Abstract
Medical data often appear in the form of numerical matrices or sequences. We develop mathematical tools for automatic screening of such data in two medical contexts: diagnosis of systemic lupus erythematosus (SLE) patients and identification of cardiac abnormalities. The idea is first to implement adequate data normalizations and then identify suitable hyperparameters and distances to classify relevant patterns. To this purpose, we discuss the applicability of Plackett-Luce models for rankings to hyperparameter and distance selection. Our tests suggest that, while Hamming distances seem to be well adapted to the study of patterns in matrices representing data from laboratory tests, dynamic time warping distances provide robust tools for the study of cardiac signals. The techniques developed here may set a basis for automatic screening of medical information based on pattern comparison.
Highlights
Medical data often appear in the form of numerical matrices or sequences
Specific vital signals are recorded as time sequences, such is the case of electrocardiograms, for example
We develop mathematical tools for automatic screening of data stored in the form of numerical time sequences or matrices and illustrate the results in two medical contexts: diagnosis of systemic lupus erythematosus (SLE) patients and identification of cardiac abnormalities
Summary
Medical data often appear in the form of numerical matrices or sequences. We develop mathematical tools for automatic screening of such data in two medical contexts: diagnosis of systemic lupus erythematosus (SLE) patients and identification of cardiac abnormalities. We apply clustering techniques to locate relevant time frames and seek specific patterns in the data to select a possible diagnosis, resorting to adequate distances.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have