The US Patent Office issued a patent #9,655,564 titled "Use of machine learning for classification of magneto cardiograms" co-invented by Prof. Boleslaw Szymanski.

The US Patent Number 9,655,564 titled Use of machine learning for classification of magneto cardiograms was granted on May 23, 2017 to investors Dr. Karsten Sternickel of Germany, Prof. Mark Embrechts of RPI and Prof. Boleslaw Szymanski of NeST, RPI.  The patent discloses a method for the use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also disclosed is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering.