Reinforcement Learning Model for Mass Casualty Triage Taking into Account the Medical Capability

doi:10.15683/kosdi.2023.3.31.044

All Issue

2023 Vol.19, Issue 1 Preview Page Next Page

Original Article

Reinforcement Learning Model for Mass Casualty Triage Taking into Account the Medical Capability 의료능력을 고려한 대량전상자 환자분류 강화학습 모델: 박병호¹ㆍ조남석²*
Byeongho Park¹, Namsuk Cho²*; ¹Graduate student, Department of Defense Science, Korea National Defense University, Nonsan, Republic of Korea
²Professor, Department of Defense Science, Korea National Defense University, Nonsan, Republic of Korea

31 March 2023. pp. 44-59

PDF

Abstract

Purpose: In the event of mass casualties, triage must be done promptly and accurately so that as many patients as possible can be recovered and returned to the battlefield. However, medical personnel have received many tasks with less manpower, and the battlefield for classifying patients is too complex and uncertain. Therefore, we studied an artificial intelligence model that can assist and replace medical personnel on the battlefield. Method: The triage model is presented using reinforcement learning, a field of artificial intelligence. The learning of the model is conducted to find a policy that allows as many patients as possible to be treated, taking into account the condition of randomly set patients and the medical capability of the military hospital. Result: Whether the reinforcement learning model progressed well was confirmed through statistical graphs such as cumulative reward values. In addition, it was confirmed through the number of survivors whether the triage of the learned model was accurate. As a result of comparing the performance with the rule-based model, the reinforcement learning model was able to rescue 10% more patients than the rule-based model. Conclusion: Through this study, it was found that the triage model using reinforcement learning can be used as an alternative to assisting and replacing triage decision-making of medical personnel in the case of mass casualties.

Keywords

Mass Casualty

Triage

Medical Capability

Artificial Intelligence

Reinforcement Learning

연구목적: 대량전상자 발생 시 신속하고 정확한 환자분류가 진행되어야 최대한 많은 환자를 회복시켜 전장으로 돌려보낼 수 있다. 그러나 복잡한 전투현장에서 적은 의료인력으로 대량전상자의 환자분류를 시행하기란 임무는 과다하고 환경은 불확실하다. 따라서, 전투현장에서 의료인력을 보조하고 대체할 수 있는 인공지능 모델에 대해 논의하고자 한다. 연구방법: 인공지능의 한 분야인 강화학습을 활용하여 환자분류 모델을 제시한다. 모델의 학습은 무작위로 설정된 환자의 상태와 병원시설의 의료능력을 고려하여 최대 다수의 환자가 치료받을 수 있는 정책을 찾도록 진행된다. 연구결과: 강화학습 모델이 정상적으로 학습되었음은 누적 보상 값 등을 통하여 확인하였고, 학습된 모델이 정확하게 환자를 분류하는 것은 생존자 수를 통해 확인하였다. 또한, 규칙 기반 모델과 비교하여 성능을 검증하였으며, 강화학습 모델이 규칙 기반 모델에 비해 약 10%만큼 더 많은 환자를 생존시킬 수 있었다. 결론: 강화학습을 이용한 환자분류 모델은 의료인력의 대량전상자 환자분류 의사결정을 보조하고 대체하는 대안으로 활용 가능하다.

