Marek Lubicz

Boosted SVM for extracting rules from imbalanced data in application to prediction of the post-operative life expectancy in the lung cancer patients

In this paper, we present boosted SVM dedicated to solve imbalanced data problems. Proposed solution combines the benefits of using ensemble classifiers for uneven data together with cost-sensitive support vectors machines. Further, we present oracle-based approach for extracting decision rules from the boosted SVM. In the next step we examine the quality of the proposed method by comparing the performance with other algorithms which deal with imbalanced data. Finally, boosted SVM is used for medical application of predicting post-operative life expectancy in the lung cancer patients.

Simulation modelling of emergency medical services

Abstract This paper deals with the problem of application of simulation modelling in Emergency Medical Services (EMS) systems. Approaches to modelling of EMS are discussed and a review of EMS simulation models is presented. A simple simulation model of a rural EMS system in Poland is described. Some results of the initial application of the model are presented. Possibilities of simulation modelling for solving EMS managerial and planning problems are briefly analysed.

A system dynamics model to study the impact of an age pyramid on emergency demand

This paper describes a system dynamics simulation model to analyse the relationship between age pyramid and the volume of patients arriving to hospital emergency departments located in a sub-region of Lower Silesia of Poland. The study relies on demographic and historical demand data, and the cohort forecasts for the population of the region. The results of the simulation experiments provide insights into the relationship between sub-regional demographic trends and population needs in relation to hospital emergency arrivals. The preliminary findings indicate that the forecasted long-term demographic changes in the population may increase the number of emergency patients in the area.

Cost Sensitive SVM with Non-informative Examples Elimination for Imbalanced Postoperative Risk Management Problem

In this paper we propose a novel combined approach to solve the imbalanced data issue in the application to the problem of the post-operative life expectancy prediction for the lung cancer patients. This solution makes use of undersampling techniques together with cost-sensitive SVM (Support Vector Machines). First, we eliminate non-informative examples by applying Tomek links together with one-sided selection. Second, we take advantage of using cost-sensitive SVM with penalty costs calculated respecting cardinalities of minority and majority examples. We evaluate the presented solution by comparing the performance of our method with SVM-based approaches that deal with uneven data. The experimental evaluation was performed on real-life data from the postoperative risk management domain.

Effectiveness and efficiency of product quality inspection processes

Abstract This paper deals with the question of describing and evaluating product quality inspection processes, related to discrete production system. The following problems were discussed: • classification of characteristics proposed for describing the effects of industrial processes; • formulation of definitions of the effectiveness and efficiency coefficients of quality inspection processes; • practical examples of effectiveness and efficiency analysis, using actual numerical data from two industrial enterprises.

Applications of Operations Research and Intelligent Techniques in the Health Systems

Operations research and quantitative methods, including the ones based on artificial or computational intelligence, have been applied in health care for decades. While looking at areas of applications and evolution of techniques one can notice trends, emerging problem areas, and also international disparities in the application-oriented research. Due to the scale of the problem, in this paper we explore these ideas by means of analysis of a limited, though comprehensive sample of the research results presented in the period 1985–2015 at annual conferences of the EURO Working Group Operational Research Applied to Health Services. The technical background for this research is a bibliometric analysis based on SciMAT—a Science Mapping Analysis software Tool, developed at the University of Granada.