CN114299453A - Vital sign information integrated processing method, equipment and system based on artificial intelligence - Google Patents
Vital sign information integrated processing method, equipment and system based on artificial intelligence Download PDFInfo
- Publication number
- CN114299453A CN114299453A CN202111669378.7A CN202111669378A CN114299453A CN 114299453 A CN114299453 A CN 114299453A CN 202111669378 A CN202111669378 A CN 202111669378A CN 114299453 A CN114299453 A CN 114299453A
- Authority
- CN
- China
- Prior art keywords
- vital sign
- sign information
- target object
- integrated processing
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The specification relates to the technical field of data processing, and provides a vital sign information integrated processing method, equipment and a system based on artificial intelligence, wherein the method comprises the following steps: acquiring various vital sign information of a target object in real time; converting the vital sign information into structured vital sign information; inputting the structured vital sign information into a pre-trained first machine learning model for analysis, and obtaining the vital sign change trend of the target object; and outputting auxiliary early warning information according to the vital sign change trend. The embodiment of the specification can improve timeliness and accuracy of identifying the change trend of the vital signs of the target object.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a method, a device, and a system for integrated processing of vital sign information based on artificial intelligence.
Background
The current integrated processing mode of vital sign information is as follows: collecting vital sign information output by various devices such as vital sign monitoring and supporting devices and video acquisition cameras together in a direct or machine room connection mode and the like to realize centralized monitoring (for example, collecting the vital sign information to a central matrix all-in-one machine); or, the pure data information of the same kind of equipment is collected to carry out centralized monitoring (such as a central monitoring workstation or an infusion pump workstation); and the relevant workers can check the results and manually judge whether to intervene or deal with the results according to the checked results. However, the existing vital sign information integration processing scheme does not have data analysis capability, and is difficult to integrate various vital sign information to accurately, timely and efficiently identify the change trend of the vital signs of the target object.
Disclosure of Invention
An object of the embodiments of the present specification is to provide a method, a device, and a system for integrated processing of vital sign information based on artificial intelligence, so as to improve timeliness and accuracy of identifying a change trend of a vital sign of a target subject.
In order to achieve the above object, in one aspect, an embodiment of the present specification provides an artificial intelligence based vital sign information integrated processing method, including:
acquiring various vital sign information of a target object in real time;
converting the vital sign information into structured vital sign information;
inputting the structured vital sign information into a pre-trained first machine learning model for analysis, and obtaining the vital sign change trend of the target object;
and outputting auxiliary early warning information according to the vital sign change trend.
In an embodiment of the present specification, the vital sign information includes a digitized image; the converting the vital sign information into structured vital sign information includes:
extracting regional image features from the digitized image;
identifying the region type of each region image feature by using a preset classification algorithm;
determining the data type of each subarea in each area image characteristic according to the area type;
and converting each sub-region feature in each region image feature into structured vital sign information according to the data type.
In an embodiment of the present specification, the input of the first machine learning model further comprises clinical constraint parameters; the change trend of the vital signs of the target object comprises the abnormal probability of the vital signs.
In an embodiment of this specification, the outputting auxiliary early warning information according to the vital sign change trend includes:
outputting the vital sign change trend of the target object and a dialog box through a human-computer interface; the dialog box comprises a first control for indicating approval and a second control for indicating non-approval;
when receiving an operation aiming at the first control, judging whether the abnormal probability of the vital sign exceeds a preset probability threshold;
and if the abnormal probability of the vital signs exceeds a preset probability threshold, outputting clinical auxiliary early warning information to target equipment.
In an embodiment of this specification, the outputting auxiliary early warning information according to the vital sign change trend further includes:
when an operation for the second control is received, the clinical constraint parameters are adjusted and re-analyzed using the first machine learning model.
In an embodiment of this specification, the method further includes:
acquiring a job scene monitoring image aiming at a target object in real time;
converting the job scene monitoring image into structured job scene monitoring data;
inputting the monitoring data of the structured operation scene into a pre-trained second machine learning model for analysis, and obtaining an operation monitoring result aiming at the target object;
and outputting auxiliary early warning information according to the operation monitoring result.
In another aspect, the present specification further provides a vital sign information integrated processing device, which includes a memory, a processor, and a computer program stored on the memory, and when the computer program is executed by the processor, the computer program executes the instructions of the above method.
