EUVIMEDEUVIMED entdecken
Open Access

An Accurate Deep Learning–Based System for Automatic Pill Identification: Model Development and Validation

Junyeong Heo iD, Youjin Kang iD, SangKeun Lee iD, Dong-Hwa Jeong iD, Kang-Min Kim iD

Journal of Medical Internet Research · 2023

DOI: 10.2196/41043 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, 2023. Verfasst von Junyeong Heo und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, Korea University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Artificial Intelligence, Deep Learning. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Medication errors account for a large proportion of all medical errors. In most homes, patients take a variety of medications for a long period. However, medication errors frequently occur because patients often throw away the containers of their medications.

Objective

We proposed a deep learning–based system for reducing medication errors by accurately identifying prescription pills. Given the pill images, our system located the pills in the respective pill databases in South Korea and the United States.

Methods

We organized the system into a pill recognition step and pill retrieval step, and we applied deep learning models to train not only images of the pill but also imprinted characters. In the pill recognition step, there are 3 modules that recognize the 3 features of pills and their imprints separately and correct the recognized imprint to fit the actual data. We adopted image classification and text detection models for the feature and imprint recognition modules, respectively. In the imprint correction module, we introduced a language model for the first time in the pill identification system and proposed a novel coordinate encoding technique for effective correction in the language model. We identified pills using similarity scores of pill characteristics with those in the database.

Results

We collected the open pill database from South Korea and the United States in May 2022. We used a total of 24,404 pill images in our experiments. The experimental results show that the predicted top-1 candidates achieve accuracy levels of 85.6% (South Korea) and 74.5% (United States) for the types of pills not trained on 2 different databases (South Korea and the United States). Furthermore, the predicted top-1 candidate accuracy of our system was 78% with consumer-granted images, which was achieved by training only 1 image per pill. The results demonstrate that our system could identify and retrieve new pills without additional model updates. Finally, we confirmed through an ablation study that the language model that we emphasized significantly improves the pill identification ability of the system.

Conclusions

Our study proposes the possibility of reducing medical errors by showing that the introduction of artificial intelligence can identify numerous pills with high precision in real time. Our study suggests that the proposed system can reduce patients’ misuse of medications and help medical staff focus on higher-level tasks by simplifying time-consuming lower-level tasks such as pill identification.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceDeep LearningHumansDatabases, FactualPrescriptionsRepublic of Korea

Stichwörter der Autor:innen

automatic pill searchcharacter-level language modeldeep learningmachine learningpill identificationpill recognitionpill retrieval

Autor:innen und Institutionen

  • Department of Mathematics, Korea University, Seoul, Republic of Korea.
  • Visual Display Division, Samsung Electronics, Suwon, Republic of Korea.
  • Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea.
  • Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea.
  • Department of Artificial Intelligence, The Catholic University of Korea, Bucheon, Republic of Korea.
  • Department of Data Science, The Catholic University of Korea, Bucheon, Republic of Korea.

ORCID-Profile: Junyeong Heo, Youjin Kang, SangKeun Lee, Dong-Hwa Jeong, Kang-Min Kim

Zitieren

APA

Heo, J., Kang, Y., Lee, S., Jeong, D. H., & Kim, K. M. (2023). An Accurate Deep Learning–Based System for Automatic Pill Identification: Model Development and Validation. Journal of Medical Internet Research. https://doi.org/10.2196/41043

Vancouver

Heo J, Kang Y, Lee S, Jeong DH, Kim KM. An Accurate Deep Learning–Based System for Automatic Pill Identification: Model Development and Validation. Journal of Medical Internet Research. 2023. doi:10.2196/41043

BibTeX
@article{Heo2023,
  author = {Heo, Junyeong and Kang, Youjin and Lee, SangKeun and Jeong, Dong-Hwa and Kim, Kang-Min},
  title = {An Accurate Deep Learning–Based System for Automatic Pill Identification: Model Development and Validation},
  journal = {Journal of Medical Internet Research},
  year = {2023},
  doi = {10.2196/41043}
}
Kostenlos starten →