CN112542235B - Method and system for automatically monitoring turnover nursing working quality - Google Patents

Method and system for automatically monitoring turnover nursing working quality Download PDF

Info

Publication number
CN112542235B
CN112542235B CN202011490726.XA CN202011490726A CN112542235B CN 112542235 B CN112542235 B CN 112542235B CN 202011490726 A CN202011490726 A CN 202011490726A CN 112542235 B CN112542235 B CN 112542235B
Authority
CN
China
Prior art keywords
patient
lying position
over
turning
time
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.)
Active
Application number
CN202011490726.XA
Other languages
Chinese (zh)
Other versions
CN112542235A (en
Inventor
龙子弋
姜楠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Mingri United Digital Technology Co ltd
Original Assignee
Guangdong Mingri United Digital Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Mingri United Digital Technology Co ltd filed Critical Guangdong Mingri United Digital Technology Co ltd
Priority to CN202011490726.XA priority Critical patent/CN112542235B/en
Publication of CN112542235A publication Critical patent/CN112542235A/en
Application granted granted Critical
Publication of CN112542235B publication Critical patent/CN112542235B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Social Psychology (AREA)
  • Marketing (AREA)
  • Human Computer Interaction (AREA)
  • Quality & Reliability (AREA)
  • Psychiatry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses a method and a system for automatically monitoring the working quality of turn-over nursing, wherein the method comprises the following steps: setting the lying position of the patient and keeping the lying position for the maximum time period; collecting video and identifying facial features; determining a human prone position from the facial features; calculating the time length of the patient in a lying position, and comparing the time length with the set maximum time length of the lying position; and determining whether to carry out turn-over reminding according to the comparison result. The invention is not limited by the bedridden position of the patient, can accurately judge different lying positions, can realize automatic recording and evaluation of turning nursing operation, and avoids the condition of inaccurate and unreal data recording caused by subjective reasons.

