Patient monitoring method and system

Abstract

A method of processing wireless sensor data at a server, the method comprising the steps of: receiving sensor data from a plurality of wireless sensors; determining a device type associated with the received sensor data; retrieving and activating at least one processing program for the received sensor data, the at least one processing program comprising a driver configured to process the sensor data into parameterized data; and converting the received data into parameterized data. A method for generating a normalized component risk score based on measurements of one or more physiological parameters of a patient, the method comprising the steps of: receiving sensor data; determining a physiological parameter from the sensor data; determining a normalized component risk score based on the physiological parameter; and outputting the normalized component risk score.

Description

Technical Field

[0001] This disclosure relates in its entirety to the collection and remote processing of data from one or more wireless sensors. More specifically, this disclosure relates to the real-time collection, monitoring, and display of patient data. Background Technology

[0002] In today's healthcare environment, patients may be in a variety of health states due to their underlying medical conditions or controlled surgical interventions. In many cases, patients are monitored to assess their health status, detect early signs of deterioration, and determine the need for changes in treatment. Most patients with unstable health conditions will experience some form of respiratory failure or altered respiratory function.

[0003] Outside of specialized care settings such as the ICU and cardiothoracic care, current existing technologies for monitoring patient health status, and specifically for monitoring respiratory failure or changes in respiratory function, are either through manual observation and estimation (e.g., manually counting breaths to obtain respiratory rate) or through the use of sensors coupled to the patient and monitoring one or more of the patient's physiological parameters. Sensors such as pulse oximeters or heart rate sensors are typically used. Manual monitoring is performed only occasionally, and sensor data checks are performed only intermittently.

[0004] In healthcare settings, patient medical records are typically kept as paper charts at the patient's bedside. Often, to track patient monitoring, healthcare providers manually record data on the patient chart at regular intervals, detailing instantaneous sensor readings and comparing them to previous readings over time. This imposes a significant time constraint on nurses or other healthcare providers.

[0005] Electronic health records are increasingly being used by healthcare providers to provide accurate and up-to-date information about the care an individual is receiving. To provide patients with the best, most coordinated, and most cost-effective healthcare, healthcare providers need constant access to their patients' up-to-date medical histories.

[0006] definition

[0007] Patient: An individual who is receiving treatment for a condition or disease, or who is otherwise monitored for health or health status, which may take place in a typical hospital setting or alternatively in a home or aged care setting. Summary of the Invention

[0008] In a first aspect, this disclosure can be broadly said to include a method for generating a component risk score based on measurements of one or more physiological parameters of a patient, the method comprising the steps of: receiving sensor data; determining the patient's physiological parameters based on the sensor data; determining a component risk score based on the physiological parameters; and outputting the normalized component risk score.

[0009] Optionally, the sensor data may be received via one or more announcement channels of a short-range wireless communication component.

[0010] Optionally, determining the component risk score includes associating at least one of the at least one physiological parameter with a risk interval among a plurality of corresponding risk intervals, each of the plurality of risk intervals having a corresponding first upper limit threshold and a first lower limit threshold, wherein the at least one associated physiological parameter falls between the first upper limit threshold and the first lower limit threshold of the corresponding risk interval.

[0011] Optionally, this component risk score corresponds to a clinical risk index. Optionally, this clinical risk index corresponds to an early warning score.

[0012] Optionally, the physiological parameter may include any one or more of the following: respiratory rate, SpO2 (oxygen saturation), supplemental oxygen, temperature, body temperature, heart rate and systolic blood pressure, and carbon dioxide level.

[0013] Optionally, the supplemental oxygen is determined by sensors on the breathing device and / or sensors integrated into the breathing device.

[0014] Optionally, this risk range corresponds to a predetermined early warning score.

[0015] Optionally, the multiple risk intervals include a first risk interval and a second risk interval.

[0016] Optionally, the size of the first risk interval may differ from the size of the second risk interval.

[0017] Optionally, the size of the risk range is limited by the difference between its first upper limit threshold and its first lower limit threshold.

[0018] Optionally, the physiological parameter may be one of temperature, body temperature, blood pressure, respiratory rate, heart rate, carbon dioxide level, and SpO2 (blood oxygen saturation).

[0019] Optionally, the physiological parameter and the component risk score are stored as a time series.

[0020] Optionally, the physiological parameter and the risk score of the component can be updated in real time.

[0021] Optionally, the risk score for this component can be recalculated at regular time intervals.

[0022] Optionally, the risk score may be recalculated only when new sensor data is received and updated physiological parameters are determined.

[0023] Optionally, the method further includes the following steps: determining a second physiological parameter based on the sensor data; determining a second component risk score based on the second physiological parameter; outputting the second component risk score; and determining a total component risk score based on the first component risk score and the second component risk score.

[0024] Optionally, determining the total component risk score includes selecting the highest component risk score between the first component risk score and the second component risk score as the total component risk score.

[0025] Optionally, determining the total component risk score includes averaging the first component risk score and the second component risk score.

[0026] Optionally, determining the total component risk score includes calculating a weighted average of the first component risk score and the second component risk score, wherein the weighting is based on a predetermined set of rules.

[0027] Optionally, determining the total component risk score includes summing the first component risk score and the second component risk score and comparing the sum with a predetermined threshold.

[0028] Optionally, the method further includes the step of: displaying the component risk score in a first view of the display screen, wherein the component risk score is displayed together with a patient identifier that corresponds to a patient associated with the sensor data and the physiological parameter derived from the sensor data.

[0029] Optionally, the patient identifier may include any one or more of the following: patient name, patient ID, location identifier, and bed identifier.

[0030] Optionally, the component risk score is displayed in the form of an instrument, wherein the instrument divides the multiple risk intervals into segments based on a second upper limit threshold and a second lower limit threshold.

[0031] Optionally, the instrument displays the rolling average of the component risk score.

[0032] Optionally, displaying the component risk score may also include displaying a graphical time series showing the current and historical values ​​of the component risk score.

[0033] Optionally, the method further includes the step of displaying the physiological parameter in the first view of the display screen.

[0034] Optionally, displaying the physiological parameter may also include displaying a graphical time series showing the current and historical values ​​of the physiological parameter.

[0035] Optionally, the graphical time series is updated in real time when the updated value is determined.

[0036] Optionally, the method further includes the following steps: displaying the second physiological parameter; displaying the second component risk score; and displaying the total component risk score.

[0037] Optionally, the display of the first physiological parameter and the second physiological parameter is arranged based on their associated first component risk score and associated second component risk score.

[0038] Optionally, the display of the first physiological parameter and the second physiological parameter is arranged according to the relative contribution of the first physiological parameter and the second physiological parameter to the total component risk score.

[0039] Optionally, the method further includes the steps of: receiving parameters of a therapy provided to the patient by the respiratory support device and / or usage data indicating the patient's use of the respiratory support device; and displaying the therapy parameters and / or the usage data on the display screen.

[0040] Optionally, the therapy parameters and / or the usage data are displayed as a time series and updated in real time.

[0041] Optionally, the method further includes the step of displaying one or more patient identifiers in a second view of the display screen, each patient identifier being associated with a patient and a component risk score; wherein the one or more patient identifiers are arranged on the display screen based on the relative value of their associated component risk scores.

[0042] Optionally, the one or more patient identifiers are grouped into regions of the display, each region being associated with a risk interval among the plurality of risk intervals.

[0043] Optionally, the size and / or relative positioning of the one or more patient identifiers within their area on the display is based on one or more of the rate of change and direction of change of the corresponding component risk score.

[0044] Optionally, when the determined value of the associated component risk score is updated, the arrangement of the one or more patient identifiers is updated in real time.

[0045] Optionally, the one or more patient identifiers are in the form of cards.

[0046] Optionally, each of the one or more patient identifiers includes a risk indicator.

[0047] Optionally, the risk indicator includes a numerical value indicating the patient's risk level based on the patient's component risk score and the associated risk interval.

[0048] Optionally, the risk indicator is updated in real time when the updated value of the component risk score is determined.

[0049] Optionally, this value is a rolling average.

[0050] Optionally, the risk indicator may also include a risk trend indicator configured to change its status based on whether the patient’s risk level is rising, falling, or remaining unchanged.

[0051] Optionally, the risk trend indicator uses color coding.

[0052] Optionally, the one or more patient identifiers may also include a display of one or more physiological parameters associated with the patient, wherein the selection and arrangement of the one or more physiological parameters are based on their contribution to the component risk score.

[0053] Optionally, the display of one or more physiological parameters can be updated in real time.

[0054] Optionally, the display of the one or more physiological parameters includes a rolling average of the one or more physiological parameters.

[0055] Optionally, each of the one or more patient identifiers includes one or more of the following elements: patient identifier number, ward number, bed number, bed location, patient name, and an indication of the time elapsed since the clinician last interacted with the patient.

[0056] Optionally, the presence, size, and / or display parameters of the one or more elements are based on one or more of the following: the magnitude, rate of change, and direction of change of the component risk score.

[0057] Optionally, the presence, size, and / or display parameters of the one or more elements are based on one or more of the following: the amount of time elapsed since the patient identifier moved from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score; and an estimated amount of time elapsed until the patient identifier moved from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score.

[0058] Optionally, the second risk range is a higher risk range than the first risk range.

[0059] Optionally, the estimated time dimension can be provided by analyzing trends in the historical values ​​of the component risk score.

[0060] Optionally, the one or more patient identifiers are grouped into areas of the display, each area being associated with a discharge risk determined at least in part based on the component risk score.

[0061] Optionally, the size and / or relative positioning of the one or more patient identifiers within their area on the display is based on one or more of the rate of change and direction of change of the corresponding component risk score.

[0062] Optionally, when the determined value of the associated component risk score is updated, the arrangement of the one or more patient identifiers is updated in real time.

[0063] Optionally, the one or more patient identifiers are in the form of cards.

[0064] Optionally, each of the one or more patient identifiers includes a discharge risk indicator.

[0065] Optionally, the discharge risk indicator includes a numerical value that indicates the patient's risk level upon discharge based on the patient's component risk score.

[0066] Optionally, the discharge risk indicator is updated in real time when the updated value of the component risk score is determined.

[0067] Optionally, this value is a rolling average.

[0068] Optionally, the discharge risk indicator may also include a discharge risk trend indicator, which is configured to change its state based on whether the patient's discharge risk level increases, decreases, or remains unchanged.

[0069] Optionally, the discharge risk trend indicator uses color coding.

[0070] Optionally, the one or more patient identifiers may also include a display of one or more physiological parameters associated with the patient, wherein the selection and arrangement of the one or more physiological parameters are based on their contribution to the component risk score.

[0071] Optionally, the display of one or more physiological parameters can be updated in real time.

[0072] Optionally, the display of the one or more physiological parameters includes a rolling average of the one or more physiological parameters.

[0073] Optionally, each of the one or more patient identifiers includes one or more of the following elements: patient identifier number, ward number, bed number, patient name, and an indication of the time elapsed since the clinician last interacted with the patient.

[0074] Optionally, the presence, size, and / or display parameters of the one or more elements are based on one or more of the following: the magnitude, rate of change, and direction of change of the discharge risk score and / or the component risk score.

[0075] Optionally, the presence, size, and / or display parameters of the one or more elements are based on one or more of the following: the amount of time elapsed since the patient identifier moved from one area of ​​the display associated with the first discharge risk interval to another area of ​​the display associated with the second discharge risk interval due to a change in the corresponding component risk score; and the estimated amount of time elapsed until the patient identifier moved from one area of ​​the display associated with the first discharge risk interval to another area of ​​the display associated with the second discharge risk interval due to a change in the corresponding component risk score.

[0076] Optionally, the second risk range is a lower risk range than the first risk range.

[0077] Optionally, the estimated time dimension can be provided by analyzing trends in the historical values ​​of the component risk score.

[0078] Optionally, the discharge risk score depends on one or more of the following: patient characteristics, treatment characteristics, and / or socioeconomic factors. Optionally, the patient characteristics include one or more of the following: age, weight, race, and sex. Optionally, the treatment characteristics include one or more of the following: condition, diagnosis, treatment used, treatment device used, and duration of treatment. Optionally, the socioeconomic factors include one or more of the following: the patient's support network and family environment.

[0079] Optionally, the discharge risk may be determined by one or more of the following: a decision tree, a rule engine, or a flowchart.

[0080] Optionally, the display can be configured to switch between showing discharge risk and component risk scores.

[0081] Optionally, the method includes sending an alert to the display.

[0082] Optionally, the method includes displaying summative physiological parameters over multiple time periods.

[0083] Optionally, the summary may include any one or more of the selected value, average, maximum value, minimum value, mean, upper quartile value, lower quartile value, and median value.

[0084] Optionally, the multiple time periods may include integer hours, days, weeks, and / or months.

[0085] Optionally, each of these physiological parameters is displayed on a separate axis.

[0086] Optionally, this summary physiological parameter is presented in the form of a graph.

[0087] Optionally, the chart may include any one or more of the following: radar chart, area chart, lollipop chart, radial bar chart, star chart.

[0088] Optionally, the chart may include at least two time periods.

[0089] Optionally, the chart displays the risk categories corresponding to these physiological parameters.

[0090] Optionally, the chart displays interpolated data between adjacent time periods.

[0091] Optionally, the chart summarizes the data based on stored time-series data.

[0092] In another aspect, this disclosure can be broadly said to include a patient monitoring system configured to perform the methods described above.

[0093] Optionally, the patient monitoring system includes: one or more sensors; and a processing server.

[0094] Optionally, the component risk score is a normalized component risk score and / or includes normalization of the component risk score.

[0095] Optionally, the normalized component risk score is determined by performing feature scaling or min-max normalization on the physiological parameter within the first threshold of the risk interval to provide a measure of the location of the physiological parameter within the first threshold of the risk interval.

[0096] Optionally, determining the normalized component risk score includes standardizing the size of each of the plurality of risk intervals to a preferred size W, wherein each risk interval has a second upper limit threshold and a second lower limit threshold separated by W.

[0097] Optionally, the normalized component risk score can be determined according to the following formula:

[0098]

[0099] In one aspect, this disclosure can be broadly categorized as including a method for monitoring a patient using multiple health sensors to identify patients with deteriorating health, the method comprising: receiving sensor data from the multiple sensors via one or more notification channels of a short-range wireless communication component, the sensor data being based on measurements of an individual patient; determining physiological parameters of the individual patient based on the sensor data; determining a health status based on the physiological parameters; and outputting the health status.

[0100] Optionally, the above-mentioned methods may optionally include any of the steps or features of the foregoing aspects or the following aspects, wherein the health status is a component risk score.

[0101] In one aspect, this disclosure can be broadly categorized as including a method for operating a sensor system to monitor the health of a patient, the method comprising: receiving sensor data from a plurality of sensors via one or more notification channels of a short-range wireless communication component; determining one or more physiological parameters of the patient based on the sensor data from the plurality of sensors; determining a health status based on the physiological parameters; and outputting the health status.

[0102] Optionally, each of the plurality of sensors is associated with, attached to, or capable of being attached to a piece of furniture. Optionally, the furniture includes one or more of a bed and a chair. Optionally, the processing system is operable to identify a patient ID by determining a patient ID associated with the furniture. Optionally, the plurality of sensors includes a sensor under the mattress. Optionally, the sensor includes a sensor under the mattress pad. Optionally, the sensor is a non-contact sensor for respiratory rate and / or heart rate. Optionally, the hub receives transmitted data from the plurality of sensors on an announcement channel.

[0103] Optionally, the above-mentioned methods may optionally include any of the steps or features of the foregoing aspects or the following aspects, wherein the health status is a component risk score.

[0104] In one aspect, this disclosure can be broadly described as including a method for operating a sensor system to monitor the health of a patient, the method comprising: receiving sensor data from a plurality of sensors via one or more notification channels of a short-range wireless communication component, the sensor data indicating one or more physiological parameters of the patient; detecting, based on the sensor data, whether the patient's health parameter is above or below a predetermined threshold; and outputting an indication of the health parameter to a healthcare provider so that the healthcare provider provides treatment to the patient.

[0105] Optionally, detecting whether the patient's health parameter is higher or lower than the predetermined threshold includes comparing two or more different physiological parameters, each of which is obtained from sensor data from the plurality of sensors.

[0106] Optionally, detecting whether the patient's health parameter is higher or lower than the predetermined threshold includes: determining the one or more physiological parameters based on the sensor data; determining the patient's health parameter based on the one or more physiological parameters; and comparing the health parameter with the predetermined threshold.

[0107] Optionally, the above-mentioned methods may optionally include any of the steps or features of the foregoing aspects or the following aspects, wherein the health status is a component risk score.

[0108] In another aspect, this disclosure can broadly include a method for operating a hub for monitoring the health of a patient, the method comprising: receiving a first data packet from a first sensor peripherally to the hub via a first notification channel of a short-range communication component, wherein the first data packet contains sensor data from the first sensor relating to a first physiological measurement of the patient; transmitting the first data packet to a server peripherally to the hub via a network communication component; receiving a second data packet from a second sensor peripherally to the hub via a second notification channel of the short-range communication component, wherein the second data packet contains sensor data from the second sensor relating to a second physiological measurement of the patient; and transmitting the second data packet to the server via the network communication component.

[0109] Optionally, the first notification channel is the same as the second notification channel.

[0110] Optionally, the first notification channel is different from the second notification channel.

[0111] Optionally, the method further includes processing the first data packet at least partially before transmitting the first data packet to the server.

[0112] Optionally, the method further includes formatting the first data packet before transmitting it to the server.

[0113] Optionally, the method also includes adding a timestamp to the first data group.

[0114] Optionally, the method may further include forwarding the raw data and / or unprocessed first sensor data in the first data packet to the server.

[0115] Optionally, the first physiological parameter is the same as the second physiological parameter, and the method further includes combining the first data packet and the second data packet before transmitting the first data packet and the second data packet to the server.

[0116] Optionally, the network communication component is a wireless internet component.

[0117] Optionally, the first data packet is received from the first sensor via the first notification channel in a continuous stream of data packets.

[0118] Optionally, the first data packet and the second data packet may be transmitted to the server simultaneously.

[0119] Optionally, the method further includes receiving a third data packet from a third sensor at the periphery of the hub via a third notification channel of the short-range communication component, wherein the third data packet contains sensor data from the third sensor relating to a third physiological measurement of the patient.

[0120] Optionally, the first data packet includes a patient identifier, and the second data packet includes the patient identifier.

[0121] Optionally, the above-mentioned methods may optionally include any of the steps or features of the foregoing aspects or the following aspects, wherein the health status is a component risk score.

[0122] In another aspect, this disclosure can be broadly described as including a hub for a system for monitoring the health of a patient, the hub comprising: a short-range communication component; a network communication component; a processor; and a memory storing instructions, which, when executed by the processor, cause the processor to: receive a first data packet from a first sensor peripheral to the hub via a first notification channel of the short-range communication component, wherein the first data packet contains sensor data from the first sensor relating to a first physiological measurement of the patient; transmit the first data packet to a server peripheral to the hub via the network communication component; receive a second data packet from a second sensor peripheral to the hub via a second notification channel of the short-range communication component, wherein the second data packet contains sensor data from the second sensor relating to a second physiological measurement of the patient; and transmit the second data packet to the server via the network communication component.

