Edge computing system for local data processing in clinical networks

Abstract

An edge computing system for locally processing data in a clinical network managed by a remote central server device 100, comprising at least one medical device 5AA, a SAN, at least one first edge node 3A, at least one medical device 5AA, a monitoring device 7 assigned to the SAN, the at least one first edge node 3A comprising a connection interface 13 adapted to establish a data connection with the at least one medical device 5AA, the SAN, and at least one of the remote central server device 100 and the monitoring device 7, and a processing module 15 adapted to (i) aggregate raw data from the at least one medical device 5AA, the SAN, (ii) combine at least metadata with the aggregated raw data to generate processed data, and (iii) transmit the processed data via the data connection to the monitoring device 7 and / or the remote central server device 100. A method and computer program product for locally processing data in a clinical environment are also described.

Description

[Technical field]

[0001] The present invention relates to an edge computing system for locally processing data in a clinical network managed by a remote central server device and to a method for locally processing data in a clinical environment as claimed in claim 1. [Background technology]

[0002] Current state-of-the-art systems for processing data in a clinical environment are divided into two network areas: the so-called point-of-care networks and the hospital IT networks.

[0003] Point-of-care networks provide automated electronic data capture of patient-related and healthcare information, as well as device operational data. Medical / health device communication standards are specified in ISO / IEEE 11073. Hospital IT networks facilitate the exchange and storage of healthcare information and can be specified by standards such as DICOM, HL7 v2, or HL7 FHIR.

[0004] Thus, point-of-care networks currently known in the art focus only on aspects of obtaining healthcare information near the patient's bed and room elements. However, processing of the obtained information, such as specific data processing and visualization, requires a higher perspective and data integration. Such specific data processing, in the prior art, typically relies on a central server architecture that manages the hospital IT network.

[0005] Such a central server requires hardware capabilities that are difficult to predict in order to handle the potentially large volume of requests originating from many remote devices. Also, such a central server architecture presents a potential single point of failure. Thus, if the central server fails, the entire system may stop functioning as desired and intended. Further problems arise if communication with the central server is compromised. Summary of the Invention [Problem to be solved by the invention]

[0006] It is an object of the present invention to provide a computing system and method for processing data in a more efficient and reliable manner. [Means for solving the problem]

[0007] This object is achieved by an edge computing system for processing data locally in a clinical network managed by a remote central server device, comprising the features of claim 1.

[0008] Therefore, edge computing systems are At least one medical device, at least one first edge node, and a monitoring device assigned to the at least one medical device, wherein the at least one first edge node: a connection interface adapted to establish a data connection with at least one medical device and at least one of a remote central server device and a monitoring device; A processing module, (i) aggregating raw data from at least one medical device; (ii) at least combining the metadata with the aggregated raw data to generate processed data; (iii) a processing module adapted to transmit the processed data via a data connection to the monitoring device and / or to a remote central server device; Equipped with.

[0009] Although an edge computing system is managed by a remote central server device, the remote central server device may not be part of the actual edge computing system per se, however, in examples, the edge computing system may include a remote central server device.

[0010] The at least one medical device can be understood as a passive device or an active device that can be associated with the patient and located in the vicinity of the patient. For example, the medical device can be located at the patient's bedside. An example of a passive medical device is a device that monitors at least one vital function of the patient, such as blood pressure, heart rate, etc., and therefore can also be called a "patient monitoring device." An example of an active medical device can be an infusion device, such as an infusion pump.

[0011] The monitoring device may be a physiological electronic monitoring device that may also use electronic medical charts and records. Typically, one such monitoring device may be used to monitor the status of multiple medical devices simultaneously. For example, the monitoring device may include a computer, such as a desktop computer, and a display, such as a touch screen display. The computer may run software, such as software that effectively organizes users, such as nurses, and provides infusion status to assist users in prioritizing their actions. In an example, 24 rooms / 48 beds may be monitored. However, in further examples, more or fewer rooms / beds may be monitored.

[0012] In this specification, at least one first edge node can be understood as a computing device that can act as a portal to enable communication between medical devices connected to the edge node, to enable communication with other edge nodes, as well as other medical devices, monitoring devices, and remote central server devices connected to other edge nodes. Also, corresponding to the name "edge node", the computing device can be generally considered to perform at least one function at the edge of a physical location. For example, the first edge node can directly communicate with a remote central server device, or can indirectly communicate with a remote central server device, for example via at least one second edge node that can connect multiple first edge nodes.

