CN116417134A - Bulk sick and wounded medical post-delivery full-flow decision-making method and system - Google Patents
Bulk sick and wounded medical post-delivery full-flow decision-making method and system Download PDFInfo
- Publication number
- CN116417134A CN116417134A CN202310084447.0A CN202310084447A CN116417134A CN 116417134 A CN116417134 A CN 116417134A CN 202310084447 A CN202310084447 A CN 202310084447A CN 116417134 A CN116417134 A CN 116417134A
- Authority
- CN
- China
- Prior art keywords
- sick
- wounded
- vital sign
- information
- medical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004083 survival effect Effects 0.000 claims abstract description 109
- 238000004458 analytical method Methods 0.000 claims abstract description 45
- 238000007781 pre-processing Methods 0.000 claims abstract description 29
- 238000003062 neural network model Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 18
- 238000010606 normalization Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 9
- 238000012351 Integrated analysis Methods 0.000 claims 1
- 238000011084 recovery Methods 0.000 abstract description 9
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 8
- 230000036772 blood pressure Effects 0.000 description 4
- 230000036760 body temperature Effects 0.000 description 4
- 208000027418 Wounds and injury Diseases 0.000 description 3
- 230000006378 damage Effects 0.000 description 3
- 208000014674 injury Diseases 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 230000036387 respiratory rate Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
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
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a whole flow decision method and a whole flow decision system for batch sick and wounded medical treatment, wherein the method comprises the steps of collecting vital sign information of each sick and wounded in batches to be fed back; preprocessing the collected vital sign information of each sick and wounded; predicting survival time of each sick and wounded based on the vital sign information of each sick and wounded after pretreatment and a pre-constructed comprehensive analysis model of the vital sign information of each sick and wounded; classifying treatment priorities of the batches of the sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction; medical relief aid decision information for a batch of patients to be relief is generated based on the treatment priority classification results and the existing medical relief resources. The invention can realize the intelligent decision of the full-flow medical post-delivery of the batch of sick and wounded, fills the blank of the industry, and effectively improves the medical post-delivery efficiency of the batch of sick and wounded, thereby being beneficial to improving the survival rate and recovery rate of the batch of sick and wounded rate and disability rate.
Description
Technical Field
The invention relates to the technical field of medical post-delivery, in particular to a whole flow decision method and a whole flow decision system for batch post-delivery of sick and wounded medical treatment.
Background
To obtain an excellent rescue for a batch of sick and wounded, it is necessary to send the sick and wounded to an appropriate rescue agency within the time period of the aged rescue. However, there is a great conflict between the demand for on-site relief of injuries and diseases in batches of sick and wounded and the relief conditions, and medical post-delivery decisions must be rationally planned for timely and effective relief.
At present, in the aspect of medical post-delivery decision, an auxiliary decision is provided for the post-delivery decision of a single sick and wounded mainly by means of a path planning technology, so that the full-flow medical post-delivery intelligent decision of a batch of sick and wounded cannot be realized, the post-delivery efficiency is low, and the survival rate and the recovery rate of the sick and wounded are affected.
Disclosure of Invention
The invention aims at solving at least one of the technical problems in the prior art, and particularly creatively provides a full-flow decision method and a full-flow decision system for batch sick and wounded medical treatment, which can realize full-flow medical treatment of the batch sick and wounded, fill the blank of industry, and effectively improve the medical treatment post-delivery efficiency of the batch sick and wounded, thereby being beneficial to improving the survival rate and recovery rate of the batch sick and wounded and reducing the death rate and disability rate.
To achieve the above object of the present invention, according to a first aspect of the present invention, there is provided a bulk sick and wounded medical back-delivery full-flow decision-making method, the method comprising the steps of:
collecting vital sign information of each sick and wounded in batches to be sent back;
preprocessing the collected vital sign information of each sick and wounded;
predicting survival time of each sick and wounded based on the vital sign information of each sick and wounded after pretreatment and a pre-constructed comprehensive analysis model of the vital sign information of each sick and wounded;
classifying treatment priorities of the batches of the sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction;
generating medical relief aid decision information for a batch of patients to be relief based on the treatment priority classification results and the existing medical relief resources, wherein,
the medical post-delivery auxiliary decision information comprises medical post-delivery target medical institution information, medical post-delivery tool information, medical post-delivery medical personnel information, medical post-delivery medical equipment information, medical post-delivery path planning information and medical post-delivery required time information of each sick and wounded.
Preferably, the vital sign information includes continuous vital sign information and discrete vital sign information, and the preprocessing the vital sign information of each patient acquired includes:
carrying out one-hot coding treatment on the discrete feature information;
carrying out normalization processing on the continuous body sign information by adopting a sliding window method;
and splicing and fusing the discrete vital sign information after the one-hot encoding processing and the continuous vital sign information after the normalization processing to obtain the vital sign information of each pre-processed sick and wounded.
