PubMed Health⌕ Search

Biomedical subjects

B Zupan

Publications and source records attributed to B Zupan.

16 recordsLinked to original sources
PubMed2004

Clustering gene expression data with temporal abstractions.

This paper describes a new technique for clustering short time series coming from gene expression data. The technique is based on the labelling of the time series through temporal trend abstractions and a consequent clustering of the series on the basis of their labels. Clustering is performed at three different levels of aggregation of the original time series, so that the results are organized and visualized as a three-levels hierarchical tree. Results on simulated and on yeast data are shown. The technique appears robust and efficient and the results obtained are easy to be interpreted.

Algorithms↗
PubMed2001

Feature mining and predictive model construction from severe trauma patient's data.

In management of severe trauma patients, trauma surgeons need to decide which patients are eligible for damage control. Such decision may be supported by utilizing models that predict the patient's outcome. The study described in this paper investigates the possibility to construct patient outcome prediction models from retrospective patient's data at the end of initial damage control surgery by using feature mining and machine learning techniques. As the data used comprises rather excessive number of features, special attention was paid to the problem of selecting only the most relevant features. We show that a small subset of features may carry enough information to construct reasonably accurate prognostic models. Furthermore, the techniques used in our study identified two factors, namely the pH value when admitted to ICU and the worst partial active thromboplastin time, to be of highest importance for prediction. This finding is pathophysiologically reasonable and represents two of three major problems with severe trauma patients, metabolic acidosis, hypothermia, and coagulopathy.

Algorithms↗
PubMed2001

Predicting patient's long-term clinical status after hip arthroplasty using hierarchical decision modelling and data mining.

Construction of a prognostic model is presented for the long-term outcome after femoral neck fracture treatment with implantation of hip endoprosthesis. While the model is induced from the follow-up data, we show that the use of additional expert knowledge is absolutely crucial to obtain good predictive accuracy. A schema is proposed where domain knowledge is encoded as a hierarchical decision model of which only a part is induced from the data while the rest is specified by the expert. Although applied to hip endoprosthesis domain, the proposed schema is general and can be used for the construction of other prognostic models where both follow-up data and human expertise is available.

Aged↗
PubMed2001

Decisions at hand: a decision support system on handhelds.

One of the applications of clinical information systems is decision support. Although the advantages of utilizing such aids have never been theoretically disputed, they have been rarely used in practice. The factor that probably often limits the utility of clinical decision support systems is the need for computing power at the very site of decision making--at the place where the patient is interviewed, in discussion rooms, etc. The paper reports on a possible solution to this problem. A decision-support shell LogReg is presented, which runs on a handheld computer. A general schema for handheld-based decision support is also proposed, where decision models are developed on personal computers/workstations, encoded in XML and then transferred to handhelds, where the models are used within a decision support shell. A use case where LogReg has been applied to clinical outcome prediction in crush injury is presented.

Confidence Intervals↗
PubMed2001

GenePath: a computer program for genetic pathway discovery from mutant data.

The sequencing of the human genome and the genomes of several model organisms is the first step toward the long-term objective of genetic research: the identification of all genes, and the discovery of their functions and mutual interactions. This article presents a methodology and a computer program called GenePath to support the discovery of gene function. GenePath uses mutant data and available genetic knowledge to identify potential genetic pathways. Several pilot applications based on experimental results from Dictyostelium and C. elegans confirmed the usefulness of the proposed schema. Our results suggest that GenePath is a valuable tool that can be used as an intelligent assistant to support genetic reasoning.

Animals↗
PubMed2000

Predictive model for survival at the conclusion of a damage control laparotomy.

BACKGROUND: We employed modern statistical and data mining methods to model survival based on preoperative and intraoperative parameters for patients undergoing damage control surgery. METHODS: One hundred seventy-four parameters were collected from 68 damage control patients in prehospital, emergency center, operating room, and intensive care unit (ICU) settings. Data were analyzed with logistic regression and data mining. Outcomes were survival and death after the initial operation. RESULTS: Overall mortality was 66.2%. Logistic regression identified pH at initial ICU admission (odds ratio: 4.4) and worst partial thromboplastin time from hospital admission to ICU admission (odds ratio: 9.4) as significant. Data mining selected the same factors, and generated a simple algorithm for patient classification. Model accuracy was 83%. CONCLUSION: Inability to correct pH at the conclusion of initial damage-control laparotomy and the worst PTT can be predictive of death. These factors may be useful to identify patients with a high risk of mortality.

Critical Illness↗
PubMed2000

Machine learning for survival analysis: a case study on recurrence of prostate cancer.

Machine learning techniques have recently received considerable attention, especially when used for the construction of prediction models from data. Despite their potential advantages over standard statistical methods, like their ability to model non-linear relationships and construct symbolic and interpretable models, their applications to survival analysis are at best rare, primarily because of the difficulty to appropriately handle censored data. In this paper we propose a schema that enables the use of classification methods--including machine learning classifiers--for survival analysis. To appropriately consider the follow-up time and censoring, we propose a technique that, for the patients for which the event did not occur and have short follow-up times, estimates their probability of event and assigns them a distribution of outcome accordingly. Since most machine learning techniques do not deal with outcome distributions, the schema is implemented using weighted examples. To show the utility of the proposed technique, we investigate a particular problem of building prognostic models for prostate cancer recurrence, where the sole prediction of the probability of event (and not its probability dependency on time) is of interest. A case study on preoperative and postoperative prostate cancer recurrence prediction shows that by incorporating this weighting technique the machine learning tools stand beside modern statistical methods and may, by inducing symbolic recurrence models, provide further insight to relationships within the modeled data.

