Development of an AI-Based Model for Identifying Doping Drugs Through Pill Image Analysis

Abstract

The purpose of this study is to develop a model for identifying prohibited doping drugs through AI-based pill image analysis. To achieve this objective, the study utilized the oral medication image dataset provided by AI Hub. The dataset was divided into prohibited and allowed drugs, and a total of 160,056 images of 500 types of oral medications were used. The performance of the prediction model was evaluated using five metrics: Recall, Precision, Sensitivity, Specificity, and Accuracy. A CNN (Convolutional Neural Network) model and the SIFT (Scale-Invariant Feature Transform) algorithm were applied to analyze the external features of the drugs, such as size, color, and shape. The model demonstrated a high accuracy of 96.5% in distinguishing between prohibited and allowed drugs. Moreover, it achieved superior performance in key metrics, including Recall/Sensitivity (95.2%), Precision (98.6%), and Specificity (98.2%).

Keywords

doping drug identification artificial intelligence pill image image analysis anti-doping

Get full access to this article

View all access options for this article.

References

Backhouse

S. H.

McKenna

(2011). Doping in sport: A review of medical practitioners’ knowledge, attitudes and beliefs. International Journal of Drug Policy, 22(3), 198–202. https://doi.org/10.1016/j.drugpo.2011.03.002

Bekbolatova

Mayer

Ong

C. W.

Toma

(2024). Transformative potential of AI in healthcare: Definitions, applications, and navigating the ethical landscape and public perspectives. Healthcare, 12(2), 125. https://doi.org/10.3390/healthcare12020125

Bell

Ten Have

Lauchs

(2016). A case study analysis of a sophisticated sports doping network: Lance Armstrong and the USPS Team. International Journal of Law, Crime and Justice, 46, 57–68. https://doi.org/10.1016/j.ijlcj.2016.03.001

Bhasin

Storer

T. W.

Berman

Callegari

Clevenger

Phillips

Casaburi

Tricker

Shirazi

(1996). The effects of supraphysiologic doses of testosterone on muscle size and strength in normal men. New England Journal of Medicine, 335(1), 1–7. https://doi.org/10.1056/NEJM199607043350101

Burger

Burge

M. J.

(2022). Digital image processing: An algorithmic introduction. Springer Nature. https://doi.org/10.1007/978-3-031-05744-1

Cadwallader

A. B.

De La Torre

Tieri

Botrè

(2010). The abuse of diuretics as performance‐enhancing drugs and masking agents in sport doping: Pharmacology, toxicology and analysis. British Journal of Pharmacology, 161(1), 1–16. https://doi.org/10.1111/j.1476-5381.2010.00789.x

Chen

R. C.

Pao

C. T.

Chen

Y. H.

Jian

J. C.

(2010). Automatic drug image identification system based on multiple image features. In Computational collective intelligence. Technologies and applications: Second international conference, ICCCI 2010, Kaohsiung, Taiwan, November 10-12, 2010, Proceedings, Part II 2 (pp. 249–257). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-16732-4_27

Cho

(2015). Sport celebrity in South Korea: Park, Tae-Hwan from new generation to fallen angel. Asia Pacific Journal of Sport and Social Science, 4(3), 223–236. https://doi.org/10.1080/21640599.2015.1127943

Demant

Streicher-Abel

Garnica

Demant

Garnica

Streicher-Abel

(2013). Overview: Image preprocessing. In Industrial Image Processing (pp. 25–63). Berlin, Heidelberg: Springer. https://doi.org/10.1007/978-3-642-33905-9_2

10.

Garcia

E. A.

(2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284. https://doi.org/10.1109/TKDE.2008.239

11.

Heo

Kang

Lee

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, 25, Article e41043. https://doi.org/10.2196/41043

12.

Kim

Park

J. H.

Lee

J. Y.

(2024). AI-based betting anomaly detection system to ensure fairness in sports and prevent illegal gambling. Scientific Reports, 14(1), 6470. https://doi.org/10.1038/s41598-024-57195-8

13.

Kim

(2020). Network analysis on the issues of steroid usage exposure through YouTube. Journal of Sport and Leisure Studies, 81, 193–204. https://doi.org/10.51979/KSSLS.2020.07.81.193

14.

Kim

M. J.

(2007). Rechtliche Aspekte des Dopings im Sport. The Journal of Sports and Entertainment Law, 10(4), 53–104. https://doi.org/10.19051/kasel.2007.10.4.53

15.

Lee

S. Y.

Park

J. H.

Yoon

Lee

J. Y.

(2023). A validation study of a deep learning-based doping drug text recognition system to ensure safe drug use among athletes. Healthcare, 11(12), 1769. https://doi.org/10.3390/healthcare11121769

16.

Lippi

Franchini

Guidi

G. C.

(2008). Doping in competition or doping in sport? British Medical Bulletin, 86(1), 95–107. https://doi.org/10.1093/bmb/ldn014

17.

Metushi

I. G.

Wagner

Ahrens

Ericsson

Rabin

Sobolevsky

Tygart

T. T.

(2024). Breaking boundaries: Exploring performance enhancement and anti-doping testing in sports. Clinical Chemistry, 70(7), 897–904. https://doi.org/10.1093/clinchem/hvae074

18.

Park

J. H.

Yoon

S. H.

Yoon

Lee

S. Y.

Lee

J. Y.

(2022). Developement of doping drug recognition system: Application of deep learning-based OCR technology. The Korean Journal of Physical Education, 61(6), 83–92. https://doi.org/10.23949/kjpe.2022.11.61.6.7

19.

Pavot

(2022). A gap or lacuna in the world anti-doping code? Remarks on the CAS interpretation in IOC, WADA, and ISU v. RUSADA, Kamila Valieva and Russian olympic committee (CAS OG 22-08, CAS OG 22-09, and CAS OG 22-10). Frontiers in Sports and Active Living, 4, 946608. https://doi.org/10.3389/fspor.2022.946608

20.

Yang

Wei

Chen

Huang

Kang

Yao

Wang

Amin

M. B.

(2023). Survey on explainable AI: From approaches, limitations and applications aspects. Human-Centric Intelligent Systems, 3(3), 161–188. https://doi.org/10.1007/s44230-023-00038-y