TY - GEN

T1 - Detection of erythropoietin in blood to uncover doping in sports using machine learning

AU - Rahman, Maxx Richard

AU - Bejder, Jacob

AU - Bonne, Thomas Christian

AU - Andersen, Andreas Breenfeldt

AU - Huertas, Jesús Rodríguez

AU - Aikin, Reid

AU - Nordsborg, Nikolai Baastrup

AU - Maass, Wolfgang

N1 - Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - Sports officials around the world are facing challenges due to the unfair nature of doping practices used by unscrupulous athletes to improve their performance. This practice includes blood transfusion, intake of anabolic steroids or even hormone-based drugs like erythropoietin to increase their strength, endurance, and ultimately their performance. While direct detection and identification of erythropoietin in blood samples of athletes have proven an effective means to uncover doping, not all the cases are easily detectable, and some analyses are too costly to be carried out on every sample. This leads to a need to develop an indirect method for detecting erythropoietin in blood samples based on different blood biomarkers. In this paper, we presented a comparison of different machine learning algorithms combined with statistical analysis approaches to identify the presence of erythropoietin drug in blood samples collected at both sea level and moderate altitude. The results presented indicate that ensemble methods like random forest and X Gboost algorithms may provide an effective tool to aid anti-doping organisations in most effectively distributing scarce resources. Implementation of these methods on the samples from elite athletes may both enhance the deterrence effect of anti-doping as well as increases the likelihood of catching doped athletes.

AB - Sports officials around the world are facing challenges due to the unfair nature of doping practices used by unscrupulous athletes to improve their performance. This practice includes blood transfusion, intake of anabolic steroids or even hormone-based drugs like erythropoietin to increase their strength, endurance, and ultimately their performance. While direct detection and identification of erythropoietin in blood samples of athletes have proven an effective means to uncover doping, not all the cases are easily detectable, and some analyses are too costly to be carried out on every sample. This leads to a need to develop an indirect method for detecting erythropoietin in blood samples based on different blood biomarkers. In this paper, we presented a comparison of different machine learning algorithms combined with statistical analysis approaches to identify the presence of erythropoietin drug in blood samples collected at both sea level and moderate altitude. The results presented indicate that ensemble methods like random forest and X Gboost algorithms may provide an effective tool to aid anti-doping organisations in most effectively distributing scarce resources. Implementation of these methods on the samples from elite athletes may both enhance the deterrence effect of anti-doping as well as increases the likelihood of catching doped athletes.

KW - Blood doping

KW - Drug abuse

KW - Erythropoietin

KW - Machine learning

KW - rhEPO

KW - Sports

U2 - 10.1109/ICDH55609.2022.00038

DO - 10.1109/ICDH55609.2022.00038

M3 - Article in proceedings

AN - SCOPUS:85138027304

T3 - IEEE International Conference on Digital Health

SP - 193

EP - 201

BT - Proceedings - 2022 IEEE International Conference on Digital Health, ICDH 2022

A2 - Ahamed, Sheikh Iqbal

A2 - Ardagna, Claudio Augistino

A2 - Bian, Hongyi

A2 - Bochicchio, Mario

A2 - Chang, Carl K.

A2 - Chang, Rong N.

A2 - Damiani, Ernesto

A2 - Liu, Lin

A2 - Pavel, Misha

A2 - Priami, Corrado

A2 - Shahriar, Hossain

A2 - Ward, Robert

A2 - Xhafa, Fatos

A2 - Zhang, Jia

A2 - Zulkernine, Farhana

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Digital Health, ICDH 2022

Y2 - 10 July 2022 through 16 July 2022

ER -