Preferably, the predicting survival time of each patient based on the preprocessed vital sign information of each patient and the pre-constructed comprehensive analysis model of the vital sign information of each patient includes:
and taking the vital sign information of each preprocessed sick and wounded as the input of the sick and wounded vital sign information comprehensive analysis model, and respectively processing the vital sign information of each preprocessed sick and wounded by using the sick and wounded vital sign information comprehensive analysis model to obtain the survival time of each sick and wounded.
Preferably, the treatment priority classification of the batch of patients to be sent back based on the predicted survival time of each patient includes:
searching the treatment priority matched with the survival time of each sick and wounded in a preset survival time-treatment priority corresponding relation table based on the predicted survival time of each sick and wounded, and determining the treatment priority of each sick and wounded;
and classifying the treatment priority of the fed-back batch of sick and wounded based on the determined treatment priority of each sick and wounded to obtain treatment priority classification results, wherein the treatment priority classification results comprise the number of sick and wounded corresponding to each treatment priority.
Preferably, the constructing process of the comprehensive analysis model of the patient sign information comprises the following steps:
constructing a training sample set, wherein the training sample set comprises patient vital sign sample data and patient real survival time corresponding to the patient vital sign sample data;
inputting the patient vital sign sample data into an LSTM neural network model, and predicting survival time of the patient vital sign sample data by adopting the LSTM neural network model to obtain predicted survival time corresponding to the patient vital sign sample data;
constructing a cross entropy loss function of the patient vital sign sample data based on the patient real survival time and the predicted survival time;
training the LSTM neural network model based on the vital sign sample data of the sick and wounded and the cross entropy loss function to obtain a trained LSTM neural network model, and determining the trained LSTM neural network model as the sick and wounded vital sign information comprehensive analysis model.
According to a second aspect of the present invention, there is also provided a bulk patient medical follow-up whole procedure decision system, the system comprising:
the information acquisition module is used for acquiring vital sign information of each sick and wounded in batches to be sent back;
the information preprocessing module is used for preprocessing the collected vital sign information of each sick and wounded;
the survival time prediction module is used for predicting the survival time of each sick and wounded based on the vital sign information of each sick and wounded after pretreatment and a pre-constructed comprehensive analysis model of the vital sign information of the sick and wounded;
the sick and wounded classifying module is used for classifying treatment priority of the batch of sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction;
a decision information generation module for generating medical post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered based on the treatment priority classification result and the existing medical post-delivery resource, wherein,
the medical post-delivery auxiliary decision information comprises medical post-delivery target medical institution information, medical post-delivery tool information, medical post-delivery medical personnel information, medical post-delivery medical equipment information, medical post-delivery path planning information and medical post-delivery required time information of each sick and wounded.
Preferably, the vital sign information includes continuous vital sign information and discrete vital sign information, and the information preprocessing module is specifically configured to:
carrying out one-hot coding treatment on the discrete feature information;
carrying out normalization processing on the continuous body sign information by adopting a sliding window method;
and splicing and fusing the discrete vital sign information after the one-hot encoding processing and the continuous vital sign information after the normalization processing to obtain the vital sign information of each pre-processed sick and wounded.
Preferably, the survival time prediction module is specifically configured to:
and taking the vital sign information of each preprocessed sick and wounded as the input of the sick and wounded vital sign information comprehensive analysis model, and respectively processing the vital sign information of each preprocessed sick and wounded by using the sick and wounded vital sign information comprehensive analysis model to obtain the survival time of each sick and wounded.
Preferably, the patient classification module is specifically configured to:
searching the treatment priority matched with the survival time of each sick and wounded in a preset survival time-treatment priority corresponding relation table based on the predicted survival time of each sick and wounded, and determining the treatment priority of each sick and wounded;
and classifying the treatment priority of the fed-back batch of sick and wounded based on the determined treatment priority of each sick and wounded to obtain treatment priority classification results, wherein the treatment priority classification results comprise the number of sick and wounded corresponding to each treatment priority.
Preferably, the system further comprises a model construction module for constructing the comprehensive analysis model of the patient sign information, wherein the model construction module is specifically used for:
constructing a training sample set, wherein the training sample set comprises patient vital sign sample data and patient real survival time corresponding to the patient vital sign sample data;
inputting the patient vital sign sample data into an LSTM neural network model, and predicting survival time of the patient vital sign sample data by adopting the LSTM neural network model to obtain predicted survival time corresponding to the patient vital sign sample data;
constructing a cross entropy loss function of the patient vital sign sample data based on the patient real survival time and the predicted survival time;
training the LSTM neural network model based on the vital sign sample data of the sick and wounded and the cross entropy loss function to obtain a trained LSTM neural network model, and determining the trained LSTM neural network model as the sick and wounded vital sign information comprehensive analysis model.