키워드

대량전상자

환자분류

의료능력

인공지능

강화학습

References

Abe, D., Inaji, M., Hase, T., Takahashi, S., Sakai, R., Ayabe, F., Tanaka, Y., Otomo, Y., Maehara, T. (2022). "A prehospital triage system to detect traumatic intracranial hemorrhage using machine learning algorithms." JAMA Network Open, Vol.5, No.6, e2216393. 10.1001/jamanetworkopen.2022.16393 35687335 PMC9187955
Ahn, C.-W, Lim, T.-H. (2015). "Emergency medical services in disasters." Hanyang Medical Reviews, Vol. 35, No. 3, pp. 136-140. 10.7599/hmr.2015.35.3.136
Altevogt, B.M, Gostin, L.O., Hanfling, D., Hanson, S.L., Stroud, C. (2009). Guidance for Establishing Crisis Standards of Care for Use in Disaster Situations. National Academies Press a Letter Report. US.
Boltin, N.D., Culley, J.M., Valafar, H. (2022). "Application of dimensional reduction in artificial neural networks to improve emergency department triage during chemical mass casualty incidents." arXiv preprint arXiv, 2204.00642
Janousek, J.T., Jackson, D.E., De Lorenzo, R.A., Coppola, M. (1999). "Mass casualty triage knowledge of military medical personnel." Military Medicine, Vol. 164, No. 5, pp. 332-335. 10.1093/milmed/164.5.332
Jenkins, J.L., McCarthy, M.L., Sauer, L.M., Green, G.B., Stuart, S., Thomas, T.L., Hsu, E.B. (2008). "Mass-casualty triage: Time for an evidence-based approach." Prehospital and Disaster Medicine, Vol. 23, No. 1, pp. 3-8. 10.1017/S1049023X00005471 18491654
Kang, D.Y., Cho, K.J., Kwon, O., Kwon, J.M., Jeon, K.H., Park, H. (2020). "Artificial intelligence algorithm to predict the need for critical care in prehospital emergency medical services." Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine, Vol. 28, No. 1, pp. 1-8. 10.1186/s13049-020-0713-4 32131867 PMC7057604
Kim, D., You, S., So, S., Lee, J., Yook, S., Jang, D.P., Park, H.K. (2018). "A data-driven artificial intelligence model for remote triage in the prehospital environment." PLoS One, Vol. 13, No. 10, e0206006. 10.1371/journal.pone.0206006 30352077 PMC6198975
Lee, K.-J. (2018). Golden Hour 1. Heuleum Publishing Inc, South Korea.
Lim, G.-S, Hwang, S.-O. (2017). Rescue and Emergency Care. 8^th ed, KoonJA Publishing Inc. South Korea.
Raita, Y., Goto, T., Faridi, M.K., Brown, D.F., Camargo, C.A., Hasegawa, K. (2019). "Emergency department triage prediction of clinical outcomes using machine learning models." Critical Care, Vol. 23, No. 1, pp. 1-13. 10.1186/s13054-019-2351-7 30795786 PMC6387562
Razzaki, S., Baker, A., Perov, Y., Middleton, K., Baxter, J., Mullarkey, D., Johri, S. (2018). "A comparative study of artificial intelligence and human doctors for the purpose of triage and diagnosis." arXiv preprint arXiv, 1806.10698.
Sacco, W., Navin, M., Fiedler, K. (2005). " Precise formulation and evidence based application of resource constrained triage." Academic Emergency Medicine, Vol. 12, No. 8, pp. 759-770. 10.1197/j.aem.2005.04.003 16079430
Sacco, W.J., Navin, D.M., Waddell, R.K., Fiedler, K.E., Long, W.B., Buckman Jr, R.F. (2007). "A new resource constrained triage method applied to penetrating-injured victims." Journal of Trauma and Acute Care Surgery, Vol. 63, No. 2, pp. 316-325. 10.1097/TA.0b013e31806bf212 17693830
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O. (2017). "Proximal policy optimization algorithms." arXiv preprint arXiv, 1707.06347.
Soltan, A.A., Kouchaki, S., Zhu, T., Kiyasseh, D., Taylor, T., Hussain, Z.B., Peto, T., Brent, A.J., Eyre, D.W., Clifton, D.A. (2021). "Rapid triage for COVID-19 using routine clinical data for patients attending hospital: Development and prospective validation of an artificial intelligence screening test." The Lancet Digital Health, Vol. 3, No. 2, pp. 78-87. 10.1016/S2589-7500(20)30274-0 33509388
Super, G., Groth, S., Cleary, V. (1983). START: A Training Triage Module. Hoag Presbyterian Memorial Hospital, Newport Beach, CA.
Sutton, R.S., Barto, A.G. (2018). Reinforcement Learning: An Introduction, Second Edition, J-Pub, US.
Townsend, C.M. (2021), Sabiston Textbook of Surgery. 21^th ed. US.
Yoo, M.-R. (2015). Disaster Nursing Practice. Sumunsa. South Korea.

Information

Publisher :The Korean Society of Disaster Information
Publisher(Ko) :한국재난정보학회
Journal Title :Journal of the Society of Disaster Information
Journal Title(Ko) :한국재난정보학회논문집
Volume : 19
No :1
Pages :44-59
DOI :https://doi.org/10.15683/kosdi.2023.3.31.044

[1] Abe, D., Inaji, M., Hase, T., Takahashi, S., Sakai, R., Ayabe, F., Tanaka, Y., Otomo, Y., Maehara, T. (2022). "A prehospital triage system to detect traumatic intracranial hemorrhage using machine learning algorithms." JAMA Network Open, Vol.5, No.6, e2216393. 10.1001/jamanetworkopen.2022.16393 35687335 PMC9187955

[2] Ahn, C.-W, Lim, T.-H. (2015). "Emergency medical services in disasters." Hanyang Medical Reviews, Vol. 35, No. 3, pp. 136-140. 10.7599/hmr.2015.35.3.136

[3] Altevogt, B.M, Gostin, L.O., Hanfling, D., Hanson, S.L., Stroud, C. (2009). Guidance for Establishing Crisis Standards of Care for Use in Disaster Situations. National Academies Press a Letter Report. US.

