Computers and biomedical research, an international journal最新文献

In the validation of medical expert systems, agreement among different human specialists on a random sample of cases may be taken as a substitute to a missing gold standard. Distance measures between pairs of experts, extensively described in previous studies, do not take into account the influence of chance-expected agreement. A weighted kappa index, with three different weighting schemes, is proposed as an alternative to be applied in the general situation of N cases assessed by E experts about K possible diagnoses, each of them qualified with one of G ordinal categories. A hierarchical cluster analysis, applied to the kappa matrices generated, allows for the classification of the expert system among clinical specialists, providing a relative assessment of its diagnostic ability. The above methodology is applied to the validation of two medical expert systems, PNEUMON-IA and RENOIR.

The RT interval is a measure of the ventricular repolarization and is partially influenced by the sympathovagal balance. The analysis of the variation of the duration of the RT and RR intervals might bring new information about the arrhythmogenic vulnerability and autonomic imbalance. The RR signal and its spectral density (SD) are characterized by two different patterns during the sleep period. On the basis of this information, RT and RR sequences have been automatically classified into two patterns, R and N. In this work, we propose a methodology to define new variables that are able to distinguish patients with hypertrophic cardiomyopathy (HCM) who later developed sudden cardiac death (SCD) from HCM patients without such episode during the follow-up. These variables are based on the instantaneous frequency calculation using time-frequency representation of the RT and RR signals previously classified into R and N patterns. In this study, three spectral bands have been considered: low-frequency band (LF, 0–0.07 Hz), mid-frequency band (MF, 0.07–0.15 Hz), and high-frequency band (HF, 0.15–0.45 Hz). Then a suitable combination of mean energy and mean frequency of the RT and RR signals in the MF and HF bands has allowed HCM patients with SCD to be discriminated from HCM patients without SCD (P < 0.001).

Based on new advancements in digital technology, we developed a PC- and DSP-based measurement and control system for isolated papillary muscle experiments. High flexibility was obtained through a three level control. Length or force was controlled real-time with a sample frequency of 5000 Hz. Muscle length and up to three segment lengths were measured simultaneously and each of these lengths could be chosen as feedback variable. Individual algorithms were implemented for different twitch types. Batches of twitches were organized in experiment protocols. The system included a new twitch type, namely a controlled auxotonic twitch. In this twitch, the muscle acted against a virtual ideal spring, giving a proportional change in developed force and shortening. The value of the virtual spring constant could be set on-line or defined in the experiment protocol. An increasing virtual spring constant represented a smooth transition from isotonic to isometric conditions.

A wavelet domain nonlinear filtering method for improving the signal-to-noise ratio (SNR) of the evoked potentials (EP) is proposed. The method modifies the selective filtering technique proposed for edge detection in images by Xu et al. for the case of signals which require a smooth transition at the edge points. It identifies the significant features of a noisy signal based on the correlation between the scales of its nonorthogonal subband decompositions. The signal transition information from interscale correlation coupled with the change in variance around the identified transition region is used to differentiate between noise and the signal. A nonlinear function such as a Gaussian smoothing function applied around the identified edge in the wavelet domain leads to smoothing in the signal space also. Numerical results obtained by applying the proposed nonlinear filtering method on middle latency responses of auditory evoked potentials show that the method is well suited for signal enhancement applications.

Genetic linkage calculations can be time consuming, even on a fast computer. The ability to collect large family pedigrees has increased the magnitude of linkage computations. Sequential genetic algorithms have many successful applications in very different domains, but they have a main drawback in their utilization. Evaluations are very time-consuming, e.g., a pedigree consisting of 55 nodes takes about 70 min on a DEC-Alpha processor and about 270 min on a 166 MHz Pentium for certain likelihood calculations. This time increases exponentially with the increase in the size of the pedigree. In order to solve these shortcomings and to study new models of higher efficiency and efficacy, parallel platforms are being used for genetic programs. LINKAGE is a software package for performing genetic likelihood calculations; FASTLINK is an improved, faster version of it. This paper provides a parallel implementation of the “Linkmap” program (one of the four programs in LINKAGE/FASTLINK) for a heterogeneous environment, using a static and a dynamic strategy for task allocation. It was found that the increased performance by the dynamic strategy was close to the estimated maximum speed up.

Subcutaneous adipose tissue thickness was measured in 590 healthy subjects at 15 specific body sites by means of the new optical device, lipometer, providing a high-dimensional and partly highly intercorrelated set of data, which had been analyzed by factor analysis previously. N-2-N back-propagation neural networks are able to perform low-dimensional display of high-dimensional data as a special application. We report about the performance of such a 15-2-15 network and compare its results with the output of factor analysis. As test data for verification, measurement values on women with proven diabetes mellitus type II (NIDDM) are used. Surprisingly our 15-2-15 neural network is able to reproduce the classification pattern resulting from factor analysis very precisely. After extracting the network weights the classification of new subjects is even more simple with the neural network as compared with factor analysis. In addition, the network weights are able to cluster highly correlated body sites nicely to different groups, corresponding to different regions of the human body. Thus, the analysis of these weights provides additional information about the structure of the data. Therefore, N-2-N networks seem to be a good alternative method for analyzing high-dimensional data with strong intercorrelation.

We propose an automated method for sleep stage scoring using hybrid rule- and case-based reasoning. The system first performs rule-based sleep stage scoring, according to the Rechtschaffen and Kale's sleep-scoring rule (1968), and then supplements the scoring with case-based reasoning. This method comprises signal processing unit, rule-based scoring unit, and case-based scoring unit. We applied this methodology to three recordings of normal sleep and three recordings of obstructive sleep apnea (OSA). Average agreement rate in normal recordings was 87.5% and case-based scoring enhanced the agreement rate by 5.6%. This architecture showed several advantages over the other analytical approaches in sleep scoring: high performance on sleep disordered recordings, the explanation facility, and the learning ability. The results suggest that combination of rule-based reasoning and case-based reasoning is promising for an automated sleep scoring and it is also considered to be a good model of the cognitive scoring process.

This paper presents a new software, Pk-fit, to fit nonlinear models to kinetic and dynamic data. Directly connected to the spreadsheet, a statistical software component manager is available. In the data manager, Pk-fit includes the noncompartmental analysis module, the compartmental analysis module, the nonlinear kinetic process module, the drug absorption module, the pharmacodynamic data modeling module, the simultaneous fitting module, and the user-defined library module. In this paper, we present a detailed comparison of the kinetic analysis using Pk-fit and common software packages, PCNONLIN, MODFIT, MKMODEL, NONMEM, and SIPHAR, based on the textbook published by Gabrielsson in 1992, “Compilation of Analyzed Data Sets for Pharmacokinetic Software Evaluation.” The comparison of Pk-fit with the reference softwares revealed that the parameters and their dispersion found with Pk-fit are consistent with the ones estimated with the other programs. In conclusion, Pk-fit constituted a valid tool for pharmacokinetic/pharmacodynamic data analysis.