According to the scheme, the invention provides a whole flow decision method and a whole flow decision system for batch sick and wounded medical treatment, and vital sign information of each sick and wounded in batches to be fed back is collected; preprocessing the collected vital sign information of each sick and wounded; predicting survival time of each sick and wounded based on the vital sign information of each sick and wounded after pretreatment and a pre-constructed comprehensive analysis model of the vital sign information of each sick and wounded; classifying treatment priorities of the batches of the sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction; medical post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered is generated based on the treatment priority classification result and the existing medical post-delivery resources, wherein the medical post-delivery auxiliary decision information comprises medical post-delivery target medical institution information, medical post-delivery tool information, medical post-delivery medical personnel information, medical post-delivery medical equipment information, medical post-delivery path planning information and medical post-delivery required time information of each sick and wounded. The invention can realize the full-flow medical post-delivery intelligent decision of the batch of sick and wounded, fills the blank of the industry, provides technical support for the medical post-delivery of the batch of sick and wounded, and effectively improves the medical post-delivery efficiency of the batch of sick and wounded, thereby being beneficial to improving the survival rate and recovery rate of the batch of sick and wounded, reducing the death rate and disability rate, and solving the problems that the prior art cannot realize the full-flow medical post-delivery intelligent decision of the batch of sick and wounded, resulting in low post-delivery efficiency and affecting the survival rate and recovery rate of the sick and wounded.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flow chart of a bulk patient medical follow-up full flow decision method in accordance with a preferred embodiment of the present invention;
FIG. 2 is a schematic diagram of a bulk patient medical follow-up full-flow decision making system in accordance with a preferred embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Referring now to FIG. 1, a flow chart of a method for bulk patient healthcare post-delivery full-flow decision making in accordance with a preferred embodiment of the present invention may include the steps of:
s101, collecting vital sign information of each sick and wounded in batches to be sent back;
when a large-scale injury occurs, the density of the generated sick and wounded is high, and for sick and wounded who cannot be treated at some on-site medical sites, the medical treatment and treatment of the sick and wounded needs to be reasonably organized by a health department according to the actual conditions of the sick and wounded, and the sick and wounded are sent to better treatment.
In order to realize effective back-feeding of the batch of sick and wounded, vital sign information of each sick and wounded in the batch to be back-fed needs to be collected according to a preset data collection rule. Specifically, vital sign information such as oxygen demand saturation, blood pressure, body temperature, respiratory rate and electrocardio data of a sick and wounded can be collected fast by depending on a wearable device integrated with a corresponding sign information detection sensor.
S102, preprocessing collected vital sign information of each sick and wounded;
after collecting vital sign information of each sick and wounded in batches to be sent later, preprocessing is needed to be carried out on the collected vital sign information of each sick and wounded, and the vital sign information of each sick and wounded is processed into a data form which can be directly analyzed and processed by the comprehensive analysis model of the vital sign information of the sick and wounded.
S103, predicting survival time of each sick and wounded based on the vital sign information of each sick and wounded after pretreatment and a pre-constructed comprehensive analysis model of the vital sign information of each sick and wounded;
after preprocessing the collected vital sign information of each sick and wounded, the survival time of each sick and wounded can be predicted according to the preprocessed vital sign information of each sick and wounded and a pre-built comprehensive analysis model of the vital sign information of each sick and wounded, namely, the preprocessed vital sign information of each sick and wounded is used as the input of the comprehensive analysis model of the vital sign information of each sick and wounded, and the vital sign information of each sick and wounded after preprocessing is respectively processed by using the comprehensive analysis model of the vital sign information of each sick and wounded, so that the survival time of each sick and wounded is obtained.
S104, classifying treatment priorities of the batches of the sick and wounded to be sent back based on the survival time of each sick and wounded obtained through prediction;
after the survival time of each sick and wounded is predicted, the treatment priority classification is further required to be performed on the batch of sick and wounded to be sent back according to the predicted survival time of each sick and wounded, namely, which treatment priority each sick and wounded belongs to is determined according to the predicted survival time of each sick and wounded, so that the subsequent classification decision of medical treatment sending back is conveniently realized according to the treatment priority corresponding to each sick and wounded.
S105, medical treatment post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered is generated based on the treatment priority classification result and the existing medical treatment post-delivery resources.
After the treatment priority classification is performed on the batch of patients to be sent, medical post-sending auxiliary decision information of the batch of patients to be sent is needed to be generated according to the treatment priority classification result and the existing medical post-sending resources. Because the time limit of the time-efficient treatment of the sick and wounded with different treatment priority levels is different, and the medical post-treatment resources of higher level are limited, the existing medical post-treatment resources (post-treatment medical institution, medical post-treatment tool, medical post-treatment medical personnel, medical post-treatment medical equipment, etc.) need to be comprehensively allocated according to the treatment priority classification result, so that each sick and wounded in the batch of the sick and wounded to be post-treated is post-treated within the time limit of the time-efficient treatment of the sick and wounded by utilizing the existing limited medical post-treatment resources.
