Leveraging code-free deep learning for pill recognition in clinical settings: A multicenter, real-world study of performance across multiple platforms.

Journal: Artificial intelligence in medicine
PMID:

Abstract

BACKGROUND: Preventable patient harm, particularly medication errors, represent significant challenges in healthcare settings. Dispensing the wrong medication is often associated with mix-up of lookalike and soundalike drugs in high workload environments. Replacing manual dispensing with automated unit dose and medication dispensing systems to reduce medication errors is not always feasible in clinical facilities experiencing high patient turn-around or frequent dose changes. Artificial intelligence (AI) based pill recognition tools and smartphone applications could potentially aid healthcare workers in identifying pills in situations where more advanced dispensing systems are not implemented.

Authors

  • Amir Reza Ashraf
    Department of Pharmaceutics and Central Clinical Pharmacy, Faculty of Pharmacy, University of Pécs, Pécs, Hungary. Electronic address: ashraf.amir.reza@pte.hu.
  • Anna Somogyi-Végh
    Department of Pharmaceutics and Central Clinical Pharmacy, Faculty of Pharmacy, University of Pécs, Pécs, Hungary.
  • Sára Merczel
    Department of Pharmacy, Somogy County Kaposi Mór Teaching Hospital, Kaposvár, Hungary.
  • Nóra Gyimesi
    Péterfy Hospital and Jenő Manninger Traumatology Center, Budapest, Hungary.
  • András Fittler
    Department of Pharmaceutics and Central Clinical Pharmacy, Faculty of Pharmacy, University of Pécs, Pécs, Hungary.