On the other hand, an embodiment of the present specification further provides an artificial intelligence based vital sign information integrated processing system, including:
the multiple vital sign monitoring devices are used for acquiring vital sign information of a target object in real time;
a vital sign information integrated processing device for:
acquiring various vital sign information of a target object in real time;
converting the vital sign information into structured vital sign information;
inputting the structured vital sign information into a pre-trained first machine learning model for analysis, and obtaining the vital sign change trend of the target object;
and outputting auxiliary early warning information according to the vital sign change trend.
In an embodiment of the present specification, the vital sign monitoring device includes a first type device and a second type device; the vital sign information acquired by the first equipment is non-digital vital sign information; the vital sign information collected by the second type of equipment is digital vital sign information.
As can be seen from the technical solutions provided by the embodiments of the present specification, the embodiments of the present specification analyze and process the structured vital sign information by using the pre-trained machine learning model, the change trend of the vital signs of the target object can be obtained, whether auxiliary early warning information is output or not is determined according to the change trend of the vital signs, namely, the automatic integration and the automatic analysis processing of the vital sign information are realized, thereby improving the timeliness of identifying the vital sign change trend of the target object, compared with the prior art, and manually judging whether to perform intervention or handling according to the observed result, the embodiment of the specification is based on a pre-trained machine learning model, the structured vital sign information is analyzed, processed and early warned, so that human errors can be avoided, and the method is more accurate and reliable, and further improves the accuracy of recognizing the change trend of the vital signs of the target object.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort. In the drawings:
FIG. 1 is a block diagram illustrating an artificial intelligence based vital signs information integrated processing system in some embodiments of the present description;
FIG. 2 illustrates a flow chart of a method for artificial intelligence based vital sign information integration processing in some embodiments of the present description;
FIG. 3 illustrates a flow chart of converting digitized vital signs information into structured vital signs information in some embodiments of the present description;
FIG. 4 shows a schematic diagram of a region image in an exemplary embodiment of the present description;
FIG. 5 shows a schematic view of a sub-region image in the mid-region image shown in FIG. 4;
FIG. 6 is a schematic diagram illustrating a training process of a machine learning model in some embodiments of the present description;
FIG. 7 is a flow chart illustrating a method for artificial intelligence based vital sign information integration processing in further embodiments of the present description;
FIG. 8 is a schematic illustration of a surgical procedure scene monitoring image in an exemplary embodiment of the present description;
fig. 9 shows a block diagram of a vital sign information integrated processing device in some embodiments of the present specification.
[ description of reference ]
1. A first type of device;
2. a second type of device;
3. a video conversion device;
4. a data exchanger;
5. a vital sign information integrated processing device;
6. a data server;
7. an interactive terminal;
8. a display screen;
9. a guidance terminal;
10. an EAI data platform;
11. an upgrade manager;
902. a vital sign information integrated processing device;
904. a processor;
906. a memory;
908. a drive mechanism;
910. an input/output interface;
912. an input device;
914. an output device;
916. a presentation device;
918. a graphical user interface;
920. a network interface;
922. a communication link;
924. a communication bus.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.
In view of the fact that the existing vital sign information integration scheme does not have data analysis capability and is difficult to integrate various vital sign information to accurately, timely and efficiently identify the vital sign change trend of a target object, the embodiment of the specification provides an improved vital sign information integration processing scheme. It should be noted that the vital sign information in the embodiments of the present specification may be vital sign information of a target subject (e.g. a human or an animal) (typical vital sign information may include, for example, heart rate, pulse, blood pressure, respiration, blood oxygen, etc.). Moreover, the vital sign information integration processing scheme in the embodiment of the present specification may perform integration processing on not only various vital sign information but also various non-vital sign information (for example, operation scene monitoring such as surgery). Therefore, the embodiments of the present disclosure may be applied to Intensive Care Unit (ICU), specialized examination room (e.g., mirror chamber), operating room, ward, nursing center, and other scenarios.
Fig. 1 illustrates an artificial intelligence based vital signs information integration processing system in some embodiments of the present description, which may include: the system comprises a plurality of first-class devices 1, a plurality of second-class devices 2, a video conversion device 3, a data exchanger 4, a vital sign information integrated processing device 5, a data server 6, an interaction terminal 7, a display screen 8, a guidance terminal 9 and the like.