For example, the most severe (i.e., highest treatment priority) may employ the fastest, least-powerful medical follow-up (e.g., helicopter) tool, and the higher-grade medical follow-up personnel may be configured to address the emergency situation of the patient.
Specifically, the existing medical post-delivery resources can be distributed to all the sick and wounded in the batch of sick and wounded to be post-delivered according to the preset medical resource overall distribution principle and the treatment priority classification result, so that the medical post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered is obtained, and technical support is provided for the medical post-delivery of the batch of sick and wounded through the obtained medical post-delivery auxiliary decision information.
Specifically, the medical post-delivery auxiliary decision information includes medical post-delivery target medical institution information, medical post-delivery tool information, medical post-delivery medical personnel information, medical post-delivery medical equipment information, medical post-delivery path planning information, and medical post-delivery required time information of each sick and wounded.
In summary, the embodiment provides a method for performing a whole flow decision-making for medical post-delivery of bulk sick and wounded, which includes collecting vital sign information of each sick and wounded in the bulk sick and wounded to be post-delivered; preprocessing the collected vital sign information of each sick and wounded; predicting the survival time of each sick and wounded based on the pretreated vital sign information of each sick and wounded and the pre-constructed comprehensive analysis model of the vital sign information of each sick and wounded; then, classifying treatment priorities of the batches of the sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction; and finally, generating medical treatment post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered based on the treatment priority classification result and the existing medical treatment post-delivery resources.
According to the full-flow decision-making method for batch sick and wounded medical treatment postfeeding, full-flow medical treatment postfeeding intelligent decision-making of batch sick and wounded can be realized, the industry blank is filled, technical support is provided for batch sick and wounded medical treatment postfeeding, the medical treatment postfeeding efficiency of batch sick and wounded is effectively improved, the survival rate and recovery rate of batch sick and wounded are improved, the death rate and disability rate are reduced, and the problems that the prior art cannot realize full-flow medical treatment postfeeding intelligent decision-making of batch sick and wounded, the postfeeding efficiency is low, and the survival rate and recovery rate of sick and wounded are affected are solved.
In one embodiment, the vital sign information includes continuous vital sign information (e.g., electrocardiographic data) and discrete vital sign information (e.g., aerobic saturation, blood pressure, body temperature, and respiration rate). Because the comprehensive analysis model of the patient sign information cannot directly process the acquired continuous sign information and discrete sign information, different data preprocessing modes are needed to process the continuous sign information and the discrete sign information respectively, and then the continuous sign information and the discrete sign information are subjected to data fusion. Specifically, the preprocessing of the vital sign information of each patient includes:
carrying out one-hot coding treatment on the discrete feature information;
carrying out normalization processing on the continuous body sign information by adopting a sliding window method;
and splicing and fusing the discrete vital sign information after the one-hot encoding processing and the continuous vital sign information after the normalization processing to obtain the vital sign information of each pre-processed sick and wounded.
In one embodiment, the treatment priority classification of the bulk of patients to be sent back based on the predicted survival time of each patient includes:
searching the treatment priority matched with the survival time of each sick and wounded in a preset survival time-treatment priority corresponding relation table based on the predicted survival time of each sick and wounded, and determining the treatment priority of each sick and wounded;
and classifying the treatment priority of the fed-back batch of sick and wounded based on the determined treatment priority of each sick and wounded to obtain treatment priority classification results, wherein the treatment priority classification results comprise the number of sick and wounded corresponding to each treatment priority.
Specifically, the survival time-treatment priority correspondence table is preset according to empirical data. The survival time-treatment priority correspondence in this embodiment is as follows:
in one embodiment, the constructing process of the comprehensive analysis model of the patient sign information comprises the following steps:
constructing a training sample set, wherein the training sample set comprises patient vital sign sample data and patient real survival time corresponding to the patient vital sign sample data;
inputting the patient vital sign sample data into an LSTM (Long Short-Term Memory network) neural network model, and predicting the survival time of the patient vital sign sample data by adopting the LSTM neural network model to obtain the predicted survival time corresponding to the patient vital sign sample data;
constructing a cross entropy loss function of the patient vital sign sample data based on the patient real survival time and the predicted survival time;
training the LSTM neural network model based on the vital sign sample data of the sick and wounded and the cross entropy loss function to obtain a trained LSTM neural network model, and determining the trained LSTM neural network model as the sick and wounded vital sign information comprehensive analysis model.
