Hostname: page-component-cd9895bd7-hc48f Total loading time: 0 Render date: 2024-12-25T20:38:30.812Z Has data issue: false hasContentIssue false
  • English
  • Français

Applications of Artificial Intelligence and Machine Learning in Disasters and Public Health Emergencies

Published online by Cambridge University Press:  17 June 2021

Sally Lu ,
Gordon A. Christie ,
Thanh T. Nguyen ,
Jeffrey D. Freeman  and
Edbert B. Hsu
Sally Lu
Affiliation:
Office of Critical Event Preparedness and Response (CEPAR), Johns Hopkins University, Baltimore, MD, USA
Gordon A. Christie
Affiliation:
Asymmetric Operations Sector, Johns Hopkins Applied Physics Laboratory, Laurel, MD, USA
Thanh T. Nguyen
Affiliation:
School of Information Technology, Deakin University, Waurn Ponds, VIC, Australia
Jeffrey D. Freeman
Affiliation:
National Health Mission, Johns Hopkins Applied Physics Laboratory, Laurel, MD, USA
Edbert B. Hsu*
Affiliation:
Office of Critical Event Preparedness and Response (CEPAR), Johns Hopkins University, Baltimore, MD, USA
*
Corresponding author: Edbert B. Hsu, Email ehsu1@jhmi.edu.
Get access Rights & Permissions [Opens in a new window]

Abstract

Indexed literature (from 2015 to 2020) on artificial intelligence (AI) technologies and machine learning algorithms (ML) pertaining to disasters and public health emergencies were reviewed. Search strategies were developed and conducted for PubMed and Compendex. Articles that met inclusion criteria were filtered iteratively by title followed by abstract review and full text review. Articles were organized to identify novel approaches and breadth of potential AI applications. A total of 1217 articles were initially retrieved by the search. Upon relevant title review, 1003 articles remained. Following abstract screening, 667 articles remained. Full text review for relevance yielded 202 articles. Articles that met inclusion criteria totaled 56 articles. Those identifying specific roles of AI and ML (17 articles) were grouped by topics highlighting utility of AI and ML in disaster and public health emergency contexts. Development and use of AI and ML have increased dramatically over the past few years. This review discusses and highlights potential contextual applications and limitations of AI and ML in disaster and public health emergency scenarios.

Keywords

machine learningartificial intelligencepublic health emergenciesdisaster preparedness
Type
Systematic Review
Information
Disaster Medicine and Public Health Preparedness , Volume 16 , Issue 4 , August 2022 , pp. 1674 - 1681
Copyright
© Society for Disaster Medicine and Public Health, Inc. 2021