[0123] In another aspect, this disclosure can be broadly categorized as including a system for monitoring the health of a patient, the system comprising: a central hub including a short-range communication component having a plurality of notification communication channels; a first sensor peripheral to the central hub, the first sensor being configured to acquire a measurement of a first physiological parameter of the patient and transmit first data packets to the central hub via a first notification channel of the plurality of notification communication channels, wherein each of the first data packets contains data related to the measurement of the first physiological parameter; and a second sensor peripheral to the central hub and the first sensor, the second sensor being configured to acquire a measurement of a second physiological parameter of the patient and transmit second data packets to the central hub via a second notification channel of the plurality of notification communication channels, wherein each of the second data packets contains data related to the measurement of the second physiological parameter.

[0124] Optionally, the two aspects mentioned above may optionally include any step or feature of the following system, wherein the health status is a component risk score.

[0125] In another aspect, this disclosure can be broadly categorized as including a patient management system comprising: a data management server communicating with a plurality of sensors configured to measure one or more physiological parameters of a plurality of patients, the data management server being configured to: receive sensor data from the plurality of sensors via a network; determine a component risk score for each of the plurality of patients based on the sensor data; assign the plurality of patients to a plurality of groups based at least in part on the component risk score and a plurality of rules; and cause a display to show one or more patient identifiers on a graphical user interface in a first display mode, each patient identifier being associated with one of the plurality of patients and its component risk score; wherein the one or more patient identifiers are arranged on the display screen based on the value of their associated component risk score.

[0126] Optionally, the sensor data may be received via one or more announcement channels of a short-range wireless communication component.

[0127] Optionally, the component risk score can be calculated according to the above and / or the following method steps.

[0128] Optionally, this component risk score corresponds to a clinical risk index.

[0129] Optionally, the physiological parameter may include any one or more of the following: respiratory rate, SpO2 (oxygen saturation), supplemental oxygen, temperature, body temperature, heart rate and systolic blood pressure, and carbon dioxide level.

[0130] Optionally, the one or more patient identifiers are grouped into regions of the display, each region being associated with an upper and lower threshold for the component risk score, the thresholds defining multiple risk intervals.

[0131] Optionally, the size and / or relative positioning of the one or more patient identifiers within their area on the display is based on one or more of the rate of change and direction of change of the corresponding component risk score.

[0132] Optionally, when the determined value of the associated component risk score is updated, the arrangement of the one or more patient identifiers is updated in real time.

[0133] Optionally, the one or more patient identifiers are in the form of cards.

[0134] Optionally, each of the one or more patient identifiers includes a risk indicator.

[0135] Optionally, the risk indicator includes a numerical value indicating the patient's risk level based on the patient's component risk score and the associated risk interval.

[0136] Optionally, the risk indicator is updated in real time when the updated value of the component risk score is determined.

[0137] Optionally, this value is a rolling average.

[0138] Optionally, the risk indicator may also include a risk trend indicator configured to change its status based on whether the patient’s risk level is rising, falling, or remaining unchanged.

[0139] Optionally, the risk trend indicator uses color coding.

[0140] Optionally, the one or more patient identifiers are grouped into regions of the display, each region being associated with an upper and lower threshold for discharge risk, which depends at least in part on the component risk score.

[0141] Optionally, the size and / or relative positioning of the one or more patient identifiers within their area on the display is based on one or more of the rate of change and direction of change of the corresponding component risk score.

[0142] Optionally, when the determined value of the associated component risk score is updated, the arrangement of the one or more patient identifiers is updated in real time.

[0143] Optionally, the one or more patient identifiers are in the form of cards.

[0144] Optionally, each of the one or more patient identifiers includes a discharge risk indicator.

[0145] Optionally, the discharge risk indicator includes a numerical value indicating the patient's discharge risk level based on the patient's component risk score.

[0146] Optionally, the discharge risk indicator is updated in real time when the updated value of the component risk score is determined.

[0147] Optionally, this value is a rolling average.

[0148] Optionally, the discharge risk indicator may also include a risk trend indicator configured to change its status based on whether the patient’s risk level increases, decreases, or remains unchanged.

[0149] Optionally, the discharge risk trend indicator uses color coding.

[0150] Optionally, the one or more patient identifiers may also include a display of one or more physiological parameters associated with the patient, wherein the selection and arrangement of the one or more physiological parameters are based on their contribution to the component risk score.

[0151] Optionally, the display of one or more physiological parameters can be updated in real time.

[0152] Optionally, the display of the one or more physiological parameters includes a rolling average of the one or more physiological parameters.

[0153] Optionally, each of the one or more patient identifiers includes one or more of the following elements: patient identifier number, ward number, bed number, patient name, and an indication of the time elapsed since the clinician last interacted with the patient.

[0154] Optionally, the existence, size, and display parameters of the one or more elements are based on one or more of the following: the magnitude, rate of change, and direction of change of the component risk score.

[0155] Optionally, the presence, size, and / or display parameters of the one or more elements are based on one or more of the following: the amount of time elapsed since the patient identifier moved from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score; and an estimated amount of time elapsed until the patient identifier moved from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score.

[0156] Optionally, the second risk range is a higher risk range than the first risk range.

[0157] Optionally, the estimated time dimension can be provided by analyzing trends in the historical values ​​of the component risk score.

[0158] Optionally, the sensor data is received from a respiratory support device that includes or communicates with the plurality of sensors.

[0159] Optionally, the component risk score is a normalized component risk score.

[0160] In another aspect, this disclosure can be broadly described as including a patient management method comprising: receiving sensor data via a network from a plurality of sensors configured to measure one or more physiological parameters of a plurality of patients; determining a component risk score for each of the plurality of patients; assigning the plurality of patients to a plurality of groups based at least in part on the component risk score and a plurality of rules; and causing a display to show one or more patient identifiers on a graphical user interface in a first display mode, each patient identifier being associated with one of the plurality of patients and its component risk score; wherein the one or more patient identifiers are arranged on the display based on the relative value of their associated component risk scores.

[0161] Optionally, the sensor data may be received via one or more announcement channels of a short-range wireless communication component.

[0162] Optionally, the component risk score can be calculated using any one or more of the method steps outlined above or below, and / or the system outlined above or below can be used.

[0163] Optionally, assigning the multiple patients to multiple groups includes reassigning patients from a first group with an associated risk interval to a second group with a second associated risk interval.

[0164] Optionally, the method further includes the step of generating an alert status if the second associated risk interval is associated with a higher clinical risk than the first risk interval.

[0165] Optionally, this alert status triggers a notification to the hospital's monitoring system.

[0166] Optionally, the warning condition triggers a notification to the secondary display.

[0167] Optionally, the auxiliary display is a portable computing device. Optionally, the portable computing device is associated with the clinician responsible for the reassigned patient.

[0168] Optionally, this component risk score corresponds to a clinical risk index.

[0169] Optionally, the physiological parameter may include any one or more of the following: respiratory rate, SpO2 (oxygen saturation), supplemental oxygen, temperature, body temperature, heart rate and systolic blood pressure, and carbon dioxide level.

[0170] Optionally, the component risk score is a normalized component risk score.

[0171] In another aspect, this disclosure can be broadly said to include a patient management method comprising: receiving sensor data via a network from a plurality of sensors configured to measure one or more physiological parameters of a plurality of patients; determining a component risk score for each of the plurality of patients; selecting patients from the plurality of patients based on an assigned user of the system, assigning the selected patients to a plurality of groups at least in part based on the component risk score and a plurality of rules; and causing a display to show one or more patient identifiers on a graphical user interface in a first display mode, each patient identifier being associated with a selected patient.

[0172] Optionally, the component risk score can be calculated using any one or more of the method steps outlined above or below, and / or the system outlined above or below can be used.

[0173] Optionally, the one or more patient identifiers are arranged on the display screen based on the relative value of their associated component risk scores.

[0174] Optionally, assigning the multiple patients to multiple groups includes reassigning patients from a first group with an associated risk interval to a second group with a second associated risk interval.

[0175] Optionally, the method further includes the step of generating an alert status if the second associated risk interval is associated with a higher clinical risk than the first risk interval.

[0176] Optionally, this alert status triggers a notification to the assigned user.

[0177] Optionally, the alert status triggers a notification to the secondary display for the assigned user.

[0178] Optionally, the selection of a patient from the plurality of patients is also based on the assigned user and / or the location of the display.

[0179] Optionally, the assigned user is a clinician. Optionally, the patient selection is based on the patient being cared for by the assigned user.

[0180] Optionally, the method includes: assigning selected patients to multiple groups based at least in part on the component risk score and multiple rules; and causing a second display to display one or more patient identifiers on a graphical user interface in a second display mode, each patient identifier being associated with the multiple patients.

[0181] Optionally, the component risk score is a normalized component risk score.

[0182] In another aspect, this disclosure can be broadly described as including a method for processing wireless sensor data at a server, the method comprising the steps of: receiving sensor data from a plurality of wireless sensors; determining a device type associated with the received sensor data; retrieving and activating at least one processing program for the received sensor data, the at least one processing program including a driver configured to process the sensor data into parameterized data; and converting the received data into parameterized data.

[0183] Optionally, the device type is determined by the characteristics of the received sensor data and / or the device ID encoded in the received sensor data.

[0184] Optionally, the at least one processing procedure corresponds to the determined device type.

[0185] Optionally, the sensor data includes a continuous stream of data packets.

[0186] Optionally, the method further includes the step of storing parameterized data.

[0187] Optionally, the parameterized data is stored as a time series.

[0188] Optionally, the method further includes the step of determining the event based on the stored parameterized data.

[0189] Optionally, the parameterized data is sensor-independent, wherein measurement data from multiple wireless sensors can be interchanged.

[0190] Optionally, the sensor data received from the plurality of wireless sensors is received from a wireless router, which then forwards the received data to the server.

[0191] Optionally, the wireless router forwards the received data to the server in real time.

[0192] Optionally, the sensor data is from a short-range wireless sensor (optionally Bluetooth). TM (Announcement groups for wireless sensors).

[0193] Optionally, the step of activating the processor includes: determining whether a processor exists for the received sensor data, or instantiating a processor for the received data.

[0194] Optionally, this step of determining the processing procedure includes identifying one or more features of the structure of the sensor data.

[0195] Optionally, this step of determining the processing procedure includes identifying one or more features of a portion of the sensor data.

[0196] Optionally, this portion of the sensor data may include a notification portion.

[0197] Optionally, identifying one or more features includes comparing the structure of the sensor data with multiple known structures.

[0198] Optionally, the method further includes the step of deactivating the processing procedure if no additional sensor data is received within a certain time period.

[0199] Optionally, the method further includes the step of identifying a patient associated with the device.

[0200] Optionally, the method further includes the step of identifying a piece of furniture associated with the device.

[0201] Optionally, the furniture may include one or more of a bed and a chair.

[0202] Optionally, the method further includes identifying a patient associated with the furniture. Optionally, the method further includes determining the location associated with the furniture. Optionally, determining the location includes reading a locator associated with a known location. Optionally, the locator includes an RFID device. Optionally, the location includes an area within a hospital ward. Optionally, the wireless router includes a sensor for sensing the locator. Optionally, the sensor is an RFID reader. Optionally, the locator has a limited range. Optionally, the sensor includes a sensor under the mattress. Optionally, the sensor includes a sensor under the mattress pad. Optionally, the sensor is a non-contact sensor for respiratory rate and / or heart rate.

[0203] Optionally, the method further includes identifying a clinician associated with at least one of the device, the location, and / or the furniture. Optionally, the method further includes updating the clinician and the location associated with the device.

[0204] Optionally, the method also includes associating the wireless router with the furniture.

[0205] Optionally, the method further includes the step of associating the parameterized data with the identified patient.

[0206] Optionally, the received sensor data is associated with a timestamp.

[0207] Optionally, the received sensor data is associated with a timestamp at the router or the server.

[0208] Optionally, each data packet of the received sensor data is associated with a timestamp.

[0209] Optionally, the method further includes the step of associating a timestamp with the received sensor data.

[0210] Optionally, each of the processors is operated within a container, wherein multiple containers are created to process the sensor data from the multiple wireless sensors.

[0211] Optionally, the method further includes a controller configured to monitor the processor and the received sensor data and adjust available processing resources.

[0212] Optionally, prior to this step of determining the device type, the received sensor data is stored in a cache (bus) that allows for the allocation of processing capacity.

[0213] Optionally, the database is a time-series database.

[0214] Optionally, the method also includes obtaining a trust rating for each of the plurality of wireless sensors.

[0215] Optionally, obtaining the trust rating includes any one or more of the following steps: determining a trust rating based on the sensor data; obtaining the trust rating from the processing program; and obtaining the trust rating from the server. Optionally, the method also includes selecting among readings from the plurality of wireless sensors based on the trust rating.

[0216] Optionally, the method further includes comparing sensor data from multiple sensors. Optionally, the method further includes calibrating a sensor with a lower trust rating based on a sensor with a higher trust rating. Optionally, the method further includes determining an accuracy limit for the sensor based on the trust rating.

[0217] Optionally, the method includes calculating a component risk score based on the parameterized data. Optionally, the component risk score may be calculated using any one or more method steps outlined above or below, and / or the system outlined above or below may be used.

[0218] In another aspect, this disclosure can be broadly described as including a method for processing wireless sensor data at a server, the method comprising the steps of: receiving at least one sensor data from a first sensor of a plurality of wireless sensors; identifying a first patient associated with the at least one sensor data; deriving a first parameter from the at least one sensor data; and adding the first parameter from the at least one sensor data to a time-series record in the first patient's medical record.

[0219] Optionally, the method further includes the steps of: receiving at least one sensor data from a second sensor among the plurality of wireless sensors; identifying a second patient associated with the at least one sensor data; deriving a second parameter from the at least one sensor data; and adding the second parameter from the at least one sensor data to a time-series record in the medical record of the second patient.

[0220] Optionally, the first patient and the second patient are the same patient.

[0221] Optionally, the plurality of wireless sensors may include one or more of the following: a respiratory rate sensor, a heart rate sensor, an SpO2 sensor, and a temperature sensor.

[0222] Optionally, the server receives data from the at least one sensor in real time.

[0223] Optionally, identifying the first patient includes the following steps: identifying a piece of furniture associated with the at least one sensor data; and identifying the patient associated with the furniture. Optionally, the furniture is a bed or a chair.

[0224] In another aspect, this disclosure can be broadly described as including a method for collecting data from a plurality of wireless sensors, the method comprising the steps of: associating each of the plurality of wireless sensors with a patient; receiving sensor data from one of the plurality of wireless sensors at a server; identifying the patient associated with the sensor data; processing the sensor data to identify at least one parameterized data; and associating the at least one parameterized data with the patient.

[0225] Alternatively, the patient may be associated with the sensor via scanning technology.

[0226] Optionally, the method further includes the step of storing the parameterized data in the patient's electronic medical record, wherein the electronic measurement records include a time-series database.

[0227] Optionally, the sensor data can be received in real time.

[0228] Optionally, the plurality of wireless sensors may include one or more of the following: a respiratory rate sensor, a heart rate sensor, an SpO2 sensor, and a temperature sensor.

[0229] Optionally, identifying the first patient includes the following steps: identifying a piece of furniture associated with the at least one sensor data; and identifying the patient associated with the furniture. Optionally, the furniture is a bed or a chair.

[0230] Optionally, the component method may use the system outlined above and / or below and / or include any method steps outlined above or below.

[0231] In another aspect, this disclosure can be broadly said to include a method for processing wireless sensor data at a server, the method comprising the steps of: receiving sensor data from one of a plurality of wireless sensors; determining device characteristics of the received data; processing the received data into parameterized data based on the device characteristics; and storing the parameterized data.

[0232] Optionally, the method further includes the steps of: determining a patient ID associated with the received data; and associating the parameterized data with the patient ID. Optionally, determining the patient ID includes: determining a bed ID or chair ID associated with the wireless sensor data; and determining the patient ID associated with the bed ID or chair ID.

[0233] Optionally, one of the multiple wireless sensors includes one or more of the following: a temperature sensor, a respiratory rate sensor, a heart rate sensor, an SpO2 sensor, a carbon dioxide sensor, and a blood pressure sensor.

[0234] Optionally, the device is characterized by a sensor type or sensor manufacturer.

[0235] Optionally, the method further includes the step of determining a driver for interpreting the sensor data.

[0236] Alternatively, the driver may be determined based on the characteristics of the device.

[0237] Optionally, the sensor data comes from short-range wireless communication, and the server receives the sensor data via long-range wireless communication.

[0238] Optionally, the short-range wireless communication is Bluetooth. TM And / or the long-distance wireless communication is TCP / IP.

[0239] Optionally, the method also includes temporarily storing the received sensor data before determining the characteristics of the device.

[0240] Optionally, the method also includes temporarily storing the processed data before storing the parameterized data.

[0241] Alternatively, the temporary storage device may include a bus or a cache.

[0242] Optionally, the sensor data can be received in real time.

[0243] Optionally, the plurality of wireless sensors may include one or more of the following: a respiratory rate sensor, a temperature sensor, a heart rate sensor, an SpO2 sensor, a carbon dioxide sensor, and a blood pressure sensor.

[0244] Optionally, the method includes calculating a component risk score based on the parameterized data. Optionally, the component risk score may be calculated using any one or more method steps outlined above or below, and / or the system outlined above or below may be used.

[0245] In another aspect, this disclosure can be broadly categorized as including a processing system for processing measurement results from multiple sensors to an electronic patient record with an associated patient ID, the processing system comprising: a processing server that communicates data with a hub, the hub being operable to receive transmissions from the multiple sensors; and one or more databases for storing the multiple electronic patient records therein; wherein the processing system is operable to: receive sensor data from one of the multiple sensors via the hub; identify the sensor that transmitted the sensor data; identify the patient ID associated with the sensor; determine at least one parameterized data based on the sensor data; and store the parameterized data in at least one electronic patient record in the electronic patient record.

[0246] Optionally, the system also includes a medical device for providing treatment to a patient associated with the patient ID, wherein the processing system is further configured to: receive one or more treatment parameters from the medical device via the hub, identify the patient ID associated with the medical device and / or the treatment parameters, and store the received treatment parameters in at least one electronic patient record in the electronic patient record.

[0247] Optionally, the therapeutic parameters include one or more of the flow rate, humidity, and O2 fraction of the gas stream delivered to the patient.

[0248] Optionally, the plurality of sensors includes wearable sensors that can be mounted on the patient.

[0249] Optionally, the server receives the sensor data from the hub in real time.

[0250] Optionally, the plurality of sensors may include one or more of the following: a respiratory rate sensor, a temperature sensor, a heart rate sensor, an SpO2 sensor, a carbon dioxide sensor, and a blood pressure sensor.

[0251] Optionally, the hub is associated with, attached to, or capable of being attached to a piece of furniture. Optionally, the furniture includes one or more of a bed and a chair. Optionally, the processing system is operable to identify a patient ID by determining a patient ID associated with the furniture. Optionally, the hub includes a sensor for sensing the locator. Optionally, the sensor is an RFID reader. Optionally, the sensor has a limited range.