The first type of device 1 and the second type of device 2 are both vital signs monitoring devices for vital support, monitoring, etc. In an embodiment, the vital signs monitoring device may comprise a single function vital signs monitoring device, such as a ventilator, an electrocardiograph, a blood pressure monitor, or the like. In another embodiment, the vital signs monitoring device may further comprise a multifunctional vital signs monitoring device, such as a vital signs monitor (an instrument with the functionality of non-invasive blood pressure (NIBP), pulse rate, Mean Arterial Pressure (MAP), blood oxygen saturation (SpO2), temperature monitoring, etc.). The first device 1 can acquire non-digital vital sign information (i.e., analog vital sign information) of a target subject in real time, but does not have a digital communication interface, and is difficult to perform digital communication with the outside. The second type of device 2 can acquire digitized vital sign information (i.e. digital vital sign information) of a target subject in real time, and has a digital communication interface capable of performing digital communication with the outside.
For easy viewing, the above-mentioned terminal equipment for life support, monitoring, etc. is generally configured with a display screen; in other words, these terminal devices may output video signals, for example, the first type device 1 may output video signals of analog quantity, and the second type device 2 may output video signals of digital quantity. However, since the formats of the analog video signals output by different first-type devices 1 may be different, the subsequent processing is not facilitated; the video conversion device 3 can be used for converting non-digitized video signals of different formats acquired by the first type device 1 into digitized video signals of the same format. Obviously, the video converter 3 in the embodiment of the present specification also has a role of data aggregation, that is, the video converter 3 can communicate with a plurality of first type devices 1 and process the video signals output by them.
Although the output of different second-type devices 2 is digitized vital sign information, the data formats or data structures of the digitized vital sign information may be different, and in order to facilitate the analysis processing of the pre-trained machine learning model, the digitized vital sign information output by different second-type devices 2 needs to be standardized and structured. Therefore, the data exchanger 4 can be used to normalize and structure the digitized vital sign information output by each second-type device 2, and provide the digitized vital sign information to the data server 6, and write the digitized vital sign information into the database by the data server 6.
The vital sign information integrated processing device 5 may be configured to: acquiring various vital sign information of a target object from the video conversion equipment 3 in real time; converting the vital sign information into structured vital sign information; inputting the structured vital sign information into a pre-trained first machine learning model for analysis, and obtaining the vital sign change trend of the target object; and outputting auxiliary early warning information according to the vital sign change trend. Therefore, the structural vital sign information is analyzed and processed by utilizing the pre-trained machine learning model, the vital sign change trend of the target object can be obtained, whether auxiliary early warning information is output or not is determined according to the vital sign change trend, namely, the automatic integration and automatic analysis and processing of the vital sign information are realized, the timeliness of identifying the vital sign change trend of the target object is improved, and compared with the traditional technology in which whether intervention or response processing is carried out or not is judged manually according to the checked result, the structural vital sign information is analyzed and processed and early warned based on the pre-trained machine learning model in the embodiment of the specification, human errors can be avoided, the method is more accurate and reliable, and the accuracy of identifying the vital sign change trend of the target object is also improved.
The interactive terminal 7 is mainly used for realizing interaction between devices or man-machine interaction. The interactive terminal 7 may be different devices according to different application scenarios. For example, in an ICU scenario, the interactive terminal 7 may be a client of a relevant person (e.g., a doctor or a nurse), so that the vital sign information integrated processing device 5 may confirm the integrated processing result to the relevant person (only the integrated processing result approved or confirmed by the relevant person may be used for assisting the early warning judgment); in some embodiments, the user terminal may be a self-service terminal device, a mobile terminal (i.e., a smart phone), a display, a desktop computer, a tablet computer, a notebook computer, a digital assistant, or a smart wearable device. Wherein, wearable equipment of intelligence can include intelligent bracelet, intelligent wrist-watch, intelligent glasses or intelligent helmet etc.. Of course, the user end is not limited to the electronic device with a certain entity, and may also be an application program running in the electronic device. In the operation monitoring scene, the interactive terminal 7 can be a tracking camera, and can acquire the real-time picture of the operation scene through the tracking camera and provide the real-time picture for the vital sign information integrated processing equipment 5 to process; of course, the vital sign information integrated processing device 5 may also control the tracking camera to adjust the tracking range by an instruction as needed.
The display screen 8 may be a centralized display screen, and may be used to visually display the processing result of the vital sign information integrated processing device 5, and may also be used to display auxiliary early warning information. And the display screen 8 may also support display screen switching as needed.
