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: Existing apnea monitors fail to detect clinically important apnea events because they fail to distinguish cardiac artifacts from a chest impedance signal and therefore fail to detect cessation of breathing. A system and method are disclosed that provides improved apnea detection, particularly in a neonatal setting. The disclosed techniques filter out cardiac artifacts from the chest impedance signal, allowing determining a probability of an apnea event. Detection of an apnea event may then be used to trigger an alarm, initiate automatic physical stimulation of the patient, or both.

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 technique for predicting fluid responsiveness in a critically ill patient comprises measuring physiological data of the patient, then generating an estimate of pulse pressure variability from a Fourier transform of the physiological waveform. Both invasive and non-invasive physiological data measurements may be used.

Abstract: A set of software programs runs in a parallel configuration on local hospital servers. The software gathers all the data directed to it from a hospital patient's data sources (including, but not limited to, data formats from patient monitor devices, HL7 feeds, and other hospital data systems). Data can be time-synchronized, transformed, and routed from both currently networked device and non-networked devices. The data is made available for redisplay and analysis to system users and program agents.

Abstract: A set of applications can access a specific patient's real-time or historical physiological data from a clinical care unit and calculate new disease specific physiological indicators or be a virtual physiological monitor for that patient. The applications are run on a remote server and push the resulting data to an endpoint device.

Abstract: A patient alarm application provides a way for allowing clinical personnel to monitor and control patient-specific alarm settings. A user interface allows clinical personnel to compare graphical representations of unit population vital signs data with patient-specific vital signs data as well timelines of alarms for the patient. Analysis of the alarm data allows the user interface to show clinical personnel the estimated effects of changes to alarm threshold settings.

Abstract: The Alarm Management System allows hospitals and critical care units to manage alarms generated by patient monitors and includes the following components: The Alarm Dashboard provides a display of alarm history and trends categorized as desired by hospital administrators. The Alarm Criticality Discernment Tool assists in distinguishing between critical and non-critical alarms. This Tool can allow a clinician to accommodate patient-specific or doctor-specific rules, alarm thresholds, or exceptions. The Alarm Renderer Tool provides physiological data for a predetermined period before the alarm and upon receiving a patient alarm, allows the alarm and the physiological data displayed visually to be forwarded to a care provider to assist in the determination of the criticality of the alarm. The Alarm Router Tool is a set of rules and editor for routing and escalating unacknowledged alarms to other care providers and recording these events.