To the reliability of medical diagnosis based on empirical data

Some abilities to apply intelligent data analysis (IDA) tools to support medical diagnostic decision-making are discussed. There is described an original mathematical technique to identify and to delete artefacts of IDA and Machine Learning (e.g. overfitting, ets.) to be used in medical diagnostics. This IDA-scheme is based on the reasoning tools of the so called JSM-method of reasoning automation. Productivity of the proposed IDA-techniques demonstrated by examples of diagnostics of human brain tumor pseudoprogression.