Using data preprocessing and single layer perceptron to analyze laboratory data.

During daily work in hospitals a large amount of clinical data is produced each day. Totally computerized patient records are not yet widely used but a large part of essential information is already stored on computer files. These include laboratory test results, diagnoses, codes for operations, codes of histopathological diagnoses and maybe even the patient's medication. Accordingly, these databases include much clinical knowledge that would be useful for clinicians. Laboratories try to support clinicians by producing reference values for laboratory tests. It is, of course, necessary information but, however, it does not give very much information about the weight of evidence that an abnormal laboratory test will give in special clinical settings. We have developed a software package - DiagaiD - in order to build a smart link between patient databases and clinicians. It utilizes neural network-based machine learning techniques and can produce decision support which meets the special needs of clinicians. From example cases it can learn clinically relevant transformations from original numeric values to logical values. By using data transformation together with a single layer perceptron it is possible to build nonlinear models from a set of preclassified example cases. In this paper, we use two small datasets to show how this scheme works in the diagnosis of acute appendicitis and in the diagnosis of myocardial infarction. Results are compared with those obtained using logistic regression or backpropagation neural networks. The performance of our neuro-fuzzy tool seemed to be slightly better in these two materials but the differences did not reach statistical significance.