Description

Method and system for automatically monitoring turnover nursing working quality
Technical Field
The invention relates to the technical field of nursing monitoring, in particular to a method and a system for automatically monitoring the working quality of turn-over nursing.
Background
A common complication of long-term bedridden patients is pressure sores. Such as cerebral palsy, spinal injury, and advanced parkinsonism, etc., which can not turn over autonomously, pressure sores often occur. Pressure sores are damaged and necrotic tissue caused by loss of normal function of the skin due to long-term compression of body parts, blood circulation disorders, and lack of tissue nutrition. The domestic related report shows that the occurrence rate of pressure sores of neurologic patients can reach 30% -60%, and the incidence rate of pressure sores of patients lying in bed for a long time in home care can reach 20% -50%. Pressure sores not only harm the health of patients, reduce the quality of life, obviously increase the burden of caregivers, but also increase the medical expense.
Pressure sores can be prevented from occurring by good care. One of the simple and effective measures is to change the body position of the bedridden patient on time and correctly, namely to turn over regularly. Therefore, the ministry of health in 2010 will help the patient turn over and list it as one of the "inpatient basic care service items (trial runs"), which becomes an important content of the high-quality care service. Because the condition that nurses have insufficient braiding often exists in the ward, the reasonable arrangement of the turning time can ensure the comfort of patients, does not increase the occurrence of pressure sores and can reduce the workload of nursing staff. The omission or negligence of the turning nursing work is reduced, and the satisfaction degree of patients is improved. At present, the manual recording mode is still generally adopted in nursing work to track the execution condition of the turning work, so that the operation condition of the turning work cannot be accurately recorded, and the precious time of nurses is also occupied by frequent recording.
Therefore, if the turnover nursing work can be automatically monitored, reminded and evaluated, the omission of the nursing work can be avoided, and the improvement of the nursing quality is promoted.
The application number is: 201721278896.5, titled: the invention patent of a turn-over monitoring device discloses a turn-over monitoring device, which is provided with RFID transmitting and reading equipment, wherein RFID signals in corresponding areas on a bed or clothes can be shielded by utilizing the characteristic of high dielectric constant of a human body when the human body is in the prone position in different directions. The time length of the patient in the prone position in all directions can be judged through analysis of the RFID signal sources, and alarming is carried out according to the set time threshold. The judgment of the patient lying position in this way depends on the specific RFID area blocked by the patient, and when the patient lying position is inconsistent with the area or blocked incompletely, the accurate judgment cannot be obtained. Wearing RFID clothing by a patient can cause discomfort to the patient or increase the burden of care. The invention also cannot realize the record and evaluation of the turn-over nursing operation.
The application number is: 201510172068.2, titled: the invention patent of the intelligent turn-over alarm system discloses an intelligent turn-over alarm system, and provides an intelligent turn-over alarm system, wherein a plurality of pressure switches arranged in a cushion can be opened or closed when a patient changes a body position, and switch signals are uploaded to a controller. And when the controller does not receive information numbers from different pressure switches within the set alarm time, a turn-over alarm is sent out. The invention is similar to the former thought that the judgment of the patient lying position depends on the specific area of the patient on the bed to trigger the on-off of the pressure switch. Therefore, when the patient lying position does not coincide with the occupied area, accurate judgment cannot be made. Moreover, the pressure sensing mode is also limited by the influence of the individual morphology and the weight to generate false alarm. This approach requires a specific mattress to be laid on the bed, which can affect the comfort of the patient in a long-term bed. The invention also cannot realize the record and evaluation of the turn-over nursing operation.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for automatically monitoring the turning nursing working quality, which can accurately judge different lying positions without being limited by the lying position of a patient.
In a first aspect of the present invention, there is provided a method of identifying a human prone position, comprising:
Collecting a video of a patient in real time;
identifying facial features of a patient in the patient video;
A human prone position is determined from the facial features.
Optionally, the identifying facial features of the patient in the patient video, wherein the facial features are identified using an edge-computed convolutional neural network model.
Optionally, the human body prone position is determined according to the facial features, wherein the human body prone position is determined according to the spatial distribution condition of the facial features, and is any one of a prone position, a left lateral position and a right lateral position.
In a second aspect of the present invention, there is provided a method of identifying a turn-over in a human body, comprising:
the human body lying position is identified by adopting the method for identifying the human body lying position;
judging whether the turning over occurs or not through the identified change of the human body lying position of the same patient.
In a third aspect of the present invention, a method for automatically monitoring the quality of care for turning over is provided, comprising:
setting the lying position of the patient and keeping the lying position for the maximum time period;
identifying the patient's prone position by the method of identifying the human prone position;
calculating the time length of the patient in a lying position, and comparing the time length with the set maximum time length of the lying position;
and determining whether to carry out turn-over reminding according to the comparison result.
Optionally, the method further comprises monitoring patient turn-over, wherein whether turn-over occurs is determined by the identified change in the human prone position of the same patient;
When the turning action is monitored, the time of turning is recorded, and video clips of preset minutes before the time point are intercepted.
Optionally, determining whether to perform a turn-over reminding according to the comparison result, wherein any one of a turn-over reminding, an immediate turn-over reminding and a turn-over delay reminding is performed according to the comparison result.
Optionally, the method further comprises: evaluating the turnover nursing working quality;
calculating the proportion of the turning delay operation and the total time length of the accumulated turning delay to form a turning care working quality report.
Optionally, the time length of the patient in a lying position is calculated, wherein each time the change of the lying position is detected, the current lying position starting time is recorded, the time length of the current lying position is accumulated, and the lying position time length is accumulated until the next lying position is detected.