[0252] Optionally, the sensor includes an under-mattress sensor. Optionally, the sensor includes an under-padded sensor. Optionally, the sensor is a non-contact sensor for respiratory rate and / or heart rate. Optionally, the hub receives transmitted data from the plurality of sensors on an announcement channel.

[0253] Optionally, the method includes calculating a component risk score based on the parameterized data. Optionally, the component risk score may be calculated using any one or more method steps outlined above or below, and / or the system outlined above or below may be used.

[0254] In another aspect, this disclosure can be broadly categorized as including a system for processing patient measurements, the system comprising: a plurality of wireless sensors; one or more databases for storing a plurality of electronic patient records therein, each patient record being associated with a patient ID; a hub configured to receive wireless transmissions from the plurality of wireless sensors; and a processing server operable to: receive a wireless transmission from one of the plurality of sensors via the hub; identify the sensor that transmitted the wireless transmission; identify the patient ID associated with the sensor; determine at least one parameterized data based on the wireless transmission; and store the parameterized data in at least one electronic patient record in the electronic patient record.

[0255] Optionally, the system also includes a medical device for providing treatment to a patient associated with the patient ID, wherein the hub is further configured to receive one or more treatment parameters from the medical device, and the processing server is also operable to identify the patient ID associated with the medical device and / or the treatment parameters, and store the received treatment parameters in at least one of the electronic patient records.

[0256] Optionally, the therapeutic parameters include one or more of the flow rate, humidity, and O2 fraction of the gas stream delivered to the patient.

[0257] Optionally, the processing server is also capable of: retrieving and activating at least one processor, the at least one processor including a driver configured to process the wireless transmission into the at least one parameterized data.

[0258] Optionally, the at least one processing program is associated with the sensor that transmits the wireless transmission.

[0259] Optionally, the sensor that transmits the wireless transmission can be identified by the characteristics of the wireless transmission and / or the device ID encoded in the wireless transmission.

[0260] Optionally, the wireless transmission includes a continuous stream of data packets.

[0261] Optionally, the parameterized data is stored as a time series.

[0262] Optionally, the processing server can also operate to: determine events based on the parameterized data.

[0263] Optionally, the hub forwards the wireless transmission to the server in real time.

[0264] Optionally, the wireless transmission is a short-range wireless sensor (optionally Bluetooth). TM (Announcement groups for wireless sensors).

[0265] Optionally, the processing server receives the sensor data from the hub in real time.

[0266] Optionally, the plurality of wireless sensors may include one or more of the following: a respiratory rate sensor, a heart rate sensor, an SpO2 sensor, a carbon dioxide sensor, and a blood pressure sensor.

[0267] Optionally, the processing server can also operate to: determine whether a processing program exists for the received wireless transmission, or instantiate a processing program for the received wireless transmission.

[0268] Optionally, the processing server can also operate to identify one or more features of the structure of the received wireless transmission.

[0269] Optionally, the processing server can also operate to identify one or more features of a portion of the received wireless transmission.

[0270] Optionally, this portion of the received wireless transmission may include an announcement portion.

[0271] Optionally, the processing server can also operate to compare the structure of the received wireless transmission with a plurality of known structures.

[0272] Optionally, the processing server can also be operated to deactivate the processing procedure if no additional wireless transmission is received within a certain period of time.

[0273] Optionally, the hub is associated with, attached to, or capable of being attached to a piece of furniture. Optionally, the furniture includes one or more of a bed and a chair. Optionally, the processing system is operable to identify a patient ID by determining a patient ID associated with the piece of furniture. Optionally, the piece of furniture has a furniture ID. Optionally, the hub includes a sensor for sensing the locator. Optionally, the sensor is an RFID reader. Optionally, the sensor has a limited range.

[0274] Optionally, the plurality of sensors includes a sensor under the mattress. Optionally, the sensor includes a sensor under the mattress pad. Optionally, the sensor is a non-contact sensor for respiratory rate and / or heart rate. Optionally, the hub receives transmitted data from the plurality of sensors on an announcement channel.

[0275] In another aspect, this disclosure can be broadly said to include a wireless sensor configured to transmit over at least one announcement channel or wireless communication system, the wireless communication system including: a first frequency bandwidth announcement channel; and a second frequency bandwidth data channel, wherein the wireless sensor is configured to sense values ​​and broadcast the sensed values ​​over the at least one announcement channel.

[0276] Optionally, the system may also include one or more of the following: a respiratory rate sensor, a temperature sensor, a heart rate sensor, an SpO2 sensor, a carbon dioxide sensor, and a blood pressure sensor.

[0277] In another aspect, this disclosure can be broadly described as including a method for transmitting sensor measurement results from a wireless sensor having at least one announcement channel or mode and at least one data channel or mode, the method comprising transmitting the sensed measurement results on the at least one announcement channel or mode.

[0278] Optionally, the method further includes the step of: optionally encrypting the sensed measurement results using ChaCha encoding or Diffie-Hellman encoding.

[0279] Optionally, the sensed measurement results are sent as part of a notification packet, which includes the sensed measurement results and a device identification portion.

[0280] Optionally, the sensed measurement results are sent as a continuous stream of data packets.

[0281] Optionally, the method includes calculating a component risk score based on parameterized data. Optionally, the component risk score may be calculated using any one or more method steps outlined above or below, and / or the system outlined above or below may be used.

[0282] In another aspect, this disclosure can be broadly categorized as including a system for processing patient measurement results, the system comprising: a plurality of wireless sensors having at least one notification channel or mode and at least one data channel or mode, wherein the wireless sensors are configured to transmit sensor data on the at least one notification channel or mode; a hub configured to receive the sensor data from the plurality of wireless sensors via the at least one notification channel or mode; and a processing server operable to: receive the sensor data from one of the plurality of wireless sensors via the hub; identify the sensor that transmitted the sensor data; determine at least one parameterized data based on the sensor; and store the parameterized data.

[0283] Optionally, any of the above systems and / or methods further includes the step of: displaying the parameterized data on a display screen in a first view, wherein the parameterized data is displayed together with a corresponding patient identifier.

[0284] Optionally, the patient identifier may include any one or more of the following: patient name, patient ID, location identifier, and bed identifier.

[0285] Optionally, two or more patient identifiers and associated parameterized data may be displayed in this first view.

[0286] Optionally, the displayed patient identifier depends on any one or more of the following: the registered user of the display, the location of the display, and / or the registered location of the display. Optionally, the registered location of the display includes a room or ward in a hospital.

[0287] Optionally, when a patient identifier is selected, a second view is displayed on the screen, which includes the current and historical values ​​of the parameterized data for the corresponding patient as a time series.

[0288] Optionally, the second view also includes a component risk score indicator that characterizes the patient’s risk of deterioration based on at least a portion of the available parametric data.

[0289] Optionally, this component risk score corresponds to a clinical risk index and / or an early warning score.

[0290] Optionally, the component risk score indicator is provided in the form of an instrument, wherein the instrument is segmented according to a threshold in the corresponding parameterized data.

[0291] Optionally, the threshold corresponds to the integer value of the component risk score.

[0292] Optionally, any of the systems described above may further include a display system configured to display the parameterized data on a display screen in a first view, wherein the parameterized data is displayed together with the corresponding patient identifier.

[0293] Optionally, the patient identifier may include any one or more of the following: patient name, patient ID, location identifier, and bed identifier.

[0294] Optionally, two or more patient identifiers and associated parameterized data may be displayed in this first view.

[0295] Optionally, the system is configured to receive a selection of a patient identifier and, upon detecting such selection, display a second view on the screen, the second view including the current and historical values ​​of the parameterized data of the corresponding patient as a time series.

[0296] Optionally, the display screen is configured to display a component risk score indicator characterizing the patient's risk of deterioration, based on at least a portion of the available parametric data, as part of the second view.

[0297] Optionally, the component risk score indicator indicates the value of one or more parameterized data relative to one or more thresholds.

[0298] Optionally, one or more thresholds can be customized by the user or clinician.

[0299] Optionally, alarm conditions are set based on the values ​​of the one or more parameterized data relative to one or more thresholds.

[0300] Optionally, the component risk score indicator is provided in the form of an instrument, wherein the instrument is segmented according to a threshold in the corresponding parameterized data.

[0301] Optionally, the threshold corresponds to the integer value of the component risk score.

[0302] Optionally, the component risk score is a normalized component risk score.

[0303] In another aspect, this disclosure can be broadly said to include an electronic device comprising: a touch-sensitive display; one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including instructions for performing steps of any of the methods described above.

[0304] In another aspect, this disclosure can be broadly said to include a hospital bed comprising: a hub operable to receive transmissions from multiple sensors associated with the hospital bed and / or a patient associated with the hospital bed, the hub being configured to transmit measurement results from the multiple sensors to a processing system.

[0305] Optionally, the hub forwards raw sensor data to the processing system. Optionally, the hub includes a position sensor configured to sense the position of the hospital bed. Optionally, the position sensor includes an RFID reader configured to read RFID sensors.

[0306] Alternatively, the bed may be a hospital bed.

[0307] Optionally, the processing system is configured to process the measurement result into an electronic patient record. Optionally, the processing system includes: a processing server that communicates with one or more databases for storing multiple electronic patient records; wherein the processing system is operable to: receive data via the hub; identify the sensor transmitting the sensor data; identify a patient ID associated with the sensor; determine at least one parameterized data based on the sensor data; and store the parameterized data in at least one electronic patient record within the electronic patient record.

[0308] Optionally, the bed includes one or more sensors.

[0309] Optionally, the one or more sensors include non-contact sensors for sensing physiological parameters.

[0310] Optionally, the one or more sensors include under-mattress sensors configured to sense physiological parameters.

[0311] Optionally, the physiological parameter may include any one or more of the following: respiratory rate, SpO2 (oxygen saturation), supplemental oxygen, temperature, body temperature, heart rate and systolic blood pressure, and carbon dioxide level.

[0312] Optionally, the patient parameters include respiratory rate and heart rate.

[0313] In another aspect, this disclosure can be broadly said to include a patient monitoring system comprising a data management server that communicates with a hub wirelessly coupled to a plurality of sensors configured to measure one or more physiological parameters of a plurality of patients, the data management server being configured to receive sensor data from the plurality of sensors via the hub; wherein at least one of the plurality of sensors includes at least one non-contact sensor configured to measure at least one of respiratory rate and heart rate, and wherein the hub is configured to transmit the sensor data to the data management server, and the data management server is configured to convert the received sensor data into parameterized data.

[0314] Optionally, one or more of the multiple sensors are associated with and / or coupled to a piece of furniture. Optionally, the piece of furniture is a hospital bed or chair. Optionally, the piece of furniture is associated with a patient. Optionally, a patient ID is used.

[0315] Optionally, the one or more sensors include an under-mattress sensor.

[0316] Optionally, the patient management system is used in one or more of the following settings: a hospital or a home environment. Optionally, the patient management system is used in a hospital's intensive care unit.

[0317] Optionally, the system is configured to allow one or more additional sensors to connect to the hub and the data management server.

[0318] Optionally, the data management system is configured to calculate component risk scores based at least in part on the parameterized data.

[0319] Optionally, the one or more sensors include any one or more of the following: a respiratory rate sensor and a heart rate sensor.

[0320] Optionally, the one or more sensors may include multiple types of sensors, each type of sensor being configured to sense different physiological parameters.

[0321] Optionally, these sensors include sensors for one or more of the following: respiratory rate, SpO2 (oxygen saturation), supplemental oxygen, temperature, body temperature, heart rate and systolic blood pressure, and carbon dioxide level.

[0322] Optionally, the component method may use the system outlined above and / or below and / or include any method steps outlined above or below.

[0323] Features from one or more aspects or configurations can be combined with features from one or more other aspects or configurations.

[0324] As used in this article, the plural form of a noun refers to the plural and / or singular forms of that noun.

[0325] As used herein, the term “and / or” means “and” or “or”, or, where the context allows, “and” or “or”.

[0326] The term "comprising" as used in this specification means "at least partially comprising". When interpreting each statement containing the term "comprising" in this specification, features other than the one or more features following that term may also be present. Related terms such as "comprising" and "including" will be interpreted in the same manner.

[0327] References to the numerical ranges disclosed herein (e.g., 1 to 10) also include references to all rational numbers within that range (e.g., 1, 1.1, 2, 3, 3.9, 4, 5, 6, 6.5, 7, 8, 9, and 10) and any ranges of rational numbers within that range (e.g., 2 to 8, 1.5 to 5.5, and 3.1 to 4.7), and therefore, all subranges of all ranges explicitly disclosed herein are hereby explicitly disclosed. These are merely examples of a particular intent, and all possible combinations of numerical values ​​between the enumerated minimum and maximum values ​​are considered to be explicitly stated in a similar manner in this application.

[0328] This disclosure can be broadly defined to include any portion, element, and feature individually or jointly referenced or indicated in the specification of this application, as well as any or all combinations of any two or more of the said portions, elements, and features.

[0329] When a particular integer having a known equivalent value in the art as described herein is referred to herein, such known equivalent value is considered to be incorporated herein as if it were described separately.

[0330] This disclosure includes the foregoing and also envisions the following constructions, which are given as examples only. Attached Figure Description

[0331] Specific aspects and modifications will become apparent to those skilled in the art from the detailed description of the following figures, in which:

[0332] Figure 1 A patient monitoring system 10 according to one aspect of this disclosure is illustrated.

[0333] Figure 2 An example is a bed locator system installed in a room of the facility.

[0334] Figure 3An example is shown of the preprocessing server portion of a patient monitoring system 10 according to one aspect of this disclosure.

[0335] Figure 4 An example is shown of the post-processing server portion of a patient monitoring system 10 according to one aspect of this disclosure.

[0336] Figure 5 This is a flowchart illustrating a method performed at a router according to one aspect of this disclosure.

[0337] Figure 6 This is a flowchart illustrating a method according to one aspect of this disclosure.

[0338] Figure 7 This is a flowchart illustrating a method according to one aspect of this disclosure.

[0339] Figure 8 This is a flowchart illustrating a data collection method according to one aspect of this disclosure.

[0340] Figure 9 and Figure 10 The elements of the graphical user interface provided on the screen of the display system are shown.

[0341] Figure 11 and Figure 12 An exemplary early warning scoring form for the early warning scoring system for adults used in New Zealand since 2021 is shown.

[0342] Figure 13 The elements of the graphical user interface provided on the screen of the display system are shown.

[0343] Figure 14 This diagram illustrates how component risk scores and clinical risk indices can be based on patient data.

[0344] Figure 15 Exemplary early warning score categories and their corresponding ranges for normalized clinical risk indices are shown.

[0345] Figure 16 The patient view shows the monitored patient data and component risk scores.

[0346] Figure 17 A patient view with multiple real-time patient data readings and component risk scores is shown.

[0347] Figure 18 Real-time patient data for each time period is displayed.

[0348] Figure 19 A radar chart showing patient data at different times is presented.

[0349] Figure 20 Group views of multiple monitored patients are shown, with each group view represented by a card.

[0350] Figure 21 It shows Figure 20 Example cards.

[0351] Figure 22 and Figure 23 The group view shows the sections and the cards are scaled for emphasis.

[0352] Figure 24 This shows a segment of the group view where the display of cards has been adjusted based on the risk range.

[0353] Figure 25 A group view of multiple patients considering discharge is shown, with each patient represented by a card. Detailed Implementation

[0354] While certain aspects and examples are disclosed herein, the subject matter of the invention extends beyond the specifically disclosed aspects to other alternative aspects and / or uses, and to modifications and equivalents thereof. Therefore, the scope of the claims or aspects appended herein is not limited to any of the particular aspects described herein. For example, in any method or process disclosed herein, the actions or operations of the method or process may be performed in any suitable order and are not necessarily limited to any particular disclosed order. Various operations may be described sequentially as multiple discrete operations in a manner that may aid in understanding certain aspects; however, the order of description should not be construed as implying that these operations are sequentially dependent. Additionally, some structures described herein may embody integrated components or individual components. For comparison of the various aspects, certain aspects and advantages of these aspects are described. Not all such aspects or advantages are necessarily achieved through any particular aspect. Thus, for example, various aspects may be implemented in a manner that achieves or optimizes one or a set of advantages as taught herein, without necessarily achieving other aspects or advantages as otherwise taught or suggested herein.

[0355] It should be emphasized that many variations and modifications can be made to the aspects described herein, and elements of these variations and modifications should be understood to fall within other acceptable examples. All such modifications and variations are intended to be included within the scope of this disclosure and protected by the following claims. Furthermore, nothing in the foregoing disclosure is intended to imply that any particular component, feature, or process step is necessary or essential. In some aspects, the process or method steps described herein are implemented by the disclosed system. In some aspects, the system described herein implements one or more of the disclosed methods and processes.

[0356] System Overview

[0357] Figure 1 A system is shown that provides monitoring of one or more patients in a hospital or home setting. The locations of these patients may be referred to as facilities, encompassing hospitals, medical facilities, or homes. Aspects of this disclosure constitute at least a part of the system. In short, the system collects patient data from multiple sensors 20 and subsequently transmits that data to one or more processing servers 40 via an intermediate router and / or hub 30. The terms "hub" and "router" may be used interchangeably to refer at least to a device configured to receive wireless communications from sensors and send communications to servers.

[0358] Sensor 20 may include patient-worn sensors, sensors mounted to furniture 22 (such as hospital bed 1), and / or non-contact sensors. Sensors 20, 22 may be attached to or part of a therapy device 21. For example, these sensors may be attached to or part of a respiratory support device or respiratory therapy device. For example, the respiratory support device or therapy device may be a high-flow therapy device for anesthesia or sedation (e.g., Airvolumetric). TM 2 or Airvo TM 3) Or a humidifier or THRIVE TM Therapeutic devices. This system can also communicate with surgical humidifiers or other gas delivery or gas regulation devices used during surgical procedures, anesthesia, or sedation. These sensors can include different types of sensors configured to measure various physiological parameters. In a specific aspect, the system is configured to monitor a patient's respiratory health, as this is often an indicator of other health problems / diseases. Furthermore, respiratory distress or failure often triggers patient transfer to intensive care, which requires significant resources and reduces the quality of patient care, compared to earlier treatment of health problems / diseases.

[0359] Conventional systems rely on patient self-reporting, healthcare practitioners performing regular vital sign measurements, and / or sensor information collected in various ways. However, patients are often unaware that their condition is deteriorating until they require intensive care or higher levels of care. Similarly, regular vital sign measurements provide only a limited, general picture of the patient's condition and only draw attention after the patient requires intensive care or higher levels of care. Furthermore, the different collection of information from sensors (e.g., blood pressure sensors, cardiac monitors, temperature sensors, respiratory monitors, etc.) can limit the availability of information from any single sensor (e.g., available only to a practitioner in the room) and / or provide an incomplete picture of the patient's health status (e.g., when the practitioner cannot see information from multiple sensors simultaneously).

