**1. Introduction**

528 New Advances in the Basic and Clinical Gastroenterology

Nitsche CJ, Jamieson N, Lerch MM, Mayerle JV. Drug induced pancreatitis. Best Practice &

Onder, G., Petrovic, M., Tangíísuram, B., Meinardi, M.C., Markito-Notenboom W.P.,

Ouwerkerk J, Boers-Doets COuwerkerk J, Boers-Doets C. Best practices in the management

Pirmohamed M, James S, Meakin S, Green C, Scott AK, Walley TJ, Farrar K, Park BK &

Ramachandran, R. & Kakar, S. Histological patterns in drug-induced liver disease. J. Clin.

Ramirez E, Carcas AJ, Borobia AM, Lei SH, Piñana, E, Fudio S & Frias J A

Russo MW, Galanko jA, Shrestha R, Fried MW & Watkins P. Liver transplantation for acute

Sánchez Muñoz-Torrero JF, Barquilla P, Velasco R, Fernández Capitán MC, Pacheco N,

Sgro, C. et al. Incidence of drug-induced hepatic injuries: a French populationbased study.

Tai-Yin Wu, Min-Hua Jen, Alex Bottle, Mariam Molokhia, Paul Aylin, Derek Bell, Azeem

Wester K, Jönsson A, Spigset O, Druid H, Hägg S. Incidence of fatal adverse drug reactions: a population based study. Br J Clin Pharmacology 2008 / 65:4 / 573–579 White, R.A., Xu, H., Denny, J.C., Roden , D.M., Krauss, R.M., McCarty, C.A., Davis, R.L.,

Wikman-Jorgensen, López-Calleja E, Safont-Gasó P, Matarranz-del-Amo M, Andrés

pharmacogenomics. Clin. Pharmmacol. Ther. 89, 379-386 (2011)

in two German university hospitals. Drug Saf. 2008;31(9):789-98.

Patients 65 years or older. Arch. Intern. Med. 170(13): 1142-1148 (2010). Ostapowicz, G. et al. Results of a prospective study of acute liver failure at 17 tertiary care

centers in the United States. Ann. Intern. Med. 137, 947–954 (2002).

prospective analysis of 18 820 patients. BMJ. 329,15-9 (2004).

risk factors. Eur J Clin Pharmacol (2010) 66:1257–1264

Somers, S., Rajkumar, C., Bernabei, R., van der Cammen T.J.M. Development and Validation of a Score to Assess Risk of Adverse Drug Reactions Among In-Hospital

of toxicities related to anti-EGFR agents for metastatic colorectal cancer. Eur J Oncol

Breckenridge AM. Adverse drug reactions as a cause of admission to hospital:

Pharmacovigilance Program From Laboratory Signals for the Detection and Reporting of Serious Adverse Drug Reactions in Hospitalizad Patients. Clin

liver failure from drug induced liver injury in the United States. Liver Transpl. 10,

Vicente L, & all. Adverse drug reactions in internal medicine units and associated

Majeed. Ten-year trends in hospital admissions for adverse drug reactions in England 1999–2009 J R Soc Med 2010: 103: 239–250. DOI 10.1258/jrsm.2010.100113 Watkins, P.B., Seligman, P.j., Pears, j.S., Avigan, M.I. & Senior, j.R. Using controlled clinical trials to learn more about acute drug-induced liver injury. Hepatology 48, 1680–1689 (2008). Wawruch M, Macugova A, Kostkova L, Luha J, Dukat A, Murin J, Drobna V, Wilton L,

Kuzelova M The use of medications with anticholinergic properties and risk factors for their use in hospitalised elderly patients. Pharmacoepidemiol Drug Saf. 2011

Skaar, T., Lamba, J., Savoga, G. The emerging role of electronic medical records in

Navarro R & Merino-Sánchez J. Antiagregation and anticoagulation, relationship with upper gastrointestinal bleeding. Rev Esp Enferm Dig 2011; 103: 360-365. Zopf Y, Rabe C, Neubert A, Hahn EG, Dormann H. Risk factors associated with adverse

drug reactions following hospital admission: a prospective analysis of 907 patients

Research Clinical Gastroenterology 24 (2010) 143–155 O'Grady, j.G. Acute liver failure. Postgrad. Med. J. 81, 148–154 (2005).

Nurs. 2010 Sep;14(4):337-49

Pathol. 62, 481–492 (2009).

Pharmacol Ther. 87 (1): 74-86.

Hepatology 36, 451–455 (2002).

Jun 13. doi: 10.1002/pds.2169.

1018–1023 (2004).

Due to the latest research (Engelbrecht, 2007; Rutkowski, 2008) the subject of Computational Intelligence has been divided into five main regions, namely, neural networks, evolutionary algorithms, swarm intelligence, immunological systems and fuzzy systems.

Our attention has been attracted by the possibilities of medical applications provided by immunological computation algorithms. Immunological computation systems are based on immune reactions of the living organisms in order to defend the bodies from pathological substances. Especially, the mechanisms of the T-cell reactions to detect strangers have been converted into artificial numerical algorithms.

