CN116975709A - Injury classification early warning system based on vital sign data - Google Patents
Injury classification early warning system based on vital sign data Download PDFInfo
- Publication number
- CN116975709A CN116975709A CN202310762312.5A CN202310762312A CN116975709A CN 116975709 A CN116975709 A CN 116975709A CN 202310762312 A CN202310762312 A CN 202310762312A CN 116975709 A CN116975709 A CN 116975709A
- Authority
- CN
- China
- Prior art keywords
- injury
- data
- model
- server
- classification
- 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
- 208000014674 injury Diseases 0.000 title claims abstract description 94
- 208000027418 Wounds and injury Diseases 0.000 title claims abstract description 92
- 230000006378 damage Effects 0.000 title claims abstract description 92
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000033001 locomotion Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 4
- 239000008280 blood Substances 0.000 claims description 4
- 210000004369 blood Anatomy 0.000 claims description 4
- 230000036760 body temperature Effects 0.000 claims description 4
- 230000035487 diastolic blood pressure Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 229910052760 oxygen Inorganic materials 0.000 claims description 4
- 239000001301 oxygen Substances 0.000 claims description 4
- 230000035485 pulse pressure Effects 0.000 claims description 4
- 230000035488 systolic blood pressure Effects 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000036387 respiratory rate Effects 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000012163 sequencing technique Methods 0.000 abstract description 4
- 230000036541 health Effects 0.000 description 11
- 238000000034 method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008733 trauma Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 208000000884 Airway Obstruction Diseases 0.000 description 1
- 208000032456 Hemorrhagic Shock Diseases 0.000 description 1
- 208000004756 Respiratory Insufficiency Diseases 0.000 description 1
- 206010049771 Shock haemorrhagic Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002498 deadly effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004064 dysfunction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 201000004193 respiratory failure Diseases 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 208000037974 severe injury Diseases 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000472 traumatic effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7465—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network
- A61B5/747—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network in case of emergency, i.e. alerting emergency services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G16H40/60—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 operation of medical equipment or devices
- G16H40/67—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 operation of medical equipment or devices for remote operation
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Data Mining & Analysis (AREA)
- Physiology (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Cardiology (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Nursing (AREA)
- Fuzzy Systems (AREA)
- Psychiatry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Pulmonology (AREA)
- General Business, Economics & Management (AREA)
- Emergency Medicine (AREA)
- Emergency Management (AREA)
Abstract
The invention provides a life sign data-based injury classification early warning system, which comprises at least one portable wearing device and a server which is in wireless connection with the portable wearing devices, wherein the server is also in wireless connection with at least one mobile rescue terminal, the portable wearing device detects sign information and environment information of personnel and performs primary screening according to detection results to judge whether the personnel is an injury, the portable wearing device corresponding to the injury sends the sign information, the environment information and the position information to the server through a wireless network, the server is constructed with at least one prediction model, the server receives the sign data of the injury and inputs the prediction model to predict the injury of the injury, and performs rescue sequencing according to injury severity, and the server sends the rescue sequencing results, the environment information and the position information of the corresponding injury to the mobile rescue terminal. The system realizes on-site injury prediction and classification, and has accurate prediction and good applicability.
Description
Technical Field
The invention belongs to the technical field of vital sign detection, and particularly relates to a life sign data-based injury classification early warning system.
Background
With the continuous development of technology, wearable vital sign detection technology is also continuously advancing. Currently, chest strap type detection devices have been widely used in the fields of health management, medical monitoring, fitness tracking, and the like. For example, in chinese patents CN 214856778U, CN113925473a and CN103462592B, such devices can only realize respiratory monitoring and other relatively single vital signs, and do not have a injury prediction function, so that rescue workers cannot be guided to rescue injured personnel according to injury severity, and the requirements of professional fields such as military exercises, special operations, rescue and the like cannot be met.
Disclosure of Invention
Therefore, the invention aims to provide the injury classification early warning system based on vital sign data, so as to solve the injury prediction problem of injured persons in the professional fields of military exercises, special operations, rescue and the like, and further improve rescue efficiency and rescue quality.
