Next Generation Hybrid Intelligent Medical Diagnosis Systems
Many medical diagnosis problems (MDPs) are difficult to be solved by physicians. Frequently, the difficult MDPs solving by physicians require the assistance of the medical computing systems, which many times should be intelligent. Many papers presented in the specialized literature prove, that the intelligence of a system (frequently agent-based) can offer advantages in the MDPs solving versus a system that does not have such intelligence. Cooperative hybrid (human-machine) medical diagnosis systems seem to be well suited for the solving of many difficult MDPs. A difficult aspect in the design of such systems consists in the establishment of how to combine in an optimal way the humans and intelligent systems interoperation in order to solve the undertaken problems in the most efficient way. With this purpose, a novel hybrid medical system, called Intelligent Medical Hybrid System (IntHybMediSys) is proposed in this paper, a system which combines efficiently the humans and computing systems advantages in the problem-solving. We give a definition to the Difficult Medical Diagnosis Problem Solving Intelligence. IntHybMediSys is a highly complex hybrid system composed of physicians and intelligent agents that can interoperate intelligently in different points of decision in order to solve efficiently very difficult medical diagnosis problems. IntHybMediSys is able to handle emergent information that rise during the medical problems solving that allows the precise establishment of the most efficient contributor (a physician or an artificial agent) at each contribution during a problem-solving. This kind of problem-solving has as an effect the increase of accuracy of the elaborated diagnostic.
KeywordsIntelligent hybrid medical system Machine intelligence Difficult medical diagnosis problem
Laszlo Barna Iantovics acknowledge the support of the COROFLOW project PN-III-P2-2.1-BG-2016-0343, Contract: 114BG/2016.
- 3.Iantovics, L.B., Chira, C., Dumitrescu, D.: Principles of the Intelligent Agents. Casa Cartii de Stiinta Press, Cluj-Napoca (2007)Google Scholar
- 4.Imam, I.F.: Intelligent Adaptive Agents. Papers from the 1996 AAAI Workshop. Technical Report WS-96-04, AAAI Press, CA (1996)Google Scholar
- 11.Al-Qaysi, I., Unland, R., Weihs, C., Branki, C.: Medical diagnosis decision support HMAS under uncertainty HMDS. Stud. Comput. Intell. 326, 67–94 (2011)Google Scholar
- 14.McCarthy, J.: Programs with common sense, In. Proceedings of the Teddington Conference on the Mechanization of Thought Processes, Her Majesty’s Stationery Oce, London (1959)Google Scholar
- 19.Alotaibi, S.J.: ICT classroom LMSs: examining the various components affecting the acceptance of college students in the use of blackboard systems. Adv. Intell. Syst. Comput. 498, 523–532 (2016)Google Scholar
- 21.Jin, F., Ni, Z., Pei, L., Chen, H., Li, Y., Zhu, X., Ni, L.: A decision support model for group decision making with intuitionistic fuzzy linguistic preferences relations. Neural Comput. Appl., 1–22 (2017). Google Scholar
- 22.Iantovics, L.B.: Intelligent computations for complex problem solving. In: Hluchý, L., Kurdel, P., Sebestyénová, J. (eds.) Proceedings of the 7th International Workshop on Grid Computing for Complex Problems (GCCP 2011), pp. 27–36 (2011)Google Scholar
- 24.Turing, A.M.: Computing machinery and intelligence. Mind, New Series, vol. 59(236), pp. 433–460. Oxford University Press on behalf of the Mind Association (1950)Google Scholar
- 25.Kuppusamy, K.S., Aghila, G.: HuMan: an accessible, polymorphic and personalized CAPTCHA interface with preemption feature tailored for persons with visual impairments. Univ. Access Inform. Soc., 1–24 (2017).Google Scholar