The tutorial terminal 9 is provided with tutorial software for generating parameterized clinical rules and providing them to the data server, which writes them to the database. The parameterized clinical rules are clinical constraint parameters; when the machine learning model is trained, the training input is used for realizing the training of the machine learning model under the supervision of clinical rules, thereby being beneficial to obtaining a more accurate machine learning model. When the method is actually applied, the method is used as the input of a pre-trained machine learning model so as to obtain more accurate integrated analysis processing results. The clinical rules are instructive clinical rules summarized according to clinical papers, clinical guidelines, and/or clinical consensus. For example, in an exemplary embodiment, one clinical rule may be: the normal range of blood oxygen concentration is greater than 90%. In individual scenarios, there may not be a corresponding clinical rule, and the parameterized clinical rule may be randomly given, so that the machine learning model can be trained to be used for research and discovery of the clinical rule in the corresponding scenario.
With continued reference to fig. 1, the artificial intelligence based vital sign information Integration processing system may further include an EAI (Enterprise Application Integration) data platform 10. The EAI data platform 10 may be used for information extraction and integration of various heterogeneous information systems, and provides the obtained data to the data server 6, and the data is written into a database by the data server 6 for model training. In one embodiment, the heterogeneous Information System may include, for example, EMR (Electronic Medical Record), HIS (Hospital Information System), PACS (Picture Archiving and Communication Systems), LIS (Laboratory Information Management System), and the like. Basic information (such as name, age, sex, bed, etc.) and medical records of the target subject can be obtained from the EMR or HIS, and diagnostic data (such as medical images, test data, etc.) of the target subject can be obtained from the PACS or LIS.
With continued reference to fig. 1, the artificial intelligence based vital signs information integrated processing system may further include an upgrade manager 11. The upgrade manager 11 may be used to uniformly manage online updates of a plurality of second-type devices 2 to reduce update costs and operation and maintenance pressure.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
The embodiment of the specification further provides an artificial intelligence-based vital sign information integrated processing method, which can be applied to the vital sign information integrated processing device side of the system. Referring to fig. 2, in some embodiments, the method for processing vital sign information based on artificial intelligence may include the following steps:
s201, obtaining various vital sign information of the target object in real time.
S202, converting the vital sign information into structured vital sign information.
S203, inputting the structured vital sign information into a pre-trained first machine learning model for analysis, and obtaining the vital sign change trend of the target object.
And S204, outputting auxiliary early warning information according to the vital sign change trend.
In the embodiment of the specification, the structured vital sign information is analyzed and processed by using the pre-trained machine learning model, so that the vital sign change trend of the target object can be obtained, and whether auxiliary early warning information is output or not is determined according to the vital sign change trend, namely, the automatic integration and automatic analysis and processing of the vital sign information are realized, so that the timeliness of identifying the vital sign change trend of the target object is improved.
In some embodiments, obtaining multiple vital sign information of the target subject in real time may refer to: and acquiring various vital sign information of the target object from the video conversion device and the data exchanger in real time. As will be understood by those skilled in the art, in a special case, it may happen that all of the multiple vital sign monitoring devices are first type devices, and then obtaining multiple vital sign information of the target subject in real time may refer to: acquiring various vital sign information of a target object from video conversion equipment in real time; in another special case, a situation that all of the multiple vital sign monitoring devices are the second type of devices may also occur, and the obtaining of the multiple vital sign information of the target subject in real time may refer to: and acquiring various vital sign information of the target object from the data exchanger in real time.
Referring to fig. 3, in some embodiments, for a digitized image of the plurality of vital sign information, the converting the vital sign information into structured vital sign information may include the steps of:
s301, extracting regional image features from the digitized image.
The area image may be a digitized image or a composite image formed by splicing a plurality of digitized images. The size parameter of the area image can be set according to the requirement, and the size parameter can be adjusted. In some embodiments, any suitable image feature extraction method (e.g., histogram of oriented gradients method, etc.) may be employed to extract regional image features.
S302, identifying the region type of each region image feature by using a preset classification algorithm.
And identifying the region type of each region image feature, namely identifying the image output by the vital sign monitoring device of which each region image feature is. For example, in an exemplary embodiment, the region type of the identified one region image feature may be a ventilator type; in another exemplary embodiment, the region type of the identified one region image feature may be an electrocardiograph type. In some embodiments, a decision tree algorithm may be employed to identify the region type that identifies each region image feature. It should be clear that this is only an exemplary illustration, and in other embodiments, any other suitable classification algorithm may be used according to the needs, and the description is not limited to this.
S303, determining the data type of each sub-area in the image characteristics of each area according to the area type.