The aim of the invention can be achieved by the following technical scheme: the utility model provides a life sign data-based injury classification early warning system, includes at least one portable wearing device and with each portable wearing device wireless connection's server, the server still wireless connection has at least one removal rescue end, portable wearing device detects personnel's sign information, environmental information and carries out the preliminary screening according to the testing result and judges whether be the wounded, and portable wearing device that wounded corresponds sends sign information, environmental information and positional information to the server through wireless network, the server has constructed at least one kind of predictive model, the server accepts wounded's sign data and input predictive model and predicts wounded's injury to rescue ordering is carried out according to injury severity, and the server sends the rescue ordering result and the environmental information, the positional information of corresponding wounded to the removal rescue end.
In the above-mentioned injury classification and early warning system based on vital sign data, the vital sign information collected by the portable wearable device includes, but is not limited to, heart rate, respiratory rate, body temperature, blood oxygen, systolic pressure, diastolic pressure, and pulse pressure; the environmental information includes, but is not limited to, posture, fall, position, and motion interactions.
In the injury classification early warning system based on vital sign data, the construction of the prediction model comprises the following steps: pre-training data are prepared in advance, 60% -80% of the data are randomly taken to be used for training a model, and 20% -40% of the data are used for verifying the model; training at least one machine learning algorithm by using training model data to obtain models corresponding to the number of the machine learning algorithms; the data for the verification model is used for testing the model, the data for the verification model is input into the model to obtain the injury classification result, and the injury classification result is compared with the actual injury classification: the proportion of correctly predicting the injury classification is recorded as the accuracy rate, and the proportion of successfully predicting the injury in the actual data of the injury is recorded as the recall rate; and according to the accuracy and recall rate of each algorithm model, different weights are distributed to each model, and the weighted average of the output results of each model is used as the life sign injury classification prediction result.
In the injury classification early warning system based on vital sign data, the construction of the prediction model further comprises the step of artificially giving injury prediction results.
In the injury classification early warning system based on vital sign data, the artificial demarcating weight is specifically that an expert with actual injury rescue experience gives an artificial injury classification prediction result and rescue priority advice according to injury severity prediction values, personnel environment information and personnel state elements, wherein the personnel state elements comprise but are not limited to movement states and whether to call for help.
In the injury classification early warning system based on vital sign data, the machine learning algorithm includes, but is not limited to, a machine learning algorithm including XGBOOST, random forest, naive bayes, support vector machine, and multi-layer perceptron.
In the injury classification early warning system based on vital sign data, the pre-training data is taken from an emergency database of a hospital; the pre-training data are single group of sign data or a combination of sign data for a period of time; the sign information collected by the portable wearable device is single-group data or combination of multiple groups of data in a period of time.
Compared with the prior art, the injury classification early warning system based on vital sign data has the following advantages:
1. compared with the prior art that the medical personnel can do clinical diagnosis, the system has the most important innovation that the remote early warning of the injury is started in advance when the personnel are not injured in executing tasks, and the process of searching and rescuing treatment of the injured is changed.
2. The operation is completed by being distributed on the wearing equipment of each person, so that a large number of communication, data transmission and operation generated by the server are avoided, and the efficiency and reliability of the whole system are improved.
3. In the process of executing complex tasks, personnel face the conditions of intense exercises and no network, can still acquire and record various sign data, and timely report to the rear after communication is restored.
4. Environmental factors and personnel behaviors are added into the injury classification process, so that the prediction accuracy is improved.
5. And the method is compatible with a group of sign data and a period of sign data as a data source, and the trained algorithm model can finally embody the feature of sign trend change, so that the accuracy is better and the applicability is stronger.
Drawings
Fig. 1 is a schematic workflow diagram of an injury classification early warning system based on vital sign data in an embodiment of the invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by way of example with reference to the accompanying drawings are intended to illustrate the invention and should not be construed as limiting the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The injury classification early warning system based on vital sign data comprises at least one portable wearing device and a server which is in wireless connection with each portable wearing device, wherein the server is also in wireless connection with at least one mobile rescue terminal.