In a fourth aspect of the present invention, there is provided a system for identifying a human prone position, comprising:
the acquisition module acquires the video of the patient in real time;
a facial feature recognition module that recognizes facial features of a patient in the patient video;
A prone position identification module that determines a human prone position based on the facial features.
In a fifth aspect of the present invention, there is provided a system for identifying a turn-over in a human body, comprising:
the acquisition module acquires the video of the patient in real time;
a facial feature recognition module that recognizes facial features of a patient in the patient video;
a prone position identification module that determines a human prone position from the facial features;
And the turning identification module judges whether turning occurs or not through the identified change of the human body lying position of the same patient.
In a sixth aspect of the present invention, a system for automatically monitoring the quality of care for turning over, comprises:
A setting module that sets a recumbent position of the patient and maintains the recumbent position for a maximum period of time;
the acquisition module acquires the video of the patient in real time;
a facial feature recognition module that recognizes facial features of a patient in the patient video;
a prone position identification module that determines a human prone position from the facial features;
The calculation comparison module is used for calculating the time length of the patient in a lying position according to the result of the lying position identification module and comparing the time length with the set maximum time length of the lying position;
and the judging module is used for determining whether to turn over to remind according to the comparison result of the calculation and comparison module.
Compared with the prior art, the embodiment of the invention has at least one of the following advantages:
(1) According to the method and the system, the prone position and the turning-over of the patient are identified by adopting the video data acquired by the camera, so that the method and the system are not limited by the position of the patient on a sickbed, and are more accurate; further, the non-contact video acquisition mode can bring better comfort level to the patient, and nursing operation of nurses on the patient is not affected;
(2) According to the method and the system, the prone position is analyzed in an edge computing mode, the prone position and the turning over can be judged without transmitting video data to the outside, and the privacy of a patient is protected;
(3) The method and the system realize automatic recording and evaluation of the turnover nursing work, reduce the time of manual recording by nurses and avoid the situation of inaccurate and unreal data recording caused by subjective reasons;
(4) According to the method and the system, the video of the specific time interval before turning over is automatically intercepted, the real data of the operation process is reserved, the operation process of the turning over process can be better retrospectively analyzed, and the nursing quality is improved.
Drawings
Embodiments of the present invention are further described below with reference to the accompanying drawings:
FIG. 1 is a flow chart of a method for identifying a human prone position according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for identifying a turn-over of a human body according to an embodiment of the present invention;
Fig. 3 is a flowchart of a method for automatically monitoring and evaluating the quality of turn-over care work according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
Fig. 1 is a flowchart of a method for identifying a human body position according to an embodiment of the present invention. Referring to fig. 1, the method for identifying a human prone position in this embodiment includes the following steps:
S100, collecting a patient video in real time;
S200, identifying facial features of a patient in a patient video;
s300, determining the human body lying position according to the facial features.
According to the embodiment of the invention, the patient lying position is judged by adopting the method of identifying facial features by a machine vision technology, and the different lying positions can be accurately judged without being limited by the lying position of the patient.
In a preferred embodiment, the real-time capturing of the patient video in S100 may be performed by using an existing video capturing device, such as an RGB-D camera or a thermal camera, and the non-contact video capturing manner may provide better comfort for the patient, without affecting the nursing operation of the nurse on the patient.
In a preferred embodiment, the facial features of the patient in the identification patient video of S200 may be identified using an edge-computed convolutional neural network model. The convolutional neural network model using edge computation may use the prior art, such as 3DDE(Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees)、SAN(Style Aggregated Network for Facial Landmark Detection)、TS3(Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection) et al face keypoint detection model. In the embodiment, the prone position is analyzed in an edge computing mode, the prone position and the turning over can be judged without transmitting video data to the outside, and the privacy of a patient is protected.
In particular, identifying facial features of a patient in a patient video includes, but is not limited to, eyebrows, eyes, nose, mouth, mandibular contour, and the like. These feature areas are marked as points by the face key point detection model, such as the eyebrow, eyes, nose, mouth, and mandible contours can be marked with 68 points. The feature region and the newly added facial feature may be marked with more points. The model further extracts coordinates of each key point in three-dimensional space. When the patient lying position changes, the coordinates of the facial feature key points in the three-dimensional space change.
In a preferred embodiment, the human body prone position is determined according to the facial features in S300, and the human body prone position may be determined according to the spatial distribution change condition of the facial features, and the human body prone position is any one of a prone position, a left side prone position, and a right side prone position. The change of the spatial distribution of the facial features means that the coordinates of the facial key points in the three-dimensional space change along with the change of the patient lying position. The included angle between the curved surface formed by the surface characteristics and the horizontal plane can be analyzed through space vector matrix operation. And judging whether the human body lying position is any one of the lying position, the left side lying position and the right side lying position according to a preset angle range. If the horizontal position is defined as-45 degrees to 45 degrees, the left side horizontal position is < 45 degrees, and the right side horizontal position is >45 degrees.
Fig. 2 is a flowchart of a method for identifying a turn-over of a human body according to an embodiment of the present invention. Referring to fig. 2, the method for identifying a turn-over of a human body in this embodiment includes the following steps:
S100, acquiring a patient video in real time, wherein the video is required to cover the face of a patient;
S200, identifying facial features of a patient in a patient video;
S300, determining the human body lying position according to facial features;
s400, judging whether the turning over occurs or not according to the identified change of the human body lying position of the same patient.
