CN118800458B - Method and system for predicting complications after cardiothoracic surgery - Google Patents
Method and system for predicting complications after cardiothoracic surgery Download PDFInfo
- Publication number
- CN118800458B CN118800458B CN202411288140.3A CN202411288140A CN118800458B CN 118800458 B CN118800458 B CN 118800458B CN 202411288140 A CN202411288140 A CN 202411288140A CN 118800458 B CN118800458 B CN 118800458B
- Authority
- CN
- China
- Prior art keywords
- patient
- data information
- lung
- oxygenation
- postoperative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013132 cardiothoracic surgery Methods 0.000 title claims abstract description 21
- 238000006213 oxygenation reaction Methods 0.000 claims abstract description 97
- 210000004072 lung Anatomy 0.000 claims abstract description 86
- 238000004458 analytical method Methods 0.000 claims abstract description 74
- 230000002980 postoperative effect Effects 0.000 claims abstract description 64
- 230000002685 pulmonary effect Effects 0.000 claims abstract description 63
- 238000009423 ventilation Methods 0.000 claims abstract description 61
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 208000035965 Postoperative Complications Diseases 0.000 claims abstract description 41
- 230000000241 respiratory effect Effects 0.000 claims abstract description 38
- 238000009826 distribution Methods 0.000 claims abstract description 37
- 238000012502 risk assessment Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims description 34
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 17
- 239000001301 oxygen Substances 0.000 claims description 17
- 229910052760 oxygen Inorganic materials 0.000 claims description 17
- 239000008280 blood Substances 0.000 claims description 15
- 210000004369 blood Anatomy 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000001356 surgical procedure Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 11
- 206010058046 Post procedural complication Diseases 0.000 claims description 10
- 239000007789 gas Substances 0.000 claims description 9
- 238000005399 mechanical ventilation Methods 0.000 claims description 9
- 238000003745 diagnosis Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 239000003814 drug Substances 0.000 claims description 5
- 230000004199 lung function Effects 0.000 claims description 5
- 238000012896 Statistical algorithm Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 229940079593 drug Drugs 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000002640 oxygen therapy Methods 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 4
- 230000002227 vasoactive effect Effects 0.000 claims description 4
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 3
- 230000003827 upregulation Effects 0.000 claims description 3
- 210000000115 thoracic cavity Anatomy 0.000 claims 4
- 210000000038 chest Anatomy 0.000 claims 3
- 230000004044 response Effects 0.000 abstract description 3
- 230000001771 impaired effect Effects 0.000 abstract description 2
- 238000011084 recovery Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000009325 pulmonary function Effects 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004393 prognosis Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010001052 Acute respiratory distress syndrome Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000010241 blood sampling Methods 0.000 description 1
- 210000003123 bronchiole Anatomy 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 210000003928 nasal cavity Anatomy 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
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
- G16H50/30—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
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method and a system for predicting complications after cardiothoracic surgery, which relate to the technical field of medical treatment, and a postoperative data monitoring module comprehensively performs physical examination on patients, data information related to respiratory state, abnormal lung distribution and lung expansion degree is collected, and basic support is provided for subsequent data processing and analysis. Through the preliminary analysis module of lung, the system can construct postoperative oxygenation factor Yhyz to whether the oxygenation capacity of the lung of patient is impaired is preliminarily judged, the timely emission of complication prediction instruction is ensured, and the real-time response capability of the system is further enhanced. The comprehensive analysis module calculates the alveolar ventilation Ftqz and the pulmonary expansion capacity coefficient Fkxs of each pulmonary segment in detail, and fits and obtains the risk assessment index Fpzs by combining the trained complication prediction model, so that the high-precision prediction of postoperative complications is further realized.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a method and a system for predicting complications after cardiothoracic surgery.
Background
Cardiothoracic surgery is a complex and high-risk area of modern medicine involving various surgical procedures on the heart, lungs, and chest. With the continuous progress of medical technology, the success rate of cardiothoracic surgery is gradually improved, but postoperative complications are still an important clinical challenge, and the postoperative complications not only can prolong the hospitalization time of patients, but also can cause more serious health problems and even threaten the lives of the patients, so that early prediction and effective management of the postoperative complications of cardiothoracic surgery are important clinical attention.