The workflow of the system is shown in figure 1:
the portable wearable device detects physical sign information and environmental information of personnel and adopts a boundary value method to carry out preliminary screening according to the detection result to judge whether the personnel are wounded, so that the personnel possibly wounded are screened out.
During primary screening, the portable wearable device monitors vital signs and environments, wherein the vital signs comprise heart rate, respiratory rate, body temperature, blood oxygen, systolic pressure, diastolic pressure, pulse pressure and the like, and the environment information comprises body position and posture, falling, position, action interaction and the like of a person. The portable wearable device is based on whether these metrics are outside of normal ranges, e.g., heart rate less than 60, heart rate greater than 120, prone position for 30 seconds, etc. And primarily screening out personnel possibly having abnormal signs or abnormal behaviors. And then the sign information, the environment information and the position information of the corresponding personnel are sent to a server through a wireless network. Through the preliminary screening, partial normal personnel are eliminated, and normal personnel data are not uploaded to the server any more, so that the server is prevented from generating a large number of communication, data transmission and operation, the communication frequency is reduced, the data do not need to participate in operation of subsequent steps, and the efficiency and reliability of the whole system are improved.
The server is provided with at least one prediction model, receives physical sign data of the wounded, inputs the prediction model to predict the wounded condition of the wounded, carries out rescue sequencing according to the severity of the wounded condition, and sends rescue sequencing results, environment information and position information of the corresponding wounded to the mobile rescue terminal.
Specifically, the construction of the prediction model includes the following steps: .
1. Pre-training data is prepared in advance, and the source of the data can be a hospital self-emergency database; the pre-training data is single group of sign data or a combination of sign data for a period of time; the sign information collected by the portable wearable device is a single set of data or a combination of multiple sets of data in a period of time. Then 70% of the data was randomly taken for training the model and 30% of the data was used for validating the model.
When a single set of characterization data is employed, the mechanism for each piece of data is shown in Table 1:
| sequence number | Age of | Sex (sex) | Source | Body temperature | Pulse pressure | Respiration | Blood oxygen | Heart rate of heart | Systolic pressure | Diastolic blood pressure | Classification of traumas |
| 1 | 34 | Man's body | Emergency database | 36.5 | 98 | 22 | 92 | 57 | 155 | 57 | Light injury |
| 2 | 49 | Man's body | Emergency database | 36.5 | 95 | 16 | 89 | 58 | 153 | 58 | Light injury |
| 3 | 48 | Female | Emergency database | 36.5 | 93 | 20 | 100 | 83 | 173 | 80 | Light injury |
| 4 | 56 | Female | Emergency database | 36.6 | 92 | 22 | 72 | 63 | 155 | 63 | Health care |
| …… |
When a combination of sign data is employed for a period of time, the data structure for each person is shown in table 2:
table 2 is an optimization of table 1, which is integrated with the whole system and is adapted to the portable wearable device in the system, so that the continuous physical sign data can be collected for a period of time when the model training data set is prepared and the model is applied. Through the optimization, the accuracy of the injury classification is improved, and several high-probability deadly injuries of a battlefield can be predicted. Such as traumatic hemorrhagic shock, coagulation dysfunction, respiratory failure, airway obstruction, cannot predict any one injury, and can only be matched with the one with the closest sign change characteristics among the several injury types involved in model training. Correspondingly, when the model trained by using the combined data is applied, the data combination for a period of time is input instead for calculation.
2. Training at least one machine learning algorithm by using training model data to obtain models corresponding to the number of the machine learning algorithms; in the step, the machine learning algorithm can adopt XGBOOST, random forest, naive Bayes, support vector machine, multi-layer perceptron and other algorithms, and then a plurality of corresponding models are obtained through training.
3. And (3) testing each model obtained in the step (2) by using data for a verification model, inputting the data for the verification model into the model to obtain the injury classification result, and comparing the injury classification result with the actual injury classification: the proportion of correctly predicted injury classification is recorded as accuracy, and the proportion of successfully predicted injury in actual data of severe injury is recorded as recall.
4. And according to the accuracy and recall rate of each algorithm model, different weights are distributed to each model, and the weighted average of the output results of each model is used as the life sign injury classification prediction result. Specifically, two models are simultaneously operated as examples: let the accuracy of the model M1 with the first accuracy be p1, the recall be r1, the accuracy of the model M2 with the second accuracy be p2, the recall be r2, and the weight of M1 may be (p1+r1) ×1 and the weight of M2 may be (p2+r2) ×0.5.
The construction of the prediction model also comprises the step of artificially giving the injury prediction result. The artificial defining weight is that an expert with actual treatment experience of the wounded gives out an artificial injury classification prediction result and treatment priority advice according to injury severity prediction values, personnel environment information and personnel state elements, wherein the personnel state elements comprise, but are not limited to, movement states and whether to call for help.
The opinion questionnaire filled in by each expert is shown in the table 3, and after the references (high falling, body position and active help calling) are manually given, the correction opinion of the prediction result of the vital sign injury classification algorithm and whether to take precedence treatment opinion are given.
| Prediction result of vital sign injury classification model | Falling from high place | Body position | Active help calling | Expert advice of the results of the classification of traumas | Priority of treatment |
| Health/light/medium/heavy injury | √ | √ | √ | Health/light/medium/heavy injury | 1/0 |
| Health/light/medium/heavy injury | √ | √ | × | ||
| Health/light/medium/heavy injury | √ | × | √ | ||
| Health/light/medium/heavy injury | × | √ | √ | ||
| Health/light/medium/heavy injury | √ | × | × | ||
| Health/light/medium/heavy injury | × | √ | × | ||
| Health/light/medium/heavy injury | × | × | √ | ||
| Health/light/medium/heavy injury | × | × | × |
The correlation between 4 parameters of [ vital sign injury classification prediction result ], [ high place falling ], [ body position ], [ active help calling ], [ 4 ] and expert opinion can be counted, and most expert opinions are taken to form a table as follows:
the expert opinion is combined with the model prediction, so that the final injury prediction result is more accurate and reliable, and the erroneous judgment of the system is reduced, thereby improving the rescue efficiency and the rescue quality.
The specific embodiments described herein are offered by way of example only to illustrate the spirit of the invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions thereof without departing from the spirit of the invention or exceeding the scope of the invention as defined in the accompanying claims.
Claims (8)
1. The utility model provides a life sign data-based injury classification early warning system, includes at least one portable wearing device and with each portable wearing device wireless connection's server, the server still wireless connection has at least one removal rescue end, portable wearing device detects personnel's sign information, environmental information and carries out the preliminary screening according to the testing result and judges whether be the wounded, and portable wearing device that wounded corresponds sends sign information, environmental information and positional information to the server through wireless network, the server has constructed at least one kind of predictive model, the server accepts wounded's sign data and input predictive model and predicts wounded's injury to rescue ordering is carried out according to injury severity, and the server sends the rescue ordering result and the environmental information, the positional information of corresponding wounded to the removal rescue end.
2. The vital sign data-based injury classification and pre-warning system of claim 1 wherein the vital sign information collected by the portable wearable device includes, but is not limited to, heart rate, respiratory rate, body temperature, blood oxygen, systolic pressure, diastolic pressure, and pulse pressure; the environmental information includes, but is not limited to, posture, fall, position, and motion interactions.
3. The injury classification pre-warning system based on vital sign data according to claim 1 or 2, wherein the construction of the predictive model comprises the steps of: .
a. Pre-training data are prepared in advance, 60% -80% of the data are randomly taken to be used for training a model, and 20% -40% of the data are used for verifying the model;
b. training at least one machine learning algorithm by using training model data to obtain models corresponding to the number of the machine learning algorithms;
c. the data for the verification model is used for testing the model, the data for the verification model is input into the model to obtain the injury classification result, and the injury classification result is compared with the actual injury classification: the proportion of correctly predicting the injury classification is recorded as the accuracy rate, and the proportion of successfully predicting the injury in the actual data of the injury is recorded as the recall rate;
d. and according to the accuracy and recall rate of each algorithm model, different weights are distributed to each model, and the weighted average of the output results of each model is used as the life sign injury classification prediction result.
4. The vital sign data-based injury classification and early warning system of claim 3 wherein 70% of the data is randomly taken for training and 30% of the data is used for validating the model.
5. The vital sign data-based injury classification and early warning system of claim 3 wherein the construction of the predictive model further comprises the step of artificially presenting injury prediction results.
6. The vital sign data-based injury classification and early warning system of claim 5, wherein the artificial injury prediction result is specifically that an expert with actual injury rescue experience gives an artificial injury classification prediction result and rescue priority advice according to injury severity prediction values, personnel environment information and personnel status elements, wherein the personnel status elements include but are not limited to movement status and whether to call for help.
7. A vital sign data-based injury classification pre-warning system according to claim 3, wherein the machine learning algorithm includes, but is not limited to, a machine learning algorithm including XGBOOST, random forest, naive bayes, support vector machine, multi-layer perceptron.
8. The vital sign data-based injury classification and pre-warning system of claim 3 wherein the pre-training data is taken from an emergency database; the pre-training data are single group of sign data or a combination of sign data for a period of time; the sign information collected by the portable wearable device is single-group data or combination of multiple groups of data in a period of time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762312.5A CN116975709A (en) | 2023-06-27 | 2023-06-27 | Injury classification early warning system based on vital sign data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762312.5A CN116975709A (en) | 2023-06-27 | 2023-06-27 | Injury classification early warning system based on vital sign data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116975709A true CN116975709A (en) | 2023-10-31 |
Family
ID=88477538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310762312.5A Pending CN116975709A (en) | 2023-06-27 | 2023-06-27 | Injury classification early warning system based on vital sign data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116975709A (en) |
-
2023
- 2023-06-27 CN CN202310762312.5A patent/CN116975709A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11942203B2 (en) | Systems and methods for providing and managing a personalized cardiac rehabilitation plan | |
| US10478065B2 (en) | Systems and methods for monitoring subjects in potential physiological distress | |
| CN108430570B (en) | Obtaining high resolution information from an implantable medical device | |
| CN102281816B (en) | Method and apparatus for determining critical care parameters | |
| AU2005265092B2 (en) | Systems and methods for real-time physiological monitoring | |
| US10898075B2 (en) | Wearable stress-testing device | |
| US7433853B2 (en) | Expert system for patient medical information analysis | |
| US6735551B2 (en) | System for maintenance and management of health | |
| US6811537B2 (en) | System and method for providing diagnosis and monitoring of congestive heart failure for use in automated patient care | |
| EP1102198A2 (en) | Automated collection and analysis patient care system and method for diagnosing and monitoring respiratory insufficiency and outcomes therof | |
| US20070106129A1 (en) | Dietary monitoring system for comprehensive patient management | |
| CN116509350B (en) | Medical monitoring system based on intelligent bracelet | |
| CN111798982A (en) | Police health management system and health management method | |
| EP3844778A1 (en) | Digital companion for healthcare | |
| CN113205884A (en) | Blood sugar prediction method, system and application thereof | |
| CN116975709A (en) | Injury classification early warning system based on vital sign data | |
| US20200107778A1 (en) | Using biometrics to measure, catalog, analyze, predict and/or monitor emergency responder stress to optimize performance and health | |
| Ivascu et al. | Real-time health status monitoring system based on a fuzzy agent model | |
| CN117315885B (en) | Remote sharing alarm system for monitoring urine volume of urine bag and electrocardiograph monitor | |
| CN110974215B (en) | Early warning system and method based on wireless electrocardiogram monitoring sensor group | |
| WO2023053176A1 (en) | Learning device, behavior recommendation device, learning method, behavior recommendation method, and recording medium | |
| AU2012201266B2 (en) | Systems and methods for real-time physiological monitoring | |
| CN118280535A (en) | Slow disease management system | |
| CN114783561A (en) | Rehabilitation management system used by patient with cognitive disorder after stroke | |
| CN118319258A (en) | Wireless multifunctional physical sign monitoring 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 |