In some cases, the image output by a vital signs monitoring device may include multiple display sub-regions (simply sub-regions), each of which may display different parameters, which may be of the same or different data types. Therefore, based on the pre-trained machine learning model, the sub-regions included in each region image can be identified, and the data types of the sub-regions can be identified. In the embodiments of the present specification, the data type may be a waveform type, a text type, a number type, or the like. For example, in the area image of the type of ventilator shown in fig. 4, a plurality of sub-areas are included, a main sub-area displays some waveform parameters, and other sub-areas display numerical parameters or text parameters. Taking the sub-region shown in fig. 5 as an example (the sub-region is a sub-region of the region image shown in fig. 4), the data type of the sub-region can be confirmed to be a digital type by identification.
S304, converting each sub-region feature in each region image feature into structured vital sign information according to the data type.
For the sub-region characteristics belonging to the number type or the character type, corresponding number parameters or character parameters can be directly written into a database table so as to be converted into structured vital sign information; for the graph parameters such as waveforms, the graph parameters can be converted into corresponding character strings firstly, and then the character strings are written into a database table, so that the graph parameters can also be converted into structured vital sign information.
In embodiments of the present specification, the input to the first machine learning model may further include clinical constraint parameters, and the clinical constraint parameters are also structured data; therefore, after the structured vital sign information and the clinical constraint parameters are input into the pre-trained first machine learning model, the pre-trained first machine learning model can analyze the structured vital sign information under the constraint of the clinical constraint parameters, and therefore the more accurate vital sign change trend of the target object can be obtained.
In some embodiments, the initial first machine learning model may be any suitable machine learning model, which is not limited in this specification and may be selected according to actual needs. In some embodiments, the pre-trained first machine learning model may be trained based on the training process shown in fig. 6, wherein the data set required for training may be retrieved from the database through the data server. For example, in the flow shown in fig. 6, the video output screen of the medical device is collected at a set frequency, which may be data collected in advance and stored in a database. In the flow shown in fig. 6, the purpose of the comparison and judgment is mainly to determine whether the output result of the currently trained machine learning model matches the actual situation; if the image is consistent with the actual situation, the training can be continued by using other images in the training data set; if not, the region image parameters (such as the size of the region image) can be adjusted and the region image features can be re-extracted for re-training. In this way, until each image in the training data set is correctly analyzed, or the output result of the currently trained machine learning model reaches the set evaluation index value.
The vital sign trend can be a trend of one or more vital signs over time, and can be determined from the input by a pre-trained first machine learning model. It should be noted that the vital sign change trend has a correlation with the inputted various kinds of structured vital sign information, i.e. the inputted various kinds of structured vital sign information can be analyzed to one or more kinds of vital sign change trends. For example, in an exemplary embodiment, when the breathing rate of the target subject is increased, the blood pressure is decreased, and the heart rate is increased, it may be determined that the target subject has a trend of blood oxygenation that is lower.
In some embodiments, when the target subject's vital sign variation trend exceeds a normal range (which may be set based on clinical constraint parameters), the target subject's vital sign variation trend may also include a vital sign abnormality probability. In this case, the outputting auxiliary early warning information according to the vital sign change trend may include the following steps:
(1) outputting the vital sign change trend of the target object and a dialog box through a human-computer interface; the dialog box comprises a first control for representing approval and a second control for representing non-approval for confirmation by the relevant person.
(2) And when receiving the operation aiming at the first control, judging whether the abnormal probability of the vital sign exceeds a preset probability threshold value.
For example, when the relevant person clicks the first control, that is, receives an operation for the first control, the relevant person recognizes the vital sign change trend (including recognizing the abnormal probability of the vital sign therein). At this time, it may be determined whether the vital sign abnormality probability exceeds a preset probability threshold.
(3) And if the abnormal probability of the vital signs exceeds a preset probability threshold, outputting clinical auxiliary early warning information to the target equipment. The target device may be any terminal device (e.g., a mobile phone, a desktop computer, a display, etc.) which is convenient for the relevant person to perceive in time, so that the relevant person can make a response decision accordingly.
In an embodiment of this specification, the outputting auxiliary early warning information according to the vital sign change trend may further include: when receiving the operation aiming at the second control, indicating that the related personnel does not recognize the vital sign change trend (including not recognizing the abnormal probability of the vital sign); at this point, the clinical constraint parameters may be adjusted and re-analyzed using the first machine learning model.
