Biomedical subjects

L Bobrowski

Publications and source records attributed to L Bobrowski.

5 recordsLinked to original sources

PubMed2006

Induction of similarity measures and medical diagnosis support rules through separable, linear data transformations.

OBJECTIVES: To improve the medical diagnosis support rules based on comparisons of diagnosed patients with similar cases (precedents) archived in a clinical database. The case-based reasoning (CBR) or the nearest neighbors (K-N) classifications, which operate on referencing (learning) data sets, belong to this scheme. METHODS: Inducing similarity measure through special linear transformations of the referencing sets aimed at the best separation of these sets. Designing separable transformations can be based on dipolar models and minimization of the convex and piecewise linear (CPL) criterion functions in accordance with the basis exchange algorithm. RESULTS: Separable linear transformations allow for some data sets to decrease the error rate of the K-N classification rule based on the Euclidean distance. Such results can be seen on the example of data sets taken from the Hepar system of diagnosis support. CONCLUSIONS: Medical diagnosis support based on the CBR or the K-NN rules can be improved through separable transformations of the referencing sets.

Algorithms↗

PubMed2001

Diagnosis supporting rules of the Hepar system.

The "Hepar" system comprises a clinical database and the shell of procedures that aim at data analysis and the support of diagnosis. The database consists of hepatological patient cases. Each case is described by about 200 medical findings and histopathologically verified diagnosis. The diagnosis supporting rules of "Hepar" are based on visualizing data transformations and on the similarity based techniques. The applied linear visualizing transformations of data sets on the plane aim at separating of the groups of patients associated with different diseases. The resulting diagnostic maps by the visual inspection allow to find such cases in the database that are similar to the previously diagnosed patients. This paper examines combining of data transformations with the nearest neighbors techniques in the support of diagnosis. We report the results on the experimental comparisons of different decision rules including the feature selection procedure.

Decision Support Techniques↗

PubMed1984

Selection of medical tests based on linear nonseparability of data sets: a study on evaluation of liver diseases tests.

A new method of solving the problem of medical tests selection is proposed. This method is based on the notion of linear nonseparability of data. A measure of linear nonseparability is computed by minimization of the perceptron criterion function. A multistage strategy of search of the minimum sufficient tests subset is described. This strategy is reliable in the sense that it allows us to find the least (globally) sufficient number of tests. The considerations are illustrated on a liver diseases data example.

Diagnosis, Differential↗

PubMed1980

Comparison of two unsupervised algorithms.

The binary decision element described by the decision rule depending upon weight vector w is a model of neuron examined in this paper. The environment of the element is described by some unknown, stationary distribution (p(kappa). The input signals kappa[n] of the element appear in each step n independently in accordance with the distribution p(kappa). During an unsupervised learning process the weight vector w[n] is changed on the base of the input vector kappa[n]. In the paper there are regarded two self-learning algorithms which are stochastic approximation type. For both algorithms the same rule of past experiences neglecting or the rule of weight decrease has been introduced. The first algorithm differs from the other one by a rule of weight increase. It has been proved that only one of these algorithms always leads to the same decision rule in a given environment p(kappa).

Decision Making↗

PubMed1978

Learning processes in multilayer threshold nets.

An algorithm of learning in multilayer threshold nets without feedbacks is proposed. The net is built of threshold elements with binary inputs. During a learning process each input vector chi is accompanied by a teacher's decision omega (omega epsilon(1,...,M)). The pairs (chi[n], omega[n]) appear in successive steps independently according to some unknown stationary distribution p(chi, omega). The problem of learning of a threshold net has been decomposed to a series of problems of learning of the threshold elements. The proposed learning algorithm of the threshold elements has a perceptron-like form. It was proven that a decision rule of the threshold net stabilizes after a finite number of steps. For definite classes (p(chi,omega))K of distributions p(chi, omega), an optimal decision rule stabilizes after a finite number of steps. These classes (p(chi, omega))K also contain distributions describing learning processes with perturbations.

Feedback↗