For continuous vital sign information with time sequence, common deep learning models cannot well utilize hidden information included in time sequence, the cyclic neural network RNN is only short-term memory of the last moment, in the embodiment, when the model is built aiming at the time continuous vital sign information, the LSTM neural network model with a gate-leading mechanism can process the hidden information in any moment, so that the precision of the comprehensive analysis model of the vital sign information of the sick and wounded can be effectively improved.
Referring to fig. 2, a schematic structural diagram of a system for making a decision on a total flow of batch patient medical back-feeding according to a preferred embodiment of the present invention may include:
the information acquisition module 201 is used for acquiring vital sign information of each patient in the batch of patients to be sent back;
when a large-scale injury occurs, the density of the generated sick and wounded is high, and for sick and wounded who cannot be treated at some on-site medical sites, the medical treatment and treatment of the sick and wounded needs to be reasonably organized by a health department according to the actual conditions of the sick and wounded, and the sick and wounded are sent to better treatment.
In order to realize effective back-feeding of the batch of sick and wounded, vital sign information of each sick and wounded in the batch to be back-fed needs to be collected according to a preset data collection rule. Specifically, vital sign information such as oxygen demand saturation, blood pressure, body temperature, respiratory rate and electrocardio data of a sick and wounded can be collected fast by depending on a wearable device integrated with a corresponding sign information detection sensor.
An information preprocessing module 202, configured to preprocess collected vital sign information of each patient;
after collecting vital sign information of each sick and wounded in batches to be sent later, preprocessing is needed to be carried out on the collected vital sign information of each sick and wounded, and the vital sign information of each sick and wounded is processed into a data form which can be directly analyzed and processed by the comprehensive analysis model of the vital sign information of the sick and wounded.
A survival time prediction module 203, configured to predict survival time of each patient based on the vital sign information of each patient after preprocessing and a pre-constructed comprehensive analysis model of the vital sign information of the patient;
after preprocessing the collected vital sign information of each sick and wounded, the survival time of each sick and wounded can be predicted according to the preprocessed vital sign information of each sick and wounded and a pre-built comprehensive analysis model of the vital sign information of each sick and wounded, namely, the preprocessed vital sign information of each sick and wounded is used as the input of the comprehensive analysis model of the vital sign information of each sick and wounded, and the vital sign information of each sick and wounded after preprocessing is respectively processed by using the comprehensive analysis model of the vital sign information of each sick and wounded, so that the survival time of each sick and wounded is obtained.
A sick and wounded classification module 204, configured to classify the treatment priority of the bulk sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction;
after the survival time of each sick and wounded is predicted, the treatment priority classification is further required to be performed on the batch of sick and wounded to be sent back according to the predicted survival time of each sick and wounded, namely, which treatment priority each sick and wounded belongs to is determined according to the predicted survival time of each sick and wounded, so that the subsequent classification decision of medical treatment sending back is conveniently realized according to the treatment priority corresponding to each sick and wounded.
The decision information generation module 205 is configured to generate medical post-delivery auxiliary decision information of a batch of sick and wounded to be post-delivered based on the treatment priority classification result and the existing medical post-delivery resource.
After the treatment priority classification is performed on the batch of patients to be sent, medical post-sending auxiliary decision information of the batch of patients to be sent is needed to be generated according to the treatment priority classification result and the existing medical post-sending resources. Because the time limit of the time-efficient treatment of the sick and wounded with different treatment priority levels is different, and the medical post-treatment resources of higher level are limited, the existing medical post-treatment resources (post-treatment medical institution, medical post-treatment tool, medical post-treatment medical personnel, medical post-treatment medical equipment, etc.) need to be comprehensively allocated according to the treatment priority classification result, so that each sick and wounded in the batch of the sick and wounded to be post-treated is post-treated within the time limit of the time-efficient treatment of the sick and wounded by utilizing the existing limited medical post-treatment resources.
For example, the most severe (i.e., highest treatment priority) may employ the fastest, least-powerful medical follow-up (e.g., helicopter) tool, and the higher-grade medical follow-up personnel may be configured to address the emergency situation of the patient.
Specifically, the existing medical post-delivery resources can be distributed to all the sick and wounded in the batch of sick and wounded to be post-delivered according to the preset medical resource overall distribution principle and the treatment priority classification result, so that the medical post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered is obtained, and technical support is provided for the medical post-delivery of the batch of sick and wounded through the obtained medical post-delivery auxiliary decision information.
Specifically, the medical post-delivery auxiliary decision information includes medical post-delivery target medical institution information, medical post-delivery tool information, medical post-delivery medical personnel information, medical post-delivery medical equipment information, medical post-delivery path planning information, and medical post-delivery required time information of each sick and wounded.