Referring to fig. 7, in other embodiments, the method for processing vital sign information based on artificial intelligence may further include the following steps:
and S701, acquiring a job scene monitoring image aiming at the target object in real time.
S702, converting the job scene monitoring image into structured job scene monitoring data.
And S703, inputting the monitoring data of the structured operation scene into a pre-trained second machine learning model for analysis, and obtaining an operation monitoring result aiming at the target object.
And S704, outputting auxiliary early warning information according to the operation monitoring result.
Such as operation, besides the need of monitoring vital signs, the operation scene monitoring can be carried out; in the embodiment of the specification, the operation scene monitoring image is analyzed by using the pre-trained machine learning model, the operation monitoring result for the target object can be obtained, and whether auxiliary early warning information is output or not is determined according to the operation monitoring result, that is, automatic monitoring of the operation scene is realized, so that timeliness of monitoring of the operation scene is improved. Therefore, the system is more suitable for monitoring scenes such as operation fields, panoramas and the like in operation processes (such as actual operation and operation simulation) in scenes such as an operating room, a special examination room and the like. The panorama may refer to a panorama in a working process of an operating room and a special examination room, and include a limb movement, a facial expression, a thoracic fluctuation, and the like of a target object, an operation scene (for example, as shown in fig. 8) of a relevant person such as an operator, and the like.
In some embodiments, acquiring a job scene monitoring image for a target object in real-time may refer to: a job scene monitoring image for a target object is acquired from a plurality of tracking cameras in real time. Therefore, under the monitoring of the working scene, the artificial intelligence based vital sign information integrated processing system can also comprise a plurality of tracking cameras, and the tracking cameras can perform full-range monitoring on the working scene aiming at the target object autonomously or under the control of the vital sign information integrated processing device.
In some embodiments, the converting the job scene monitoring image into the structured job scene monitoring data may include the steps of:
(1) and extracting regional image features from the job scene monitoring image.
The operation scene monitoring image is a digitized image, and the region image may be one operation scene monitoring image or a composite image formed by splicing a plurality of operation scene monitoring images. The size parameters of the area image can be set according to needs, and the size parameters can be adjusted. In some embodiments, any suitable image feature extraction method (e.g., histogram of oriented gradients method, etc.) may be employed to extract regional image features.
(2) And identifying the region type of each region image feature by using a preset classification algorithm.
Since the shooting range and the tracking target (or called an object of interest) of different tracking cameras can be different, the region type of each region image feature is identified, that is, the image captured by which tracking camera is identified as each region image feature. In some embodiments, a decision tree algorithm may be employed to identify the region type that identifies each region image feature. It should be clear that this is only an exemplary illustration, and in other embodiments, any other suitable classification algorithm may be used according to the needs, and the description is not limited to this.
(3) And determining the type of the interest object of each sub-area in the image characteristic of each area according to the type of the area.
In some cases, the image output from a tracking camera may include multiple display sub-regions (simply sub-regions), each of which may display a different object of interest. Therefore, based on the pre-trained machine learning model, sub-regions included in each region image can be identified, and the object of interest in each sub-region can be identified. In the embodiments of the present specification, the object of interest refers to an object that needs to be monitored (for example, an action of an operator, a surgical instrument, a surgical site of a target object, and the like).
(4) And converting each subarea characteristic in each area image characteristic into structured job scene monitoring data.
Because the interest object is image data, the image data can be converted into a corresponding character string, and then the character string is written into a database table, so that the image data can be converted into structured job scene monitoring data.
In embodiments of the present specification, the input to the second machine learning model may further include clinical constraint parameters, and the clinical constraint parameters are also structured data; therefore, the structured job scene monitoring data and the clinical constraint parameters are input into the pre-trained second machine learning model, so that the pre-trained second machine learning model can analyze the structured job scene monitoring data under the constraint of the clinical constraint parameters, and a more accurate job monitoring result aiming at the target object can be obtained.
In some embodiments, the initial second machine learning model may be any suitable machine learning model, which is not limited in this specification and may be selected according to actual needs. The pre-trained second machine learning model is similar to the training process of the first machine learning model, and is not described herein again.
The job monitoring result may include whether the operation of the operator is in compliance. For example, whether the preoperative preparation is complete, whether the intraoperative procedure is properly standardized (e.g., whether the surgical instrument is taken by mistake, whether the surgical instrument is withdrawn after use, etc.). The job monitoring result may also include whether the target object's limb movements, facial expressions, etc. are normal or not for assisting in monitoring the target object's vital signs.