[4] Boltin, N.D., Culley, J.M., Valafar, H. (2022). "Application of dimensional reduction in artificial neural networks to improve emergency department triage during chemical mass casualty incidents." arXiv preprint arXiv, 2204.00642

[5] Janousek, J.T., Jackson, D.E., De Lorenzo, R.A., Coppola, M. (1999). "Mass casualty triage knowledge of military medical personnel." Military Medicine, Vol. 164, No. 5, pp. 332-335. 10.1093/milmed/164.5.332

[6] Jenkins, J.L., McCarthy, M.L., Sauer, L.M., Green, G.B., Stuart, S., Thomas, T.L., Hsu, E.B. (2008). "Mass-casualty triage: Time for an evidence-based approach." Prehospital and Disaster Medicine, Vol. 23, No. 1, pp. 3-8. 10.1017/S1049023X00005471 18491654

[7] Kang, D.Y., Cho, K.J., Kwon, O., Kwon, J.M., Jeon, K.H., Park, H. (2020). "Artificial intelligence algorithm to predict the need for critical care in prehospital emergency medical services." Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine, Vol. 28, No. 1, pp. 1-8. 10.1186/s13049-020-0713-4 32131867 PMC7057604

[8] Kim, D., You, S., So, S., Lee, J., Yook, S., Jang, D.P., Park, H.K. (2018). "A data-driven artificial intelligence model for remote triage in the prehospital environment." PLoS One, Vol. 13, No. 10, e0206006. 10.1371/journal.pone.0206006 30352077 PMC6198975

[9] Lee, K.-J. (2018). Golden Hour 1. Heuleum Publishing Inc, South Korea.

[10] Lim, G.-S, Hwang, S.-O. (2017). Rescue and Emergency Care. 8^th ed, KoonJA Publishing Inc. South Korea.

[11] Raita, Y., Goto, T., Faridi, M.K., Brown, D.F., Camargo, C.A., Hasegawa, K. (2019). "Emergency department triage prediction of clinical outcomes using machine learning models." Critical Care, Vol. 23, No. 1, pp. 1-13. 10.1186/s13054-019-2351-7 30795786 PMC6387562

[12] Razzaki, S., Baker, A., Perov, Y., Middleton, K., Baxter, J., Mullarkey, D., Johri, S. (2018). "A comparative study of artificial intelligence and human doctors for the purpose of triage and diagnosis." arXiv preprint arXiv, 1806.10698.

[13] Sacco, W., Navin, M., Fiedler, K. (2005). " Precise formulation and evidence based application of resource constrained triage." Academic Emergency Medicine, Vol. 12, No. 8, pp. 759-770. 10.1197/j.aem.2005.04.003 16079430

[14] Sacco, W.J., Navin, D.M., Waddell, R.K., Fiedler, K.E., Long, W.B., Buckman Jr, R.F. (2007). "A new resource constrained triage method applied to penetrating-injured victims." Journal of Trauma and Acute Care Surgery, Vol. 63, No. 2, pp. 316-325. 10.1097/TA.0b013e31806bf212 17693830

[15] Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O. (2017). "Proximal policy optimization algorithms." arXiv preprint arXiv, 1707.06347.

[16] Soltan, A.A., Kouchaki, S., Zhu, T., Kiyasseh, D., Taylor, T., Hussain, Z.B., Peto, T., Brent, A.J., Eyre, D.W., Clifton, D.A. (2021). "Rapid triage for COVID-19 using routine clinical data for patients attending hospital: Development and prospective validation of an artificial intelligence screening test." The Lancet Digital Health, Vol. 3, No. 2, pp. 78-87. 10.1016/S2589-7500(20)30274-0 33509388

[17] Super, G., Groth, S., Cleary, V. (1983). START: A Training Triage Module. Hoag Presbyterian Memorial Hospital, Newport Beach, CA.

[18] Sutton, R.S., Barto, A.G. (2018). Reinforcement Learning: An Introduction, Second Edition, J-Pub, US.

[19] Townsend, C.M. (2021), Sabiston Textbook of Surgery. 21^th ed. US.

[20] Yoo, M.-R. (2015). Disaster Nursing Practice. Sumunsa. South Korea.

Journal of the Society of Disaster Information ISSN:1976-2208(Print) 2671-5287(Online) 한국재난정보학회논문집

All Issue