A method and system for detection of respiratory variation in pulse oximetry are provided. In one embodiment, the method includes detecting a pattern consistent with a respiratory cycle of a waveform representing cardiac oscillations and identifying an abnormality based on the pattern. The method further includes triggering an alarm in response to identifying an abnormality. A system is further provided including a database and a module. The database to store data representing a physiological condition of a patient over a period of time, wherein the data comprises data corresponding to respiratory activity and data corresponding to cardiac oscillations, wherein the data corresponding to respiratory activity comprises a first waveform and the data corresponding to the cardiac oscillations comprises a second waveform; and a module for detecting a pattern of the second waveform consistent with a cycle of a first waveform and detecting an abnormality in the pattern, wherein when an abnormality is detected an alarm is triggered to alert a health care provider of the abnormality.