Studies of responsiveness in the R-EGFR and Rcerb-B2 oncogenes spaces: a customized application for thyroid lesions.

Among variety of diagnostic approaches suitable for clinical analysis of thyroid lesions, the two oncogenes (R-EGFR and Rcerb-B2) are believed to be of discriminative power. In a retrospectively collected patient material we have defined different lesion types (normal tissue, benign and malignant tumours). Those were taken as class definitions in analysis performed to assign discriminating performance. Standard multivariate statistics has not performed satisfactory partly due to the data distribution and partly due to presence of the noise. Therefore we have developed a method for the classification purpose, which was based on principle of minimising generalised classification error. Results of the separation between carcinoma and normal tissue reached accuracy 70%, other classification attempts ended up in poor results. In general, misclassifications could be explained with the data quality (noise) and, when it came to benign lesions, with responsiveness of the oncogenes to tumour tissues.

Machine learning for the quality of life in inflammatory bowel disease.

Presence of a chronic disease influences patients' lives and reinforces demands to accept and then cope with the illness. In the case of inflammatory bowel disease, quality of life greatly differs through phases of remissions and relapses. Could the quality of life questionnaire tell the difference? In this study we are disclosing possibilities of assessing patients' perspectives by analysing analogue scale statements regarding concerns and worries related to ulcerative colitis. Some two hundred Swedish patients, 3/4 in remission and 1/4 in relapse, filled out a booklet containing 36 statements. To characterise the disease activity, we have used multivariate discrimination. To structure and describe in details paths distinguishing the remission from relapse, we have used an artificial intelligence procedure. Applications of the CART (Classification And Regression Trees) algorithm resulted in a set of classifiers which are, based on the similar subsets of significant variables, i.e. statements. Best reached classification accuracy did not exceed 80% in any case. Other classifiers namely, K-nearest-neighbour (KNN), Learning Vector Quantization (LVQ) and Back Propagation Neural Network (BPNN) confirmed that outcome. An expectation that the disease activity should clearly speak throughout the questionnaire held for a certain number of the observations such as pain and suffering, loss of bowel control, dying early, feeling alone, ability to have children, being treated as different and concerns regarding the medication. To highlight the difference of incorrect 20%, K-means clustering was performed. The results settled a basis for a hypothesis that the studied quality of life instrument captures more than the disease activity.