[0360] Specifically, conventional sensors all output in different formats for display on different devices at the patient's location and / or in different user interfaces. Each device may have a proprietary format or communication protocol requiring the ability to independently monitor and limit combined measurement data. Furthermore, the sheer number of sensors in the facility necessitates extensive collection and processing of potentially interfering signals. Each of these technical limitations can force healthcare practitioners to respond only to critical needs and negatively impact the quality of care received by patients and / or treatment outcomes. For example, delaying care until intensive care or higher levels of care can negatively affect a patient's ability to recover from their health condition / illness. Moreover, higher levels of care require significant resources, diverting the attention of healthcare practitioners and / or available space in the healthcare facility away from other patients. In some cases, the system and / or method offers an open architecture that allows for easy addition or removal of sensors. In some cases, the system and / or method also allows hospitals to apply their own monitoring protocols and / or custom system protocols, monitoring protocols, and / or output displays. An open architecture can allow for the implementation of custom monitoring protocols in a simple and centralized manner. For example, because raw sensor data is processed at the server, only the server processing and / or procedures need to be adjusted or customized to change the system and / or method.

[0361] In some cases, to overcome these technical limitations of conventional systems, the systems and methods disclosed herein can help allow healthcare providers to detect early-stage deterioration in a patient's respiratory health, thereby enabling rapid and timely intervention by the chief clinician. For example, the systems and methods disclosed herein can use multiple sensors 20 to continuously (or nearly continuously) monitor various vital signs (e.g., respiratory health and / or cardiac health, etc.). Data from multiple sensors 20 can help detect respiratory deterioration at an early stage (e.g., once a change in respiratory health has occurred), reducing (or eliminating) the need for self-reporting from patients and providing an important supplement to periodic vital sign measurements. Accordingly, early identification can allow healthcare providers to initiate treatment for respiratory distress / illness significantly earlier, which can help avoid the need to elevate the patient to intensive care (or other high-level care). Therefore, the systems and methods disclosed herein are expected to help improve patient outcomes and help reduce the resource requirements associated with treating patients, thereby allowing healthcare providers to have more bandwidth and / or resources to treat other patients.

[0362] Furthermore, as discussed in more detail below, the disclosed systems and methods enable the efficient collection, storage, processing, and / or analysis of data from multiple sensors 20 at a central location. For example, the systems and methods disclosed herein can use multiple sensors 20 to collect raw patient-related data and / or use a router 30 to collect raw data from the multiple sensors 20. More specifically, in some cases, the multiple sensors 20 and the router 30 can use short-range wireless communication protocols (e.g., Bluetooth). TM The system communicates via an advertisement channel. Using an advertisement channel to transmit data allows any number of sensors to communicate with router 30 without requiring dedicated channels, dedicated connections, and / or specified data formats. Therefore, the systems and methods disclosed herein allow a larger number and / or a wider variety of sensors to communicate with router 30. Additionally or alternatively, router 30 and each of the multiple sensors 20 require less power because router 30 and the multiple sensors 20 do not need to maintain a continuous connection with each other. In some cases, using advertisement signals or packets to transmit (optionally encoded) sensor data reduces the power consumption and / or bandwidth consumption of the sensors and / or hubs. This means that sensors and / or hubs use less power or require a smaller power supply to operate, and the system is easier to use due to the reduced need for charging.

[0363] Additional or alternatively, additional sensors may be added specifically to tailor monitoring to the healthcare needs of a particular patient without interrupting the network and / or requiring network updates to accommodate these additional sensors. After router 30 receives data from multiple sensors, router 30 may forward the data to processing server 40. In one aspect, router 30 passes the raw data directly to processing server 40 without caching or performing any other processing on the data or along with it. This allows the data to be forwarded (and ultimately displayed) in real-time or near real-time, providing a higher resolution view of the patient's health status. Processing server 40 processes the raw sensor data to produce parameterized data, which is then stored and added to the patient's electronic medical record and optionally displayed on a screen as part of the patient monitor hardware in a hospital or home environment.

[0364] Therefore, the systems and methods described herein are expected to reduce the resource requirements for accommodating multiple sensors 20. Furthermore, compared to conventional systems, the systems and methods described herein allow for the collection, processing, display, and / or analysis of data from various sensors at a central location.

[0365] Detailed description of system components and operations

[0366] The configuration and operation of the system will now be described in further detail.

[0367] In one aspect, multiple sensors 20 are configured to monitor the patient and generate sensor data indicative of the patient's condition. These sensors may be referred to as health sensors because they measure patient physiological parameters that indicate the patient's health. These parameters can indicate improvement or deterioration in the patient's health.

[0368] In one aspect, the plurality of sensors includes one or more of a respiratory rate sensor, a temperature sensor, a heart rate sensor, and a SpO2 sensor, provided in the form of one or more wearable sensors that can be mounted on a patient, noting that respiratory distress is often a key indicator of deteriorating patient health. In another aspect, the plurality of sensors 20 may include one or more sensors disposed in or under a piece of furniture, for example, under the mattress or chair of a patient's hospital bed. These sensors may be able to determine one or more physiological parameters of the patient, such as respiratory rate and heart rate. For example, a cardiac impactor allows for the measurement of heart rate and / or respiratory rate without contact with the patient's body. Those skilled in the art will understand that any suitable sensors can be incorporated into the plurality of sensors 20, provided they operate as described below.

[0369] The benefits of using one or more sensors under a patient's mattress include improved patient comfort by eliminating the need for additional sensors to measure parameters. Furthermore, healthcare providers save time by not needing to attach any corresponding sensors to the patient and avoid the risk of forgetting to attach sensors or the sensors accidentally detaching from the patient. Sensors placed under the mattress are also more hygienic and do not require replacement or cleaning between different patients occupying the bed. Attaching non-contact sensors to a piece of furniture also reduces sensor movement and measurement errors associated with poor patient-sensor attachment. In some cases, this also improves patient compliance because the sensors do not require patient input and are simply part of the furniture. This means, for example, that no attachment or movement is required to connect the patient to the bed or its location.

[0370] In conventional systems, inaccurate sensors can distort a healthcare provider's interpretation of the data, requiring the provider to perform multiple measurements with the same sensor during periodic vital sign measurements, or to rely on inaccurate sensors. To overcome this deficiency in current technology, multiple sensors 20 can include more than one sensor sensing the same parameter, wherein system 10 is configured to average the data to determine the measured parameter or select data from the sensor with the highest quality data (e.g., lowest noise signal). Alternatively, system 10 can prioritize measurements from selected and / or trusted sensors. Even if the underlying technologies may be similar, the accuracy and reliability of sensors can vary significantly, for example, between manufacturers and models. In other cases, different sensors 20 will provide more accurate results based on different technologies, tolerances, or accuracy levels (e.g., an electrocardiogram will generally be more accurate than a pulse oximeter). By prioritizing more accurate sensors, the performance of system 10 is improved because more accurate data is available.

[0371] In one aspect, system 10 obtains a rating for each sensor 20 (e.g., a rating of sensor accuracy, or the confidence level of a sensor value). This rating may be provided in the signal from the sensor 20, or may be obtained (e.g., through the sensor's processing program) in a processing server, or may be obtained, for example, from a database. This rating system creates a hierarchy of sensors 20 based on available sensors and the rating of each sensor. This hierarchy ensures the use of the most accurate information. The sensor with the highest rating can then be used to determine the most accurate sensor value. Where multiple sensors are available, system 10 may also monitor the accuracy of less accurate sensors. This monitoring can be used to adjust less accurate sensors if or when a more accurate sensor goes offline. For example, offsetting or setting accuracy limits for sensor data may be considered. In one aspect, accuracy limits (either determined relative to other sensors or provided to system 10) may be interpreted by the system to determine when to trigger an alarm or set a risk zone based on sensor accuracy.

[0372] In one aspect, the system uses the distance to the wireless sensor or the strength of the wireless sensor to determine whether the sensor should be processed. This allows the system to ignore sensors that are too far away, thereby reducing the processing load.

[0373] Multiple sensors 20 are configured to send sensor data to router 30. In one aspect, the sensor data is in the form of raw or unprocessed data from the sensors. If one or more of the multiple sensors 20 are analog sensors, the sensor data may be in the form of analog signals or alternatively in the form of digital values ​​representing analog signals.

[0374] As discussed above, in one aspect of this technology, data transmission from multiple sensors 20 to router 30 is provided via short-range wireless transmission, such as NFC (Near Field Communication), RFID (Radio Frequency Identification), and ZigBee. TM Or any other suitable means. In the illustrated aspect, via Bluetooth TM Data transmission is performed where sensor data is encoded into announcement data packets (e.g., suitable for announcement channels in short-range wireless protocols). These announcement data packets are typically used for handshaking or agreeing on a communication protocol between two devices, rather than for sending sensor data as disclosed herein. Therefore, router 30 can read sensor data without needing to pair with each of the multiple sensors 20. Consequently, router 30 does not need to maintain a separate connection with each of the multiple sensors 20. This allows system 10 to use any type of sensor with minimal configuration, including sensors that might otherwise be incompatible and not routinely paired with router 30 or processing server 40. This also allows system 10 to work with a far greater number of sensors than would be possible if router 30 had to be fully paired with each of the multiple sensors 20. Furthermore, since individual sensors do not need to maintain a connection with router 30, this improves battery life.

[0375] Therefore, sensor data transmission between multiple sensors 20 and router 30 can be considered connectionless, allowing sensors to be added to or removed from the system without involving any complexities associated with handshaking and handover. In one aspect, the notification data packets contain a Bluetooth unique to each device / sensor. TM The MAX address / UUID and the payload section containing sensor data are also included. In another aspect, this payload section includes additional information such as the brand and model of the sensor device or other metadata. In some cases, only the wireless connectivity announcement section is used to reduce the time, bandwidth, and / or processing required to transmit sensor data.

[0376] In another aspect, the wireless hub receives transmissions on at least one advertised channel. The wireless communication system of this hub has a first frequency bandwidth configured to receive the advertised channel from multiple sensors and a second frequency bandwidth data channel configured to receive data, with data transmission typically initiating after a handshake is performed on the advertised channel. However, the wireless hub can be configured to monitor the advertised channel and receive sensed values ​​on at least one advertised channel. Receiving sensed values ​​on the advertised channel reduces the time required to connect to devices and allows more devices to connect and transmit to the server. The hub can optionally use ChaCha encoding or Diffie-Hellman encoding to decrypt the sensed readings. The hub can determine or directly forward the sensed measurement portion and device identification portion of the data on the advertised channel to the server. Optionally, the sensed measurement results are transmitted as a continuous stream of data packets.

[0377] In one aspect, sensor data is transmitted as a continuous data stream. In another aspect, sensor data is transmitted at fixed intervals. Alternatively, sensor data is encoded and transmitted once sensor 20 generates new and / or updated data, so that bandwidth is not consumed in transmitting unchanged sensor readings. In yet another aspect, sensor data transmission is facilitated by pull notifications from router 30. In a preferred aspect, sensor data transmission is performed in real time. In one aspect, the sensor data is transmitted at intervals set by individual sensors among the multiple sensors 20, the processing server 40 being unaware of these intervals and still able to accept sensor data transmissions at any time. In yet another aspect, system 10 is optimized for data transmission at frequencies of 1 Hz or lower, but may be able to handle higher frequencies, such as 10 Hz.

[0378] In one aspect, multiple sensors 20 are programmed to operate using a data protocol / data specification, such that sensor data is processed in accordance with Bluetooth protocols. TM Output in the specified format.

[0379] In one aspect, router 30 includes a controller, antenna, and power supply, and is configured to receive sensor data from multiple sensors 20 and forward said data to processing server 40. In another aspect, the sensor data is timestamped upon reception and before transmission to processing server 40. This is achieved via Bluetooth. TMThe router 30 receives sensor data in the notification data packet and transmits the received data to the server 40 for processing. The router 30 can operate with a large number of sensors with minimal configuration and processing requirements. Notification data packets can be received on a common notification channel or from multiple notification channels. This can depend on the architecture or protocol of the short-range wireless communication device used. The router 30 can format or otherwise process the data packets before forwarding them to the server 30. For example, the router 30 can add timestamps, decode the signal, and / or package the signal using other incoming signals.

[0380] The methods and mechanisms for transmitting data from the multiple sensors 20 to the router 30 and from the router 30 to the processing server 40 do not need to be the same; that is, the router acts as a gateway. For example, in the illustrated aspect, the router 30 exports data received from the multiple sensors 20 to the processing server 40 via the IP communication protocol. In an alternative aspect, the router 30 exports the received sensor data to a local server via Ethernet.

[0381] In one respect, router 30 is powered by Cassia. TM X2000, X1000, E1000 Bluetooth TM (Enterprise Bluetooth) TM Routers or similar devices are provided.

[0382] In the illustrated aspect, the processing server 40 includes a scheduler 60, one or more processors 70, internal storage 80, a time-series database 90, a processor 100, and an event handler 110.

[0383] In one aspect, sensor data is timestamped and cached upon receipt at processing server 40. The timestamping of received sensor data by processing server 40 enables system 10 to handle irregular real-time data streams without performing interpolation or time averaging. Furthermore, server 40 can use a single central clock to synchronize data received from multiple sensors 20 and reduce timing errors in the data. The timestamps on the received sensor data are carried and used in the parameterized data output by processing server 40, providing a time series indicating the patient's condition. The use of caching allows for asynchronous reception and processing of sensor data received from multiple sensors 20, so that temporary bandwidth limitations, such as those affecting the transmission of sensor data from router 30, do not require halting the processing of data already received and cached at processing server 40.

[0384] The sensor data is then passed to a scheduler 60, which is configured to determine the source device and / or device type (i.e., the type of sensor that generated the sensor data). In one aspect, this is achieved by identifying at least a portion of one or more characteristics of the received sensor data (such as Bluetooth). TM MAC address / UUID or Bluetooth TM The determination is implemented by a class of sensors. In one aspect, the scheduler 60 performs pattern matching on the sensor data packets received from each individual sensor. In another aspect, the source device is identified via a device ID encoded into the sensor data generated by that particular device. In one aspect, device identification is performed by the router 30, and the device ID is sent along with the sensor data to the processing server 40.

[0385] After identifying the source device, the scheduler 60 retrieves the driver 71 and activates the corresponding process 70. If the process 70 is not present for sensor data from the identified source device, the scheduler 60 can operate to instantiate the process 70. In one aspect, the processing server 40 can retrieve the process 70 and driver 71 corresponding to any potential device ID from an external source that can continuously update / maintain the data as new sensors become available. In another aspect, the server 40 may include a library of definitions for various drivers. Additionally, the server 40 can build drivers based on pre-stored data types, and / or multiple sensors 20 can be programmed to transmit data of standard data structures / standard types. The server 40 can build custom drivers based on received sensor data and a database.

[0386] The scheduler 60 then forwards the sensor data to the activated processor 70, which includes a driver 71 that runs to process the sensor data into parameterized data. This processor / driver architecture allows the processing server 40 to process sensor data from any conceivable brand, name, and model of sensor, and is suitable for operation with any new sensors added to the system after initial setup. Furthermore, because the sensor data is centrally processed by the processing server 40, there is no need to update the router or sensor software to accommodate changes in system 10.

[0387] In one respect, parameterized data corresponds to one or more physiological parameters of a patient, such as respiratory rate, body temperature, carbon dioxide level, heart rate, and SpO2.

[0388] Once parameterized, the data is sensor-independent; that is, it has values ​​and units / sizes based on specific parameters and does not require factors related to the specific brand or model of the originating sensor to interpret the parameterized data. In one aspect, if no additional corresponding sensor data is received within a predetermined time period or once the transmission of sensor data has been resolved, the scheduler 60 deactivates the processor 70.

[0389] In one aspect, each processor 70 runs in an independent container 72 within the processing server 40, allowing for better resource control and parallel processing of sensor data from different individual sensors by different processors 70. Alternatively, each container 72 may contain one or more processors 70 up to the configurable limit.

[0390] When sensor data is received from additional sensors of multiple sensors 20, additional processing program 70 and container 72 can be instantiated.

[0391] In one respect, drive 71 is accessed directly by scheduler 60 without using dedicated handler 70.

[0392] The parameterized data is cached and subsequently stored in storage device 80 by processing server 40. In the illustrated aspect, the parameterized data is stored as a time series in dedicated database 90, where the time series is a sequence of timestamp and parameterized value pairs, and for each patient ID, a separate time series is provided for each physiological parameter of the parameterized data. The pre-stored cache allows for asynchronous processing of sensor data and storage of the resulting parameterized data.

[0393] The parameterized data is then added to the patient's electronic medical record. This parameterized data is further passed to an event handler 110, which can generate an alert and / or trigger an action when the parameterized data falls below or exceeds a predetermined threshold for a predetermined time period. Whether the parameterized data is above or below the predetermined threshold can determine whether the system should provide an indication (or, for example, a component risk score) to the healthcare provider or clinician, or output an instruction on the parameterized data on a display. This can ensure appropriate care is provided to the patient, or provide alerts or automated care.

[0394] In one aspect, the processing server 40 is also used to register patients for each of the plurality of sensors 20 using a patient registration service 41, which registers patients and associates the device ID of each of the plurality of sensors 20 with a patient ID. In another aspect, the patient's personal information is also stored, but separately from the patient ID, so that the patient ID can be shared and / or looked up without infringing on patient privacy. In another aspect, these device ID-patient ID pairs are stored in a database at the processing server 40. In another aspect, the patient registration service 41 is hosted outside the processing server 40, wherein the processing server 40 has access to a database 45 in which patient IDs and device IDs are stored.

[0395] In an alternative aspect, or in combination with the foregoing aspects, the processing server 40 is also configured to register hospital beds for each of the plurality of sensors 20 using a bed registration service that registers the hospital beds and associates the device ID of each of the plurality of sensors 20 with the bed ID of the bed. In one aspect, these device ID-bed ID pairs are stored in a database at the processing server 40. In another aspect, the bed registration service is hosted outside the processing server 40, wherein the processing server 40 has access to a database 45 in which the bed IDs and device IDs are stored. In one aspect, this works in the bed registration service in the same manner as the patient registration service described herein. Although beds are described, the registration process may be associated with other hospital furniture, including chairs.

[0396] Associated sensors with hospital beds can reduce the complexity of tracking within the system. In some facilities, such as hospitals, clinicians identify patients by the location of hospital beds and / or hospital beds in specific rooms or wards. By associating sensors with hospital beds, the location of relevant patients can be directly indicated to clinicians when attention is needed.

[0397] In one aspect, each hospital bed can be identified as having a location within the hospital. This identification process may include detecting a location marker associated with that location within the hospital. This location marker may be a short-range wireless device. In some cases, a passive short-range wireless device is used, so that the location marker does not require a power source. For example, an RFID tag is a passive device that can be read by a hub. For instance, each potential bed location may have an associated RFID tag. A router 30 on the bed can detect this RFID tag at the bed location. This detection allows for the association between the bed and its location determined by the system. The patient can then be associated with the bed.

[0398] If a hospital bed is moved around the hospital, its location can be automatically updated, thus automatically updating the patient's location as well. The bed's location can also update other recorded data or associations. For example, the location can be associated with a clinician. If moving the bed to a new location changes the clinician (e.g., a nurse or doctor), the system can update the clinician responsible for that bed to the clinician at the new location. For example, if the bed is moved between wards, the supervising clinician and / or ward workflow can be automatically updated.