In summary, the embodiment provides a system for performing a whole flow decision-making after batch patient medical treatment, which collects vital sign information of each patient in the batch patient to be sent after the patient is treated by an information collecting module; preprocessing the collected vital sign information of each sick and wounded through an information preprocessing module; predicting the survival time of each sick and wounded based on the vital sign information of each sick and wounded after preprocessing and a pre-constructed comprehensive analysis model of the vital sign information of each sick and wounded by a survival time prediction module; classifying treatment priorities of the batch of the patients to be sent back based on the survival time of each patient obtained by prediction through the patient classification module; and generating medical treatment post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered by the decision information generation module based on the treatment priority classification result and the existing medical treatment post-delivery resources.
According to the full-flow medical post-delivery decision-making system for the batch sick and wounded, full-flow medical post-delivery intelligent decision-making for the batch sick and wounded can be realized, the industry blank is filled, technical support is provided for the medical post-delivery of the batch sick and wounded, the medical post-delivery efficiency of the batch sick and wounded is effectively improved, the survival rate and the recovery rate of the batch sick and wounded are improved, the death rate and the disability rate are reduced, the problem that the full-flow medical post-delivery intelligent decision-making for the batch sick and wounded cannot be realized in the prior art, the post-delivery efficiency is low, and the survival rate and the recovery rate of the sick and wounded are affected is solved.
In one embodiment, the vital sign information includes continuous vital sign information (e.g., electrocardiographic data) and discrete vital sign information (e.g., aerobic saturation, blood pressure, body temperature, and respiration rate). Because the comprehensive analysis model of the patient sign information cannot directly process the acquired continuous sign information and discrete sign information, different data preprocessing modes are needed to process the continuous sign information and the discrete sign information respectively, and then the continuous sign information and the discrete sign information are subjected to data fusion. Specifically, the information preprocessing module is specifically configured to:
carrying out one-hot coding treatment on the discrete feature information;
carrying out normalization processing on the continuous body sign information by adopting a sliding window method;
and splicing and fusing the discrete vital sign information after the one-hot encoding processing and the continuous vital sign information after the normalization processing to obtain the vital sign information of each pre-processed sick and wounded.
In one embodiment, the survival time prediction module is specifically configured to:
and taking the vital sign information of each preprocessed sick and wounded as the input of the sick and wounded vital sign information comprehensive analysis model, and respectively processing the vital sign information of each preprocessed sick and wounded by using the sick and wounded vital sign information comprehensive analysis model to obtain the survival time of each sick and wounded.
In one embodiment, the patient classification module is specifically configured to:
searching the treatment priority matched with the survival time of each sick and wounded in a preset survival time-treatment priority corresponding relation table based on the predicted survival time of each sick and wounded, and determining the treatment priority of each sick and wounded;
and classifying the treatment priority of the fed-back batch of sick and wounded based on the determined treatment priority of each sick and wounded to obtain treatment priority classification results, wherein the treatment priority classification results comprise the number of sick and wounded corresponding to each treatment priority.
Specifically, the survival time-treatment priority correspondence table is preset according to empirical data. The survival time-treatment priority correspondence in this embodiment is as follows:
| survival time | Priority of treatment |
| 0-30 minutes | Highest to |
| 30 minutes to 90 minutes | High height |
| 90 minutes to 180 minutes | In (a) |
| 180 minutes to 270 minutes | Low and low |
In one embodiment, the system further comprises a model building module for building the patient sign information comprehensive analysis model, the model building module being specifically configured to:
constructing a training sample set, wherein the training sample set comprises patient vital sign sample data and patient real survival time corresponding to the patient vital sign sample data;
inputting the patient vital sign sample data into an LSTM neural network model, and predicting survival time of the patient vital sign sample data by adopting the LSTM neural network model to obtain predicted survival time corresponding to the patient vital sign sample data;
constructing a cross entropy loss function of the patient vital sign sample data based on the patient real survival time and the predicted survival time;
training the LSTM neural network model based on the vital sign sample data of the sick and wounded and the cross entropy loss function to obtain a trained LSTM neural network model, and determining the trained LSTM neural network model as the sick and wounded vital sign information comprehensive analysis model.
For continuous vital sign information with time sequence, common deep learning models cannot well utilize hidden information included in time sequence, the cyclic neural network RNN is only short-term memory of the last moment, in the embodiment, when the model is built aiming at the time continuous vital sign information, the LSTM neural network model with a gate-leading mechanism can process the hidden information in any moment, so that the precision of the comprehensive analysis model of the vital sign information of the sick and wounded can be effectively improved.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The whole flow decision method for batch patient medical post-delivery is characterized by comprising the following steps:
collecting vital sign information of each sick and wounded in batches to be sent back;
preprocessing the collected vital sign information of each sick and wounded;
predicting survival time of each sick and wounded based on the vital sign information of each sick and wounded after pretreatment and a pre-constructed comprehensive analysis model of the vital sign information of each sick and wounded;
classifying treatment priorities of the batches of the sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction;
generating medical relief aid decision information for a batch of patients to be relief based on the treatment priority classification results and the existing medical relief resources, wherein,
the medical post-delivery auxiliary decision information comprises medical post-delivery target medical institution information, medical post-delivery tool information, medical post-delivery medical personnel information, medical post-delivery medical equipment information, medical post-delivery path planning information and medical post-delivery required time information of each sick and wounded.
