Constantinos Koutsojannis

Cefuroxime-induced coronary artery spasm manifesting as Kounis syndrome.

Allergic angina and allergic myocardial infarction (Kounis syndrome) occurring during the course of a drug-induced allergic reaction in the absence of angiographically stenosed coronary arteries, is rare in clinical practice.This paper reports the case of a 70-year-old woman with no significant risk factors for coronary artery disease who developed coronary artery spasm after intravenous injection of cefuroxime.A subsequent coronary angiogram revealed normal coronary arteries (type I variant of the syndrome). The allergic reaction following cefuroxime administration seems to have triggered the development of coronary artery spasm. Susceptible individuals expressing an amplified mast cell degranulation effect may be more vulnerable to coronary artery spasm. The clinical implications of this syndrome are also discussed.

Penicillin allergy in cancer patients manifesting as Kounis syndrome.

Two cases of allergic angina and allergic myocardial infarction (Kounis syndrome) following penicillin administration are described. The patients suffered from lung and mandible neoplasms and had previously received several courses of antineoplastic therapy without any sequelae. One patient had normal coronary arteries (type I variant of the syndrome) and the other had coronary artery disease with previous myocardial infarction (type II variant of the syndrome). The allergic reaction following penicillin administration seemed to have triggered the development of an acute coronary artery spasm in the first patient and an acute myocardial infarction in the second. This report shows that susceptible individuals expressing a magnified mast cell degranulation effect may be more vulnerable to coronary artery spasm and plaque erosion or rupture.

Using a hybrid AI approach for exercise difficulty level adaptation

An intelligent and adaptive web-based education system is presented. The system uses a hybrid AI approach, a combination of an expert systems approach and a genetic algorithm approach, to determine the difficulty levels of the provided exercises. The genetic algorithm is used to extract some kind of rules from the data acquired from the interactions of the students. Those rules are used to modify expert rules provided by the Tutor. In this way, feedback from the students is taken into account for determination of the difficulty levels of the questions/exercises. Experimental results show the validity of the method.

Nickel allergy, Kounis syndrome and intracardiac metal devices

Metal-induced allergic reactions are not rare in every day practice but nickel, cobalt and chromium are the most common offenders. Other metal anions and metal alloys represent also emerging causes for hypersensitivity reaction in humans. The metal struts of endovascular and intracardiac devices are usually alloys containing nickel and constitute causes for allergic reactions with possible intracardiac and intracoronary mast cell activation resulting in the Kounis hypersensitivity coronary syndrome. Newer intracoronary stents avoid nickel thus making them less allergenic. It is advisable that, before any device implantation, careful history of any metal allergy should be taken and efforts should be made for the development of new devices with better biocompatibility.

Knowledge-Based Adaptive Assessment in a Web-Based Intelligent Educational System

In this paper, we present an adaptive and intelligent Web-based educational system that uses AI techniques for personalized assessment of the learners. More specifically, we focus on a mechanism for on-line creation of a user-adapted test, which can be used alongside the predetermined test. The user can ask for such a test any time he/she is willing to do so, even if he/she has not studied all predetermined concepts of a learning goal. A small rule base is used by an expert system inference engine for making decisions on the difficulty level of the exercises to be included in the test. This is based on the evaluation of the learner during concept studying. Adaptive assessment of the learner can be repeatedly used until there is no further need. Another small rule-base is used for deciding on whether a new test is suggested or not. This is based on the learners previous test assessment results. Preliminary experimental results show that the users need less time to study a learning goal when using the adaptive assessment capability of the system

Fuzzy-evolutionary synergism in an intelligent medical diagnosis system

In this paper, we present the design, implementation and evaluation of HIGAS, a hybrid intelligent system that deals with diagnosis and treatment consultation of acid-base disturbances based on blood gas analysis data. The system mainly consists of a fuzzy expert system that incorporates an evolutionary algorithm in an off-line mode. The diagnosis process, the input variables and their values were modeled based on expert’s knowledge and existing literature. The fuzzy rules are organized in groups to be able to simulate the diagnosis process. Differential evolution algorithm is used to fine-tune the membership functions of the fuzzy variables. Medium scale experimental results show that HIGAS does better than its non-hybrid version, non-experts and other previous computer-based approaches.

Combining expert systems and adaptive hypermedia technologies in a Web based educational system

In this paper, we present a Web-based intelligent education system to help students in the context of an AI course. We concentrate on the adaptivity and student evaluation aspects of the system. Adaptivity refers to the capability of the system to adapt teaching to student needs, specified by the student model characteristics. Student evaluation refers to the evaluation of the knowledge level of a student, which is one of the most important characteristics, with regards to taught concepts. Adaptive hypermedia techniques, like graphical link annotation, and an intelligent technique, i.e. a rule-based expert system, are used to achieve the above goals. An evaluation of the system showed encouraging results as far as its usability and learning are concerned.

A Web-based education system for predicate logic

In this paper, we present a Web-based system teaching predicate logic as a knowledge representation and reasoning language. The system is adaptable in the sense that it allows the students to choose their own way of using it. Students can evaluate themselves, by selecting the complexity and the difficulty level of the exercises. Another interesting point of the system is its open exercising facility, by which the students can try any conversion of a FOPC formula to clause form. This is achieved by calling LISP code, which is part of an automated theorem prover. Incorporation of LISP code into the hypermedia application was an interesting implementation problem. An initial evaluation of the system showed encouraging results as far as its usability and learning are concerned.

Lepirudin Anaphylaxis and Kounis Syndrome

To the Editor: In an ongoing lepirudin pharmacosurveillance program, Greinacher et al1 reported that 4 patients experienced fatal anaphylaxis after reexposure to lepirudin and died shortly after the onset of the event. Three patients died from acute cardiorespiratory arrest and 1 from acute myocardial infarction. These cases are characteristic examples of drug-induced Kounis syndrome2—the concurrence of allergic or hypersensitivity reactions with acute coronary syndromes.3 Kounis syndrome is caused by certain environmental exposures, poisons, and venoms; conditions such as angioedema, bronchial asthma, exercise-induced anaphylaxis, food allergy, idiopathic anaphylaxis, serum sickness, urticaria, and mastocytosis; drugs via inflammatory mediators such as histamine, tryptase, and chymase; and arachidonic acid products such as leukotrienes. There are several categories of drugs that are capable of inducing Kounis syndrome. These include antibiotics, analgesics, antineoplastics, …

Using Machine Learning Techniques to Improve the Behaviour of a Medical Decision Support System for Prostate Diseases

Prostate gland diseases, including cancer, are estimated to be of the leading causes of male deaths worldwide and their management are based on clinical practice guidelines regarding diagnosis and continuing care. HIROFILOS-II is a prototype hybrid intelligent system for diagnosis and treatment of all prostate diseases based on symptoms and test results from patient health records. It is in contrast to existing efforts that deal with only prostate cancer. The main part of HIROFILOS-II is constructed by extracting rules from patient records via machine learning techniques and then manually transforming them into fuzzy rules. The system comprises crisp as well as fuzzy rules organized in modules. Experimental results show more than satisfactory performance of the system. The machine learning component of the system, which operates off-line, can be periodically used for rule updating, given that enough new patient records have been added to the database.