Decision trees based on automatic learning and their use in cardiology

Computerized information systems, especially decision support systems, have become an increasingly important role in medical applications, particularly in those where important decision must be made effectively and reliably. But the possibility of using computers in medical decision making is limited by many difficulties, including the complexity of conventional computer languages, methodologies and tools. Thus a conceptual simple decision making model with the possibility of automating learning should be used. In this paper we introduce a cardiological knowledge-based system based on the decision tree approach supporting the mitral valve prolapse determination. Prolapse is defined as the displacement of a bodily part from its normal position. The term mitral valve prolaps (PMV), therefore, implies that the mitral leaflets are displaced relative to some structure, generally taken to be the mitral annulus. The implications of the PMV are the following: disturbed normal laminar blood flow, turbulence of the blood flow, injury of the chordae tendinae, the possibility of thrombus's composition, bacterial endocarditis, and finally hemodynamic changes defined as mitral insufficiency and mitral regurgitation. Uncertainty persists about how it should be diagnosed and about its clinical importance. It is our deep belief that the echocardiography enables properly trained experts armed with proper criteria to evaluate PMV almost 100%. But unfortunately, there are some problems concerned with the use of echocardiography. In that manner we have decided to start a research project aimed at finding new criteria and enabling the general practitioner to evaluate PMV using conventional methods and to select potential patients from the general population. To empower one to perform needed activities we have developed a computer tool called ROSE (computeRised prOlaps Syndrom dEtermination) based on algorithms of automatic learning. This tool supports the definition of new criteria and the selection of potential PMV-patients.     

Pleural effusion in patients infected with the human immunodeficiency virus

In order to analyze the etiology, cytological and biochemical characteristics, and outcome of pleural disease in patients infected with HIV, the medical records of 86 HIV-positive patients with pleural effusion were reviewed. Controls were 106 HIV-negative patients with parapneumonic or tuberculous effusion. Most HIV-positive patients were intravenous drug abusers (95.3%). Pleural effusions in HIV-positive patients were caused by infections in 76 (89.4%) cases. Parapneumonic effusion was diagnosed in 59 patients and tuberculous pleuritis in 15 patients.Staphylococcus aureus was the most frequently isolated bacteria. Parameters for differentiating complicated cases of parapneumonic exudate from uncomplicated cases, such as pleural fluid pH<7.20 (sensitivity 80% vs. 84.3%), pleural fluid glucose<35 mg/dl (sensitivity 45% vs. 56.25%) pleural fluid LDH > 1600 Ul/l (sensitivity 85% vs. 62.50%), showed similar sensitivity in HIV-positive and HIV-negative patients. Monocytes in pleural fluid were significantly decreased in tuberculous pleuritis in HIV-positive patients (506±425 vs. 1014±1196 monocytes/ml, p<0.05). No significant differences were detected in the outcome of HIV-positive and HIV-negative patients with pleural disease. It can be concluded that the pleural effusion was of predominantly infectious etiology in HIV-positive patients from populations with a high prevalence of intravenous drug abuse. Neither the biochemical parameters in pleural fluid nor the outcome differed significantly between HIV-positive and HIV-negative patients.     

Somatosensory evoked potential monitoring during intracranial surgery

In the neurosurgical approach to intracranial aneurysms which are often accompanied by arterial spasm and cortical ischaemia, monitoring procedures aim to obtain useful information on cerebral function. SEPs evoked by stimulation of the median nerve at the wrist and of the tibial nerve at the medial malleolus were registered in 45 patients with intracranial aneurysms during neurosurgical procedures. Our results show SEP abnormalities during different stages of neurosurgical procedures in 36 patients out of the monitored 45. Significant abnormalities of SEPs with respect to the control group were decrease of the amplitude of N 20-P 25 complex, lengthening of the absolute latency of the waves N 20- and P 25 and lengthening of the central conduction time (CCT) (N 13-N 20). The greatest SEP abnormalities were registered during the neurosurgical approach to aneurysm and during the clipping procedure. However, the changes were reversible in the majority of the patients. The aim of this paper was to focus on early detection of some cerebral function disturbances during the neurosurgical procedure as well as the prevention of possible brain damage.