Volume 35 (2013): Issue 1 (December 2013)

Intrauterine insemination (IUI) is one of many treatments provided to infertility patients. Many factors such as, but not limited to, quality of semen, the age of a woman, and reproductive hormone levels contribute to infertility. Therefore, the aim of our study is to establish a statistical probability concerning the prediction of which groups of patients have a very good or poor prognosis for pregnancy after IUI insemination. For that purpose, we compare the results of two analyses: Cluster Analysis and Kohonen Neural Networks. The k-means algorithm from the clustering methods was the best to use for selecting patients with a good prognosis but the Kohonen Neural Networks was better for selecting groups of patients with the lowest chances for pregnancy.

The analysis of survival data often aims at the prediction of failure time distribution. In cases of competing risk events, the time distributions of more than one failure are under investigation. In this paper, the comparison of two approaches to analyzing survival data with competing risks is presented. The analyses are performed by use of an ensemble of dipolar trees with and without adjustment to competing risks.

Infertility is recognized as a major problem of modern society. Assisted Reproductive Technology (ART) is the one of many available treatment options to cure infertility. However, the efficiency of the ART treatment is still inadequate. Therefore, the procedure’s quality is constantly improving and there is a need to determine statistical predictors as well as contributing factors to the successful treatment. There is a concern over the application of adequate statistical analysis to clinical data: should classic statistical methods be used or would it be more appropriate to apply advanced data mining technologies? By comparing two statistical models, Multivariable Logistic Regression analysis and Artificial Neural Network it has been demonstrated that Multivariable Logistic Regression analysis is more suitable for theoretical interest but the Artificial Neural Network method is more useful in clinical prediction.

In this work, a system for the classification of liver dynamic contest- enhanced CT images is presented. The system simultaneously analyzes the images with the same slice location, corresponding to three typical acquisition moments (without contrast, arterial- and portal phase of contrast propagation). At first, the texture features are extracted separately for each acquisition mo- ment. Afterwards, they are united in one “multiphase” vector, characterizing a triplet of textures. The work focuses on finding the most appropriate features that characterize a multi-image texture. At the beginning, the features which are unstable and dependent on ROI size are eliminated. Then, a small subset of remaining features is selected in order to guarantee the best possible classification accuracy. In total, 9 extraction methods were used, and 61 features were calculated for each of three acquisition moments. 1511 texture triplets, corresponding to 4 hepatic tissue classes were recognized (hepatocellular carcinoma, cholangiocarcinoma, cirrhotic, and normal). As a classifier, an adaptive boosting algorithm with a C4.5 tree was used. Experiments show that a small set of 12 features is able to ensure classification accuracy exceeding 90%, while all of the 183 features provide an accuracy rate of 88.94%.

The figures visualizing single and combined classifiers coming from decision trees group and Bayesian parametric and nonparametric discriminant functions show the importance of diversity of bagging or boosting combined models and confirm some theoretical outcomes suggested by other authors. For the three medical sets examined, decision trees, as well as linear and quadratic discriminant functions are useful for bagging and boosting. Classifiers, which do not show an increasing tendency for resubstitution errors in subsequent boosting deterministic procedures loops, are not useful for fusion, e.g. kernel discriminant function. For the success of resampling classifiers’ fusion, the compromise be- tween accuracy and diversity is needed. Diversity important in the success of boosting and bagging may be assessed by concordance of base classifiers with the learning vector.

This paper addresses the issue of the stability of lists of genes identified as differentially expressed in microarray experiments. The similarities be- tween gene rankings yielded by various gene selection methods performed with resampled datasets were assessed. The mean percentage of overlapping genes for two rankings varied from 10 to 90% depending on the applied gene selection method and the size of the list. The assessment of the stability of obtained gene rankings seems to be relevant in the analysis of microarray data.

Infertility is a serious social problem. Very often the only treatment possibility are IVF methods. This study explores the possibility of outcome prediction in the early stages of treatment. The data, collected from the previous treatment cycles, were divided into four subsets, which corresponded to the selected stages of treatment. On each such subset, sophisticated data mining analysis was carried out, with appropriate imputations and classification procedures. The obtained results indicate that there is a possibility of predicting the final outcome at the beginning of treatment.

Poincaré plot is a return map which can help perform graphical analysis of data. We can also fit an ellipse to the plot shape by determining descriptors SD1, SD2 and SD1/SD2 ratio to study the data quantitatively. In this paper we show examples of application of Poincaré plots in analysis of various kinds of biomedical signals: RR intervals, EMG, gait data and EHG.

This article describes methods used in estimating skeletal age based both on the evaluation of skeletal maturation of the palm and the wrist (Greulich and Pyle’s atlas method) and the Cervical Vertebral Maturation method (CVM). The method of evaluating the skeletal age based on the measurement of cervical vertebrae with equations introduced by A. Machorowska-Pieniążek is also mentioned. The article shows results obtained by computer analysis of the age of cervical vertebrae compared to the results gained from the implemented equations provided by A. Machorowska-Pieniążek and the results obtained from the atlas method.

Ruby and Perl are programming languages used in many fields. In this paper we would like to present their usefulness with regard to basic bioinformatic problems. We concentrate on a comparison of widely used Perl and relatively rarely used Ruby to show that Ruby can be a very efficient tool in bioinformatics. Both Perl and Ruby have a built-in regular expressions (or regexp) engine, which is essential in solving many problems in bioinformatics. We present some selected examples: printing the file content, removing comments from a FASTA file, using hashes, printing nucleotides included in a sequence, searching for a specific nucleotide in sequence and translating nucleotide sequences into protein sequences obtained in GenBank format. It is our belief that Ruby’s popularity will rise because of its simple syntax and the richness of its methods. Programs in Ruby are very easy to read and therefore easier to maintain and debug, which are the most important characteristics for a programming language.

