Krzysztof Słowiński

Rough classification of patients after highly selective vagotomy for duodenal ulcer

Abstract The concept of “rough” sets is used to approximate the analysis of an information system describing 77 patients with duodenal ulcer treated by highly selective vagotomy (HSV). The patients are described by 11 attributes. The attributes concern sex, age, duration of disease, complication of duodenal ulcer and various factors of gastric secretion. Two values of sex and age are distinguished, five values of complications and three or four values of secretion attributes, according to norms proposed in this paper. For each patient, the result of treatment by HSV is expressed in the Visick grading which corresponds to four classes. Using the method of rough classification it is shown that the given norms ensure a good classification of patients. Afterwards, some minimum sets of attributes significant for high-quality classification are obtained. Upon analysis of values taken by attributes belonging to these sets a “model” of patients in each class is constructed. This model gives indications for treatment by HSV.

Sensitivity analysis of rough classification

Rough classification of patients after highly selective vagotomy (HSV) for duodenal ulcer is analysed from the viewpoint of sensitivity of previously obtained results to minor changes in the norms of attributes. The norms translate exact values of pre-operating quantitative attributes into some qualitative terms, e.g. “low”, “medium” and “high”. An extensive computational experiment leads to the general conclusion that original norms following from medical experience were well defined, and that the results of analysis of the considered information system using rough sets theory are robust in the sense of low sensitivity to minor changes in the norms of attributes.

Rough Sets as a Tool for Studying Attribute Dependencies in the Urinary Stones Treatment Data Set

The medical experience with urolithiasis patients treated by the extracorporeal shock wave lithotripsy (ESWL) is analysed using the rough set approach. The evaluation of the significance of attributes for qualifying patients to the ESWL treatment is the most important problem for the clinical practice. The use of a simple rough set model gives a high number of possible reducts which are difficult to interpret. So, the heuristic strategies based on the rough set theory are proposed to select the most significant attributes. All these strategies lead to similar results having a good clinical interpretation.

Rough Set Theory and Rule Induction Techniques for Discovery of Attribute Dependencies in Medical Information Systems

Problems connected with applications of the rough set theory to identify the most important attributes and with induction of decision rules from the medical data set are discussed in this paper. The medical data set concerns patients with multiple injuries. The direct use of the original rough set model leads to finding too many possibilities of reducing the input data. To solve this difficulty, a new approach integrating rough set theory, rule induction and statistical techniques is introduced. First, the Chi-square test is additionally performed in order to reject non-significant attributes. Then, starting from remaining attributes we try to construct such definitions of new attributes that improve finally discovered decision rules. The results have shown that the proposed approach integrating all methods has given better results than those obtained by applying the original rough set method.

Multistage Rough Set Analysis of Therapeutic Experience with Acute Pancreatitis

The rough set approach has been applied to analyse a multistage decision process concerning the treatment of acute pancreatitis with peritoneal lavage. The clinical experience has been represented by two kinds of information systems: system A, classifying patients described by pre-lavage attributes, and five systems B classifying patients described by attributes of the course of multistage lavage. From the medical point of view, the analysis of these information systems has aimed at identifying subsets of the most important attributes for results of the patient’s treatment and discovery of decision rules representing cause-and-effect dependencies between attributes. Achieving these aims have been facilitated by using two following rough set based strategies: adding to the core the attributes of the highest increase of discriminatory power and approach to inducing the satisfactory set of strong decision rules.

Intraspinal migration of a Kirschner wire as a late complication of acromioclavicular joint repair: a case report.

BackgroundPenetrating neck trauma involving foreign bodies is a rare event in European countries. Due to its relatively high mortality rate, the correct management strategy must be initiated from the beginning to prevent fatal complications. In the medical literature, there are only a few cases describing foreign bodies penetrating the cervical spine. Because of its rareness, many trauma centers lack the proper routine to adequately manage such injuries.Case presentationThis case report describes a 34-year-old white man of Central European descent with Kirschner wire migration and perforation of his vertebral foramen. He underwent acromioclavicular joint repair surgery 7 years ago, presented with a painful sensation around the area of his left clavicle and left side of his neck after a motorcycle accident. No neurological deficit was detected.ConclusionsIn such cases, a thorough radiological evaluation of the spinal cord and the surrounding vasculature is mandatory for a complete understanding of the extent of the injury and determining the proper surgical management. In cases of vertebral artery trauma both an endovascular and an open approach can be contemplated.

Sensitivity of Rough Classification to Changes in Norms of Attributes

Rough classification of patients after highly selective vagotomy (HSV) for duodenal ulcer is analysed from the viewpoint of sensitivity of previously obtained results to minor changes in the norms of attributes. The norms translate exact values of pre-operating quantitative attributes into 2 to 4 qualitative terms, e.g. “low”, “medium” and “high”. An extensive computational experiment leads to the general conclusion that original norms following from medical experience were well defined, and that the results of analysis of the considered information system using rough sets theory are robust in the sense of low sensitivity to minor changes in the norms of attributes.