Abstract: A method of analyzing physiological data indicative of myocardial activity is disclosed. The method comprises: identifying in the data a set of N features, each corresponding to a ventricular depolarization, and calculating M time-intervals for each ventricular depolarization feature, thereby providing a vector of N*M time-intervals. The method further comprises fitting the vector to a power density function of time-intervals, and determining possible cardiac arrhythmia based on statistical parameters characterizing the function.

Abstract: A method for diagnosis comprises receiving a signal associated with respiration of a patient. The signal is processed so as to identify features that are indicative of beginning and end times of apnea episodes. Time shifts between recurrences of the features are computed and processed so as to generate an output comprising a plurality of bands corresponding to different multiples of a cycle length of the apnea episodes.

Abstract: A method for diagnosis includes receiving a signal associated with blood oxygen saturation of a patient during sleep. The signal is filtered so as to eliminate signal components at frequencies equal to and greater than a respiratory frequency of the patient. The filtered signal is processed to detect a pattern corresponding to multiple cycles of periodic breathing.

Abstract: A method for diagnosis includes receiving a signal associated with respiration of a patient during sleep, and processing the signal to detect occurrences of a pattern corresponding to multiple cycles of periodic breathing. A cumulative duration of the occurrences is computed, and a prognosis of the patient is determined based on the cumulative duration.

Abstract: A method for diagnosis includes receiving from a sensor coupled to a body of a patient a photoplethysmograph signal, which is indicative of blood flow in the body. The photoplethysmograph signal is processed so as to identify at least one irregularity in a heart rhythm of the patient. A record indicating a time of occurrence of the at least one irregularity is made and processed so as to diagnose a pathological cardiac condition of the patient.

Abstract: A method for diagnosis includes receiving from a sensor coupled to a body of a sleeping patient a photoplethysmograph signal. The photoplethysmograph signal is processed independently of any other physiological measurements in order to identify sleep stages of the patient.

Abstract: Methods and systems that (a) adaptively segment a raw data stream(s) of different type biomedical signals; (b) assign attribute values to each segment; (c) determine an attribute domain based on a point corresponding to said segment attribute value; (d) generate a cluster set(s) in said attribute domain that includes a combination of points; (e) obtain a probability of order of appearance of each cluster point, according to its property value; (f) use said probability to update each point's property value; (g) repeat (d) through (f) while varying combinations of points in clusters according to their most updated property values and points derived from additional raw data stream adaptive segmentations; (h) associate at least one updated cluster with a normal/abnormal physiological state based on reference clusters in said domain; and (i) obtain the change probability between normal/abnormal physiological states using said probability of the order of appearance.

Abstract: A method for diagnosis of a sleep-related condition of a patient having a thorax. The method includes receiving physiological signals from sensors coupled to the thorax of the patient, and analyzing the physiological signals, independently of any electroencephalogram (EEG) or electro-oculogram (EOG) signals, in order to identify sleep stages of the patient.

Abstract: A method and system predicts changes of physiological/pathological states in a patient, based on sampling, processing and analyzing a plurality of aggregated noisy biomedical signals. A reference database of raw data streams or features is generated by aggregating one or more raw data streams. The features are derived from the raw data streams and represent physiological/pathological states. Each feature consists of biomedical signals of a plurality of patients, wherein several patients have one or more of the physiological/pathological states. A path, which is an individual dynamics, between physiological/pathological states is obtained according to their order of appearance. Then, a prediction of being in physiological/pathological states, or transitions to physiological/pathological states in the patient, is obtained by comparing the individual dynamics with known dynamics, obtained from prior knowledge.

Abstract: Methods and systems that (a) adaptively segment a raw data stream(s) of different type biomedical signals; (b) assign attribute values to each segment; (c) determine an attribute domain based on a point corresponding to said segment attribute value; (d) generate a cluster set(s) in said attribute domain that includes a combination of points; (e) obtain a probability of order of appearance of each cluster point, according to its property value; (f) use said probability to update each point's property value; (g) repeat (d) through (f) while varying combinations of points in clusters according to their most updated property values and points derived from additional raw data stream adaptive segmentations; (h) associate at least one updated cluster with a normal/abnormal physiological state based on reference clusters in said domain; and (i) obtain the change probability between normal/abnormal physiological states using said probability of the order of appearance.