Biomedical subjects

Martti Juhola

Publications and source records attributed to Martti Juhola.

22 records · Page 2Linked to original sources

PubMed2002

On distance computation in space of mixed-type variables in medical data mining.

In the next study we consider two distance metrics that were presented in the machine leaming literature for mixed-type variables. We show that they are not really metrics, but pseudometrics. The problem arose from missing values. The metrics can be redefined to satisfy the metricity definition. Distance computation can then be performed reliably without a possibility that a distance between exactly similar patient cases would not be zero. We experimented with both procedures and so-called ignore mode using two medical data sets and observed that the redefined procedure was as good as the original approach as measured with the classification ability of one-nearest neighbour searching. It is noticeable that the described problem caused by missing values can be with any distance measure if its missing values are treated in the pessimistic manner as in the original version of these distance measures.

Computer Simulation↗

PubMed2002

Nearest neighbour classification of otoneurological data.

We studied the nearest neighbour classification of patient cases with benign positional vertigo, Meniere's disease, sudden deafness, traumatic vertigo, vestibular neuritis, and vestibular schwannoma. The classification results were compared to the inference results obtained by an otoneurological expert system ONE whose inference mechanism somewhat resembles the classical nearest neighbour method. With respect to the predictive accuracy, the classification results of these two systems agreed. The best predictive accuracy for the expert system ONE was 79.7% and for the nearest neighbour method 80.5%. However, differences in the true positive rates for sudden deafness, traumatic vertigo, vestibular neuritis, and vestibular schwannoma were found. The nearest neighbour classification results will be used in the refinement of ONE's knowledge base.

Data Collection↗

PubMed2002

On prediction of hearing recovery after acute acoustic trauma caused by impulse noise.

The present study investigates the prediction of how successfully hearing returns to normal after an acute acoustic trauma caused by a firearm shot, an explosion or other impulse noise. Study material consisted of 113 conscripts who had suffered an acute acoustic trauma during their military service. A logistic regression model was formed to predict hearing recovery. From several possible variables at least five were found to be important among our dataset, which is still rather limited. However, more data will be acquired later in order to elaborate the research more widely by using other methods also.

Adolescent↗

PubMedDate not supplied

On lossy transform compression of ECG signals with reference to deformation of their parameter values.

Electrocardiogram (ECG) signals are the most prominent biomedical signal type used in clinical medicine. Their compression is important and widely researched in the medical informatics community. In the previous literature compression efficacy has been investigated only in the context of how much known or developed methods reduced the storage required by compressed forms of original ECG signals. Sometimes statistical signal evaluations based on, for example, root mean square error were studied. In previous research we developed a refined method for signal compression and tested it jointly with several known techniques for other biomedical signals. Our method of so-called successive approximation quantization used with wavelets was one of the most successful in those tests. In this paper, we studied to what extent these lossy compression methods altered values of medical parameters (medical information) computed from signals. Since the methods are lossy, some information is lost due to the compression when a high enough compression ratio is reached. We found that ECG signals sampled at 400 Hz could be compressed to one fourth of their original storage space, but the values of their medical parameters changed less than 5% due to compression, which indicates reliable results.

Algorithms↗