2. The bulk patient medical follow-up whole procedure decision method according to claim 1, wherein the vital sign information comprises continuous vital sign information and discrete vital sign information, and the preprocessing of the collected vital sign information of each patient comprises:
carrying out one-hot coding treatment on the discrete feature information;
carrying out normalization processing on the continuous body sign information by adopting a sliding window method;
and splicing and fusing the discrete vital sign information after the one-hot encoding processing and the continuous vital sign information after the normalization processing to obtain the vital sign information of each pre-processed sick and wounded.
3. The bulk patient medical follow-up whole procedure decision method according to claim 1, wherein predicting survival time of each patient based on the pre-processed vital sign information of each patient and the pre-constructed integrated analysis model of the vital sign information of each patient comprises:
and taking the vital sign information of each preprocessed sick and wounded as the input of the sick and wounded vital sign information comprehensive analysis model, and respectively processing the vital sign information of each preprocessed sick and wounded by using the sick and wounded vital sign information comprehensive analysis model to obtain the survival time of each sick and wounded.
4. The full flow medical follow-up decision method for bulk sick and wounded according to claim 1, wherein the classifying the treatment priority for the bulk sick and wounded to be follow-up based on the predicted survival time of each sick and wounded comprises:
searching the treatment priority matched with the survival time of each sick and wounded in a preset survival time-treatment priority corresponding relation table based on the predicted survival time of each sick and wounded, and determining the treatment priority of each sick and wounded;
and classifying the treatment priority of the fed-back batch of sick and wounded based on the determined treatment priority of each sick and wounded to obtain treatment priority classification results, wherein the treatment priority classification results comprise the number of sick and wounded corresponding to each treatment priority.
5. The bulk patient medical follow-up whole procedure decision method according to any one of claims 1-4, wherein the process of constructing the patient sign information comprehensive analysis model comprises:
constructing a training sample set, wherein the training sample set comprises patient vital sign sample data and patient real survival time corresponding to the patient vital sign sample data;
inputting the patient vital sign sample data into an LSTM neural network model, and predicting survival time of the patient vital sign sample data by adopting the LSTM neural network model to obtain predicted survival time corresponding to the patient vital sign sample data;
constructing a cross entropy loss function of the patient vital sign sample data based on the patient real survival time and the predicted survival time;
training the LSTM neural network model based on the vital sign sample data of the sick and wounded and the cross entropy loss function to obtain a trained LSTM neural network model, and determining the trained LSTM neural network model as the sick and wounded vital sign information comprehensive analysis model.
6. A bulk patient medical follow-up full-flow decision making system, the system comprising:
the information acquisition module is used for acquiring vital sign information of each sick and wounded in batches to be sent back;
the information preprocessing module is used for preprocessing the collected vital sign information of each sick and wounded;
the survival time prediction module is used for predicting the survival time of each sick and wounded based on the vital sign information of each sick and wounded after pretreatment and a pre-constructed comprehensive analysis model of the vital sign information of the sick and wounded;
the sick and wounded classifying module is used for classifying treatment priority of the batch of sick and wounded to be sent back based on the survival time of each sick and wounded obtained by prediction;
a decision information generation module for generating medical post-delivery auxiliary decision information of the batch of sick and wounded to be post-delivered based on the treatment priority classification result and the existing medical post-delivery resource, wherein,
the medical post-delivery auxiliary decision information comprises medical post-delivery target medical institution information, medical post-delivery tool information, medical post-delivery medical personnel information, medical post-delivery medical equipment information, medical post-delivery path planning information and medical post-delivery required time information of each sick and wounded.
7. The bulk patient medical follow-up whole procedure decision system according to claim 6, wherein the vital sign information comprises continuous and discrete vital sign information, the information preprocessing module being specifically configured to:
carrying out one-hot coding treatment on the discrete feature information;
carrying out normalization processing on the continuous body sign information by adopting a sliding window method;
and splicing and fusing the discrete vital sign information after the one-hot encoding processing and the continuous vital sign information after the normalization processing to obtain the vital sign information of each pre-processed sick and wounded.
