**6. The surgery decision based on the NS algorithm**

We wish now to follow the steps of the surgery NS algorithm to study its action in practical decision cases concerning the operation decision.

Let us thus go through the following example.

#### Step 1. *Initialization*

As the input data we introduce the set *V* = {*v*1, *v*2, *v*3, *v*4}, which consists of four patient data vectors characteristic of the "operate" type. The length of each vector is decided to be three in conformity with previously made suggestions. In Section 4 we have already initialized

*v*1 = (3, 2, 2), *v*2 = (2, 0, 2), *v*3 = (3, 1, 3), *v*4 = (3, 1, 2).

542 New Advances in the Basic and Clinical Gastroenterology

samples are eliminated whereas unmatched ones are kept. We adopt the *r*-contiguous bit matching rule for the patient data vectors as a measure of "the distance" between the

In the second step of NS the stored detectors, generated in the first stage, are used to check whether new incoming samples of patient data vectors correspond to the "operate" type or to the "do not operate" type. If an input sample, characterizing a patient, matches any detector then the patient should not be operated. When we cannot find a match between detectors and the incoming patient data vector it will mean that the decision about the surgery should be made. Figure 4 collects all steps of the surgery NS algorithm in the flow

"operate" type and the "do not operate" decision.

Fig. 4. The flow chart of the surgery NS algorithm

decision cases concerning the operation decision. Let us thus go through the following example.

Step 1. *Initialization*

*v*1 = (3, 2, 2), *v*2 = (2, 0, 2),

**6. The surgery decision based on the NS algorithm** 

We wish now to follow the steps of the surgery NS algorithm to study its action in practical

As the input data we introduce the set *V* = {*v*1, *v*2, *v*3, *v*4}, which consists of four patient data vectors characteristic of the "operate" type. The length of each vector is decided to be three in conformity with previously made suggestions. In Section 4 we have already initialized

chart.

The vectors emerge the clinical data concerning elderly patients whose the *CRP*- values are not very high. The patients' weights are not radically deviated from normal standards either. Hence, they have been operated in conformity with the surgeon's determination.

We now wish to generate the set *D* of four detectors *d*1, *d*2, *d*3, *d*4 that should not match any of *vj*, *j* =1,…,4. At the beginning of the procedure *D* is an empty set.

To measure the match grade between *vj* and candidates to be detectors we state, e.g., *r* = 2 in the *r*-contiguous bit matching rule.

Step 2. *Introduction of random candidates to act as detectors* 

We present *d* = (3, 1, 1) and check matches between *d* and each *vj*, *j* = 1,…,4, as

match((3, 2, 2), (3, 1, 1)) is false, match((2, 0, 2), (3, 1, 1)) is false, match((3, 1, 3), (3, 1, 1)) is true, match((3, 1, 2), (3, 1, 1)) is true.

Since *d* matches *v*3 and *v*4 then it cannot be classified as a detector.

We prove the next candidate *d* = (4, 3, 1) to make matches between *d* and each *vj*, *j* = 1,…,4, in the form of

match((3, 2, 2), (4, 3, 1)) is false, match((2, 0, 2), (4, 3, 1)) is false, match((3, 1, 3), (4, 3, 1)) is false, match((3, 1, 2), (4, 3, 1)) is false.

All matches are false, which means that *d*1 = *d* is the first detector placed in *D*. The set of detectors now contains one element *d*1 = (4, 3, 1). We repeat the procedure until we determine four detectors in set *D*. *D* is finally formed as

*D* = {(4, 3, 1), (2, 3, 4), (4, 4, 1), (3, 4, 0)}.

Step 3. *Operation decision making*

In the second phase of the algorithm we test data strings to organize them in either the "operate" type or in the "do not operate" type decisions. If the data vector matches any detector from *D* then the decision is made as "do not operate" (the non-self region). Otherwise, for all false matches between the data vector and *dk*, *k* = 1,…,4, we accept the operation (the self region).

We introduce *v* = (3, 2, 3). The matches to detectors are determined as

match((4, 3, 1), (3, 2, 3)) is false, match((2, 3, 4), (3, 2, 3)) is false, match((4, 4, 1), (3, 2, 3)) is false, match((3, 4, 0), (3, 2, 3)) is false.

As all matches to detectors are false we conclude the performance of surgery (decision "operate").