Immunological systems have been developed in scientific books and reports appearing during the two last decades (de Castro & Timmis, 2002; Dasgupta & Nino, 2008; Engelbrecht, 2007; Forrest et al., 1997). The basic negative selection algorithm NS was invented by Stefanie Forrest (Forrest et al., 1997) to give rise to some technical applications. We can note such applications of NS as computer virus detection (Antunes & Correia, 2011; Harmer et al., 2002; Zhang & Zhao, 2010), reduction of noise effect (Igawa & Ohashi, 2010), communication of autonomous agents (Ishida, 2004) or identification of time varying systems (Wakizono et al., 2006). Even a trial of connection between a computer and biological systems has been proved by means of immunological computation (Cohen, 2006).

Hybrids made between different fields can provide researchers with richer results; therefore associations between immunological systems and neural networks (Gao et al., 2008) have been developed as well.

In the current chapter we propose another hybrid between the NS algorithm and chosen solutions coming from fuzzy systems (Rakus-Andersson, 2007, 2009, 2010a, 2010b, 2011; Rakus-Andersson & Jain, 2009). This hybrid constitutes the own model of adapting the NS algorithm to the operation decisions "operate" contra "do not operate" in gastric cancer surgery. The choice between two possibilities to treat patients is identified with the partition of a decision region in self and non-self, which is similar to the action of the NS algorithm. The partition is accomplished on the basis of patient data strings/vectors that contain codes of states concerning some essential biological markers. To be able to identify the strings that characterize the "operate" decision we add the own method of computing the patients' characteristics as real values. The evaluation of the patients' characteristics is supported by

Selected Algorithms of Computational Intelligence in Gastric Cancer Decision Making 531

divide reference sets of *X*, *Y* and *Z* into subintervals assisting growth levels of these biological indices. To the subintervals, in turn, the codes are added. We will arrange a code

When implementing the NS algorithm we assume that vectors characteristic of self region are available as input data. We do not intend to test too many casual vectors to decide their similarity with self vectors since we want to use the NS algorithm in the effective way. We thus try to generate the strongest population of strings being representatives of the self region. In order to select this population we provide another own algorithm that converts the code vector to a real value. This value will be recognized as "characteristics of the patient".

Before studying the technique of making the self/non-self discrimination to state if the patient can be operated or not we should first be able to compare different strings *v* = (*x* = *age*, *y = CRP*, *z = body weight*), *xX*, *yY*, *zZ*, to decide their grades of affinity (coverage).

The markers *age*, *CRP*, and *body weight* are measurable features. Hence, we intend to determine the collections of codes assisting intervals, which correspond to the markers' levels. We want to accomplish a process of fuzzification of the measurable markers in order not to decide lengths of the level intervals intuitively (Rakus-Andersson, 2009, 2010a, 2010b,

A fuzzy set, say, *A* in the universe *X* is a collection of elements followed by the membership

is assigned to the membership degree equal to 1. The support of *A* is a non-fuzzy set that

The three quantitative markers *X*, *Y* and *Z* will be then differentiated into levels expressed by lists of terms. The terms from the lists are represented by fuzzy sets (Rakus-Andesson, 2007, 2010b), restricted by the membership functions lying over the domains *x x* min max , ,

In conformity with the physician's suggestions we introduce five levels of *X* , *Y* and *Z* as

*X* = "*age*" = { *X*1 = "*very young*", *X*2 = "*young*", *X*3 = "*middle-aged*", *X*4 = "*old*", *X*5 = "*very old"*}

*Y* = "*CRP-value*" = {*Y*1 = "*very low"*, *Y*2 = "*low*", *Y*3 = "*medium*", *Y*4 = "*high*", *Y*5 = "*very high*"}

*Z* = "*body weight*" = { *Z*1 = "*very underweighted*", *Z*2 = "*underweighted*", *Z*3 = "*normal*", *Z*4 = "*over weighted*", *Z*5 = "*very over weighted*"}.

*<sup>A</sup>* . *A* is called normal if at least one element in the set *A*

*<sup>A</sup> X* . Therefore

degrees that are computed by means of the membership function : [0,1]

consists of elements accompanied by membership degrees greater than 0.

vector assisting the patient's features after examining his/her values of *X*, *Y* and *Z*.

**3. Fuzzification of** *X***,** *Y* **and** *Z* **in the creation of code vectors** 

We thus should design sets of codes for each biological parameter.

Rakus-Andersson & Jain, 2009).

*A* is denoted as {( , ( )), } *A x xxX*

*y y* min max , and *z z* min max , respectively.

the collections

and

inserting importance weights assigned to powerful biological indices taking place in the operation decision process. To compute the weights of importance the Saaty algorithm (Saaty, 1978) is adopted.

We introduce the medical task to solve in Section 2. In order to establish the code systems for clinical data the fuzzification of biological markers is discussed in Section 3. In Section 4 we analyze the way of determining the patient characteristics, which should connect the mix of different codes in one value. The adaptation of the NS algorithm to surgery assumptions is made in Section 5. Finally, in Section 6 we test clinical data to prove the action of the model introduced in the paper as an applicable novelty.
