A medical device system and associated method discriminate respiratory and cardiac conditions using respiratory sounds. A sensing module acquires a first signal and a second signal, at least the second signal acquired from an acoustic transducer. A processor is configured to receive the first signal and to control the sensing module to acquire the second acoustic signal in response to a change in the first signal. The processor discriminates between a cardiac condition and a respiratory condition as a cause of the change in the first signal in response to the second acoustic signal.