[0399] In one aspect, hospital beds have an enrollment process. This enrollment process may include associating a patient with a bed. This process may associate any sensors already linked to the patient with the bed. Whether a sensor is linked to the bed or the patient may depend on whether the sensor is attached to and / or connected to the bed or the patient. For example, a sensor attached to the bed frame and / or mattress may be associated with the bed, while a sensor monitoring heart rate and attached to the patient's body may be associated with the patient (and then the patient may be associated with the bed). In some cases, staff may choose to associate sensors with the patient and / or the bed. In some cases, sensors may be associated with location. In some cases, the enrollment process may also be used to associate sensors with the bed, either separately from or in conjunction with the bed ID process.

[0400] In at least one embodiment, when one or more sensors are located on the bed but not directly attached to the patient assigned to the bed, the system is configured to verify the patient's presence in the bed before processing / accepting any data from the sensor. The presence of a patient can be detected by a pressure sensor, a PIR sensor, and / or by detecting the presence of an RFID tag embedded in a patient ID wristband. As part of the registration process, the RFID tag can be assigned to the bed and / or the patient. Bed sensors can include non-contact sensors for sensing physiological parameters. For example, under-mattress sensors can be used. Bed sensors can measure any one or more of the following: respiratory rate, SpO2 (oxygen saturation), supplemental oxygen, temperature, body temperature, heart rate and systolic blood pressure, and carbon dioxide level. In some cases, such as when non-contact sensors are unavailable, prohibitively expensive, or when alternative solutions are required, contact sensors can be used. For example, a contact SpO2 sensor can be used.

[0401] In one aspect, bedside sensors include respiratory rate sensors and heart rate sensors. For example, a cardiac pulse oximeter sensor can be used to measure both heart rate and respiratory rate without contact with the patient. The use of heart rate and respiratory rate typically provides accurate component risk scores, allowing the system to quickly identify patients with potential risk, and does not require contact with the sensors, as the patient only needs to be in a bed and / or chair. Sensor data associated with the bed can be transmitted to a processing server via a hub (which can also be associated with the bed). Advantageously, the bed provides a central location for the hub and allows for the connection of other sensors as needed or as the patient's condition develops. Optionally, a hemoglobin composition sensor can be used to provide further indications of the patient's health. Enabling the hub to receive data from multiple sensors via an announcement channel allows it to receive large amounts of data quickly and efficiently. The data can then be processed by the processing server and reported or displayed as described herein.

[0402] In one aspect, one or more non-contact sensors are used to sense respiratory rate and heart rate. The sensor can be a single sensor that senses both respiratory rate and heart rate, or a separate sensor can be used. Respiratory rate is an early indicator of a patient's health. When respiratory rate deviates from the normal range, this indicates a deterioration in respiratory health, which is often a precursor to other, more common diagnostic symptoms. For example, if a patient has the flu, their respiratory rate and heart rate rise above the normal range (i.e., resting respiratory rate and heart rate are higher than normal) before any fever or cough / runny nose develops. Therefore, changes in respiratory rate and heart rate can be a good indicator that a patient needs some kind of intervention, and providing this indicator through a non-contact sensing method attached to a piece of furniture ensures rapid, early detection of potential conditions so that they can be reported to clinicians and, for example, improved patient outcomes by initiating high-flow therapy. Under-mattress sensing also reduces the possibility of human error or missed signals because it operates automatically once the patient's presence is detected and an objective measurement is provided. Using objective measurements ensures comprehensive monitoring of all patients, including health deteriorations that may not be apparent to clinicians.

[0403] Associated sensors with hospital beds also simplify hardware attachment. For example, hospital beds typically have a power source that can connect to router 30. Similarly, sensors can be installed on hospital beds. In the case of permanent or near-permanent installation, the sensors can be permanently associated with the bed to avoid false reports. Because router 30 can be directly mounted to the bed, it can be easily maintained or updated when the bed is not in use.

[0404] In one respect, patient personal information is also stored, but separately from the bed ID, so that patient information can be shared and / or retrieved without infringing on patient privacy.

[0405] Figure 2 Six hospital beds (labeled 1 to 6) in a room (such as a hospital ward) are shown. Locators 8 (such as RFID tags) are positioned behind each bed. Each bed includes or is attached to a router 30, which may be fixed to the bed frame, for example. The router 30 may be under the bed, attached to the headboard, or otherwise connected. The hospital beds may be movable. For example, they may be equipped with wheels so that the patient can move around the facility while in bed. When each bed is moved into place or at other times, the locator 8 and router 30 communicate to determine the bed's location. For example, if bed 1 is moved into place, it communicates with the adjacent locator 8 to confirm its location in the room or facility. This communication may optionally be wireless, such as in which the locator system 8 is an RFID device read by the router 30, although wired connections or other physical connections may be used.

[0406] In some cases, the communication has a limited range. A limited range helps avoid interference or confusion between adjacent beds. For example, the communication may have a transmission distance of less than 2 meters, less than 1 meter, or less than 0.5 meters. In some cases, routers 30 for adjacent beds or beds in the same room or ward can interact to determine the relative location of the beds within the room. This can be advantageous when the locator 8 is absent or inoperable. For example, router 30 on bed 2 can obtain the measured distances between bed 1 and bed 4 and perform triangulation of the location based on these readings (or other readings). The measured distance can be calculated based on signal strength or angle of arrival. In some cases, router 30 may have a GPS or other location sensor configured to determine its location and refer to a map of the hospital or building to determine its position. Other locators 8 are possible, such as geofencing in each room or location, Bluetooth, etc. TM Or a reference point.

[0407] Figure 3One aspect is described, in which, in addition to receiving sensor data from multiple sensors 20, router 30 is also configured to receive data regarding therapies provided to a patient by one or more medical devices 200. In one aspect, the medical device 200 is a respiratory therapy device or a respiratory support device. In another aspect, the respiratory therapy device can provide respiratory therapy or support and can be a high-flow therapy device or a ventilator, or a humidifier configured to provide one or more of these. The respiratory device can be a respiratory humidifier that can regulate the gas from the ventilator before it is delivered to the patient. CPAP (Continuous Positive Airway Pressure) therapy, NHF (High-Flow Nasal Flu) therapy, or Bilevel therapy are also described. The respiratory therapy / support device can be a multimodal therapy device configured to provide both high-flow therapy and Bilevel therapy. The respiratory device has a flow generator, a humidifier, tubing, and a patient interface. The respiratory therapy device has sensors to record various therapy parameters, such as flow rate, pressure, temperature, and humidity. The device can also transmit usage information and / or data measured by onboard sensors (such as SpO2, respiratory rate, and heart rate), which are measured directly or indirectly via other physiological parameters or indicators monitored by the medical device 200 itself. In one aspect, one or more of the plurality of sensors 20 are provided as part of the medical device 200. Those skilled in the art will understand that the data processing methods disclosed herein are independent of and unrelated to the exact and specific nature of the medical device 200, provided that it operates as described below. In one aspect, one or more medical devices 200 include Bluetooth capable of connecting to a processing server 40 via a router 30. TM Communication module. In one aspect, router 30 is able to identify the type, manufacturer, and / or model of medical device 200 by the transmitted therapy data. In another aspect, router 30 identifies medical device 200 by the structure of the therapy data. In yet another aspect, the device ID of medical device 200 is encoded into the therapy data itself.

[0408] In one aspect, the sensor may include a hemoglobin composition sensor and an under-mattress sensor. The under-mattress sensor can sense respiratory rate and / or heart rate. Combining these two sensors can provide an early indication of a patient's deteriorating health.

[0409] In one aspect, the therapy data comprises one or more parameters related to: flow rate, humidity level, dew point, usage time, pressure rate, or pressure delivery; or the O2 fraction of the gas flow used to deliver to the patient; or any other suitable or desired data. In one aspect, the therapy data is broadcast to router 30, where it is timestamped, and then delivered to processing server 40. In one aspect, the therapy data can be set by a clinician and can be broadcast. In another aspect, the therapy data is timestamped upon receipt at processing server 40. In one aspect, the therapy data is encoded in Bluetooth. TM The notification data packets are collected by router 30, which then sends the therapy data to processing server 40 via IP protocol. In one aspect, the therapy device is configured to send the therapy data to a hub via the notification packets. The therapy device may include a short-range wireless interface, such as Bluetooth. TM Interface. The therapy device can incorporate the therapy data into notification packets sent by the therapy device.

[0410] The processing server 40 processes the received therapeutic data in the same manner as the sensor data described above (i.e., by activating the processor 70 corresponding to the identified medical device, or by creating the processor 70 if the appropriate driver 71 does not yet exist). This allows new medical devices to be added to the system without requiring reprogramming parts of the system to account for hardware changes; the processing server simply accesses and / or creates the processor 70 and driver 71 corresponding to the new medical device. Similarly, one or more medical devices 200 can be removed from the system, and their corresponding processors can be deactivated or otherwise deactivated, allowing the processing server 40 to continue operating efficiently.

[0411] Then, this therapeutic data can be added to the patient's electronic medical record as a time series along with corresponding processed sensor data related to the patient's physiological parameters, thereby providing a comprehensive and continuous treatment history along with the patient's corresponding physiological parameters.

[0412] The temporal pairing of parameterized data describing a patient's condition with therapeutic parameters describing the treatment status present at the time the sensor data was generated provides electronic health record readers with a measure of the efficacy of the applied therapy and a measure of patient adherence to a prescribed treatment regimen. In one aspect, this efficacy and adherence data is parameterized and stored along with the patient's corresponding therapeutic and physiological parameters.

[0413] Figure 4A portion of system 10 is depicted receiving parameterized data from processing server 40. As shown, this parameterized data can be forwarded to sensor data engine 300, which in other cases may be referred to as a data processing engine or patient data management engine. This can be part of system 10 or located externally to system 10. Sensor data engine 300 can update a copy of the patient's electronic medical record (after erasing any personal information associated with the patient, if any) and pass it to a data analysis engine or prediction engine for assessment and prediction / trend analysis, generating patient-specific alerts or notifications, and / or automatically populating patient forms and records as needed. In one aspect, the parameterized data is transmitted to display system 310, which exists in a hospital or home therapy environment, for visual display.

[0414] Figure 5 The process performed by router 30 is illustrated. At step S110, the router scans the radio frequency band for any transmissions. At step S120, it is determined whether any transmissions are incoming, such as transmissions of sensor data from one or more of the multiple sensors 20. In one aspect, router 30 is configured to scan for any known sensors registered for the patient. In another aspect, router 30 is capable of discovering newly added sensors at this stage. Once a transmission is detected, router 30 checks for an active connection to processing server 40 at step S130. If no connection is available, router 30 continues scanning locally and caching sensor data. Once a connection is active, router 30 relays the sensor data transmission to processing server 40.

[0415] Figure 6 The process executed at the scheduler 60 of the processing server 40 is illustrated. At step S210, a relevant transmission from the router 30 is received. In one aspect, this transmission is directly relayed to the scheduler 60. Alternatively, depending on available processing resources, the transmission from the router 30 is cached and fed to the scheduler 60. At step S220, the scheduler 60 identifies the device that generated the received sensor data and performs a check on the active processor 70 corresponding to the identified device. If a corresponding processor 70 is located, the sensor data is forwarded to the processor 70. Alternatively, if no active processor 70 is found, the scheduler 60 determines whether the identified device is compatible with the system 10. If incompatibility is detected, device information is recorded, and no further action is taken. On the other hand, if the device is deemed compatible, at step S240, the scheduler 60 creates a processor instance with the correct driver 71.

[0416] Figure 7Further processing performed at the scheduler 60 of the processing server 40 is illustrated. At step S310, after receiving sensor data from multiple sensors 20 via router 30 and identifying the specific device or device type that generated the sensor data, the process 70 is instantiated with the correct driver 71. At step S320, the patient registration service 41 and the associated database 45 are contacted to determine if the identified device ID is linked to a patient ID. If the device is not assigned to a patient ID, the device ID is associated with a patient ID registered with the router 30 through which the sensor data is relayed. If a device ID is found to be linked to a patient ID other than the patient ID registered with the router 30, the device ID is reassigned. At step S330, a counter is started to wait for a predetermined time length during which sensor data is expected to be received. If no sensor data is relayed from the router 30 during this period, a timeout counter is started and incremented. When the timeout condition is met before any sensor data is received, the process instance terminates automatically at step S370. In one aspect, the process terminates immediately after processing the transmission of sensor data, preventing system resources from waiting in vacancies. Upon receiving sensor data, the timeout counter is reset at step S340, and a timestamp corresponding to the reception time is created at step S350. At step S360, the transmitted sensor data is parsed by the driver. If the data contains patient-related monitoring information, such as respiratory rate, heart rate, and SpO2 data, the parameterized data, patient ID, device ID, and timestamp are cached, ready to be added to database 90, and the process returns to step S330 to await further sensor data. If the sensor data does not contain monitoring information, the process 70 returns to step S330. In one aspect, the process 70 is capable of taking corrective actions based on the driver 71, such as attempting to switch to another driver 71 (if available). If the process 70 cannot understand the sensor data, an error condition is recorded during the process of entering step S370, and the process terminates automatically.

[0417] In one aspect, this process can be adapted for use with a bed ID. The bed registration service can be contacted at or before S320 to determine if the device ID is associated with the bed IR and / or patient ID. The system can then check if the bed ID is associated with the patient ID. In this process or through another process, the device ID is linked to the patient ID via the bed ID.

[0418] Figure 8The process of storing parameterized data as a time series, performed at database 90 of processing server 40, is illustrated. At step S410, database 90 receives new parameterized data output by processor 70 or a request for patient data already stored in database 90. In the former case, a check is performed at step S430 to determine whether a time series of the sensor, parameter, and / or patient, as the object of the request, exists in database 90. If a series exists, the newly received data is appended to the existing series. Alternatively, a new series is created and new data is added as the first entry.

[0419] In the event of a request for patient data, a check is performed at step S420 to determine whether the patient identified in the request is included in database 90. If not, a corresponding error message is generated. Alternatively, a further check is performed at step S440 to determine whether a time series of the patient and / or any specific parameter that is the object of the request exists in database 90. If the result is no, an error message is returned in response to the request. If a time series is identified, the series is queried at step S450 to determine whether a measurement exists for any specific time range identified in the request, resulting in the return of the requested result in response to the initial query, or an error indicating that no corresponding data is available.

[0420] Display System 310

[0421] The aspects relating to the display of parameterized data will now be discussed in more detail. It has been found that displaying the data described below simplifies monitoring for patients, users, and / or clinicians. This data is further collected in real time and displayed substantially in real time, enabling clinicians to perform real-time monitoring and issue alerts immediately. Here, "real-time" and "substantially real-time" are used to mean that the data is processed and displayed immediately once it is generated, sent, and received. Therefore, "real-time" depends on the sensor's sampling rate, the raw data transmission rate, the latency of processing the raw data into parameterized data, and the refresh rate of the display itself.

[0422] As described above, the parameterized data can be a time-series output associated with a specific patient ID and / or bed ID, and stored in real time, periodically, or upon specific request as part of the patient's electronic medical record. This parameterized data can also be displayed via display system 310, allowing patients and clinicians to visually monitor patient status and interact with available data.

[0423] In one aspect, the display system 310 includes a screen and one or more user input components. The user input components may take the form of a graphical user interface 400 operated via one or more of an integrated touchscreen interface, a mouse and keyboard, and / or other physical control components. Additional physical controls (such as buttons, switches, and knobs) may also be provided around the periphery of the screen to allow a user (such as a clinician) to interact with the displayed information. Those skilled in the art will understand that any suitable form of user input component can be utilized. Figure 9 As shown, the screen displays a graphical user interface 400, which includes a dashboard that groups actively monitored patients. In this dashboard, clinicians can access an overview of the current status of patients within each group via a so-called “group view” 410. This “group view” provides a curated view of health data points for each patient in the group, including values ​​of some recently received parametric data, as well as the patient's name, ID, and / or bed number, and an indication of each patient's location in the hospital / ward (if applicable). Regarding which specific parametric data is displayed in the “group view,” this can include one or more of the monitored physiological parameters, such as respiratory rate, heart rate, and SpO2. The specific selection of parameters displayed can be customized by the clinician, set at the organization or facility level, or reflect system defaults. The order in which patients are displayed in the “group view” can be alphabetical or numerical (based on patient name or ID), or determined by a score associated with each patient (such as an early warning score). Patients with higher scores may appear higher or more prominently in the list. Such scoring systems are described in more detail below.

[0424] For each actively monitored patient, a single "Patient View" 420 is also accessible, either directly or by selecting a single patient entry from the aforementioned "Group View." Figure 10 As shown, the patient's name and ID are displayed again in this "patient view." The bed ID and location may also be displayed. The names and sensor IDs of the individual sensors associated with the patient, along with the associated parameterized data received from each corresponding sensor, are also shown. In one aspect, when a sensor 20 constituting part of the system is detected by repeater 30 or processing server 40 and corresponding data is received, sensor information and the associated parameterized data corresponding to each sensor are automatically added to the patient view 420. Conversely, when a sensor disconnects or stops sending data, the corresponding display element can be removed from this patient view. Alternatively, warnings or notifications may indicate data loss. This allows for reconnection in case of accidental sensor loss.

[0425] In cases where parameterized data is received from or otherwise derived from one or more medical devices 200 (such as the aforementioned respiratory therapy device), the device name and ID are displayed along with the associated parameters in a manner similar to that described above. In one aspect, the latest value received for each physiological parameter is displayed in a card located near the details of each sensor and / or medical device. When a sensor or medical device provides data on multiple parameters, a separate card is displayed for each parameter. One or more time-series graphs may also be shown, displaying the current and historical values ​​of parameters monitored by sensors and / or medical devices linked to the patient. A separate graph (each graph having a common time scale) may be provided for each parameter, or alternatively, time series of two or more parameters may be overlaid on the same graph, regardless of whether it is a device in the sensor data or a medical device. The size of the time period displayed on the graph can be adjusted by selecting from a list of preset values ​​(such as 5, 10, 15, 30 minutes or integers of days, weeks, or months) or by interacting with a sliding scale bar, dial, or other control element that forms part of the user interface 400, allowing selection of any desired time window. The portion of the time series displayed on the graph at any given time is represented by a graphical timeline 430. In the illustrated example, the highlighted area represents a time period visible on the graph. By interacting with the graph timeline 410 to change the size of the highlighted area, the length of the time period displayed on the graph can be increased or decreased. Similarly, the highlighted area can also be transposed along the timeline to move the displayed portion forward or backward in time, thereby allowing for viewing historical data at high resolution.

[0426] In another aspect, the display system 310 also includes an indicator 440, which can form part of one or both of the aforementioned "group view" and "patient view". A separate indicator 440 can be provided for each physiological parameter among the monitored and displayed physiological parameters, and can be combined with the latest value of the parameter, or alternatively, with a rolling average over a preset or user-selected time period. Figure 10 The indicator is provided as a radial gauge surrounding the parameter value. The gauge is segmented based on threshold values ​​within the parameter value, with a lower threshold on the left and an upper threshold on the right. A pointer 441 is also provided, its position indicating the current parameter value displayed at the center of the gauge.