8. The bulk patient medical follow-up whole procedure decision system according to claim 6, wherein the survival time prediction module is specifically configured to:
and taking the vital sign information of each preprocessed sick and wounded as the input of the sick and wounded vital sign information comprehensive analysis model, and respectively processing the vital sign information of each preprocessed sick and wounded by using the sick and wounded vital sign information comprehensive analysis model to obtain the survival time of each sick and wounded.
9. The bulk patient medical follow-up whole procedure decision system according to claim 6, wherein the patient classification module is specifically configured to:
searching the treatment priority matched with the survival time of each sick and wounded in a preset survival time-treatment priority corresponding relation table based on the predicted survival time of each sick and wounded, and determining the treatment priority of each sick and wounded;
and classifying the treatment priority of the fed-back batch of sick and wounded based on the determined treatment priority of each sick and wounded to obtain treatment priority classification results, wherein the treatment priority classification results comprise the number of sick and wounded corresponding to each treatment priority.
10. The bulk patient medical follow-up whole procedure decision system according to any one of claims 6-9, further comprising a model building module for building the patient sign information comprehensive analysis model, the model building module being specifically configured to:
constructing a training sample set, wherein the training sample set comprises patient vital sign sample data and patient real survival time corresponding to the patient vital sign sample data;
inputting the patient vital sign sample data into an LSTM neural network model, and predicting survival time of the patient vital sign sample data by adopting the LSTM neural network model to obtain predicted survival time corresponding to the patient vital sign sample data;
constructing a cross entropy loss function of the patient vital sign sample data based on the patient real survival time and the predicted survival time;
training the LSTM neural network model based on the vital sign sample data of the sick and wounded and the cross entropy loss function to obtain a trained LSTM neural network model, and determining the trained LSTM neural network model as the sick and wounded vital sign information comprehensive analysis model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310084447.0A CN116417134A (en) | 2023-02-01 | 2023-02-01 | Bulk sick and wounded medical post-delivery full-flow decision-making method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310084447.0A CN116417134A (en) | 2023-02-01 | 2023-02-01 | Bulk sick and wounded medical post-delivery full-flow decision-making method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116417134A true CN116417134A (en) | 2023-07-11 |
Family
ID=87048783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310084447.0A Pending CN116417134A (en) | 2023-02-01 | 2023-02-01 | Bulk sick and wounded medical post-delivery full-flow decision-making method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116417134A (en) |
-
2023
- 2023-02-01 CN CN202310084447.0A patent/CN116417134A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108305690A (en) | The nervous system disease point examines the system for distribution of out-patient department of method and the nervous system disease | |
| CN111785387B (en) | Method and system for classifying disease standardization mapping by using Bert | |
| CN112397204B (en) | Method, device, computer equipment and storage medium for predicting altitude sickness | |
| CN111524570B (en) | Ultrasonic follow-up patient screening method based on machine learning | |
| Chen | Smart health and wellbeing [Trends & Controversies] | |
| US20190378618A1 (en) | Machine Learning Systems For Surgery Prediction and Insurer Utilization Review | |
| CN117894421A (en) | Medical service automation flow optimization method | |
| Singhal | Cost optimization and affordable health care using AI | |
| Gujar et al. | Disease prediction and doctor recommendation system | |
| CN116417134A (en) | Bulk sick and wounded medical post-delivery full-flow decision-making method and system | |
| CN113052199A (en) | Method, device and equipment for training disease detection model and computer storage medium | |
| DE202023101305U1 (en) | An intelligent health and fitness data management system using artificial intelligence with IoT devices | |
| CN111986801B (en) | Rehabilitation assessment method, device and medium based on deep learning | |
| Ronzani et al. | Unstructured data in predictive process monitoring: lexicographic and semantic mapping to ICD-9-CM codes for the home hospitalization service | |
| CN118230983B (en) | Risk medicine identification method and system based on medicine feedback mining | |
| CN113450919A (en) | Construction method and construction system of heart failure early warning model and heart failure early warning device | |
| Aringhieri et al. | Leveraging structured data in predictive process monitoring: the case of the ICD-9-CM in the scenario of the home hospitalization service | |
| Zhang et al. | Application and Development Prospect of Artificial Intelligence and Big Data in Medical and Health Field | |
| Obinna et al. | A Modified Approach to Malaria Diagnosis Using Artificial Bee Colony Algorithm | |
| Priya et al. | A novel intelligent diagnosis and disease prediction algorithm in green cloud using machine learning approach | |
| AU2021101599A4 (en) | An iot based self phased analysis of adverse effects in covid recovered patients | |
| CN118398217B (en) | Multimode fusion hemodialysis data analysis method | |
| Peng et al. | Research on Exploring the Patients’ Hiding Disease Based on Symptom Weighted Clustering Technique | |
| Chen et al. | A novel health monitoring system for vital signs using IoT | |
| Chiarini-Tremblay et al. | Utilizing text mining techniques to identify fall related injuries |
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 |