Abstract: A waveform annotator system allows clinicians to annotate a physiological data waveform, providing initial annotations based on a model corresponding to a type of the physiological data. The initial annotations may be modified by the clinician as desired. The annotations are saved in an annotation database for later use by the clinician and for training the model using machine learning to improve the initial annotations based on the modifications made by the clinician. The trained model may be distributed to other waveform annotator systems.

Abstract: A system for distributed computing allows researchers performing analysis on data having legal or policy restrictions on movement of the data to perform the analysis on data at multiple sites without exporting the restricted data from each site. A primary system determines which sites contain the data to be executed by a compute job and sends the compute job to the associated site. Resulting calculated data can be exported to a primary collecting and recording system. The system allows the rapid development of analysis code for the compute jobs that can be executed on a local data set then passed to the primary system for distributed machine learning on the multiple sites without any changes to the code of the compute job.

Abstract: A user interface for clinical personnel provides selectable views of a plurality of medical risk scores. Questions whose answers are needed for calculation of those risk scores are asked in a question and answer area of the user interface, which allows some questions to be answered based on real time patient physiological data streams that are overridable by user provided answers. Where multiple risk score calculations require answers to the same question, the user provided answer may be supplied as an answer to the corresponding question for each risk score, rather than requiring the user to answer multiple times. Sparklines may be provided with the displayed risk scores to show trends in the risk score values, and may be updated in real time based on real time physiological data streams. The display of risk scores may visually distinguish between risk scores that have been validated and those are based on unvalidated answers to the questions.

Abstract: A waveform annotator system allows clinicians to annotate a physiological data waveform, providing initial annotations based on a model corresponding to a type of the physiological data. The initial annotations may be modified by the clinician as desired. The annotations are saved in an annotation database for later use by the clinician and for training the model using machine learning to improve the initial annotations based on the modifications made by the clinician. The trained model may be distributed to other waveform annotator systems.

Abstract: A programmable architecture specialized for convolutional neural networks (CNNs) processing such that different applications of CNNs may be supported by the presently disclosed method and apparatus by reprogramming the processing elements therein. The architecture may include an optimized architecture that provides a low-area or footprint and low-power solution desired for embedded applications while still providing the computational capabilities required for CNN applications that may be computationally intensive, requiring a huge number of convolution operations per second to process inputs such as video streams in real time.

Abstract: A system for distributed computing allows researchers performing analysis on data having legal or policy restrictions on movement of the data to perform the analysis on data at multiple sites without exporting the restricted data from each site. A primary system determines which sites contain the data to be executed by a compute job and sends the compute job to the associated site. Resulting calculated data can be exported to a primary collecting and recording system. The system allows the rapid development of analysis code for the compute jobs that can be executed on a local data set then passed to the primary system for distributed machine learning on the multiple sites without any changes to the code of the compute job.

Abstract: A user interface for clinical personnel provides selectable views of a plurality of medical risk scores. Questions whose answers are needed for calculation of those risk scores are asked in a question and answer area of the user interface, which allows some questions to be answered based on real time patient physiological data streams that are overridable by user provided answers. Where multiple risk score calculations require answers to the same question, the user provided answer may be supplied as an answer to the corresponding question for each risk score, rather than requiring the user to answer multiple times. Sparklines may be provided with the displayed risk scores to show trends in the risk score values, and may be updated in real time based on real time physiological data streams. The display of risk scores may visually distinguish between risk scores that have been validated and those are based on unvalidated answers to the questions.

Abstract: A graphical user interface of a medical patient monitoring system allows clinical personnel to view and manipulate historical patient data in ways not available in traditional patient monitoring systems. The graphical user interface allows zooming in or out on the historical patient data, with a format of the data adjusted at certain zoom levels. A plurality of lanes of displayed historical patient data may be displayed in the graphical user interface, and a plurality of signals may be displayed in a single lane. An electrocardiogram strip view may be enabled to present historical patient data in the form of a traditional strip view if desired.

Abstract: A programmable architecture specialized for convolutional neural networks (CNNs) processing such that different applications of CNNs may be supported by the presently disclosed method and apparatus by reprogramming the processing elements therein. The architecture may include an optimized architecture that provides a low-area or footprint and low-power solution desired for embedded applications while still providing the computational capabilities required for CNN applications that may computationally intensive, requiring a huge number of convolution operations per seconds to process inputs such as video streams in real time.