In some embodiments, when it is determined that the operation of the operator is not in compliance according to the operation monitoring result, corresponding auxiliary early warning information may be generated to a display device on the site, and the auxiliary early warning information may be output by voice or other means at the same time, so as to provide the relevant staff to perform handling in time. For example, when the operator takes the surgical instrument by mistake, the operator is timely reminded to replace the surgical instrument through voice warning, text warning and the like.
While the process flows described above include operations that occur in a particular order, it should be appreciated that the processes may include more or less operations that are performed sequentially or in parallel (e.g., using parallel processors or a multi-threaded environment).
The embodiment of the specification also provides a vital sign information integrated processing device. As shown in fig. 9, in some embodiments of the present description, the vital sign information integrated processing device 902 may include one or more processors 904, such as one or more Central Processing Units (CPUs) or Graphics Processors (GPUs), each of which may implement one or more hardware threads. The vital sign information integrated processing device 902 may further comprise any memory 906 for storing any kind of information, such as code, settings, data, etc., and in a specific embodiment, a computer program on the memory 906 and executable on the processor 904, said computer program, when executed by said processor 904, may perform the instructions of the artificial intelligence based vital sign information integrated processing method according to any of the above embodiments. For example, and without limitation, memory 906 may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of the vital signs information integrated processing device 902. In one case, when the processor 904 executes the associated instructions stored in any memory or combination of memories, the vital sign information integrated processing device 902 can perform any of the operations of the associated instructions. The vital signs information integrated processing device 902 also includes one or more drive mechanisms 908, such as a hard disk drive mechanism, an optical disk drive mechanism, etc., for interacting with any memory.
The vital signs information integrated processing device 902 may also include an input/output interface 910(I/O) for receiving various inputs (via input device 912) and for providing various outputs (via output device 914). One particular output mechanism may include a presentation device 916 and an associated graphical user interface 918 (GUI). In other embodiments, the input/output interface 910(I/O), the input device 912 and the output device 914 may not be included, and only serve as a vital sign information integrated processing device in the network. The vital signs information integrated processing device 902 may also include one or more network interfaces 920 for exchanging data with other devices via one or more communication links 922. One or more communication buses 924 couple the above-described components together.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products of some embodiments of the specification. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processor to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processor, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processor to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processor to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, the vital sign information integrated processing device includes one or more processors (CPUs), input/output interfaces, a network interface, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by the vital signs information integrated processing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The embodiments of this specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The described embodiments may also be practiced in distributed computing environments where tasks are performed by remote processors that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It should also be understood that, in the embodiment of the present specification, the term "and/or" is only one kind of association relation describing an associated object, and means that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A vital sign information integration processing method based on artificial intelligence is characterized by comprising the following steps:
acquiring various vital sign information of a target object in real time;
converting the vital sign information into structured vital sign information;
inputting the structured vital sign information into a pre-trained first machine learning model for analysis, and obtaining the vital sign change trend of the target object;
and outputting auxiliary early warning information according to the vital sign change trend.
2. The artificial intelligence based vital sign information integrated processing method of claim 1, wherein the vital sign information comprises a digitized image; the converting the vital sign information into structured vital sign information includes:
extracting regional image features from the digitized image;
identifying the region type of each region image feature by using a preset classification algorithm;
determining the data type of each subarea in each area image characteristic according to the area type;
and converting each sub-region feature in each region image feature into structured vital sign information according to the data type.
3. The artificial intelligence based vital sign information integrated processing method of claim 1, wherein the input of the first machine learning model further comprises clinical constraint parameters; the change trend of the vital signs of the target object comprises the abnormal probability of the vital signs.
4. The artificial intelligence based vital sign information integrated processing method according to claim 3, wherein the outputting auxiliary pre-warning information according to the vital sign change trend comprises:
outputting the vital sign change trend of the target object and a dialog box through a human-computer interface; the dialog box comprises a first control for indicating approval and a second control for indicating non-approval;
when receiving an operation aiming at the first control, judging whether the abnormal probability of the vital sign exceeds a preset probability threshold;
and if the abnormal probability of the vital signs exceeds a preset probability threshold, outputting clinical auxiliary early warning information to target equipment.
5. The artificial intelligence based vital sign information integrated processing method according to claim 4, wherein the outputting auxiliary pre-warning information according to the vital sign change trend further comprises:
when an operation for the second control is received, the clinical constraint parameters are adjusted and re-analyzed using the first machine learning model.