Selected Algorithms of Computational Intelligence in Gastric Cancer Decision Making 545

We emphasize that the proposal is a novel contribution in medical applications and should be still tested on larger samples of data. We can expect that, in future investigations, an introduction of the neural artificial perceptron model instead of the NS algorithm will provide us with similar results concerning surgery decisions. As an extension of the model we also wish to adapt the real-value negative selection algorithm in order to insert measured values of biological markers in data vectors instead of codes. This procedure should improve the reliability of a decision. Having results from more models we can select

The author thanks the Blekinge Research Board in Sweden for the grant funding the current research. The author is also grateful to Associate Professor Henrik Forssell for supporting

Antunes, M. & Correia, M.E. (2011). Tunable Immune Detectors for Behavior-Based

De Castro, L.N. & Timmis, J. (2002). *Artificial Immune Systems,* Springer, ISBN 978-1-85233-

Cohen, I.R. (2006). Immune System Computation and the Immunological Homunculus,

Dasgupta, D. & Nino, F. (2008). *Immunological Computation: Theory and Applications*,

Do-Kyong Kim, Sung Yong Oh, Hyuk-Chan Kwon, Suee Lee, Kyung A Kwon, Byung Geun

Engelbrecht, A.P. (2007). *Computational Intelligence*, Wiley & Sons Ltd., ISBN 978-0-470-

Forrest, S., Hofmeyr, A.S. & Somayaji, A. (1997). Computer Immunology, *Communications of* 

Gao, X.Z., Ovaska, S.I., Wang, X. & Chow, M.Y. (2008). A Neural Networks-based Negative

Harmer, P.K., Williams, P.D., Gunsch, G.H. & Lamont, G.B. (2002). An Artificial Immune

Igawa, K. & Ohashi, H. (2009). A Negative Selection Algorithm for Classification and

Ishida, Y. (2004). *Immunity-Based Systems: A Design Perspective,* Springer, ISBN 3-540-00896-9,

*Evolutionary Computation,* vol. 6, nr 3, pp. 252–280, ISSN 1089-778X

Selection Algorithm in Fault Diagnosis, *Neural Computing & Applications,* vol. 17, nr

System Architecture for Computer Security Applications, *IEEE Transactions on* 

Reduction of the Noise Effect, *Journal of Applied Soft Computing*, vol. 9, nr 1, pp. 431–

Kim, Seong-Geun Kim, Sung-Hyun Kim, Jin Seok Jang, Min Chan Kim, Kyeong Hee Kim, Jin-Yeong Han & Hyo-Jin Kim (2009). Clinical Significances of Preoperative Serum Interleukin-6 and C-reactive Protein Level in Operable Gastric

LNCS, vol. 4199, pp. 49–52, ISBN 978-3-540-45772-5

Cancer, *BMC Cancer* 9, pp. 155–156, ISSN 1471-2407

*the ACM,* vol. 40, nr 10, pp. 88–96, ISSN 1017-4656

Auerbach Publishers Inc., ISBN 978-1-420-06545-9, London

Network Intrusion Detection, *Artificial Immune Systems: 10th International Conference, ICARIS 2011*, Cambridge, UK, pp. 334–347, LNCS, vol. 6825, Springer,

the most efficient one to work on its further development.

these investigations with medical advice and data.

ISBN 978-3-642-22370-9

594-6, Berlin Heidelberg

03561-0, Chichester

438, ISSN 1568-4946

1, pp. 91–98, ISSN 1433-3058

Berlin Heidelberg New York

**8. Acknowledgment** 

**9. References** 

Another test vector *v* = (3, 4, 1) is inserted into the checking system. The match results are shown as

match((4, 3, 1), (3, 4, 1)) is false, match((2, 3, 4), (3, 4, 1)) is false, match((4, 4, 1), (3, 4, 1)) is true, match((3, 4, 0), (3, 4, 1)) is true.

Vector *v* converges to two detectors, which means the decision to be referred to "do not operate".

By setting *r* = 2 in the contiguous bit matching rule we have preserved a margin of imprecision in decision making, since we do not demand all contiguous vector codes to be equal. This gives a certain chance of operating for the patients whose mix of biological indices cannot be precisely judged. For *r* = 3 the decision will be quite strict.

The method of making medical decisions by means of immunological systems is an applicable novelty. The example has a more didactic and experimental meaning than a real medical investigation. If we really want to use the method for making decisions in the surgery discipline we should, at first, extend the length of data strings by introducing more biological markers. A very dense set of initial vectors from "self" ("operate") ought to be chosen by the algorithm belonging to Section 4. Nevertheless, the proposal of combining fuzzy systems and weighted characteristics of vectors with the NS algorithm to create the hybrid can start a new applied domain in medicine.