The purpose of the study was to analyse the level and the trends of Potential Years of Life Lost due to the main causes of death in Poland in the years 2002-2011. The material for the study was the information from the Central Statistical Office on the number of deaths due to the main causes of death in Poland in the years 2002-2011. The premature mortality analysis was conducted with the use of the PYLL (Potential Years of Life Lost) indicator. PYLL rate was calculated following the method proposed by J. Romeder, according to which premature mortality was defined as death before the age of 70. Time trends of PYLL rate and the average annual percent change (APC - Annual Percent Change) were assessed using jointpoint models and the Joinpoint Regression Program. In the years 2002-2011, PYLL rate for all-cause deaths decreased by 7.0% among men and 8.1% among women. In 2011, the main reasons for PYLL among men were: external causes (27.6%), cardiovascular diseases (24.2%) and cancers (20.3%). Among women the leading causes were: cancers (41.1%), cardiovascular diseases (19.7%) and external causes (12.5%). PYLL rate increased among men for colorectal cancer, and among women for colorectal and lung cancer. The presented epidemiological situation for premature mortality in Poland shows that in the majority of cases it is caused by preventable deaths, which highlights a need to intensify measures in primary and secondary prevention.

Statistical methods used by healthcare entities enable the collection of various information about the structure and characteristics of treated patients. They are an important source of knowledge, and form a database that plays an important role in entity management theory. In the presented study, we analysed the hospital stays of patients treated in all hospital wards of the 3^rd City Hospital in Łodź during 2012. The following, in particular, were taken into account: admittance procedure, discharge procedure, age and sex of hospitalised persons. Patients in over 55% of cases were admitted using the sud- den admittance procedure. At the same time, over 3/4 of the stays ended with a referral for further treatment in ambulatory conditions, and death occurred in approx. 5% of hospitalisations. By comparing the discharge procedures, the percentage of deaths in the Anaesthesiology and Intensive Care Wards can be seen clearly (more than 70%). Internal wards are next in turn (10.6 and 16.6%). The biggest differences in the length of hospitalisation between the studied institution and the NFZ data (which are averaged values from all medical entities in Poland) concern the E77, A49, A48, A87, A33, D18, E16, E61 and G37 groups.

Despite the great expansion and many benefits of information and communication technologies (ICT) in healthcare, the attitudes of Polish general practitioners (GPs) to e-health have not been explored. The aim of this study was to determine the GPs’ perception of ICT use in healthcare and to identify barriers to the adoption of EMR (Electronic Medical Records) in the Podlaskie Voivodeship. Online and telephone surveys were conducted between April and May 2013. Responses from 103 GP practices, 43% of all practices in the region, were analysed. The results showed that 67% of the respondents agreed that IT systems improve quality of healthcare services. In the GP group who declared at least partial EMR implementation, 71.4% see the positive impact of IT on practice staff processes and 66.1% on personal working processes. In this group, more than three-quarters of GPs did not see any positive impact of ICT on the average number of patients treated per day, number of patients within the practice or scope of services. The four most common barriers to EMR implementation were: lack of funds, risk of a malfunction in the system, resistance to change, and lack of training and proper information. Although the use of ICT by Polish GPs is limited, their attitude to e-health is generally positive or neutral and resembles the overall pattern in Europe. Barriers identified by GPs need to be taken into account to ensure the effective implementation of e-health across the country.

Health information technology (IT) in hospitals can be approached as a tool to reduce health care costs and improve hospital efficiency and profitability, increase the quality of healthcare services, and make the transition to patient-centered healthcare. A hospital’s efficiency and profitability depends on linking IT with the knowledge and motivation of medical personnel. It is important to design and execute a knowledge management strategy as a part of the implementation of IT in hospital management. A Diagnosis-Related Groups (DRG) system was introduced in Poland in 2008 as a basis for settlements between hospitals and the National Health Fund (NHF). The importance and role of a DRG system in management of healthcare entities was emphasized based on a survey of medical professionals from two hospitals in the Lubelskie province. The goal of a survey is to assess the knowledge of medical professionals about the DRG system and how the medical personnel uses the DRG system in order to achieve the strategic goals of the organization. A newly developed survey was used to assess the medical personnel’s knowledge of DRG, using 12 closed and 5 open questions. The survey was conducted on 160 medical employees from two hospitals in the Lubelskie province. In conclusion, medical personnel’s DRG knowledge unambiguously contributes to reducing hospital costs and increasing profitability. The DRG related knowledge enables personnel to obtain value from data by applying DRG data-driven decisions.

This paper presents an analysis of learning effectiveness for the courses “Selected issues in visual rehabilitation” and “Ophthalmology and ophthalmic nursing” taught in the years 2009-2011 at the Medical University of Bialystok, Poland. We compared the effectiveness of traditional and distance learning methods; an e-learning platform was implemented experimentally for the purpose of this study. We assessed the usefulness of online learning in terms of organization, knowledge gained and students’ satisfaction with the course. The study was conducted among 75 second year master degree students in the nursing field in the academic years 2009/2010 and 2010/2011. The students were divided into two groups. For the study group of 39 persons (52%), lectures and seminars took place on an e-learning platform, while 36 persons (48%) in the control group attended traditional classes. 80% of students in the e-learning group and 89% of students in the traditional group assessed the organization of both forms of courses positively. The fact that the majority of students in both the e-learning (89%) and traditional classes (86%) gave positive feedback indicates that for both forms there was a high level of content and technical preparedness. The mean scores of the final exam for both courses were 82% in the e-learning group and 79% in the traditional group in the years 2009- 2011. The above results show that both forms of learning are equally effective.