring medication safety requires accurate identification of antibiotic packaging, especially within pharmacy automation and dispensing systems. Advanced imaging and machine learning offer novel avenues for physical package recognition.
Objective
To investigate visual and textual features of antibiotic packages and evaluate their relationship with identification outcomes using unsupervised learning and efficiency-based analysis.
Methods
Thirty-six antibiotic formulations from Thailand (2016–2021) were analyzed using binary imaging, entropy metrics, packaging area ratio (PAR), and optical character recognition (OCR). K-means clustering was applied to segment package groups, and data envelopment analysis (DEA) was used to assess relative efficiency without assuming predefined functional relationships between inputs and outputs.
Results
Nine distinct image clusters were identified. Packages with mid-range entropy (7.1–7.5) and PAR (1.2–1.45) were associated with higher identification consistency. OCR text confidence influenced identification outcomes. DEA identified clusters with relatively efficient input–output configurations.
Conclusion
Integrating image-derived metrics and OCR-based features supports automated antibiotic package identification. This framework provides a structured approach for evaluating packaging characteristics in pharmacy workflows.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Faculty of Pharmaceutical Sciences, Burapha University, Chonburi, Thailand.
- Faculty of Informatics, Burapha University, Chonburi, Thailand.
- Faculty of Engineering, Thammasat University, Pathum Thani, Thailand.
ORCID-Profile: Suthabordee Muongmee
Förderung
- National Research Council of Thailand
Zitieren
APA
Sukpornsawan, P., Meepradist, Y., Auamnoy, T., Suksawatchon, U., Chokchaitam, S., & Muongmee, S. (2026). Image-based identification and DEA-based optimization modeling of antibiotic packaging using unsupervised learning techniques. PLOS One, 21(7), e0354277. https://doi.org/10.1371/journal.pone.0354277
Vancouver
Sukpornsawan P, Meepradist Y, Auamnoy T, Suksawatchon U, Chokchaitam S, Muongmee S. Image-based identification and DEA-based optimization modeling of antibiotic packaging using unsupervised learning techniques. PLOS One. 2026;21(7):e0354277. doi:10.1371/journal.pone.0354277
BibTeX
@article{Sukpornsawan2026,
author = {Sukpornsawan, Phakdee and Meepradist, Yutthapoom and Auamnoy, Titinun and Suksawatchon, Ureerat and Chokchaitam, Somchart and Muongmee, Suthabordee},
title = {Image-based identification and DEA-based optimization modeling of antibiotic packaging using unsupervised learning techniques},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {7},
pages = {e0354277},
doi = {10.1371/journal.pone.0354277}
}
EUVIMED