Acute Respiratory Distress Syndrome (ARDS) is one of the complications that may occur after chest surgery. Although various methods have been used in the clinic to assess the risk of postoperative complications, these methods often rely on the experience of the physician and conventional examination means. Particularly in the prediction of postoperative pulmonary complications, the traditional method is difficult to integrate multidimensional data such as respiratory state, pulmonary abnormal distribution, pulmonary expansion capacity and the like of a patient in real time and in various aspects, and is difficult to discover potential risks in time, so that the overall treatment effect is affected.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method and a system for predicting complications after cardiothoracic surgery, which solve the problems in the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a heart and chest surgical postoperative complications prediction system comprises a postoperative data monitoring module, a data processing module, a lung preliminary analysis module, a comprehensive analysis module and a prediction management module;
The postoperative data monitoring module is used for carrying out physical examination on a patient after the chest surgery and acquiring relevant respiratory state data information, relevant pulmonary abnormal distribution data information and relevant expansion degree data information of the patient through a report acquired by the physical examination;
The data processing module is used for preprocessing the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information which are acquired in the postoperative data monitoring module, and constructing a postoperative complications data set after being processed by a dimensionless technique;
The lung preliminary analysis module is used for constructing an oxygenation factor Yhyz of a patient after operation according to the related respiratory state data information, preliminarily judging whether the current lung oxygenation capacity of the patient is damaged according to the numerical value of the oxygenation factor Yhyz, and if so, sending out a complication prediction instruction;
The comprehensive analysis module is used for respectively calculating the alveolar ventilation Ftqz and the pulmonary expansion capacity coefficient Fkxs of each pulmonary segment according to the related pulmonary abnormality distribution data information and the related expansion degree data information after receiving the complications prediction instruction, and fitting to obtain a risk assessment index Fpzs by combining the trained complications prediction model;
The prediction management module is used for presetting an evaluation threshold value W, and comparing the evaluation threshold value W with the risk evaluation index Fpzs for analysis so as to comprehensively predict the risk degree of postoperative complications of the current patient.
Preferably, the postoperative data monitoring module comprises a physical examination unit and an acquisition unit;
The physical examination unit is used for checking the postoperative state of a patient subjected to cardiothoracic surgery through a plurality of groups of monitoring devices, wherein the plurality of groups of monitoring devices comprise an arterial blood gas analyzer, a breathing machine, a lung function tester and a pressure sensor;
The acquisition unit is used for acquiring and recording related respiratory state data information, related pulmonary abnormality distribution data information and related expansion degree data information of a patient according to patient reports acquired by a plurality of groups of monitoring equipment, wherein the related respiratory state data information comprises arterial blood oxygen partial pressure Dfy and suction oxygen concentration Xynd before, during and after operation of the patient;
The related pulmonary abnormality distribution data information includes total ventilation Mzz and dead space ventilation Wtz per minute for each pulmonary segment in the patient's lungs after surgery;
the relevant expansion degree data information includes tidal volume Cqz, positive end expiratory pressure Hmzy and plateau pressure Pty.
Preferably, the data processing module comprises a preprocessing unit and an integration unit;
The preprocessing unit is used for checking and identifying missing data, repeated data and data formats in the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information so as to remove the repeated data, correct the data formats and fill the missing values;
The integration unit is used for carrying out standardized processing on the preprocessed data information by utilizing a dimensionless processing technology so as to eliminate the dimensionality difference among different data sources, and combining the data from the different data sources into a unified view by combining a multi-sensor data fusion technology so as to construct a postoperative complication data set.
Preferably, the lung preliminary analysis module comprises a lung preliminary analysis unit and a preliminary diagnosis unit;
The lung preliminary analysis unit is used for constructing an oxygenation factor Yhyz of a patient after operation according to the related respiratory state data information, and the oxygenation factor is obtained in the following manner: ; wherein Dfy represents an arterial blood oxygen partial pressure and Xynd represents an intake oxygen concentration.