[0427] In one aspect, meter segments are determined and color-coded based on the patient's associated status. For example, a meter corresponding to a patient's heart rate might have segments colored green, representing values ​​between a lower threshold of 40 bpm and an upper threshold of 160 bpm, generally considered healthy. These thresholds can also be set to predetermined values ​​associated with the facility and / or country where System 10 is adopted. In one aspect, System 10 is provided with a lookup table of such predetermined values, and these predetermined values ​​are automatically used when a location is entered and / or detected. These thresholds can also be manually defined or selected by a technician during the initial setup of the system, and can also be edited by clinicians or users according to their specific preferences. In one aspect, these thresholds can be set by the facility based on, for example, protocols used at the facility. In a particular aspect, the meter segments are divided according to parameter thresholds of a scoring system (such as an early warning scoring system), and can be color-coded accordingly.

[0428] Alternatively or additionally, instruments are provided to reflect a component risk score. This component risk score can be a single numerical value reflecting a patient's risk of deterioration. A component risk score can be referred to as and / or represent a patient's health parameter, and vice versa; the terms "component risk score" and "health parameter" are understood to be interchangeable herein. In some cases, a component risk score includes at least a subset of the measurements required for a clinical risk index, such as the composite early warning score (EWS). A clinical risk index is used to measure a patient's risk of deterioration by quantifying the combined effect of risks indicated by various physiological parameters. A clinical risk index can be referred to as and / or represent a patient's health status, and vice versa; the terms "clinical risk index" and "health status" are understood to be interchangeable herein. A clinical risk index provides a comprehensive overview of a patient's condition at a given point in time. However, clinical risk indices typically include qualitative assessments and / or assessments performed by a clinician. Furthermore, clinical risk indices are only valid if all measurements are available, as they typically consist of a specific combination of multiple physiological parameters. Component risk scores use multiple sensed physiological parameters to approximate or generate numerical values ​​reflecting a patient's risk of deterioration, or approximate a clinical risk index. The component risk score and / or the health parameter can be determined using a single physiological parameter with the highest risk level. In some cases, a component risk score is calculated for each physiological parameter, and then the calculated values ​​are compared to determine the final component risk score, for example, based on the highest value.

[0429] Examples of clinical risk indices include the Early Warning Score (EWS), the NHS National Early Warning Score (NEWS), and the Clinical Risk Index for Infants (CRIB). These indices quantify the combined impact of multiple physiological parameters on a patient. Processing a clinical risk index involves collecting measurements of the parameters, classifying the risks of each parameter, and assessing the combined impact of the risks of each parameter. However, if one or more parameters are missing, the combined impact cannot be calculated due to missing values, the specificity of the index requirements, and / or the inability to calculate the risk index. For example, some risk indices require clinicians to examine the patient and determine, for example, their level of consciousness. If this examination is unavailable or cannot be measured in real time, an official risk index cannot be calculated. In such cases, component risk scores can be used instead. Component risk scores identify the risk constituted by each measurable (or measurable) item. Therefore, component risk scores attempt to predict the risk index based on the available measurements. In some cases, this is equivalent to component risk scores using the highest risk score of any of the measured parameters, which is generally equivalent to the risk index process. In some cases, multiple risk indices or risk scores can be calculated in parallel. This can be advantageous when different indices or scores target different potential problems or risk categories.

[0430] By calculating and displaying a patient's component risk score in real time, clinicians can assess the patient and modify their treatment before the patient's condition deteriorates too much. The score can be derived from one or more physiological parameters, such as systolic blood pressure, heart rate, oxygen saturation, respiratory rate, and body temperature. Additional physiological parameters, such as level of consciousness, can be added to the index. The score can be calculated using a total weighting system, in which points are assigned to each component physiological parameter based on the degree of physiological abnormality (i.e., deviation from expected normal values). In some cases, the total score reflects the highest-risk component. The highest-risk component represents the physiological parameter that poses the highest risk to the patient. It can be calculated by calculating the individual risk components for each physiological parameter and comparing them. This can be simplified by normalizing the individual risk components before comparison. This avoids requiring all the data with the risk index before calculating the risk score, which is an advantage of component risk scoring. This component can be normalized to the scale of the score. For example, if respiratory rate and temperature are monitored, with respiratory rate in yellow and body temperature in red, the total score is red (or the calculated score is in the red zone). Normalization can help compare measurements in component risk scores to identify the highest individual risk. Alternatively, known relationships or scaling between scores can be used to compare the original scores to address potentially disparate units within each risk score.

[0431] Figure 11 and Figure 12An exemplary clinical risk index framework in tabular form from the Early Warning Scoring System for Adults used in New Zealand since 2021 is shown, including color zones associated with each index or score value, designated risk intervals or risk categories, and associated ranges for component physiological parameters. Component risk scores may include any one or more component physiological parameters. In some cases, component risk scores may include any one or more component physiological parameters that can be measured or sensed. Alternative clinical risk indices and scoring frameworks may be used. Alternative component risk scores may be developed based on these frameworks. The frameworks employed may vary by country or region. In one aspect, the instrument is segmented according to these scoring boundaries and color-coded accordingly. In use, the specific clinical risk index framework, component risk scores, and / or early warning scoring system employed may also vary by patient, facility, or location, where it is envisioned that separate systems (and thresholds) will be used in obstetrics and gynecology and pediatric applications.

[0432] In one aspect, each measurement parameter of the component risk score is compared to one or more thresholds, wherein the value of the measurement parameter relative to said thresholds is indicated on a display. These thresholds may involve, for example, Figure 11 The illustrated early warning scoring table compares each measurement parameter against a corresponding threshold defined in the early warning scoring framework and assigns it to a corresponding risk zone or risk category (white, yellow, orange, red, and blue in the illustrated example). Specifically, each parameter may have multiple corresponding thresholds representing different (i.e., worsening or improving) conditions of the patient. For example, a measured respiratory rate is taken in real-time or substantially real-time from a sensor worn by the patient, an under-bed sensor, or a medical device. This measured respiratory rate is compared against various thresholds in the early warning framework. The measured respiratory rate is then categorized based on the comparison with the thresholds. In a specific scenario, if the respiratory rate is less than 5 breaths per minute, the patient is categorized as being in the blue risk zone or risk category, indicating a need for urgent attention / resurrection. Similarly, if the respiratory rate is between 5 and 8, the patient is categorized as being in the red risk zone or risk category. Figure 11 The table shown defines example thresholds for the early warning framework. SpO2 (or any other parameter measured individually or in combination) can also be used to establish a patient's status within the early warning framework. The same or similar thresholds and / or measurements can be similarly used for component risk scoring, or they can be adjusted based on other clinical risk indices.

[0433] The system also allows users, technicians, or clinicians to define custom thresholds. It is envisioned that individual hospitals can set custom thresholds and define custom early warning frameworks or component risk scores. For example, component risk scores could be based on commonly available sensors or measurements. Alternatively, thresholds can be customized for each patient. Alternatively, these thresholds can be set based on race or age, BMI, or any other patient parameters. The aspects of this disclosure provide customization for both the system's inputs and outputs, which advantageously allows hospitals or clinicians to provide the required reporting and / or monitoring as set by regulations or hospital protocols. This can be centrally managed due to the system's openness and the flexibility of its architecture in handling the storage and display of patient health parameters, patient data, or ward or multi-ward profiles.

[0434] Based on the patient's threshold and the determined component risk score, measures can be taken, for example, such as... Figure 12 The appropriate actions are defined in the table. Additionally or alternatively, actions may include raising an alarm at the appropriate hospital alarm system or automatically transmitting a message to a clinician containing data about exceeding specific measurement parameters and thresholds. These actions may also include recording each instance (and associated metadata) of a patient's measurement parameters exceeding a specific threshold. Such instances can be added to the patient's electronic medical record. Thus, if a parameter drops below or increases above a threshold or exceeds the threshold range, the system can identify when and for which parameter this occurred and report accordingly. When a patient ID or bed ID is associated with a clinician, including with a location subsequently associated with the clinician, alarms can be sent directly to the associated clinician. This reduces the number of alarms or alerts for each clinician. In some cases, such as when an alarm is not responded to or is rejected within a period of time, an alarm or alert can be transmitted to a second clinician or the hospital alarm system. Alarms or alerts can be customized to state the urgency or situation that led to the alarm. For example, a graph of physiological parameters or a component risk score can be shown in the alarm.

[0435] Although indicator 440 is depicted as a radial instrument, those skilled in the art will understand that any suitable graphical representation, such as a linear instrument, bullet graph, or pie chart, may be used.

[0436] Figure 13A version of the aforementioned patient view 420, showing an aspect in which a patient receives therapy from a medical device 200 (such as the previously described respiratory therapy device), is illustrated. Here, a graphical representation of the therapy setup over time is shown (e.g., in the form of a time-series graph), including indications of operating modes of the therapy device and usage data, along with corresponding measured physiological parameters and indicators 440. This allows clinicians to observe the effectiveness of the therapy and intervention by observing any subsequent changes in the measured patient physiological parameters. In particular, it is envisioned that providing access to the patient's treatment history on a shared timeline with monitored physiological parameters would help establish a baseline regarding how the patient might respond to the therapy setup based on previously observed responses.

[0437] In one aspect, the system addresses the challenge of processing sensor data from multiple sensors. While more patient information helps clinicians decide on actions or treatments, identifying patient problems becomes difficult when data is provided by multiple independent sensors. By combining sensor outputs into a real-time display and presenting these outputs to draw attention to the patients most in need, the system provides sensing of improved patient health.

[0438] Component risk score

[0439] As mentioned above, in a clinical setting, there are many assessment frameworks used to aggregate various inputs to categorize the risk of a patient's condition deteriorating. A combination of physiological measurements and subjective metrics is often used to derive outputs that can guide nursing decisions, such as scores or risk intervals / categories.

[0440] The Early Warning Score (EWS) framework described earlier is an example of a clinical risk index widely used in hospitals. For each indicator or contributing physiological parameter, a score or clinical risk index is determined based on where the value of said indicator or parameter falls between predetermined thresholds. Based on this score, patients are categorized into one of five color categories or risk zones associated with the framework (e.g., white, yellow, orange, red, and blue), indicating an increased risk of health deterioration. The illustrated example corresponds to the Early Warning Score framework described above. It is conceivable that any particular color or risk zone could be used.

[0441] Routine clinical practice involves measuring a patient's physiological parameters and calculating their clinical risk index and corresponding risk intervals at regular intervals, providing a "snapshot" of the patient's condition. However, when viewing a chart of a patient's risk of deterioration over time, if the changes in the patient's clinical risk index are sufficient to cause a shift in risk intervals / color categories, the resulting chart resembles a series of steps. When a patient remains within a single risk interval for an extended period, their progression is not apparent until they switch between different intervals. However, the physiological parameters that contribute to the clinical risk index can fluctuate within the boundaries of the current interval / category. These fluctuations are not visible to clinicians because the physiological parameters range widely, corresponding to a single risk interval / category. This problem is common in most clinical risk index frameworks.

[0442] Another issue is that for many clinical risk indices, the range of values ​​for the different physiological parameters corresponding to each risk interval or category may vary. This makes it difficult to compare the relative risk borne by each contributing parameter with the overall risk associated with the patient.

[0443] In one aspect of this disclosure, a component risk score is adapted based on a clinical risk index. Figure 14 This demonstrates how various aspects of a clinical risk index can be incorporated into a component risk score. A component risk score can incorporate one or more of the following: measurements of the clinical risk index, or measurements related to or based on measurements of the clinical risk index. By using only available measurements and based on combinations, maximum, or minimum values ​​of available measurements, component risk scores can continuously estimate the clinical risk index. In some cases, such as... Figure 14 As shown, clinician-reported values ​​(such as consciousness) are not included in the component risk score. In some cases, this is because they cannot be measured in real time or require external assessment. Alternatively, the component risk score may include measurement data and clinically reported values ​​and / or patient characteristics (e.g., age, weight, height, length of hospital stay). In one aspect of this disclosure, the in-category range of parameter values ​​is normalized for each contributing measurement in the component risk score. This increases the granularity of risk information available to clinicians and allows for direct comparison of the relative risks posed by different measurements using unitless values. In some cases, normalized values ​​allow the system to rank the risk score for each contributing measurement within a risk interval. However, raw values ​​and / or risk intervals can be specified in the raw values. This, in turn, allows for tracking patient trends within a single risk interval or category using, for example, a linear scale. In some cases, the scale may be non-linear to emphasize changes in the areas of most concern. For example, the scale may be non-linear to emphasize changes in high-risk patients while low-risk patients show less change.

[0444] Using component risk scores can be particularly beneficial because it allows for tracking a patient’s risk in more granular increments than overall risk intervals or categories, making patient progression more apparent, as clinicians can track the patient’s overall risk in more detail within each interval rather than just between intervals.

[0445] Figure 15 An exemplary component risk score (in this case, referring to the previously described early warning scoring framework) and a corresponding normalized component risk score generated based on one aspect are shown. The normalization process for the component risk score or early warning scoring framework may involve splitting five risk categories or intervals into ten discrete values ​​so that patients can be graded on a 50-point risk scale from white (0) to blue (40+) across all risk intervals. Figure 11 As shown, for each measurement type (i.e., contributing physiological parameter), the range of values ​​corresponding to each category or risk interval can vary. Therefore, min-max normalization is employed to ensure that the output normalized clinical risk index always reflects the proportional distance to the next risk interval as well as the proportional distance to the previous risk interval.

[0446] In one respect, the normalized component risk score is calculated according to the following formula:

[0447]

[0448] Here, the measured values ​​are physiological parameters (e.g., a patient's respiratory rate) obtained from sensor data. The lower risk threshold is a parameter value that marks the boundary of a risk interval transitioning to a lower risk interval. Conversely, the upper risk threshold is the limit of the boundary of an adjacent higher risk interval. The lower risk score is the lower limit of the new normalized component risk score for the risk interval. The scaling factor value is equal to the range of normalized component risk scores applied to each risk interval (10 in this example, although the scaling factor number can be changed to any value depending on the desired fractional scale of the normalized component risk scores).

[0449] In a working example monitoring a single physiological parameter (e.g., respiratory rate), a patient breathing 6 times per minute would fall within the red risk zone of the early warning scoring framework (e.g., ...). Figure 11 As shown). According to Figure 11 This gives a lower risk threshold of 8 and an upper risk threshold of 5. From Figure 15As can be seen, the lower risk score for the red risk zone is 30. Plugging these values ​​into the above formula yields a normalized component risk score of 37, where the red risk zone corresponds to any normalized component risk score falling between 30 and 37. Therefore, it is immediately apparent that this patient occupies a relatively high-risk position within their current risk zone, allowing them to receive priority treatment compared to other patients with lower risk but within the same risk zone.

[0450] If a patient's respiratory rate changes to 5 or 8, and the standard early warning scoring framework would only indicate that the patient remains within the red risk zone with a score of 3, then their normalized component risk score would change from 37 to indicate that the patient has a higher or lower risk within the red risk zone. In this way, the normalized clinical risk index improves upon the non-normalized index, not only because it provides increased granularity related to the patient's location within each risk zone, but also because the change (and rate of change) of the normalized component risk score toward the risk zone threshold provides a measure of the likelihood (and time) that a patient might transition from one risk zone to another.

[0451] In another aspect, for each of the multiple physiological parameters (including but not limited to respiratory rate, heart rate, SpO2, blood pressure, body temperature, carbon dioxide level, and body temperature), an individual component risk score or a normalized component risk score can be calculated (hereinafter, where possible, the use of component risk score should be understood to also refer to or alternatively refer to the normalized component risk score). The calculated individual component risk scores are then used to determine the overall component risk score or total component risk score. In one aspect, the total component risk score is set as the highest value of the individual component risk scores. In another aspect, the total component risk score is given by averaging the values ​​of the individual component risk scores. In some cases, component risk scores can explain differences in measurement results, for example, by using a weighted average or a normalized component risk score. Alternatively, the total component risk score is given by a weighted average of the individual component risk scores, where the weighting is based on a predetermined set of rules, which may optionally depend on the framework used or the numerical values ​​and / or specific combinations of the measured physiological parameters. This can also be set by the clinician according to their preferences. In another aspect, a total component risk score is given by summing two or more component risk scores from the constituent component risk scores and comparing the sum to a predetermined threshold, wherein the threshold may also depend on the scoring framework, the value of a physiological parameter measured or set by a clinician, and / or a specific combination thereof.

[0452] Figure 16A patient view 420 is shown based on one aspect. In addition to the monitored parametric data and corresponding sensor information, a graphical display of component risk scores (normalized in this example) presented as a time series is provided. This could be individual component risk scores derived from a single physiological parameter, or it could be a total component risk score derived from multiple physiological parameters as described above.

[0453] Time series plots may be accompanied by indicators of the aforementioned type 440. In one aspect, visual indicators of risk intervals associated with different thresholds of component risk scores are extended along the time axis of the plot. Figure 16 These ratings are shown as horizontal grayscale bars, but they may be colored to match the component risk ratings.

[0454] In one aspect, the time series plot is updated in real time as new data is received from the sensor, and the latest value of the component risk score is calculated. Indicator 440 can provide a rolling average of the component risk score over a preset or user-selected time period. Alternatively, indicator 440 can be updated only when data is received that causes a change in the displayed value of the component risk score. Thus, a continuous time series representation of patient risk is provided to clinicians, which constitutes an improvement over stepwise jumps in risk intervals that would otherwise be displayed without using the component risk score.

[0455] Figure 17 This shows a patient view based on yet another aspect, where component risk scores are displayed along with real-time patient data, as described above regarding... Figure 10 This allows clinicians to visually compare trends in component risk scores with component health measures. In the aspect where a total component risk score is calculated based on two or more component physiological parameters, the order of the graphics on the screen allows data associated with each physiological parameter to be presented in descending order of their contribution to the total component risk score; that is, physiological parameters indicating a high risk patient may be located higher on the screen or in another more prominent position. This allows clinicians to visually compare trends in component risk scores with component health measures.

[0456] In another aspect, as mentioned above... Figure 11 The treatment details or parameters of the therapy applied to the patient are shown as described.

[0457] In one aspect, the patient view can show changes in real-time patient data over multiple time periods. For example, Figure 18 Patient data for three time periods are shown, although more or less data may be used. Within each time period, the average data is used to represent the variation in patient data during that period. Figure 18The chart shows three time periods (500) per week. An average was calculated within each time period (500). The median (501), upper quartile (502), and lower quartile (503) are shown. This integrates patient variation over longer time periods into the patient view. This extracts the system's stored time-series data into an overall indicator of patient health. As shown, interpolation can be used to connect time periods to create visual links between them. This interpolation is shown as linear, but an estimated curve or alternative interpolation can be used. The patient view can include risk categories (506), shown as horizontal intervals in this case. These help the patient view show variation in patient data relative to expected outcomes.

[0458] In some cases, time periods can be larger or smaller. For example, daily time periods, hourly time periods, four-hourly time periods, monthly time periods, or integers of days, weeks, or months. The number of time periods can vary; for example, there could be seven time periods, each representing a day of the week; or four time periods, each representing a week of the month. Patient views can be switchable to view different measurements and / or multiple data graphs can be displayed in each view. Patient views can have a list of preset values ​​(such as 5 minutes, 10 minutes, 15 minutes, 30 minutes, or integers of days, weeks, or months). The use of time-series databases allows the system to quickly display time-series views and / or update them in real time, as data can be quickly obtained from the time-series database. A time-series database is an optimized database used to store and provide time series data through associated time and value pairs. This allows for the generation of graphs or curves based on the data. Each data point in the database is associated with a timestamp. In some cases, time-series databases may not store data indefinitely or may reduce the amount of old data stored. This can be achieved through, for example, downsampling or deletion. This time-series database can store data over predefined time periods or windows (e.g., last year, last month, last week). Timestamps can be used as key indexes to improve data processing. In some cases, this system ensures that each sensor measurement result has an accurate timestamp to allow it to be included in the time-series database. An example time-series database is InfluxDB. TM .

[0459] Figure 19Alternative patient views are shown, illustrating patient data over different time periods. A radar chart is displayed to represent five patient data values ​​(in this case, respiratory rate, temperature, heart rate, SpO2, and blood pressure). Values ​​for two time periods, 601 and 602, are shown. These can be values ​​at a specific time, or they can be the minimum, maximum, and / or average values ​​within that time period. Radar charts allow for comparison of the values ​​of each measurement over an entire time period. For example, a clinician might notice a significant increase in heart rate while blood pressure remains more stable. Radar charts can be used to show clinicians the temporal variation of a set of characteristics without requiring them to examine each individual measurement and / or review the entire time series. Similarly, because the data is stored as a time series, time series databases are able to quickly generate the data needed for these graphs.

[0460] In some cases, alternatives to radar charts can be used, such as area charts, lollipop charts, radial bar charts, and star charts. In each case, multiple variables are represented in a single view, and measurements from multiple times or time periods (or time period averages) can be shown. In some cases, risk category 606 can be shown on the chart to, for example, allow comparison of measurement data with potential risks. While two time periods shown may be more or less usable, time series information is available, such as animations, to show changes over time. Time period charts can also allow for the determination of sensor accuracy or performance, as inaccurate readings should be highlighted during clinician review.

[0461] Figure 20 A group view based on yet another aspect is shown. As depicted, the display is horizontally divided into 1000 segments, each segment representing a specific risk interval within the component risk scoring framework utilized. In the illustrated example, the screen is divided into five segments 1000, which correspond to the white, yellow, orange, red, and blue risk intervals / categories of the early warning scoring framework.

[0462] In the group view, each patient is represented by a card 1100 displayed in segment 1000 of the display, based on the component risk score of each of the multiple monitored patients and the risk interval in which that component risk score falls. This card may reference a bed ID and / or location and, or replace the patient, to allow clinicians to quickly locate the patient. As a patient's component risk score changes, the display updates to adjust the card's positioning within its segment and, (if the score change is sufficient) eventually moves it to another segment corresponding to the new risk interval. In one aspect, the card's positioning relative to a segment may be driven by a temporal average of the component risk score, where the average is calculated over a time period that can be predetermined or set by the clinician, thus preventing the patient card from flickering between segments of the display. In another aspect, in addition to the temporal average of the component risk score, one or more predetermined rules may be used to determine the transition of a patient card from one segment to another, for example, if the value of an index indicates that the patient falls within a certain number of different risk intervals within a predetermined time period. In some cases, the system may exhibit hysteresis to slow the transition between segments. For example, the boundaries between zones may not be a single number (e.g., 30), but rather a higher number (e.g., 32) when entering a zone and a lower number (e.g., 28) when leaving a zone. In this way, patients cannot move quickly between zones, and monitoring can continue until, for example, they have completely left a high-risk zone.

[0463] Group views can be multi-ward views. Multi-ward views allow for simultaneous monitoring of multiple patients across multiple rooms and / or wards. They allow clinicians to clearly see all patients in a facility, hospital, or entire home care setting on a single monitor. In some cases, multi-ward views can be customized so that clinicians can view a subset of patients across one or more facilities. For example, a clinician might want to view the patients they are responsible for, who may be distributed across multiple locations. Multi-ward views provide the ability to view all these patients in real time, showing the most important information or the highest-risk clients in the most detail.

[0464] Each card includes key identifying information such as patient name, ID number, room and / or bed assignment. Additional health information may be displayed, including but not limited to an indicator 1200 of the total component risk score associated with the patient, the latest value of the physiological parameter that contributes most to the total component risk score, any other contributing physiological parameters being actively monitored, and parameters associated with any therapies the patient is receiving. Any such therapy parameters are not used to calculate the component risk score but still provide contextual information to clinicians monitoring the patient in this view. This allows clinicians to directly compare indicators driving health changes between patients displayed on a single screen. Example cards are shown in... Figure 21As shown in the image.

[0465] In one aspect, the indicator 1200 for the total component risk score is color-coded based on the trend of its value. That is, if the most recent consecutive calculations of the component risk score indicate a decreasing trend in patient risk (within a risk interval or between adjacent risk intervals), the indicator 1200 may be color-coded green. Conversely, an increasing trend in indicated risk may result in the indicator being color-coded red. Patients with a stable index (i.e., the score does not show a trend in either direction) may be color-coded gray or uncolored. The trend of the component risk score can also be determined by an increase or decrease in the rolling average of the component risk score, wherein in either case, the patient card is updated to improve its prominence in the group view. It is conceivable that alternative visual trend indicators may be used, including the size and font used to display the current value of the component risk score, or the color of associated graphic elements on the card.

[0466] In one aspect, the data included on the patient card (or equivalent bedside card) and its display method (e.g., layout, font size, color, font) are dynamically updated in real time or near real time based on one or more of the following: the magnitude of the patient's component risk score, the trend of the component risk score, the time elapsed since the receipt of the patient-related updated data, or the time elapsed since the clinician last observed the patient. The display of the card itself (e.g., size, background color, outline) may also be updated in real time or near real time based on one or more of the above factors.

[0467] Figure 22 and Figure 23 The diagram shows segments of a group view associated with specific risk intervals, and patient cards within each segment. As depicted, patients with component risk scores showing a trend in one direction or the other have their cards more prominently displayed within their segment. In some respects, the cards of patients who have recently changed their segment from one risk interval to another are also more prominently displayed. In one respects, this involves magnifying the patient cards and positioning them at the top of the corresponding segment. Any magnified cards within a segment can be arranged according to the gradient of the component risk score change, or its magnitude, or some combination of both factors. In some respects, the magnified cards include more information useful to clinicians, such as an expanded set of immediate measurements corresponding to physiological parameters actively monitored for that patient. In this way, patients most likely to switch between segments (or risk intervals) are highlighted to clinicians compared to patients who are likely to maintain their current risk level.

[0468] Patients with stable sub-risk scores or scores below a specific threshold of the risk interval can have their cards minimized and displayed in the lower part of the corresponding segment on the display. In one respect, these minimized cards contain the same data as those presented on the enlarged cards (albeit at a reduced size and emphasis), allowing clinicians to still access patient data without compromising the more prominent display of patient cards indicating those more likely to require attention. If any of these patients' sub-risk scores become unstable, their cards can be enlarged and repositioned at the top of the segment. This allows clinicians or system observers to identify patients under their care at the highest risk at a glance without interacting with controls and menus.

[0469] In one respect, the display of the patient card may vary depending on the section in which the patient card is displayed (i.e., the risk zone the patient falls into). Figure 24 One aspect is shown where patient cards in the "blue" section (or highest risk zone) may include bold text in a larger font.

[0470] In one respect, the size of each segment can vary according to the relative proportion of patient cards displayed within that segment. For example, when a large number of patient cards fall into the red segment, the sizes of the white, yellow, orange, and blue segments can be reduced to ensure that all patient cards in the red segment are simultaneously visible on the display at an appropriate resolution and size. Alternatively, the size of patient cards in segments corresponding to lower-risk zones can be reduced to accommodate the display of all patient cards in segments corresponding to higher-risk zones. These reduced-size cards may show less information, such as fewer immediate indicators, compared to the original configuration. In yet another respect, any segment without patient cards can be minimized or completely removed from the display. The group view described above improves current clinical practice by simplifying risk assessment. Patients are positioned on the screen based on their risk level, health trends, and relative to other patients in the group. Patients requiring clinician attention are most prominent and will be seen first on the dashboard. Additionally, clinicians can view all the aforementioned information on patient cards, along with the risk level associated with each patient under their care, on a single screen without needing to access menus or interfaces using a computer mouse or touchscreen. This allows clinicians to be presented with the most relevant information from the vast amount of data and information in the patient management system. Furthermore, the immediate, real-time nature of the data used to determine a patient's physiological parameters and sub-risk scores means that patient cards are constantly updated and moved around on the screen. This means the display ensures that clinicians can focus on the most urgent patients and / or tasks. Similarly, optionally, the use of normalized sub-risk scores reduces the amount of space required to display information.

[0471] In one aspect, the display of patient cards (or how they are displayed) can be dynamically adjusted based on the characteristics of the display. For example, the display may have registered users, such as clinicians. The display can then be updated to show only and / or highlight and / or enlarge the cards for which the nurse is responsible. In this way, the clinician's attention is directed to the patients they manage (or the beds in the rooms or wards of these patients), and a limited display area focuses on showing or only showing the data of these patients. Alternatively, a characteristic could be the location of the display. For example, the display could show and / or highlight and / or enlarge cards in the same room as the display. In some cases, the display is within RFID range of a bed locator system (such as the RFID system described above).

[0472] In one aspect, a monitor is installed in a location such as a room or ward. The monitor is configured to display a card for each patient in that room or ward. The monitor can be configured to determine which patients are in the room or ward based on the system, and only display the cards for those patients present. The display of each card can be adjusted as described above based on sub-risk scores and / or the distance between the clinician and the patient. For example, if a clinician is standing next to a patient, the monitor can essentially only display that patient. This allows the monitor to clearly show staff the current situation at a particular location. As described earlier, the cards can be enlarged and / or highlighted to indicate specific issues.

[0473] Discharge System

[0474] Regarding patient monitoring during clinician care, aspects related to the display of parametric data have been explained. However, additional views of parametric data can be used for other purposes. In some cases, the display can switch between alternative views based on clinical requirements. For example, a first view for monitoring patient health and a second view for considering whether the patient is mobile or discharged. Alternative views can be based on component risk scores (or risk indices). For each view, the component risk scores can be the same (e.g., presented differently), or alternative component risk scores can be present. Alternative views can be based on alternative indicators. In this example, we consider discharge scores. Discharge scores are a measure of the risk of a patient being discharged. Discharge scores can consist of or include component risk scores. Compared to patient monitoring, discharge scores can use adjusted component risk scores, or use different measurement features, to better represent the risk of a patient being discharged.

[0475] Figure 25A group view based on yet another aspect is shown. This aspect is configured, for example, to allow clinicians to identify patients ready for discharge. However, alternative features or combinations of features can be used to create and display patient intervals. As depicted, the display screen is horizontally divided into segments 2000, each segment representing a specific risk interval for patient discharge. In the illustrated example, the screen is divided into five segments 2000, corresponding to example intervals of risk associated with patient discharge. As described regarding component risk scoring, discharge scoring can be based on or combined with component scores and / or one or more values ​​measured in real-time or near real-time. Customizing discharge views advantageously allows hospitals or clinicians to provide the required reporting and / or monitoring mandated by regulations or hospital protocols prior to discharge. This can be centrally managed due to the system's openness and the flexibility of its architecture in handling the storage and display of patient health parameters, patient data, or ward or multi-ward profiles.

[0476] In the group view, each patient is represented by a card 2100 displayed in segment 2000 of the display, based on the discharge score of each of the multiple monitored patients and the risk interval in which that discharge score falls. As a patient's discharge score changes, the display updates to adjust the card's positioning within its segment and (if the score change is sufficient) eventually moves it to another segment corresponding to the new risk interval. In one aspect, the card's positioning relative to a segment can be driven by a time-averaged discharge score, where the average is calculated over a time period that can be predetermined or set by the clinician, thus preventing patient cards from flickering between segments of the display. In another aspect, in addition to the time-averaged discharge score, one or more predetermined rules can be used to determine the transition of a patient card from one segment to another, for example, if the score value indicates that the patient falls into different risk intervals a certain number of times within a predetermined time period. For example, if a patient's discharge risk appears to be the lowest, but the patient has only recently entered that category or frequently leaves that category, they can be placed in a higher-risk category until the discharge score has improved.

[0477] Each card includes key identifying information such as the patient's name, ID number, and room or bed assignment. Additional health information may be displayed, including but not limited to an indicator 1200 for the patient's overall discharge score, the latest value of the physiological parameter that contributes most to the overall discharge score (e.g., the highest risk component, which may limit discharge), any other contributing physiological parameters being actively monitored, and parameters associated with any therapies the patient is receiving. Any such therapy parameters are not used to calculate the discharge score but still provide contextual information in this view for clinicians considering the patient's discharge. This allows clinicians to directly compare the indicators driving health changes among patients displayed on a single screen.

[0478] Discharge scores can also be used, or alternatively, with other algorithms or measurements to determine the risk category associated with patient discharge. For example, algorithms such as decision trees, rule engines, or flowcharts can be used to determine patient categories. Characteristics may include patient measurement trends, patient characteristics (e.g., age, weight, race, sex) or treatment characteristics (condition, diagnosis, treatment used, treatment device used, treatment duration). Patient measurement trends may include discharge scores collected using a real-time patient monitoring system, portions of the discharge score, or physiological measurements. In some cases, treatment characteristics may include: initial diagnosis; diagnostic records during the patient's hospitalization; observations by caregivers or clinicians and / or comorbidities and past medical history. In some cases, socioeconomic factors, such as the patient's support network and / or family environment, may also be considered. Patient, treatment, and / or socioeconomic data may be entered into the system by clinicians, by the patient, or from electronic medical records or patient records. Available patient, treatment, and socioeconomic characteristics may be included.

[0479] In one respect, the discharge component risk score attempts at least to consider the patient's current condition and the patient's projected future condition. Patient characteristics may help assess the risk of future readmission and / or deterioration outside the care facility. Expected discharge prediction can utilize historical data on past patient performance (using the current system or based on relevant data).

[0480] In one aspect, the system can be configured to allow adjustment of discharge scores or discharge risk levels at or within each facility. This allows each facility to configure a desired discharge process that aligns with its own practices. The system can allow adjustment of any one or more inputs, weights, and classifications.

[0481] Further display can be used Figure 21 , Figure 22 and Figure 23The cards and card features shown are highlighted, but the focus is on discharge scores. In one aspect, the indicator 1200 for the total discharge score is color-coded based on the trend of its values. That is, if the most recent consecutive calculations of the discharge score indicate a decreasing trend in the patient's discharge risk (within a risk interval or between adjacent risk intervals), the indicator 1200 can be color-coded green. Conversely, an increasing trend in risk may result in the indicator being color-coded red. Patients with stable indices (i.e., indices that do not show a trend in either direction) can be color-coded gray or uncolored. Color coding can depend on the risk level; stable low risk can be color-coded green, as this also indicates suitability for discharge. The trend of the discharge score can also be determined by an increase or decrease in the rolling average of the discharge score, where in either case, the patient card is updated to improve its prominence in the group view. It is conceivable that alternative visual trend indicators could be used, including the size and font used to display the current value of the discharge score, or the color of associated graphic elements on the card.

[0482] In one aspect, the data included on the patient card and its display method (e.g., layout, font size, color, font) are dynamically updated in real-time or near real-time based on one or more of the following: the magnitude of the patient's discharge score, the trend of the discharge score, the time elapsed since the patient-related updated data was received, or the time elapsed since the clinician last observed the patient. The display of the card itself (e.g., size, background color, outline) may also be updated in real-time or near real-time based on one or more of the above factors. Although interpreted as a discharge score, in some aspects, a discharge score involves alternative metrics or requirements, such as any one or more of patient monitoring, discharge, or changes in treatment. In some cases, the system may perform tasks based on the displayed data. For example, the system may identify patients who may be ready for discharge or issue alerts to such patients. For example, if a patient indicates that they are ready for discharge or may be ready for discharge, the system may generate a discharge form. The discharge form may be provided to the clinician electronically, for example, via a link on the display. The clinician may have to perform several steps to ultimately make a discharge decision after receiving the form. Indicators on the display can indicate that the form or other materials are ready. In one aspect, the display can determine whether to show a hospital view or a monitoring view based on patient risk. For example, if the patient is in a high-risk zone, the display may only show the monitoring view.

[0483] In one aspect, the system includes an auxiliary display or device. This can provide alerts or alarms to portable computing devices, such as tablets or mobile phones. Alerts to the auxiliary device can be limited to a subset of possible alerts. For example, alerts can be sent to the auxiliary device only at a certain risk level or based on a subset of patients (e.g., patients directly under the clinician's care). In another aspect, the alert can also be flashed or announced on the main display. Using an auxiliary display to receive targeted alerts reduces the number of alarms or warnings sent to each clinician. In some cases, such as when an alarm is not responded to or is rejected within a period of time, the alarm or warning can be transmitted to a second clinician or the hospital alarm system. Alarms or warnings can be customized to state the urgency or situation that led to the alarm. For example, graphs of physiological parameters or component risk scores can be included in the alarm.

[0484] In one respect, the monitor can present only a range of patients in the discharge view. For example, the monitor can show only the lowest interval or the two lowest intervals. This reduces the complexity displayed on the screen, allowing focus on the patients most likely to be discharged. Due to the large amount of information and many potential patients, attempting to determine the appropriate patients for discharge can be difficult. Using a discharge view allows clinicians to focus on the most relevant or urgent information so that a large amount of information is clearly presented on the monitor.

[0485] In a healthcare setting, healthcare providers have limited time available to monitor patients (either through direct interaction with data provided by sensors / medical devices or by reviewing updated patient medical records). Routine practice involves reviewing data output from patient sensors / medical devices at regular intervals, such as every four hours. One or more of the above aspects can advantageously provide an efficient system for the efficient and continuous collection, processing, and evaluation of data from multiple patient sensors and / or medical devices, with corresponding electronic medical records and displays updated automatically in real time. This allows for remote, continuous, and immediate automated assessment of the patient's condition, enabling early detection of any deterioration in the patient's health or condition.

[0486] Therefore, healthcare professionals' responsiveness to sudden deterioration of patient conditions can be significantly improved without increasing their own workload by utilizing sensors and / or medical devices to continuously monitor and report patient status in real time, and by providing systems capable of dynamically receiving and processing data from such sensors and / or medical devices. In particular, this real-time aspect provides healthcare professionals with greater visibility and certainty, and allows for earlier intervention when a patient's condition worsens. Furthermore, rapid identification of patients exhibiting clinical signs of deterioration can improve patient care and treatment outcomes. This is typically expressed as a reduction in the duration of care or a decrease in the urgency of care, such as admission to the intensive care unit (ICU).

[0487] Furthermore, embodiments can be implemented using hardware, software, firmware, middleware, microcode, or any combination thereof. When implemented as software, firmware, middleware, or microcode, program code or code segments used to perform necessary tasks can be stored in a machine-readable medium (such as a storage medium or other storage device). The processor can perform the necessary tasks. A code segment can represent a procedure, function, subroutine, program, routine, subroutine, module, software package, class, or any combination of instructions, data structures, or program statements. A code segment can be coupled to another code segment or hardware circuit by passing and / or receiving information, data, parameters, arguments, or memory contents. Information, parameters, arguments, data, etc., can be passed, forwarded, or sent via any suitable means, including memory sharing, messaging, token passing, network transmission, etc.