[0013] The first edge node includes a connection interface adapted to establish a data connection with at least one medical device and at least one of a remote central server device and a monitoring device. The term "interface" can be used to refer to a hardware interface and / or a software interface that allows the first edge node to establish a data connection. The data connection can be established permanently or temporarily, i.e. when needed, and it can be an uplink and / or downlink data connection. Also, the data connection with the remote central server device and / or the monitoring device can be established directly with at least one of these devices or indirectly, for example via a second edge node.

[0014] The raw data that the processing module is adapted to aggregate from at least one medical device can be understood as data sent or read by the medical device. Each medical device can have a specific payload and protocol for transferring / receiving data. Here, the term "payload" can be used to refer to the "actual data" sent or read. The term "protocol" can be used to refer to a software protocol that utilizes proprietary software or an open source protocol that utilizes open source software.

[0015] The metadata that the processing module is adapted to combine with the aggregated raw data to generate the processed data may include a location identifier, a patient identifier, a prescription identifier, etc. In this regard, the term "metadata" may be generally understood as data that provides information about other data and that may be used to point to a specific location in a hospital topology, in an example. The specific location may be at a patient level, a room level, a ward level, and / or an organization level. Also, the mere combination of metadata and aggregated raw data may be referred to as "rich data."

[0016] The processing module is also adapted to transmit the processed data to the monitoring device and / or a remote central server device via the data connection.

[0017] Advantageously, the edge computing system allows for the division and partitioning of network and data management, where each edge node can host and execute different functional data processing at each topology level, enabling specific data processing, visualization or notification according to the actual needs of each topology level.

[0018] As such, the edge computing system described herein enables more efficient processing and transfer of data in a distributed manner.

[0019] In examples, the connection interface is further configured to retrieve analytical data from the remote central server device and / or the monitoring device, and the processing module is further configured to combine the analytical data with the raw data and metadata into processed data.

[0020] The term "analytical data" may be used herein to refer to data previously obtained from aggregated raw data and metadata and / or data extracted using algorithms to obtain meaningful information from large amounts of data, such as previously aggregated raw data and metadata. In a more specific example where an infusion is to be administered, the term "analytical data" may be data regarding the remaining infusion time, i.e., the time that elapses until the target volume is reached. The smart data generated accordingly may be visualized as a progress, for example by displaying a gauge on the display of the monitoring device.

[0021] Advantageously, when analytical data is combined with raw data and metadata into processed data, smart data can be generated that can be used both to gain new insights using the aggregated raw data and metadata, and to create models that can be used to analyze the data.

[0022] In an example, the edge computing system includes a computing resource, preferably a software library, the connection interface is further configured to establish a data connection with the computing resource and retrieve analytical data from the computing resource, and the processing module is further configured to combine the analytical data with the raw data and metadata into processed data.

[0023] Advantageously, the analytical data may be stored in a computing resource, such as a drug library, which may include, for example, data regarding a patient's past and current medications, and which may be accessed when the analytical data needs to be obtained to generate smart data.

[0024] In an example, the edge computing system includes a further first edge node, the connection interface of the first edge node is further configured to establish a data connection with the further first edge node, the further first edge node communicates with at least one further medical device, and the processing module of the first edge node is further configured to transmit and receive processed data to and from the further first edge node.

[0025] Here, the further first edge node may be of the same type as the first edge node described above, and the medical device and the further medical device may be of the same type.

[0026] Advantageously, the first edge node and the further first edge node can communicate and exchange data directly with each other, i.e. without the need for communications to be routed through a central server.

[0027] In an example, the edge computing system includes a connection interface configured to establish a data connection with at least one first edge node and at least one of a remote central server device and a monitoring device; a processing module adapted to transmit and receive the processed data to at least one first edge node; and at least a second edge node comprising:

[0028] Advantageously, a number of first edge nodes may be connected to a second edge node, and a data connection with a remote central server device and / or a monitoring device may be made directly or indirectly, for example via a higher tier edge node.