Artificial Intelligence↗
PubMed2000

Applications of qualitative multi-attribute decision models in health care.

Hierarchical decision models are a general decision support methodology aimed at the classification or evaluation of options that occur in decision-making processes. They are also important for the analysis, simulation and explanation of options. Decision models are typically developed through the decomposition of complex decision problems into smaller and less complex subproblems; the result of such decomposition is a hierarchical structure that consists of attributes and utility functions. This article presents an approach to the development and application of qualitative hierarchical decision models that is based on DEX, an expert system shell for multi-attribute decision support. The distinguishing characteristics of DEX are the use of qualitative (symbolic) attributes, and 'if-then' decision rules. Also, DEX provides a number of methods for the analysis of models and options, such as selective explanation and what-if analysis. We demonstrate the applicability and flexibility of the approach presenting four real-life applications of DEX in health care: assessment of breast cancer risk, assessment of basic living activities in community nursing, risk assessment in diabetic foot care, and technical analysis of radiogram errors. In particular, we highlight and justify the importance of knowledge presentation and option analysis methods for practical decision-making. We further show that, using a recently developed data mining method called HINT, such hierarchical decision models can be discovered from retrospective patient data.

Breast Neoplasms↗
PubMed1999

Slovenian national health insurance card: the next step.

The Slovenian national health insurance company started a full-scale deployment of the insurance smart card that is at the present used for insurance data and identification purpose only. There is ample capacity on the cards that were selected, to contain much more data than needed for the purely administrative and charging purposes. There are plans to include some basic medical information, donor information, etc. On the other hand, there are no firm plans to use the security infrastructure and the extensive network, connecting the insurance company with the more than 200 self service terminals positioned at the medical facilities through the country to build an integrated medical information system that would be very beneficial to the patients and the medical community. This paper is proposing some possible future developments and further discusses on the security issues involved with such countrywide medical information system.

Computer Security↗
PubMed1999

Naive Bayesian-based nomogram for prediction of prostate cancer recurrence.

This paper introduces a schema with naive-Bayesian classifier and patient weighting technique to develop a prostate cancer recurrence prediction model from patient data. We propose the graphical presentation of naive-Bayesian classifier with a nomogram, which can be used both for prediction or can provide means to data analysis. The resulting model was experimentally evaluated; the results were favorable both in terms of interpretability and predictive accuracy.

Bayes Theorem↗
PubMed1999

Hierarchical multi-attribute decision models and their application in health care.

Hierarchical decision models are developed through decomposition of complex decision problems into smaller and less complex subproblems. They are aimed at the classification or evaluation of options and can be used for analysis, simulation and explanation. This paper presents a set of methods for the construction and application of qualitative hierarchical decision models in health care. We present the results of four ongoing projects in oncology, radiology, community nursing and diabetic foot treatment.

Breast Neoplasms↗
PubMed1998

Relating clinical and neurophysiological assessment of spasticity by machine learning.

Spasticity following spinal cord injury (SCI) is most often assessed clinically using a five-point Ashworth score (AS). A more objective assessment of altered motor control may be achieved by using a comprehensive protocol based on a surface electromyographic (sEMG) activity recorded from thigh and leg muscles. However, the relationship between the clinical and neurophysiological assessments is still unknown. In this paper we employ three different classification methods to investigate this relationship. The experimental results indicate that, if the appropriate set of sEMG features is used, the neurophysiological assessment is related to clinical findings and can be used to predict the AS. A comprehensive sEMG assessment may be proven useful as an objective method of evaluating the effectiveness of various interventions and for follow-up of SCI patients.

Artificial Intelligence↗
PubMed1987

Cognitive vulnerability in children at risk for depression.

Cognitive, developmental, and psychodynamic theories all hypothesize that negative self-concepts acquired in childhood may induce vulnerability to depression. Children at risk because of maternal major affective disorder, compared with children of medically ill and normal mothers, were examined for evidence of negative cognitions about themselves, and were found to have more negative self-concept, less positive self-schemas, and more negative attributional style. It was further predicted that negative cognitions about the self would be related to maternal depression and chronic stress, and to the quality of perceived and actual interactions with the mother. In general, the predicted associations were obtained, supporting speculations about how maternal affective disorder is associated with stress and with relatively negative and unsupportive relationships with children that in turn diminish children's self-regard.

Adolescent↗
PubMedDate not supplied

Acquiring background knowledge for machine learning using function decomposition: a case study in rheumatology.

Domain or background knowledge is often needed in order to solve difficult problems of learning medical diagnostic rules. Earlier experiments have demonstrated the utility of background knowledge when learning rules for early diagnosis of rheumatic diseases. A particular form of background knowledge comprising typical co-occurrences of several groups of attributes was provided by a medical expert. This paper explores the possibility of automating the process of acquiring background knowledge of this kind and studies the utility of such methods in the problem domain of rheumatic diseases. A method based on function decomposition is proposed that identifies typical co-occurrences for a given set of attributes. The method is evaluated by comparing the typical co-occurrences it identifies as well as their contribution to the performance of machine learning algorithms, to the ones provided by a medical expert.

Algorithms↗