Automatic cardiac therapy advisor with hidden markov model processing

An apparatus for automatically determining which type of resuscitation treatment is most appropriate for a patient, the apparatus comprising:

• one or more processors;
• circuitry for delivering time-domain signal measurements from the patient to the one or more processors, wherein the one or more processors configured to:
• transform one or more of the time-domain signal measurements into frequency domain data representative of a frequency content of the time-domain signal measurements,
• process the frequency domain data to form a plurality of spectral bands, a content of each of the plurality of spectral bands representing the frequency content of the time- domain signal measurements within a different frequency band,
• form a weighted sum of the content of the plurality of spectral bands, with different weighting coefficients applied to at least some of the plurality of spectral bands, wherein the weighting coefficients are chosen such that the magnitudes of the weighting coefficients are non-linearly proportional to frequencies of the at least some of the plurality of spectral bands to which the weighting coefficients are applied,
• determine a recommended resuscitation treatment based on the weighted sum, and
• provide an output indication of the recommended resuscitation treatment.