[0029] In the example, the connection interface of the second edge node further includes: receiving analytical data from at least one first edge node and at least one of a remote central server device and a monitoring device; The processing module further comprises: Combining analytical data into processed data, The processed data is then transmitted via a data connection to the monitoring device and / or to a remote central server device.

[0030] The analytical data may be received, for example, from a remote central server device, the first edge node, a further first edge node, or a computing resource.

[0031] Advantageously, the second edge node may generate smart data, which may then be transmitted to the monitoring device and / or to a remote central server.

[0032] In an example, a first edge node is assigned to a patient and a second edge node is assigned to a hospital room, or a first edge node is assigned to a hospital room and a second edge node is assigned to a hospital ward.

[0033] In an example, at least one third edge node, and preferably a number of further upper level edge nodes, are disposed between the second edge node and the central server device.

[0034] The edge computing system may, for example, include at least one third edge node and further upper level edge nodes.

[0035] In an example, at least one third edge node is assigned to a hospital building and / or to the hospital.

[0036] In an example, at least one medical device is configured to disconnect a data connection with a first edge node when moving out of range of the first edge node, and to establish a data connection with a further first edge node when moving within range of the further first edge node.

[0037] For example, at least one medical device may be operable with multiple or all of the first edge nodes in the system, such as, for example, operable with at least the first edge node and further first edge nodes.

[0038] Advantageously, the medical device may automatically disconnect and reconnect to the first edge node when it is moved from one patient room to another.

[0039] In examples, the at least one medical device is at least one of an infusion device and a patient monitoring device.

[0040] Here, the injection device can be a syringe pump and / or a volumetric pump. The patient monitoring device can be an EEG monitoring device, a breath monitoring device, and / or a device for monitoring blood glucose level, blood pressure, heart rate and / or oxygen concentration.

[0041] In an example, the connectivity module of the at least one first edge node is adapted to connect to the at least one medical device via a wireless connection, preferably a wireless LAN connection.

[0042] Advantageously, an existing network can be utilized to connect the first edge node to the medical device.

[0043] In examples, the connectivity modules of the at least one first edge node and / or the at least one second edge node are adapted to operate with the communication network in accordance with EN ISO 11073 and / or in accordance with the Fast Healthcare Interoperability Resources (FHIR) standard and / or the Health Level 7 (HL7) standard.

[0044] Advantageously, the first edge node and the second edge node may be capable of connecting to a point-of-care network and to a hospital IT network.

[0045] The present invention also provides an edge computing system for processing data locally in a clinical network, comprising: a plurality of first edge nodes, each first edge node being connectable to at least one medical device for exchanging data with the at least one medical device and operable to exchange data between the plurality of first edge nodes; at least one second edge node, the second edge node being connectable to each first edge node, and to at least one of a third edge node and a remote central server device, for exchanging data; The present invention relates to an edge computing system comprising:

[0046] The present invention also provides a method for processing data locally in a clinical environment using an edge computing system, the edge computing system comprising at least one first edge node, at least one medical device, and a monitoring device assigned to the at least one medical device, the method comprising: Establishing a data connection with at least one medical device and at least one of a remote central server device and a monitoring device through a connection interface of the at least one first edge node; by a processing module of the at least one first edge node, (i) aggregating raw data from at least one medical device; (ii) combining at least the metadata with the aggregated raw data to generate processed data; (iii) transmitting the processed data via a data connection to the monitoring device and / or to a remote central server device; and The present invention relates to a method comprising the steps of:

[0047] In an example, the method comprises: Combining the analytical data with the raw data and metadata to form processed data; and / or transmitting and receiving the processed data to at least one further first edge node; Includes.

[0048] In another example, a method includes transmitting the processed data to at least one second edge node; establishing, at the second edge node, a data connection with at least one of a further first edge node, a remote central server device, and a monitoring device; Includes.

[0049] The present invention further relates to a computer program product comprising a computer readable storage medium having program instructions stored thereon, the program instructions being executable by a processor to perform the methods described herein.

[0050] Subsequently, the idea underlying the invention will be explained in more detail by referring to embodiments shown in the figures. [Brief description of the drawings]

[0051] [Figure 1] FIG. 1 is a schematic diagram of centralized data processing in a clinical environment as known in the art. [Diagram 2] FIG. 1 is a schematic diagram of distributed data processing in a clinical environment utilizing an edge computing system that processes data locally. [Diagram 3] FIG. 1 is a schematic diagram of an edge computing system for locally processing data in accordance with an embodiment of the present invention. [Figure 4A] FIG. 1 is a schematic diagram of a medical device disconnecting from a first edge node and connecting to a further first edge node. [Figure 4B] FIG. 1 is a schematic diagram of a medical device disconnecting from a first edge node and connecting to a further first edge node. [Figure 4C] FIG. 1 is a schematic diagram of a medical device disconnecting from a first edge node and connecting to a further first edge node. [Diagram 5] FIG. 1 illustrates the general steps of a case study utilizing an edge computing system. [Figure 6A] FIG. 1 illustrates a schematic upstream data flow in distributed data processing in a clinical environment utilizing an edge computing system. [Figure 6B] FIG. 1 illustrates a schematic downstream data flow in distributed data processing in a clinical environment utilizing an edge computing system. [Figure 7] FIG. 2 illustrates a simplified layer model including data types according to an embodiment of the present invention. [Figure 8] FIG. 2 illustrates a method flow according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0052] FIG. 1 shows a schematic diagram of centralized data processing in a clinical environment as known in the art. The setup shown in FIG. 1 is a simplified representation of data processing at various levels of a clinical environment. On the far left side of FIG. 1, a patient's bedroom is shown, along with a number of medical devices 5AA-5AN, such as devices for monitoring the patient's vital functions and / or infusion pumps, that may be located within the patient's bedroom and are typically located at the patient's bedside. As shown in FIG. 1, some of the medical devices 5AA-5AN include WiFi interfaces for wireless communication.

[0053] Medical devices are typically monitored using monitoring devices at the ward level. However, as indicated by the dashed horizontal arrows, data from the medical devices is first routed through the building and hospital levels to a central server located at the organization level. In the prior art example of Figure 1, an alarm situation is shown for illustrative purposes, where alarm detection and alarm silencing are performed via the central server.

[0054] The use of centralized data processing as shown in Figure 1 requires hardware capabilities that are difficult to predict in advance in order to handle a large number of potential requests originating from a large number of possible devices. Also, such a central server architecture presents a potential single point of failure: if the central server fails or communication with the server is interrupted, the entire system may stop functioning as desired and intended.

[0055] 2 shows a schematic diagram of distributed data processing in a clinical environment utilizing an edge computing system for processing data locally according to an embodiment of the present invention. The different levels of the clinical environment shown in FIG. 2 correspond to the levels shown in FIG.

[0056] At different levels of a clinical environment, different operations or functions f(x), g(x), h(x), z(x) are exemplarily shown in Figure 2. The operations f(x), g(x), h(x), z(x) are directly handled by each edge node at a specific level (not shown in Figure 2).

[0057] Here, an edge node may be responsible for the f(x) function at the ward level, e.g. silencing an alarm, whereas a further edge node at a higher level may be responsible for the g(x) function at the building level, e.g. for displaying the status of some beds or wards and supervising them etc. An edge node above the aforementioned one may be connected to a drug library at the hospital level and may retrieve / add data from / to the drug library. In the example shown in Fig. 2, a central server is at the organisation level, centralising the information and implementing advanced functions z(x) like Continuous Quality Improvement (CQI).

[0058] Distributed data processing is explained in more detail with reference to the following figures.

[0059] Figure 3 shows a schematic diagram of an edge computing system 1 for processing data locally according to an embodiment of the present invention. The edge computing system 1 shown in Figure 3 can be used for clinical environments using distributed data processing as shown above in Figure 2.

[0060] The edge computing system 1 shown in FIG. 3 includes two first edge nodes 3A, 3B. However, in a minimum configuration, the edge computing system 1 may also include only one first edge node 3A in an embodiment of the present invention. Also shown is at least one medical device 5AA, 5BA connected to each first edge node 3A, 3B. However, two or more medical devices, indicated by medical devices 5AN, 5BN shown using dashed lines, may be connected to each first edge node 3A, 3B.

[0061] The first edge nodes 3A, 3B also include connection interfaces 13 adapted to establish data connections with the medical devices 5AA, 5AN, 5BA, 5BN and at least one of the remote central server device 100 and the monitoring device 7 shown in FIG. 3. Here, the data connections can be made directly via the corresponding devices or via other edge nodes. For example, as will be explained in more detail below, the data connection from the first edge node 3A to the central server 100 is made via the second edge node 11. Also, as shown in FIG. 3, the data connection between the further first edge node 3B and the monitoring device 7 can be made via the first edge node 3A, but can also be established directly as indicated by the dashed line connecting the monitoring device 7 with the further first edge node 3B. Furthermore, FIG. 3 shows a computing resource 9 including a software library to which the first edge node 3A is connected. The further first edge node 3B and the computing resource 9 can be connected via the first edge node 3A, but can also be connected directly as indicated by the dashed line connecting the computing resource 9 to the further first edge node 3B. Also in an embodiment of the present invention, further monitoring devices 7' and further computing resources 9' may also or alternatively be connected to a further first edge node 3B.

[0062] The processing module 15 of the first edge node 3A, 3B in the embodiment shown: (i) aggregating raw data from at least one medical device 5AA, 5AN, 5BA, 5BN; (ii) combining at least the metadata with the aggregated raw data to generate processed data; (iii) transmitting the processed data to the monitoring device 7 and / or the remote central server device 100 via a data connection.

[0063] In the embodiment shown, the connection interface 13 is further configured to retrieve analytical data from the remote central server device 100 and / or the monitoring device 7, and the processing module 15 is further configured to combine the analytical data with the raw data and metadata into processed data.

[0064] The various data types are described in more detail with reference to FIG.

[0065] 3 also shows a connection between the first edge node 3A and a further first edge node 3B, the further first edge node 3B being shown to communicate with at least one further medical device 5BA. The processing module 15 of the first edge node 3A is further adapted to transmit and receive processed data to and from the further first edge node 3B.

[0066] Here, the illustrated further first edge node 3B is of the same type as the first edge node 3A. Thus, the first edge node 3A and the further first edge node 3B can communicate and exchange data directly with each other, i.e. without the need for communications to be routed through the central server device 100. Also, Figure 3 shows a dashed line between the further first edge node 3B and the second edge node 11, indicating that the further first edge node 3B can also communicate directly with the second edge node 11.

[0067] The second edge node 11 shown in Fig. 3 also includes a connection interface 13 and a processing module 15. Here, the same reference numerals as the corresponding components of the first edge nodes 3A, 3B are used, since these components may be essentially similar. The connection interface 13 of the second edge node 11 is adapted to establish a data connection with at least one of the first edge node 3A and the remote central server device 100 and the monitoring device 7. The connection interface 13 of the second edge node 11 is further adapted to receive analysis data.

[0068] The monitoring device 7 and the further first edge node 3B may be directly connected to the second edge node 11 or may connect via the first edge node 3A as shown in FIG.

[0069] The processing module 15 of the second edge node 11 is adapted to receive and transmit the processed data from the at least one first edge node 3A and is further adapted to combine the analytical data into processed data and transmit the processed data to the monitoring device 7 and / or the remote central server device 100 via the data connection.

[0070] The first edge nodes 3A, 3B shown may be assigned to respective hospital rooms and the second edge node 11 may be assigned to a ward. In further embodiments, at least a third edge node 17A, or multiple further higher level edge nodes 17N, may be located between the second edge node 11 and the central server device 100. In Figure 3, both the third edge node 17A and the higher level edge node 17N are shown by dashed lines to indicate that these entities are merely optional.

[0071] 4A-4C show schematic diagrams of a medical device 5AA disconnecting from a first edge node 3A and connecting to a further first edge node 3B.

[0072] In Figures 4A-4C, there is shown the first edge node 3A and the further first edge node 3B shown above in Figure 3. For simplicity, only one medical device 5AA is shown, but it will be apparent that further medical devices may be connected to the first edge node 3A and the further first edge node 3B when the medical device 5AA is moved from the first edge node 3A to the second edge node 3B, as shown in Figures 4A-4C.

[0073] In Fig. 4A, the medical device 5AA is shown connected to the first edge node 3A, while in Fig. 4B, the dashed line and dashed arrow indicate that the medical device 5AA is moved out of range of the first edge node 3A and into range of the further first edge node 3B. Now, as the medical device 5AA is moving into range of the further first edge node 3B, it can maintain a connection with the first edge node 3A while establishing a data connection with this further first edge node 3B. The data connection with the first edge node 3A is broken when the connection with the further first edge node 3B is established.

[0074] If the first edge node 3A and the further first edge node 3B are at a greater distance from each other, the medical device 5AA may completely disconnect from the first edge node 3A when moving out of range of the first edge node 3A, and later connect to the further first edge node 3B when the medical device 5AA moves within the range of the further first edge node 3B.

[0075] In FIG. 4C, the medical device 5AA is moved from the first edge node 3A to the further first edge node 3B and then connected to the further first edge node 3B.

[0076] In the embodiment shown, the connection is a WiFi connection, and the range is determined by the strength of the corresponding WiFi signal.

[0077] FIG. 5 shows the general steps of a case study using the edge computing system 1 shown in FIG.

[0078] To highlight the inventive concept of the edge computing system 1 shown in Fig. 3, the following case study is presented in Fig. 5. In Fig. 5, a schematic diagram of the edge computing system 1 of Fig. 3 is shown, with additional arrows added to indicate the below-described steps of the case study.

[0079] Step A: In a first step, it is assumed that an alarm event is generated in a medical device 5AA. For example, the medical device 5AA may include an infusion pump, and the alarm event may indicate a malfunction of the infusion pump.

[0080] Data indicative of the alarm event is then transmitted upstream from the medical device 5AA to the first edge node 3A.

[0081] Step B: The alarm event is then forwarded by the first edge node 3A to the monitoring device 7 for notification to a user.

[0082] To forward the alarm to the monitoring device 7, first the raw data is aggregated from the medical devices 5AA, which in this case includes data about the infusion process. The first edge node 3A then combines the aggregated raw data, which in this case includes data about the infusion pump, the patient, the patient's room ID, etc., with metadata into processed data, which is then forwarded to the monitoring device 7.

[0083] Optionally, the processed data is also sent to the central server device 100 via the second edge node 11, and via higher level edge nodes 17A, 17N located upstream between the second edge node 11 and the remote central server device 100, as indicated by the dashed arrow extending from the second edge node 11 to the remote central server device 100. Here, the occurrence of an alarm event can be logged.

[0084] Step C: The alarm event is then acknowledged by the user at the monitoring device 7 and an acknowledgement is returned to the medical device 5AA that initiated the alarm event via the first edge node 3A, and optionally to the central server device 100.

[0085] The above case study highlights that each edge node can host and execute different functional data processing at each topology level, which enables specific data processing, visualization or notification according to the actual demand of the corresponding topology level. The functional data processing can be completely independent of the data processing performed in the central server device 100.

[0086] 6A and 6B show upstream and downstream data flows in distributed data processing in a clinical environment utilizing an edge computing system that processes data locally, according to the embodiment of the present invention shown in FIGS. 3-5.

[0087] A first edge node 3A and a further first edge node 3B are exemplarily shown at bedroom level where medical devices 5AA and 5BA are also located.

[0088] In FIG. 6A, an upstream data flow is shown, where raw data originating from the medical devices 5AA and 5BA are received at the corresponding first edge node 3A, 3B. In this case, the raw data includes data related to the management of the infusion fluid, such as the infusion rate. An alarm event, shown as "alarm notification", indicates a malfunction of the infusion pump, which is represented by the aggregated raw data. Metadata including the patient ID or the ID of the corresponding medical device 5AA, 5BA are added to the raw data. The data is then sent to the second edge node 11 at the ward level. Here, the g(x) function includes a function related to supervision, such as monitoring the status of some beds. The dashed arrow extending upward from the second edge node 11 to the third edge node 17A indicates the data sent upstream to the third edge node 17A. Here, the h(x) function includes a function related to fleet management, such as monitoring the status of all beds in the building.

[0089] The central server 100 is located at the organizational level and centralizes information and performs advanced functions z(x), such as continuous quality improvement (CQI). As can be seen from Fig. 6A, data from the lowest levels can be forwarded to the central server 100, while the central server 100 does not need to be involved in data processing at lower levels of the edge computing system, as is evident by the downstream data flow shown in Fig. 6B.

[0090] In the downstream direction, the high level function z(x) at the organization level may include a function to provide updates, such as providing firmware updates to entities at lower levels, as shown in Figure 6B. The function h(x) at the building level may include providing data from a drug library to lower levels, where the g(x) function at the ward level may include providing data regarding clinical workflow to the bedroom level. As already described with reference to Figure 5, the downstream function f(x) at the bedroom level may include returning an acknowledgment to the medical device 5AA that initiated the alarm event.

[0091] At all levels shown in Figures 6A and 6B, upstream and downstream data can be combined.

[0092] FIG. 7 is a diagram illustrating a simplified layer model including data types according to an embodiment of the present invention.

[0093] At the bottom of Figure 7, the raw data is shown, which can be understood as the data sent or read by the medical devices. Each medical device can have a specific payload and protocol for transferring / receiving data.

[0094] The metadata, which the processing module combines with the raw data to generate the processed data, may include a location identifier, a patient identifier, a prescription identifier, etc. As previously described herein, the metadata may refer to a specific location within the hospital topology. The specific location may be at a patient level, a room level, a ward level, and / or an organization level. Also, the mere combination of metadata and raw data may be referred to as "rich data."

[0095] Smart data is generated at the application layer when adding analytical data to the rich data. The analytical data can be data extracted from large amounts of data, such as raw data and metadata previously aggregated using algorithms to obtain meaningful information. The smart data generated accordingly can be visualized as a progression, for example by displaying gauges on the display of the monitoring device. Historical data, or data from medical devices, can also be used to generate corresponding smart data, such as, for example, displaying the proportions of fluids administered by different medical devices and / or comparing the proportions against thresholds.

[0096] 8 is a diagram showing a method flow according to an embodiment of the present invention. The method includes the following steps: Establishing 1010 a data connection with at least one medical device and at least one of a remote central server device and a monitoring device; aggregating 1020 raw data from at least one medical device; - combining 1030 at least the metadata with the aggregated raw data to generate processed data; - transmitting 1040 the processed data via a data connection to the monitoring device and / or to the remote central server device 100; Includes.

[0097] The method also includes further optional steps which are not essential to the invention and are therefore illustrated in boxes bounded by dashed lines, namely: a step 1035 of combining the analytical data with the raw data and metadata into processed data; a step 1050 of transmitting and receiving the processed data to at least one further first edge node; a step 1060 of transmitting and receiving the processed data to at least one second edge node; Establishing 1070, at the second edge node, a data connection with at least one of the further first edge node, the remote central server device and the monitoring device; may include. [Explanation of symbols]

[0098] 1. Edge Computing System 3A, 3B First edge node 5AA, 5AN, 5BA, 5BN, 5N Medical Devices 7, 7' Monitoring Device 9. 9' Computing Resources 11, 11' Second edge node 13 Connection Interface 15 Processing Module 17A~17N Further edge nodes 100 Remote Central Server Devices 1000 How to process data locally in a clinical environment 1010 Establish 1020 Consolidate 1030 Combine 1035 Combining analytical data 1040 Send 1050 Transmitting / receiving to / from a further first edge node 1060 Sends / receives to / from the second edge node 1070 Establish a data connection at the second edge node Step A: An alarm event is generated Step B: Alarm event is forwarded Step C: Alarm event is silenced f(x), g(x), h(x), z(x) Functions in a clinical environment

Claims

1. An edge computing system for processing data locally in a clinical network managed by a remote central server device (100), comprising: The system comprises at least one medical device (5AA, 5AN), at least one first edge node (3A), and a monitoring device (7) assigned to the at least one medical device (5AA, 5AN), the at least one first edge node (3A) comprising: a connection interface (13) adapted to establish a data connection with said at least one medical device (5AA, 5AN) and with at least one of said remote central server device (100) and said monitoring device (7); A processing module (15), (i) aggregating raw data from said at least one medical device (5AA, 5AN); (ii) combining at least metadata with the aggregated raw data to generate processed data; (iii) a processing module adapted to transmit the processed data via the data connection to the monitoring device (7) and / or to the remote central server device (100); An edge computing system comprising:

2. 2. The edge computing system of claim 1, wherein the connection interface (13) is further adapted to retrieve analytical data from the remote central server device (100) and / or the monitoring device (7), and the processing module (15) is further adapted to combine the analytical data with the raw data and the metadata into the processed data.

3. 3. The edge computing system according to claim 1 or 2, characterized by a computing resource (9), preferably a software library, the connection interface (13) being further adapted to establish a data connection with the computing resource (9) and to retrieve analytical data therefrom, the processing module (15) being further adapted to combine the analytical data with the raw data and the metadata into the processed data.

4. 3. The edge computing system of claim 1 or 2, characterized by a further first edge node (3B), wherein the connection interface (13) of the first edge node (3A) is further adapted to establish a data connection with the further first edge node (3B), the further first edge node (3B) communicating with at least one further medical device (5BA, 5BN), and the processing module (15) of the first edge node (3A) is further adapted to transmit and receive the processed data to and from the further first edge node (3B).

5. a connection interface (13) adapted to establish a data connection with said at least one first edge node (3A) and with at least one of said remote central server device (100) and said monitoring device (7); a processing module (15) adapted to transmit and receive the processed data to the at least one first edge node (3A); 3. An edge computing system according to claim 1 or 2, characterized in that at least a second edge node (11) comprises:

6. The connection interface (13) of the second edge node (11) further comprises: receiving analytical data from said at least one first edge node (3A) and from at least one of said remote central server device (100) and said monitoring device (7); The processing module (15) further comprises: combining said analytical data into said processed data; 6. The edge computing system according to claim 5, characterized in that it is adapted to transmit the processed data to the monitoring device (7) and / or the remote central server device (100) via the data connection.

7. 6. The edge computing system of claim 5, wherein the first edge node (3A) is assigned to a patient and the second edge node (11) is assigned to a hospital room, or the first edge node (3A) is assigned to a hospital room and the second edge node (11) is assigned to a hospital ward.

8. 3. An edge computing system according to claim 1 or 2, characterized in that at least one third edge node (17A), preferably a plurality of further upper edge nodes (17N), are arranged between the second edge node (11) and the central server device (100).

9. 9. The edge computing system according to claim 8, characterized in that the at least one third edge node (17A) is assigned to a hospital building and / or a hospital.

10. 3. The edge computing system according to claim 1 or 2, characterized in that the at least one medical device (5AA, 5AN) is adapted to disconnect the data connection with the first edge node (3A) when moving out of range of the first edge node (3A) and to establish a data connection with the further first edge node (3B) when moving into range of the further first edge node (3B).

11. 3. The edge computing system according to claim 1 or 2, characterized in that the at least one medical device (5AA, 5AN) is at least one of an infusion device and a patient monitoring device.

12. 3. An edge computing system according to claim 1 or 2, characterized in that the connection module of the at least one first edge node (3A) is adapted to connect to the at least one medical device (5AA, 5AN) via a wireless connection, preferably a wireless LAN connection.

13. 3. The edge computing system according to claim 1 or 2, characterized in that the connection modules of the at least one first edge node (3A) and / or the at least one second edge node (11) are adapted to be operable with a communication network according to EN ISO 11073 and / or according to the Fast Healthcare Interoperability Resources (FHIR) standard and / or according to the Health Level 7 (HL7) standard.

14. A method for processing data locally in a clinical environment using an edge computer system (1), the edge computer system (1) comprising at least one first edge node (3A), at least one medical device (5AA, 5AN) and a monitoring device (7) assigned to the at least one medical device (5AA, 5AN), the method comprising: Establishing (1010) a data connection with the at least one medical device (5AA, 5AN) and at least one of a remote central server device (100) and the monitoring device (7) by a connection interface (13) of the at least one first edge node (3A); by a processing module (15) of said at least one first edge node (3A), (i) aggregating (1020) raw data from said at least one medical device (5AA, 5AN); (ii) combining at least metadata with the aggregated raw data to generate processed data (1030); (iii) transmitting (1040) said processed data via said data connection to said monitoring device (7) and / or to said remote central server device (100); and A method comprising:

15. Combining the analytical data with the raw data and the metadata into the processed data (1035); and / or 15. The method according to claim 14, characterized in that the processed data is transmitted to and received from at least one further first edge node (3B) (1050).

16. Transmitting (1060) the processed data to at least one second edge node (11); Establishing (1070) a data connection at the second edge node (11) with at least one of a further first edge node (3B), the remote central server device (100) and the monitoring device (7); 16. The method according to claim 14 or 15, characterized in that

17. 16. A computer program product comprising a computer readable storage medium having program instructions stored thereon, the program instructions being executable by a processor to perform the method (1000) of claim 14 or 15.

Images