Methods and systems to configure and use neural networks in characterizing physiological systems

A method of configuring a convolutional neural network to detect presence of coronary arterial disease or estimate localization of coronary arterial disease in a subject, the method comprising:

• generating, by the processor, a plurality of hyperparameter sets for a template convolutional neural network, wherein each of the plurality of hyperparameter sets is generated by a random, or pseudo-random selection, from a set of hyperparameters, wherein at least one hyperparameter of the set of hyperparameters is selected from the group consisting of:
• batch size, learning rate, convolutional layer, filter size, a number of filter in a first convolutional layer, an increase in filter in subsequent layer, number of additional dense layers, size of additional dense layers, activation function type, target, dilation rate, and dropout;
• training, by the processor, for each of plurality of hyperparameter sets, the template convolutional neural network, wherein in each instance of the evaluation, the template convolutional neural network is configured with a hyperparameter set of the plurality of hyperparameter sets;
• and
• evaluating, by the processor, for each of plurality of hyperparameter sets, the trained deep neural network with a first validation data set, wherein each evaluation generates a score, wherein the trained convolutional neural network is subsequently used to diagnose the presence and/or the localization of coronary arterial disease in the subject.

A system comprising:

• an acquisition device configured to acquire a biophysical signal data set of a subject acquired from one or more channels of one or more sensors;
• and
• an assessment system coupled, directly or indirectly, to said device, the assessment system comprising:
• one or more processors;
• and
• a memory having instructions stored thereon, wherein execution of the instruction by the one or more processors cause the one or more processors to:
• receive the biophysical signal data set from the acquisition device;
• pre-process the biophysical signal data set to generate one or more pre-processed data sets, wherein each pre-processed data set includes a single isolated complete cardiac cycle;
• and
• determine a value indicative of presence of cardiac disease or condition by directly inputting the pre-processed data set to one or more deep neural networks trained with a set of training biophysical signal data set acquired from patients diagnosed with the cardiac disease or condition and labeled with the presence or non-presence of the cardiac disease or condition,
• wherein an output data set is outputted via a report and/or a display based on the determined value indicative of the presence of cardiac disease or condition.