EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Image-based identification and DEA-based optimization modeling of antibiotic packaging using unsupervised learning techniques

Phakdee Sukpornsawan, Yutthapoom Meepradist, Titinun Auamnoy, Ureerat Suksawatchon, Somchart Chokchaitam, Suthabordee Muongmee iD

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Anti-Bacterial AgentsDrug PackagingUnsupervised Machine LearningImage Processing, Computer-AssistedClustering AlgorithmsCluster AnalysisThailand

Substanzen

Anti-Bacterial Agents

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}
}
Kostenlos starten →