The embodiments S100 to S300 of the present invention may be implemented by using a corresponding technique in the method for identifying a human body prone position as shown in fig. 1.
According to the embodiment of the invention, the patient lying position is judged by adopting the facial feature recognition method, and whether the patient is turned over is further judged by the change of the lying position, so that no additional equipment is required to be added on the bed surface, and no special clothes are required to be worn by the patient. Meanwhile, the information is acquired in a non-contact way, so that the original bedridden state and comfort level of a patient are not affected.
Fig. 3 is a flowchart of a method for automatically monitoring and evaluating the quality of turn-over care work according to an embodiment of the present invention. Referring to fig. 3, the method for automatically monitoring and evaluating the working quality of turn-over nursing in this embodiment may include the following steps:
S11, setting a turning-over plan, including setting the lying position of a patient and keeping the lying position for the maximum duration;
S12, for the patient with the turning plan, collecting the video of the patient in real time for analyzing the lying position/turning;
s13, identifying facial features of a patient in a patient video;
S14, determining the human body lying position according to the facial features;
s15, calculating the time length of the patient in a lying position, and comparing the time length with the set maximum time length of the lying position;
s16, determining whether to turn over to remind according to the comparison result.
In the above embodiment S11 of the present invention, a turnover plan design may be performed in advance in the system, and the setting of the turnover plan mainly takes into consideration the actual situation of the patient, and may be performed according to the advice of the doctor or the professional care personnel.
The above embodiments S12 to S14 of the present invention may be implemented by using a corresponding technique in the method for identifying a human body prone position as shown in fig. 1.
In a preferred embodiment, in S16, the time period for the patient to be in a prone position is calculated, wherein each time a prone position change is detected, the current prone position start time is recorded, the time period for the current prone position is accumulated, and the prone position time period is accumulated until the next prone position occurrence is detected. Specifically, after each prone position is detected, the time of the prone position is recorded immediately until the prone position changes.
In a preferred embodiment, in S16, whether to turn over is determined according to the comparison result, specifically, any one of a prompt to turn over, an immediate turn over prompt, and a delayed turn over prompt is performed according to the comparison result, so that a nurse can be helped to more effectively arrange a turn over nursing work for a patient in a disease area.
The relation between the comparison result and the turn-over reminding can be:
(1) If the calculated lying time length does not exceed the set lying holding maximum time length and is in the time range without reminding, reminding is not sent out;
(2) If the calculated lying time length is close to the set lying holding maximum time length, a turning-over prompt can be sent out; for example, when the current lying time length reaches N minutes before the lying time length is kept to be set, a turning-over prompt is sent out until the current lying time length reaches the set time length. Such as: n is an integer value of 15 to 30.
(3) If the calculated lying time length is very close to or equal to the set lying time length which is kept at the maximum, sending out an immediate turn-over reminding; for example, a turn-over prompt is sent out within M minutes after the current lying time exceeds the lying time, until M minutes. Such as: m is an integer value of 15-30.
(4) And if the calculated lying position duration exceeds the set lying position maintaining maximum duration, sending out a turn-over delay reminding. For example, after the current lying time exceeds the lying set time for L minutes, a turn-over delay reminding is sent out until a turn-over action is detected.
In implementations, the specific allowable time range N, M, L between the calculated lying position durations of (1) - (4) and the set lying position holding maximum duration may be set according to the actual situation of each patient. The above embodiments are merely illustrative and are not intended to limit the present invention.
In a preferred embodiment, the method for automatically monitoring and evaluating the working quality of the turn-over nursing can further comprise monitoring the turn-over of the patient based on the embodiment shown in fig. 3, wherein whether the turn-over occurs is judged by the identified change of the human body prone position of the same patient; for example, if the patient's body position changes, the patient is considered to be turned over, and if the patient's body position has not changed, the patient is considered to be not turned over. When the turning action is monitored, the time of turning is recorded, and video clips of preset minutes before the time point are intercepted. For example, in one embodiment, the preset time is an integer value between 1 and 3 minutes, i.e., a video clip 1 to 3 minutes before the point in time is truncated, to monitor the entire process. According to the embodiment, the video of the specific time interval before turning over is automatically intercepted, the real data of the operation process is reserved, the operation process of the turning over process can be better retrospectively analyzed, and the nursing quality is improved.
In a preferred embodiment, the method for automatically monitoring and evaluating the working quality of turn-over nursing further comprises the following steps on the basis of the embodiment shown in fig. 3: and evaluating the turnover nursing working quality. Specifically, the proportion of the turning delay operation and the total time length of the accumulated turning delay are calculated to form a turning care working quality report.
In a preferred embodiment, the method for automatically monitoring and evaluating the turnover nursing working quality further comprises the following steps: when the change of the lying position is detected, recording the starting time of the lying position, accumulating the duration of the current lying position, and accumulating the lying position duration until the next lying position change is detected.
According to the embodiment of the method for automatically monitoring and evaluating the turnover nursing working quality, the automatic recording and evaluation of the turnover nursing working are realized, the quality report is generated, the time for manual recording by a nurse is shortened, and the situation that the data recording is inaccurate and unreal due to subjective reasons is avoided.
Corresponding to the method of the embodiment shown in fig. 1, the embodiment of the invention further provides a system for identifying a human prone position, which includes:
the acquisition module acquires the video of the patient in real time;
A facial feature recognition module that recognizes facial features of a patient in a patient video;
A prone position identification module that determines a human prone position based on facial features.
Corresponding to the method of the embodiment shown in fig. 2, the embodiment of the invention further provides a system for identifying a turn-over of a human body, which comprises:
the acquisition module acquires the video of the patient in real time;
A facial feature recognition module that recognizes facial features of a patient in a patient video;
a prone position identification module that determines a human prone position from facial features;
And the turning identification module judges whether turning occurs or not through the identified change of the human body lying position of the same patient.
Corresponding to the method of the embodiment shown in fig. 3, a system for automatically monitoring the working quality of turn-over nursing according to the embodiment of the present invention includes:
A setting module that sets a recumbent position of the patient and maintains the recumbent position for a maximum period of time;
the acquisition module acquires the video of the patient in real time;
A facial feature recognition module that recognizes facial features of a patient in a patient video;
a prone position identification module that determines a human prone position from facial features;
the calculation comparison module is used for calculating the time length of the patient in a lying position according to the result of the lying position identification module and comparing the time length with the set maximum time length of the lying position;
the judging module is used for determining whether to turn over to remind according to the comparison result of the calculation and comparison module.
The modules in the above system may be implemented by using technologies in corresponding methods, which are not described herein. Meanwhile, the above-mentioned respective preferable technical features may be used either or in any combination without collision.
In order to better illustrate the above-described embodiments of the present invention, the following description is provided in connection with a specific application example, which, of course, is not intended to limit the invention.
In the embodiment, the RGB-D camera or the thermal camera is used for collecting the video data of the patient in real time, and the facial features of the patient are detected through the computer vision technology to monitor the lying position of the patient. When the patient keeps the same lying position for a set time, a turn-over prompt can be sent to a nursing staff. When the patient is detected to turn over, the turning over operation time is automatically recorded, and the video of the turning over process is intercepted. And giving an evaluation result according to the delay time of the actual occurrence of the turning operation. Specifically, the method can be carried out by referring to the following steps:
step 1: setting a patient turning-over plan in a disease area. The nurse sets a care plan for the patient in the ward who needs to turn over, including the recumbent position and the maximum duration of the recumbent position maintenance.
Step 2: and monitoring the turning-over of the patient. For the patient with the turning-over plan, starting an RGB-D camera or a thermal camera to monitor in real time, and continuously collecting the bedridden video of the patient for analyzing the lying position and turning over.
Step 3: detecting the lying position and the turning-over of the patient. The RGB-D camera or the thermal camera is used for collecting bedridden videos of patients, and the facial features of the patients are identified by adopting a convolutional neural network model of edge calculation. According to the spatial distribution of facial features, the prone position of the patient is determined to be a prone position, a left lateral position and a right lateral position. The patient is judged to turn over through the change of different lying positions of the patient.
Step 4: and calculating the lying time length. And after the current lying position of the patient is detected, recording the lying position starting time, and accumulating the duration of the current lying position. The lying time is accumulated until the turning-over action of the patient is detected.
Step 5: and (5) turning over to remind. To help nurses more effectively arrange for turn-over care of patients in the ward. Three turning-over reminding modes are designed, namely turning-over reminding, immediately turning-over reminding and turning-over delay reminding.
And 5.1, reminding the user of turning over. And when the current lying position duration reaches N minutes before the lying position is kept for a set duration, sending out a prompt of turning over until the set duration is reached. N is an integer value of 15 to 30.
And 5.2, immediately turning over and reminding. And sending out a prompt of turning over in M minutes after the current lying position duration exceeds the lying position set duration until M minutes. M is an integer value of 15-30.
And 5.3, turning over and reminding in a delayed manner. After the current lying position duration exceeds the lying position set duration for L minutes, a turn-over delay reminding is sent out until a turn-over action is detected. L is an integer value of 15-30.
Step 6: and recording turning-over operation. When the turning-over action of the patient is detected, the time of the turning-over action is recorded, and meanwhile, video clips X minutes before the time point are intercepted and sent to a server for storage. X is an integer value of 1 to 3.
Step 7: and evaluating the turnover nursing working quality. Calculating the proportion of each patient turning delay operation, and accumulating the total time length of the turning delay to form a disease area turning quality report.
The method and the system for automatically monitoring the turning-over nursing working quality in the embodiment of the invention are not limited by the bedridden position of the patient, and can accurately judge different lying positions. The automatic recording and evaluation of the turning care operation can be realized, and the situation that the data recording is inaccurate and unreal due to subjective reasons is avoided; the video of a specific time interval before turning over is automatically intercepted, the real data of the operation process is reserved, the operation process of the turning over process can be better retrospectively analyzed, and the nursing quality is improved.
It should be noted that, the steps in the method provided by the present invention may be implemented by using corresponding modules, devices, units, etc. in the system, and those skilled in the art may refer to a technical solution of the system to implement the step flow of the method, that is, the embodiment in the system may be understood as a preferred example for implementing the method, which is not described herein.
Those skilled in the art will appreciate that the invention provides a system and its individual devices that can be implemented entirely by logic programming of method steps, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc., in addition to the system and its individual devices being implemented in pure computer readable program code. Therefore, the system and various devices thereof provided by the present invention may be considered as a hardware component, and the devices included therein for implementing various functions may also be considered as structures within the hardware component; means for achieving the various functions may also be considered as being either a software module that implements the method or a structure within a hardware component.
The embodiments disclosed herein were chosen and described in detail in order to best explain the principles of the invention and the practical application, and to thereby not limit the invention. Any modifications or variations within the scope of the description that would be apparent to a person skilled in the art are intended to be included within the scope of the invention.

Claims (4)

1. A method for automatically monitoring the quality of turn-over care work, comprising:
setting the lying position of the patient and keeping the lying position for the maximum time period;
non-contact real-time acquisition of patient videos; identifying facial features of a patient in the patient video, wherein the facial features are identified using a convolutional neural network model of edge computation;
Determining a human body lying position according to the facial features, wherein the human body lying position is determined according to the spatial distribution condition of the facial features, and is any one of a lying position, a left lying position and a right lying position;
calculating the time length of the patient in a lying position, and comparing the time length with the set maximum time length of the lying position;
determining whether to turn over reminding according to the comparison result;
Monitoring and recording the turning of the patient, wherein whether the turning occurs is judged through the identified change of the human body lying position of the same patient;
When the turning action is monitored, recording the time of turning, and simultaneously intercepting a video clip of a preset minute before the time point;
and forming a turnover nursing working quality report by calculating the proportion of the turnover delay operation and the total duration of the accumulated turnover delay.
2. The method of automatically monitoring turn-over care work quality of claim 1, wherein facial features of a patient in the patient video are identified, wherein the facial features include eyebrows, eyes, nose, mouth, mandibular contour.
3. The method for automatically monitoring the working quality of the turnover nursing according to claim 1, wherein whether to perform the turnover reminding is determined according to the comparison result, wherein any one of the upcoming turnover reminding, the immediate turnover reminding and the turnover delay reminding is performed according to the comparison result.
4. The method of automatically monitoring turn-over care quality of claim 1, wherein the calculating the time period for the patient to be in a prone position, wherein each time a change in prone position is detected, recording a current prone position start time, accumulating the time period for the current prone position, and accumulating prone position time periods until a next prone position is detected.
CN202011490726.XA 2020-12-17 2020-12-17 Method and system for automatically monitoring turnover nursing working quality Active CN112542235B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011490726.XA CN112542235B (en) 2020-12-17 2020-12-17 Method and system for automatically monitoring turnover nursing working quality

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011490726.XA CN112542235B (en) 2020-12-17 2020-12-17 Method and system for automatically monitoring turnover nursing working quality

Publications (2)

Publication Number Publication Date
CN112542235A CN112542235A (en) 2021-03-23
CN112542235B true CN112542235B (en) 2024-06-14

Family

ID=75018951

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011490726.XA Active CN112542235B (en) 2020-12-17 2020-12-17 Method and system for automatically monitoring turnover nursing working quality

Country Status (1)

Country Link
CN (1) CN112542235B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116486574B (en) 2023-05-05 2025-11-18 立讯精密工业股份有限公司 A roll detection system, method and storage medium
CN119318472A (en) * 2023-07-17 2025-01-17 深圳迈瑞生物医疗电子股份有限公司 Monitoring equipment and prompting method for monitoring risk thereof

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108399956A (en) * 2017-02-08 2018-08-14 上海跃扬医疗科技有限公司 Managing device, home for destitute nurse management equipment and system are nursed in home for destitute

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9934427B2 (en) * 2010-09-23 2018-04-03 Stryker Corporation Video monitoring system
TWM555719U (en) * 2017-09-22 2018-02-21 顏嘉宏 Turn over monitoring device
EP3603492B1 (en) * 2018-08-01 2021-06-16 Hill-Rom Services, Inc. Systems for patient turn detection and confirmation

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108399956A (en) * 2017-02-08 2018-08-14 上海跃扬医疗科技有限公司 Managing device, home for destitute nurse management equipment and system are nursed in home for destitute

Also Published As

Publication number Publication date
CN112542235A (en) 2021-03-23

Similar Documents

Publication Publication Date Title
CN115116133B (en) Abnormal behavior detection system and method for monitoring elderly people living alone
US10463269B2 (en) System and method for machine-learning-based atrial fibrillation detection
US9754471B2 (en) Electronic switch for controlling a device in dependency on a sleep stage
US20130090571A1 (en) Methods and systems for monitoring and preventing pressure ulcers
CN113257440A (en) ICU intelligent nursing system based on patient video identification
Jones et al. Identifying movement onset times for a bed-based pressure sensor array
CN112542235B (en) Method and system for automatically monitoring turnover nursing working quality
CN108711452A (en) The health state analysis method and system of view-based access control model
KR101763302B1 (en) Smart pillow, system and method for managing/diagnosising sleep disturbance using the same
CN108430322A (en) Apparatus, method, and computer program product for continuously monitoring vital sign
CN114360023B (en) Face micro-motion change detection-based resuscitation and early warning method for anesthetized patient
CN113384247A (en) Nursing system and automatic nursing method
CN112786219A (en) Medical care management method, system and device
CN104506809B (en) A kind of severe sufferer monitoring system based on intelligent video
CN118383966B (en) An intelligent hospital bed and its dynamic pressure distribution monitoring and bedsore prevention system
CN118250113A (en) A home care system installed in a senior care tablet
CN111652192A (en) Tumble detection system based on kinect sensor
CN109044375A (en) Control system and method for tracking and detecting eyeball fatigue degree in real time
CN117133458A (en) Nursing supervision system and method for deglutition behaviors of elderly people suffering from disability and intelligence loss
CN214854733U (en) Intelligent insole
CN113017564B (en) Nursing system and method after oral surgery of children
CN117292806B (en) Equipment data risk identification early warning system based on intelligent hospital
CN120048478A (en) Oral health management system based on big data
CN114652274B (en) An intelligent sleep monitoring system with three-dimensional and multi-dimensional data
US20240378890A1 (en) In-Bed Pose and Posture Tracking System

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20221222

Address after: 2139, Building 1, No. 6, Nanjiang Second Road, Zhujiang Street, Nansha District, Guangzhou, Guangdong, 510000 (office only)

Applicant after: Guangdong Mingri United Digital Technology Co.,Ltd.

Address before: 100102 room 9, 1101, 11th floor, building 3, yard 6, Lize West Street, Chaoyang District, Beijing

Applicant before: Wenjing Technology (Beijing) Co.,Ltd.

GR01 Patent grant
GR01 Patent grant