6. The artificial intelligence based vital sign information integrated processing method of claim 1, further comprising:
acquiring a job scene monitoring image aiming at a target object in real time;
converting the job scene monitoring image into structured job scene monitoring data;
inputting the monitoring data of the structured operation scene into a pre-trained second machine learning model for analysis, and obtaining an operation monitoring result aiming at the target object;
and outputting auxiliary early warning information according to the operation monitoring result.
7. Vital sign information integrated processing device comprising a memory, a processor and a computer program stored on the memory, characterized in that the computer program, when executed by the processor, executes instructions of the method according to any one of claims 1 to 6.
8. An artificial intelligence based vital sign information integrated processing system, comprising:
the multiple vital sign monitoring devices are used for acquiring vital sign information of a target object in real time;
a vital sign information integrated processing device for:
acquiring various vital sign information of a target object in real time;
converting the vital sign information into structured vital sign information;
inputting the structured vital sign information into a pre-trained first machine learning model for analysis, and obtaining the vital sign change trend of the target object;
and outputting auxiliary early warning information according to the vital sign change trend.
9. The artificial intelligence based vital sign information integrated processing system of claim 8, wherein the vital sign monitoring device comprises a first type device and a second type device; the vital sign information acquired by the first equipment is non-digital vital sign information; the vital sign information collected by the second type of equipment is digital vital sign information.
10. A computer storage medium on which a computer program is stored, characterized in that the computer program, when being executed by a processor of a vital sign information integrated processing device, executes instructions of a method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111669378.7A CN114299453A (en) | 2021-12-31 | 2021-12-31 | Vital sign information integrated processing method, equipment and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111669378.7A CN114299453A (en) | 2021-12-31 | 2021-12-31 | Vital sign information integrated processing method, equipment and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114299453A true CN114299453A (en) | 2022-04-08 |
Family
ID=80972896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111669378.7A Pending CN114299453A (en) | 2021-12-31 | 2021-12-31 | Vital sign information integrated processing method, equipment and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299453A (en) |
-
2021
- 2021-12-31 CN CN202111669378.7A patent/CN114299453A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3537448B1 (en) | Methods and systems for using multiple data structures to process surgical data | |
| CN112071425B (en) | Data processing method and device, computer equipment and storage medium | |
| Banos et al. | mHealthDroid: a novel framework for agile development of mobile health applications | |
| JP2022520701A (en) | Systems and methods for analysis of surgical videos | |
| US20180286500A1 (en) | System for acquisition, processing and visualization of clinical data of patients | |
| US20220254486A1 (en) | System and method for a patient dashboard | |
| US11666288B2 (en) | Systems and methods for graphical user interfaces for medical device trends | |
| WO2020121308A9 (en) | Systems and methods for diagnosing a stroke condition | |
| JP2022527174A (en) | Intraoperative clinical decision support system | |
| US20170004288A1 (en) | Interactive and multimedia medical report system and method thereof | |
| CN114420231B (en) | Interpretable continuous early warning method and system for acute kidney injury, storage medium and electronic equipment | |
| WO2023018469A1 (en) | Systems and methods for evaluating health outcomes | |
| CN110070929A (en) | A kind of acquisition and cleaning method for atrial fibrillation Single diseases data | |
| KR20200000745A (en) | Medical practice data collection and management system and method | |
| KR20210151742A (en) | Method, apparatus and computer program for detecting shock occurrence through biometric image analysis of artificial intelligence model | |
| Tsampi et al. | Extending the Sana mobile healthcare platform with features providing ECG analysis | |
| CN114299453A (en) | Vital sign information integrated processing method, equipment and system based on artificial intelligence | |
| Arney et al. | An open-source, interoperable architecture for generating real-time surgical team cognitive alerts from heart-rate variability monitoring | |
| Faiola et al. | Multivariate relational visualization of complex clinical datasets in a critical care setting: A data visualization interactive prototype | |
| CN114300103A (en) | Digital operating room information management method and system | |
| EP3839960A1 (en) | Generating contextually-useful guidance for treating a patient | |
| US20210327579A1 (en) | Method and apparatus for classifying subjects based on time series phenotypic data | |
| US20220392593A1 (en) | Medical Surgery Recording, Processing and Reporting System | |
| TW202020890A (en) | Display system for medical information and method for producing display content | |
| Tesanovic et al. | eHealth personalization in the next generation RPM systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |