Abstract: A method for consolidating heterogenous electronic health data involves obtaining a native message including a multitude of data elements and generating a markup message including the multitude of data elements in a hierarchical structure. The method further involves generating a standardized message that represents the multitude of data elements in a format of a unified electronic health record database by recursively applying a machine learning model to the multitude of data elements, based on the hierarchical structure to determine a mapping between the plurality of data elements in the markup message and the plurality of data elements in the standardized message. The method also involves writing the standardized message to the unified electronic health record database.

Abstract: A method for consolidating heterogenous electronic health data involves obtaining a native message including a multitude of data elements and generating a markup message including the multitude of data elements in a hierarchical structure. The method further involves generating a standardized message that represents the multitude of data elements in a format of a unified electronic health record database by recursively applying a machine learning model to the multitude of data elements, based on the hierarchical structure to determine a mapping between the plurality of data elements in the markup message and the plurality of data elements in the standardized message. The method also involves writing the standardized message to the unified electronic health record database.

Abstract: A method for the detection of a disease comprising the steps of: (i) obtaining a biological sample from a human subject; (ii) applying the biological sample to a sialidase substrate which has been immobilized on a solid support medium; and (iii) detecting a change in the immobilized sialidase substrate is provided. The substrate is preferably 5-bromo-4-chloro-3-indoyl &agr;-D-N-acetyl neuraminic acid or a salt thereof.