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

World Health Organization. Definitions: emergencies. World Health Organization Website. https://www.who.int/hac/about/definitions/en/. Published August 2008. Accessed June 8, 2019.Google Scholar
United Nations Office for Disaster Risk Reduction (UNDRR). Sendai framework for disaster risk reduction. United Nations Disaster Risk Reduction Website. https://www.unisdr.org/we/coordinate/sendai-framework. Published 2015. Accessed October 6, 2019.Google Scholar
Murphy, KP. Machine Learning: A Probabilistic Perspective. Cambridge, MA: MIT Press; 2012.Google Scholar
Bzdok, D, Altman, N, Krzywinski, M. Points of Significance: Statistics Versus Machine Learning. Nature Methods, Nature Publishing Group 2018: 233.Google Scholar
Liaw, A, Wiener, M. Classification and regression by randomForest. R news. 2002;2(3):18-22.Google Scholar
Goodfellow, I, Bengio, Y, Courville, A, et al. (2016). Deep Learning (Vol. 1, No. 2). Cambridge: MIT Press: 2016.Google Scholar
El Naqa, I, Murphy, MJ. What is machine learning? In: Machine Learning in Radiation Oncology. New York: Springer, Cham; 2015:3-11 CrossRefGoogle Scholar
Hu, J, Niu, H, Carrasco, J, et al. Voronoi-based multi-robot autonomous exploration in unknown environments via deep reinforcement learning. IEEE Trans Veh Technol. 2020;69(12):14413-14423.CrossRefGoogle Scholar
Kégl, B. The return of AdaBoost. MH: multi-class Hamming trees. arXiv preprint. 2013. arXiv:1312.6086.Google Scholar
Piryonesi, SM, El-Diraby, TE. Data analytics in asset management: cost-effective prediction of the pavement condition index. J Infrastruct Syst. 2020;26(1):04019036. doi: 10.1061/(ASCE)IS.1943-555X.0000512 Google Scholar
Rossi, F, Van Beek, P, Walsh, T, eds. In: Handbook of Constraint Programming. Amsterdam: Elsevier; 2006:3-5.CrossRefGoogle Scholar
Erol, K, Hendler, J, Nau, DS. HTN planning: complexity and expressivity. AAAI. 1994;94:1123-1128.Google Scholar
Novák, V, Perfilieva, I, Mockor, J. Mathematical Principles of Fuzzy Logic. Berlin: Springer Science & Business Media; 2012:1-5.Google Scholar
Gubbi, J, Buyya, R, Marusic, S, et al. Internet of Things (IoT): a vision, architectural elements, and future directions. Future Gener Comput Syst. 2013;29(7):1645-1660.CrossRefGoogle Scholar
Bryant, RE. Symbolic Boolean manipulation with ordered binary-decision diagrams. ACM Comput Surv (CSUR). 1992;24(3):293-318.Google Scholar
Fernandez-Luque, L, Imran, M. Humanitarian health computing using artificial intelligence and social media: a narrative literature review. Int J Med Inform. 2018;114:136-142.CrossRefGoogle ScholarPubMed
Lamy, J-B, Séroussi, B, Griffon, N, et al. Toward a formalization of the process to select IMIA Yearbook best papers. Methods Inf Med. 2015;54(02):135-44.Google Scholar
Moher, D, Liberati, A, Tetzlaff, J, et al. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. PLoS Med. 2009;6(7):e1000097. doi: 10.1371/journal.pmed1000097 CrossRefGoogle ScholarPubMed
Zhao, X, Lovreglio, R, Nilsson, D. Modelling and interpreting pre-evacuation decision-making using machine learning. Autom Constr. 2020;113:103140.Google Scholar
Horii, H. Crowd behaviour recognition system for evacuation support by using machine learning. Int J Safety Secur Eng. 2020. doi: 10.18280/ijsse.100211 CrossRefGoogle Scholar
Bagloee, SA, Johansson, KH, Asadi, M. A hybrid machine-learning and optimization method for contraflow design in post-disaster cases and traffic management scenarios. Expert Syst Appl. 2019;124:67-81. doi: 10.1016/j.eswa.2019.01.042 Google Scholar
Forcael, E, Gonzalez, V, Orozco, F, et al. Ant colony optimization model for tsunamis evacuation routes. Comp Aided Civil Infrastr Eng. 2014;29(10):723-737.Google Scholar
Jiang, H. Mobile fire evacuation system for large public buildings based on artificial intelligence and IoT. IEEE Access. 2019;7:64101-9.CrossRefGoogle Scholar
Wang, X, Choi, TM, Liu, H, et al. A novel hybrid ant colony optimization algorithm for emergency transportation problems during post-disaster scenarios. IEEE Trans Syst Man Cybern. 2016;48(4):545-556.CrossRefGoogle Scholar
Tang, P, Shen, GQ. Decision-making model to generate novel emergency response plans for improving coordination during large-scale emergencies. Knowl Based Syst. 2015;90:111-128.CrossRefGoogle Scholar
Lopez, C, Marti, JR, Sarkaria, S. Distributed reinforcement learning in emergency response simulation. IEEE Access. 2018;6:67261-67276.CrossRefGoogle Scholar
Chaudhuri, N, Bose, I. Exploring the role of deep neural networks for post-disaster decision support. Decis Support Syst. 2020;130:113234.CrossRefGoogle Scholar
Kaufhold, MA, Bayer, M, Reuter, C. Rapid relevance classification of social media posts in disasters and emergencies: a system and evaluation featuring active, incremental and online learning. Inf Process Manag. 2020;57(1):102132.CrossRefGoogle Scholar
Pekar, V, Binner, J, Najafi, H, et al. (2020). Early detection of heterogeneous disaster events using social media. J Assoc Inf Sci Technol. 2020;71(1):43-54.CrossRefGoogle Scholar
Gupta, R, Goodman, B, Patel, N, et al. Creating xBD: a dataset for assessing building damage from satellite imagery. Proc IEEE Comput Soc Conf Vis Pattern Recognit. 2019:10-17.Google Scholar
Ream, S. Launching our open data program for disaster response. DigitalGlobe Blog. http://blog.digitalglobe.com/news/launching-our-open-data-program-for-disaster-response/. Published 2017. Accessed January 20, 2020.Google Scholar
Havas, C, Resch, B, Francalanci, C, et al. E2mC: improving emergency management service practice through social media and crowdsourcing analysis in near real time. Sensors (Basel). 2017;17(12):2766.CrossRefGoogle ScholarPubMed
Kim, D, You, S, So, S, et al. A data-driven artificial intelligence model for remote triage in the prehospital environment. PLoS One. 2018;13(10):e0206006.Google ScholarPubMed
Webster, DW. The true effect of mass shootings on Americans. Ann Intern Med. 2017;166(10):749-750.CrossRefGoogle ScholarPubMed
Griffith, T, Ablanedo, J, Dwyer, T. Leveraging a virtual environment to prepare for school shootings. In: Virtual, Augmented and Mixed Reality. Berlin: Springer, Cham; 2017:325-338.CrossRefGoogle Scholar
Gao, I. Using the social network internet of things to mitigate public mass shootings. IEEE 2nd Int Conf Collab Internet Comp. 2016:486-489.Google Scholar
Boltin, N, Vu, D, Janos, B, et al. An AI model for rapid and accurate identification of chemical agents in mass casualty incidents. HIMS 2016. 2016;2016:169-175.Google ScholarPubMed