Abstract
Medical diagnosis has always been a crucial and sophisticated matter, and despite its remarkable progresses, a reliable, cost-efficient, and fast computer-based medical diagnosis is still a challenge. There are two main types of computerized medical diagnosis systems: knowledge-based and non-knowledge-based systems. While the challenge of scalability and maintainability are the main shortcomings of the first group, the fact that the non-knowledge-based systems cannot explain the reasons for their conclusions makes them less appealing too. Moreover, even the most advanced systems fail to help the user in providing the right input. This work discusses the feasibility of the use of Holonic Multi-Agent Systems (HMASs) to tackle this problem, by performing differential diagnosis (DDx), that can improve diagnostic accuracy, and moreover guide the user in providing a more comprehensive input. The Holonic Medical Diagnosis System (HMDS), as a Multi-Agent System (MAS), offers the necessary reliability and scalability. By using Machine Learning (ML) techniques, it can also be self-adaptable to new findings. Furthermore, since it aims to perform DDx and tends to present the most likely diagnoses, the reasoning behind its output is also always implicitly recognizable. While the HMAS approach to DDx is the practical contribution of this work, the introduction of the ML techniques that support its functionality and dynamics is its theoretical contribution. Swarm Q-learning, as an off-policy reinforcement learning, is shown to be a perfect solution to this problem, and the Holonic-Q-learning technique is proposed, which can in general also be applied to any HMAS.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Definition proposed by Robert Hayward of the Centre for Health Evidence.
- 2.
- 3.
A mapping \( T:X \to X \) is a contraction on a metric space \( (X,d) \), if there exists a constant \( c \), with \( 0 \le c < 1 \), such that \( d\left( {T\left( x \right),T\left( y \right)} \right) \le c. d(x,y) \) for all \( x,y \in X \) [58].
References
Berner, E.: Clinical Decision Support Systems. Springer, New York (2016)
Berner, S.E.: Clinical Decision Support Systems: State of the Art. AHRQ Publication No. 09-0069-EF. Agency for Healthcare Research and Quality (2009)
Alther, M., Reddy, C.: Clinical Decision Support Systems, Chap. 19. In: Healthcare Data Analytics, pp. 625–656. Chapman and Hall/CRC (2015)
Miner, L., Bolding, P., Hilbe, J., Goldstein, M., Hill, T., Nisbet, R., Walton, N., Miner, G.: Practical Predictive Analytics and Decisioning Systems for Medicine: Informatics Accuracy and Cost-Effectiveness for Healthcare Administration and Delivery Including Medical Research. Academic Press, Cambridge (2014)
Merriam-Webster: Differential Diagnosis. https://www.merriam-webster.com/dictionary/differential%20diagnosis. Accessed 15 June 2017
Maude, J.: Differential diagnosis: the key to reducing diagnosis error, measuring diagnosis and a mechanism to reduce healthcare costs. Diagnosis 1(1), 107–109 (2014)
Segen, J.: Concise Dictionary of Modern Medicine. McGraw-Hill, New York (2006)
IBM WATSON. http://ibmwatson237.weebly.com/. Accessed 15 June 2017
Fisher, H., Tomlinson, A., Ramnarayan, P., Britto, J.: ISABEL: support with clinical decision making. Pediatr. Nurs. 15(7), 34–35 (2003)
Ramnarayan, P., Kulkarni, G., T., Britto, J.: ISABEL: a novel Internet-delivered clinical decision support system. In: Current perspectives in healthcare computing, pp. 245–256 (2004)
Autonomy Corporation plc: Autonomy Technology Overview (Autonomy Whitepaper). https://db.bme.hu/~gajdos/2012adatb2/4.%20eloadas%20MBC-Autonomy%20doc.pdf. Accessed 15 June 2017
Riches, N., Panagioti, M., Alam, R., Cheraghi-Sohi, S., Campbell, S., Esmail, A., Bower, P.: The effectiveness of electronic differential diagnoses (DDX) generators: a systematic review and meta-analysis. PLoS ONE 11(3), e0148991 (2016)
Yuan, M.: Watson and healthcare: how natural language processing and semantic search could revolutionize clinical decision support. https://www.ibm.com/developerworks/library/os-ind-watson/. Accessed 15 June 2017
Graber, M.L., Mathew, A.: Performance of a web-based clinical diagnosis support system for internists. J. Gen. Intern. Med. 23(1), 37–40 (2008)
Salem, H., Attiya, G., El-Fishawy, N.: A survey of multi-agent based intelligent decision support system for medical classification problems. Int. J. Comput. Appl. 123(10), 20–25 (2015)
Klüver, C., Klüver, J., Unland, R.: A medical diagnosis system based on MAS technology and neural networks. In: BPSC. LNI, vol. 147, pp. 179–191 (2009)
Iantovics, B.: Agent-based medical diagnosis systems. Comput. Inf. 27, 593–625 (2008)
Chao, S., Wong, F.: A multi-agent learning paradigm for medical data mining diagnostic workbench. In: Cao, L. (ed.) Data Mining and Multi-agent Integration, pp. 177–186. Springer, Boston, MA (2009). doi:10.1007/978-1-4419-0522-2_12
Arsene, O., Dumitrache, I., Mihu, I.: Expert system for medicine diagnosis using software agents. Exp. Syst. Appl. 42(4), 1825–1834 (2015)
Hilarie, V., Koukam, A., Rodrigue, S.: An adaptive agent architecture for holonic multiagent system. ACM TAAS 3(1), 1–24 (2008)
Abdoos, M., Mozayani, N., Bazzan, A.: Towards reinforcement learning for holonic multi-agent systems. Intell. Data Anal. 19(2), 211–232 (2015)
Shoham, Y.: Agent-oriented programming. Technical report STAN-CS-90-1335. Stanford University (1990)
Wooldridge, M.: Chapter 2: Intelligent agents. In: An Introduction to MultiAgent Systems. Wiley (2009)
Gerber, C., Siekmann, J., Vierke, G.: Holonic multi-agent systems. Technical report DFKI-RR-99-03. German Research Centre for Artificial Intelligence (1999)
Lavendelis, E., Grundspenkis, J.: Open holonic multi-agent architecture for intelligent tutoring system development. In: Proceedings of IADIS International Conference on Intelligent Systems and Agents (2008)
Koestler, A.: The Ghost in the Machine. Hutchinson, Paris (1967)
Rodriguez, S.: From analysis to design of holonic multi-agent systems: a framework, methodological guidelines and applications, Ph.D. thesis. University of Technology of Belfort-Montbéliard (2005)
Unland, R.: A holonic multi-agent system for robust, flexible, and reliable medical diagnosis. In: Meersman, R., Tari, Z. (eds.) OTM 2003. LNCS, vol. 2889, pp. 1017–1030. Springer, Heidelberg (2003). doi:10.1007/978-3-540-39962-9_97
Unland, R., Ulieru, M.: Swarm intelligence and the holonic paradigm: a promising symbiosis for a medical diagnostic system. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS, vol. 3682, pp. 154–160. Springer, Heidelberg (2005). doi:10.1007/11552451_21
Ulieru, M., Unland, R.: A stigmergic approach to medical diagnosis. In: Proceedings of the 2nd International Workshop on Multi-Agent Systems for Medicine and Computational Biology, pp. 87–103 (2006)
Shehory, O., Sycara, K., Chalasani, P., Jha, S.: Agent cloning: an approach to agnt mobility and resource allocation. IEEE Commun. Mag. 36(7), 58–67 (1998)
Ye, D.: Self-organisation in multi-agent systems: theory and applications. Ph.D. thesis. University of Wollongong (2013)
Schwaiger, A., Stahmer, B.: Probabilistic holons for efficient agent-based data mining and simulation. In: Mařík, V., Brennan, R.W., Pěchouček, M. (eds.) HoloMAS 2005. LNCS, vol. 3593, pp. 50–63. Springer, Heidelberg (2005). doi:10.1007/11537847_5
Corkill, D.: Blackboard systems. AI Exp. 6(9), 40–47 (1991)
Corkill, D.: Collaborating software: blackboard and multi-agent systems and the future. In: Proceedings of the International Lisp Conference (2003)
Black, K.: Business Statistics: For Contemporary Decision Making, 7th edn. Wiley, Hoboken (2011)
Bellman, R.: A Markovian Decision Process. J. Math. Mech. 6(5), 679–684 (1957)
Puterman, M.: Markov Decision Processes: Diecrete Stochastic Dynamic. Wiley, New York (1994)
van Hasselt, H.: Insights in Reonforcment Learning. Wöhrmann Print Service, Zutphen (2011)
Vrancx, P.: Decentralised reinforcement learning in markov games. Ph.D. thesis, Vrije Universiteit Brussel (2010)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Barto, A., Sutton, R., Anderson, C.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. SMC-13, 834–846 (1983)
Sutton, R.: Learning to predict by the methods of temporal differences. Mach. Learn. 3, 9–44 (1988)
Watkins, C.: Learning from delayed rewards. Ph.D. thesis. Cambridge University (1989)
Schwartz, A.: A reinforcement learning method for maximizing undiscounted rewards. In: Proceedings of the 10th International Conference on Machine Learning, pp. 298–305 (1993)
Rummery, G.A., Niranjan, M.: On-Line Q-Learning Using Connectionist Systems. Cambridge University Engineering Department, Cambridge (1994)
Wiering, M., van Hasselt, H.: Two novel on-policy reinforcement learning algortihms based on TD(λ)-methods. In: Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007 (2007)
Hoffman, M., Jasra, A.: Trans-dimensional MCMC for Bayesian policy learning. Neural Inf. Process. Syst. 20, 1–8 (2008)
Buşoniu, L., Babuška, R., Schutter, B.: Multi-agent reinforcement learning: an overview. In: Srinivasan, D., Jain, L.C. (eds.) Innovations in Multi-Agent Systems and Applications - 1. Studies in Computational Intelligence, vol. 310, pp. 183–221. Springer, Berlin, Heidelberg (2010)
Gambardella, L., Dorigo, M.: Ant-Q: a reinforcement learning approach to the traveling salesman problem. In: Proceedings of ML-95, 12th International Conference on Machine Learning, pp. 252–260 (1995)
Monekosso, N., Remagnino, P.: Phe-Q: a pheromone based Q-learning. In: Stumptner, M., Corbett, D., Brooks, M. (eds.) AI 2001. LNCS, vol. 2256, pp. 345–355. Springer, Heidelberg (2001). doi:10.1007/3-540-45656-2_30
Iima, H., Kuroe, Y., Matsuda, S.: Swarm reinforcement learning method based on ant colony optimization. In: 2010 IEEE International Conference on Systems Man and Cybernetics (SMC), pp. 1726–1733 (2010)
Melo, F.: Convergence of Q-learning: a simple proof. institute of systems and robotics. Technical Report, pp. 1–4 (2001)
Jaakkola, T., Jordan, M., Singh, S.: On the convergence of stochastic iterative dynamic programming algorithms. Massachusetts Institute of Technology, Artificial Intelligence Laboratory, A.I. Memo No. 1441 (1993)
Jaakkola, T., Jordan, M., Singh, S.: On the convergence of stochastic iterative dynamic programming algorithms. Neural Comput. 6(6), 1185–1201 (1994)
Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In Simoudis, E., Han, J., Fayyad, U. (eds.) Proceedings of the 2nd International Conference on Knowledge Discoverey and Data Mining (KDD-96), pp. 226–231 (1996)
Akbari, Z., Unland, R.: Automated determination of the input parameter of DBSCAN based on outlier detection. In: Iliadis, L., Maglogiannis, I. (eds.) AIAI 2016. IAICT, vol. 475, pp. 280–291. Springer, Cham (2016). doi:10.1007/978-3-319-44944-9_24
Hunter, J., Nachtergaele, B.: Applied Analysis. World Scientific Publishing, Singapore (2001)
Acknowledgement
The authors gratefully acknowledge the informative and encouraging discussions with Dr. Farzad Fakouri, MD on the medical aspects of the project, and would like to express appreciation and gratitude for his knowledgeable insight and expertise, that greatly assisted the research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Akbari, Z., Unland, R. (2017). A Holonic Multi-Agent System Approach to Differential Diagnosis. In: Berndt, J., Petta, P., Unland, R. (eds) Multiagent System Technologies. MATES 2017. Lecture Notes in Computer Science(), vol 10413. Springer, Cham. https://doi.org/10.1007/978-3-319-64798-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-64798-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64797-5
Online ISBN: 978-3-319-64798-2
eBook Packages: Computer ScienceComputer Science (R0)