[0488] In the foregoing, storage medium can refer to one or more devices for storing data, including read-only memory (ROM), random access memory (RAM), disk storage media, optical storage media, flash memory devices, and / or other machine-readable media for storing information. The terms "machine-readable media" and "computer-readable media" include, but are not limited to, portable or fixed storage devices, optical storage devices, and / or various other media capable of storing, containing, or carrying instructions and / or data, including non-transitory media.

[0489] The various exemplary logic blocks, modules, circuits, elements, and / or components described in conjunction with the examples disclosed herein can be implemented or performed using general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic components, discrete gate or transistor logic components, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in alternatives, the processor may be any conventional processor, controller, microcontroller, circuit, and / or state machine. The processor may also be implemented as a combination of computing components, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration.

[0490] The methods or algorithms described in conjunction with the examples disclosed herein may be embodied directly in hardware, software modules executable by a processor, or a combination of both, as processing units, programming instructions, or other indications, and may be contained in a single device or distributed across multiple devices. Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art. The storage medium may be coupled to the processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium may be an integral part of the processor.

[0491] Without departing from this disclosure, one or more of the components and functions illustrated in the accompanying drawings may be rearranged and / or combined into a single component or embodied as several components. Additional elements or components may also be added without departing from this disclosure. Additionally, the features described herein may be implemented in software, firmware, hardware, and / or any combination thereof.

[0492] In its various aspects, this disclosure can be embodied in computer-implemented processes, machines (such as electronic devices, or general-purpose computers, or other means providing a platform on which computer programs can be executed), processes performed by such machines, or articles of manufacture. Such articles of manufacture may include computer program products or digital information products (in which a computer-readable storage medium contains computer program instructions or computer-readable data stored thereon), as well as processes and machines for creating and using such articles of manufacture.

Claims

1. A patient management system, the patient management system comprising: A data management server, which communicates with multiple sensors configured to measure one or more physiological parameters of multiple patients, is configured to: Receive sensor data from the plurality of sensors via a network; Based on the sensor data, a component risk score is determined for each of the plurality of patients; Each of the plurality of patients is assigned to a corresponding group in a plurality of groups, at least in part based on the component risk score and multiple rules; as well as The display shows one or more patient identifiers on a graphical user interface in a first display mode, each patient identifier being associated with one of the plurality of patients and its component risk score; The one or more patient identifiers are arranged on the display screen based on the values ​​of their associated component risk scores.

2. The patient management system of claim 1, wherein the sensor data is received via one or more notification channels of a short-range wireless communication component.

3. The patient management system according to any one of claims 1 and 2, wherein the one or more patient identifiers are grouped into regions of the display, each region being associated with an upper and lower threshold of the component risk score, the thresholds defining a plurality of risk intervals.

4. The patient management system of claim 3, wherein the size and / or relative positioning of the one or more patient identifiers in their area on the display is based on one or more of the rate of change and direction of change of the corresponding component risk score.

5. The patient management system according to any one of claims 3 and 4, wherein the arrangement of the one or more patient identifiers is updated in real time when the determined value of the associated component risk score is updated.

6. The patient management system according to any one of claims 1 to 5, wherein the one or more patient identifiers are in the form of cards.

7. The patient management system according to any one of claims 1 to 6, wherein each of the one or more patient identifiers includes a risk indicator.

8. The patient management system of claim 7, wherein the risk indicator comprises a numerical value indicating the patient's risk level based on at least one of the patient's component risk score and associated risk interval.

9. The patient management system of claim 8, wherein the risk indicator is updated in real time when the updated value of the component risk score is determined.

10. The patient management system according to any one of claims 8 and 9, wherein the value is a rolling average.

11. The patient management system according to any one of claims 8 to 10, wherein the risk indicator further comprises a risk trend indicator configured to change its state according to whether the patient's risk level increases, decreases, or remains unchanged.

12. The patient management system of claim 11, wherein the risk trend indicator is color-coded.

13. The patient management system according to any one of claims 1 to 12, wherein the one or more patient identifiers further include the display of one or more physiological parameters associated with the patient. The selection and arrangement of one or more of these physiological parameters are based on their contribution to clinical risk indicators.

14. The patient management system of claim 13, wherein the display of the one or more physiological parameters is updated in real time.

15. The patient management system according to any one of claims 13 or 14, wherein the display of the one or more physiological parameters includes a rolling average of the one or more physiological parameters.

16. The patient management system according to any one of claims 1 to 15, wherein each of the one or more patient identifiers comprises one or more of the following elements: patient identification number, ward number, bed number, patient name, and an indication of the time elapsed since the clinician last interacted with the patient.

17. The patient management system of claim 16, wherein the presence, size, and display parameters of said one or more elements are based on one or more of the magnitude, rate of change, and direction of change of said component risk score.

18. The patient management system according to any one of claims 16 and 17, wherein the presence, size, and / or display parameters of said one or more elements are based on one or more of the following: The amount of time elapsed since the patient identifier moved from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score; and The estimated amount of time elapsed until the patient identifier moves from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score.

19. The patient management system of claim 18, wherein the second risk interval is a higher risk interval than the first risk interval.

20. The patient management system according to any one of claims 18 and 19, wherein the estimated time amount is provided by analyzing trends in historical values ​​of the component risk scores.

21. The patient management system according to any one of claims 1 to 20, wherein the sensor data is received from a respiratory support device including or communicating with the plurality of sensors.

22. The patient management system according to any one of claims 1 to 21, wherein the component risk score is a normalized component risk score.

23. A patient management method, the method comprising: Sensor data is received via a network from multiple sensors configured to measure one or more physiological parameters of multiple patients; Determine the component risk score for each of the plurality of patients; Each of the plurality of patients is assigned to one of the plurality of groups, at least in part, based on the component risk score and multiple rules; as well as The display shows one or more patient identifiers on a graphical user interface in a first display mode, each patient identifier being associated with one of the plurality of patients and its component risk score; The one or more patient identifiers are arranged within their respective groups on the display screen based on the relative values ​​of their associated component risk scores.

24. The method of claim 23, wherein the sensor data is received via one or more announcement channels of a short-range wireless communication protocol.

25. The method of claim 23 or 24, wherein assigning the plurality of patients to the plurality of groups comprises reassigning patients from a first group having an associated risk interval to a second group having a second associated risk interval; The method further includes the following steps: If the second associated risk interval is associated with a higher clinical risk than the first risk interval, an alert status is generated.

26. The method of claim 25, wherein the alert status triggers a notification to the hospital monitoring system.

27. A method for generating a normalized component risk score based on measurements of one or more physiological parameters of a patient, the method comprising the steps of: Receive sensor data; Determine at least one physiological parameter of the patient based on the sensor data; A component risk score is determined based on the at least one physiological parameter; Output the component risk score.

28. The method of any one of claims 27, wherein the sensor data is received via one or more announcement channels of a short-range wireless communication protocol.

29. The method of claim 27 or 28, wherein determining the component risk score comprises associating at least one of the at least one physiological parameter with a corresponding risk interval of a plurality of risk intervals, each of the plurality of risk intervals having a corresponding first upper limit threshold and a first lower limit threshold, wherein the at least one associated physiological parameter falls between the first upper limit threshold and the first lower limit threshold of the corresponding risk interval.

30. The method according to any claim 29, wherein the risk range corresponds to a predetermined early warning score value.

31. The method according to any one of claims 29 to 30, wherein the plurality of risk intervals includes a first risk interval and a second risk interval.

32. The method of claim 31, wherein the size of the first risk interval is different from the size of the second risk interval.

33. The method of claim 32, wherein the size of the risk interval is defined by the difference between its first upper limit threshold and its first lower limit threshold.

34. The method according to any one of claims 27 to 33, wherein the physiological parameter is one of body temperature, blood pressure, respiratory rate, heart rate, carbon dioxide level and SpO2.

35. The method according to any one of claims 27 to 34, wherein the physiological parameters and the component risk scores are stored as time series.

36. The method according to any one of claims 27 to 35, wherein the physiological parameters and the component risk score are updated in real time.

37. The method according to any one of claims 27 to 36, wherein the component risk score is recalculated at regular time intervals.

38. The method according to any one of claims 27 to 37, wherein the component risk score is recalculated only when new sensor data is received and updated physiological parameters are determined.

39. The method according to claims 27 to 38, further comprising the step of: The second physiological parameter is determined based on the sensor data; The second component risk score is determined based on the second physiological parameter; Output the risk score for the second component; as well as The total component risk score is determined based on the first component risk score and the second component risk score.

40. The method of claim 39, wherein determining the total component risk score comprises selecting the highest component risk score among the first component risk score and the second component risk score as the total component risk score.

41. The method of claim 39, wherein determining the total component risk score comprises averaging the first component risk score and the second component risk score.

42. The method of claim 39, wherein determining the total component risk score comprises calculating a weighted average of the first component risk score and the second component risk score, wherein the weighting is based on a predetermined set of rules.

43. The method of claim 39, wherein determining the total component risk score comprises summing the first component risk score and the second component risk score and comparing the sum with a predetermined threshold.

44. The method according to claims 27 to 43, further comprising the step of: The component risk score is displayed in a first view of the display screen, wherein the component risk score is displayed together with a patient identifier that corresponds to a patient associated with the sensor data and the physiological parameters derived from the sensor data.

45. The method of claim 44, wherein the component risk score is displayed in the form of an instrument, wherein the instrument divides the plurality of risk intervals into segments based on the second upper threshold and the second lower threshold.

46. ​​The method of claim 45, wherein the instrument displays a rolling average of the component risk score.

47. The method of any one of claims 44 to 46, wherein displaying the component risk score further comprises displaying a graphical time series showing the current and historical values ​​of the component risk score.

48. The method according to any one of claims 44 to 47, further comprising the step of: The physiological parameters are displayed in the first view of the display screen.

49. The method of claim 48, wherein displaying the physiological parameter further comprises displaying a graphical time series showing the current and historical values ​​of the physiological parameter.

50. The method of claim 49, wherein the graphical time series is updated in real time when the updated value is determined.

51. The method according to any of the preceding claims as dependent on claim 39, the method further comprising the step of: Display the second physiological parameter; Displays the risk score for the second component; as well as The total risk score is displayed.

52. The method of claim 51, wherein the display of the first physiological parameter and the second physiological parameter is arranged based on their associated first component risk score and associated second component risk score.

53. The method of claim 51, wherein the display of the first physiological parameter and the second physiological parameter is arranged according to the relative contribution of the first physiological parameter and the second physiological parameter to the total component risk score.

54. The method according to claims 27 to 53, further comprising the step of: Receive parameters of the therapy provided to the patient by the respiratory support device and / or usage data indicating the patient's use of the respiratory support device; as well as The treatment parameters and / or usage data are displayed on the screen.

55. The method of claim 54, wherein the therapy parameters and / or the usage data are displayed as a time series and updated in real time.

56. The method according to any one of claims 44 to 55, further comprising the step of: One or more patient identifiers are displayed in the second view of the display screen, each patient identifier being associated with a patient and component risk score; The one or more patient identifiers are arranged on the display screen based on the relative values ​​of their associated component risk scores.

57. The method of claim 56, wherein the one or more patient identifiers are grouped into regions of the display, each region being associated with a risk interval among the plurality of risk intervals.

58. The method of claim 57, wherein the size and / or relative positioning of the one or more patient identifiers in their area on the display is based on one or more of the rate of change and direction of change of the corresponding component risk score.

59. The method of claim 58, wherein the arrangement of the one or more patient identifiers is updated in real time when the determined value of the associated component risk score is updated.

60. The method according to any one of claims 56 to 59, wherein the one or more patient identifiers are in the form of cards.

61. The method of claim 60, wherein each of the one or more patient identifiers includes a risk indicator.

62. The method of claim 61, wherein the risk indicator comprises a numerical value indicating the patient's risk level based on the patient's component risk score and the associated risk interval.

63. The method of claim 62, wherein the value is a rolling average.

64. The method according to claims 61 to 63, wherein the risk indicator is updated in real time when the updated value of the component risk score is determined.

65. The method of any one of claims 61 to 64, wherein the risk indicator further comprises a risk trend indicator configured to change its state according to whether the patient's risk level increases, decreases, or remains unchanged.

66. The method of claim 65, wherein the risk trend indicator is color-coded.

67. The method of any one of claims 56 to 66, wherein the one or more patient identifiers further include the display of one or more physiological parameters associated with the patient. The selection and arrangement of one or more of the physiological parameters are based on their contribution to the component risk score.

68. The method of claim 67, wherein the display of the one or more physiological parameters is updated in real time.

69. The method of claim 68, wherein the display of the one or more physiological parameters comprises a rolling average of the one or more physiological parameters.

70. The method according to any one of claims 56 to 69, wherein each of the one or more patient identifiers comprises one or more of the following elements: patient identification number, ward number, bed number, patient name, and an indication of time elapsed since the clinician last interacted with the patient.

71. The method of claim 70, wherein the presence, size, and / or display parameters of said one or more elements are based on one or more of the magnitude, rate of change, and direction of change of said component risk score.

72. The method of claim 70, wherein the presence, size, and / or display parameters of said one or more elements are based on one or more of the following: The amount of time elapsed since the patient identifier moved from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score; and The estimated amount of time elapsed until the patient identifier moves from one area of ​​the display associated with the first risk interval to another area of ​​the display associated with the second risk interval due to a change in the corresponding component risk score.

73. The method of claim 72, wherein the second risk range is a higher risk range than the first risk range.

74. The method according to any one of claims 72 and 73, wherein the estimated time amount is provided by analyzing trends in historical values ​​of the component risk scores.

75. The method according to any one of claims 27 to 74, the method comprising normalizing the component risk score.

76. The method of claim 75, wherein determining the component risk score includes feature scaling or min-max normalization of the physiological parameter within a first threshold of the risk interval to provide a measure of the location of the physiological parameter within the first threshold of the risk interval.

77. The method according to any one of claims 75 to 76, wherein determining the normalized component risk score comprises standardizing the size of each of the plurality of risk intervals to a preferred size W, wherein each standardized risk interval has a second upper limit threshold and a second lower limit threshold separated by W.

78. The method of claim 77, wherein the normalized component risk score is determined according to the following formula:

79. A patient monitoring system comprising being configured to perform the method according to any one of claims 27 to 78.

80. The patient monitoring system according to claim 52, wherein the patient monitoring system comprises: One or more sensors; and Process the server.

81. A method for monitoring a patient using multiple health sensors to identify patients with deteriorating health, the method comprising: Sensor data is received from the plurality of sensors via one or more notification channels of a short-range wireless communication component, the sensor data being based on measurements of individual patients; The physiological parameters of the individual patient are determined based on the sensor data; Health parameters are determined based on the aforementioned physiological parameters; Output the health parameters.

82. A method for operating a sensor system to monitor a patient's health, the method comprising: Sensor data is received from multiple sensors via one or more announcement channels of a short-range wireless communication component; Two or more physiological parameters of the patient are determined based on the sensor data from the plurality of sensors; Health status is determined based on the aforementioned physiological parameters; as well as Output the stated health status.

83. A method for operating a sensor system to monitor a patient's health, the method comprising: Sensor data is received from multiple sensors via one or more announcement channels of a short-range wireless communication component, the sensor data indicating one or more physiological parameters of the patient; Based on the sensor data, the system detects whether the patient's health parameters are higher or lower than a predetermined threshold. as well as Output instructions on the health parameters to the healthcare provider so that the healthcare provider can provide treatment to the patient.

84. The method of claim 82 or 83, wherein detecting whether the patient's health parameter is higher or lower than the predetermined threshold comprises comparing different physiological parameters, each physiological parameter being obtained from sensor data from the plurality of sensors.

85. The method of claim 84, wherein detecting whether the patient's health parameter is higher or lower than the predetermined threshold comprises: The one or more physiological parameters are determined based on the sensor data; as well as The patient's health parameters are determined based on the one or more physiological parameters; as well as The health parameter is compared with the predetermined threshold.

86. A method for operating a hub for a system used to monitor the health of a patient, the method comprising: A first data packet is received from a first sensor surrounding the hub via a first announcement channel of a short-range communication component, wherein the first data packet contains sensor data from the first sensor related to a first physiological measurement result of the patient; The first data packet is transmitted to a server located outside the hub via a network communication component. A second data packet is received from a second sensor connected to the hub as a peripheral device via a second notification channel of the short-range communication component, wherein the second data packet contains sensor data from the second sensor related to a second physiological measurement result of the patient; and The second data packet is transmitted to the server via the network communication component.

87. The method of claim 86, wherein the first notification channel is the same as the second notification channel.

88. The method of claim 86, wherein the first notification channel is different from the second notification channel.

89. The method according to any one of claims 86 to 88, the method further comprising processing the first data packet at least partially before transmitting the first data packet to the server.

90. The method according to any one of claims 86 to 89, the method further comprising formatting the first data packet before transmitting the first data packet to the server.

91. The method according to any one of claims 86 to 90, the method further comprising adding a timestamp to the first data packet.

92. The method according to claims 86 to 88, the method further comprising forwarding the raw data and / or unprocessed first sensor data in the first data packet to the server.

93. The method according to any one of claims 86 to 92, wherein the first physiological parameter is the same as the second physiological parameter, and wherein the method further comprises combining the first data packet and the second data packet before transmitting the first data packet and the second data packet to the server.

94. The method according to any one of claims 86 to 93, wherein the network communication component is a wireless internet component.

95. The method according to any one of claims 96 to 94, wherein the first data packets are received from the first sensor in a continuous stream of data packets via the first announcement channel.

96. The method according to any one of claims 86 to 95, wherein the first data packet and the second data packet are transmitted to the server simultaneously.

97. The method of any one of claims 86 to 96, further comprising receiving a third data packet from a third sensor surrounding the hub via a third notification channel of the short-range communication component, wherein the third data packet contains sensor data from the third sensor relating to a third physiological measurement of the patient.

98. The method of any one of claims 86 to 97, wherein the first data packet includes a patient identifier, and wherein the second data packet includes the patient identifier.

99. A hub for a system for monitoring a patient's health, the hub comprising: Short-range communication components; Network communication components; processor; and A memory storing instructions that, when executed by the processor, cause the processor to: A first data packet is received from a first sensor surrounding the hub via a first announcement channel of the short-range communication component, wherein the first data packet contains sensor data from the first sensor related to a first physiological measurement result of the patient; The first data packet is transmitted to a server located outside the hub via the network communication component. A second data packet is received from a second sensor connected to the hub as a peripheral device via a second notification channel of the short-range communication component, wherein the second data packet contains sensor data from the second sensor related to a second physiological measurement result of the patient; and The second data packet is transmitted to the server via the network communication component.

100. A system for monitoring the health of a patient, the system comprising: A central hub, the central hub including a short-range communication component having multiple announcement communication channels; A first sensor is located around the central hub and is configured to obtain a measurement result of a first physiological parameter of the patient and transmit a first data packet to the central hub via a first notification channel of the plurality of notification communication channels, wherein each of the first data packets contains data related to the measurement result of the first physiological parameter. and A second sensor is located around the central hub and the first sensor. The second sensor is configured to obtain a measurement result of the patient's second physiological parameter and transmit a second data packet to the central hub via a second notification channel among the plurality of notification communication channels, wherein each of the second data packets contains data related to the measurement result of the second physiological parameter.

Images