ADAPTIVE PREDICTION OF CHANGES OF PHYSIOLOGICAL/PATHOLOGICAL STATES USING PROCESSING OF BIOMEDICAL SIGNALS

摘要

Method and system for predicting 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 and/or features is generated by aggregating one or more raw data streams. The features are derived from the raw data streams and represents physiological/pathological states. Each feature consists of biomedical signals or a plurality of patients wherein several patients have one or more of the physiological/pathological states. The features are obtained by performing, for each type of biomedical signal, adaptive segmentation of its corresponding raw data streams, and by assigning, to each segment, individual attributes that are represented by attribute values in order to obtain data related to each physiological/pathological states. Additional data streams using these attributes are generated and this process is repeated if needed.