Preferably, the preliminary diagnosis unit is used for analyzing and acquiring the pre-operative and intra-operative oxygenation factors Yhyz of the patient according to the mode of acquiring the post-operative oxygenation factors Yhyz of the patient in the lung preliminary analysis unit, and acquiring the average oxygenation factor of the whole patient through a statistical algorithmAnd by combining the post-operative oxygenation factor Yhyz of the patient with the average oxygenation factor of the patient as a wholeThe comparison is carried out to preliminarily judge whether the oxygenation capacity of the lung of the current patient is damaged, and the specific judgment content is as follows:
If the post-operative oxygenation factor Yhyz of the patient does not exceed the average oxygenation factor of the patient as a whole When the lung oxygenation capacity of the current patient is judged to be in a damaged state, a complication prediction instruction is sent outwards at the moment;
if the post-operative oxygenation factor Yhyz of the patient exceeds the average oxygenation factor of the patient as a whole And when the lung oxygenation capacity of the current patient is judged to be not in a damaged state, the lung oxygenation capacity of the current patient is judged preliminarily.
Preferably, the comprehensive analysis module comprises a local analysis unit, an expansion degree analysis unit and a comprehensive prediction unit;
The local analysis unit is used for calculating the alveolar ventilation Ftqz of each lung segment according to the related lung abnormal distribution data information after receiving the complications prediction instruction, and the alveolar ventilation Ftqz is obtained in the following manner: ; wherein Mzz represents the total ventilation per minute; wtz denotes dead space ventilation; alveolar ventilation Ftqz for each lung segment was counted and an average alveolar ventilation calculated 。
Preferably, the expansion degree analysis unit is configured to construct a pulmonary expansion capacity coefficient Fkxs according to the related expansion degree data information, and specifically obtain the expansion degree coefficient according to the following manner: ; where Cqz denotes tidal volume, pty denotes plateau pressure, and Hmzy denotes positive end-tidal pressure.
Preferably, the comprehensive prediction unit is used for constructing a complication prediction model by using convolutional neural network technology, and constructing an oxygenation factor Yhyz, a lung expansion capacity coefficient Fkxs and average alveolar ventilation of a patient after operationInput into a complication prediction model to fit the acquired risk assessment index Fpzs, specifically by the following formula: ; wherein, C represents a correction constant, AndAre all weight values, wherein,，And (2) and。
Preferably, the prediction management module comprises an alignment unit;
the comparison unit is used for presetting an evaluation threshold value W, and comprehensively predicting the risk degree of postoperative complications of the current patient by comparing the evaluation threshold value W with the risk evaluation index Fpzs, and comprises the following specific contents:
If the risk assessment index Fpzs is larger than the assessment threshold W, the risk of complications does not exist after the operation of the patient, at the moment, the original planned postoperative care measures are continuously implemented, the regular monitoring of monitoring every 5 hours is kept, the mechanical ventilation support of the patient is gradually reduced on the premise of ensuring the condition stability of the patient, the restorative treatment and rehabilitation training are started, and meanwhile, the patient is regularly rechecked;
If risk assessment index Fpzs =assessment threshold W, it indicates that there is a risk of complications after the patient operation, at this time, the frequency of regular monitoring will be adjusted to once every 3 hours, and the treatment scheme is fine-tuned according to the real-time monitoring result, and the specific fine-tuning device includes a ventilator;
if the risk assessment index Fpzs < the assessment threshold W, it indicates that there is a risk of complications after the patient operation, and emergency medical intervention is immediately taken at this time, where the specific emergency medical intervention includes: the mechanical ventilation parameters, up-regulation of the oxygen therapy intensity and the use of vasoactive drugs were adjusted, while the frequency of periodic monitoring was adjusted to once every 2 hours.
A method for predicting complications after cardiothoracic surgery, comprising the steps of:
Step one: performing physical examination on a patient after the chest and heart surgery, and acquiring related respiratory state data information, related pulmonary abnormal distribution data information and related expansion degree data information of the patient through a report acquired by the physical examination;
step two: preprocessing the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information which are acquired in the postoperative data monitoring module, and constructing a postoperative complications data set after dimensionless technical processing;
Step three: constructing an oxygenation factor Yhyz of the patient after operation according to the related respiratory state data information, primarily judging whether the current pulmonary oxygenation capacity of the patient is damaged according to the numerical value of the oxygenation factor Yhyz, and if so, sending out a complication prediction instruction;
Step four: after a complication prediction instruction is received, respectively calculating alveolar ventilation Ftqz and a lung expansion capacity coefficient Fkxs of each lung segment according to related lung abnormal distribution data information and related expansion degree data information, and fitting to obtain a risk assessment index Fpzs by combining a trained complication prediction model;
step five: an evaluation threshold value W is preset, and the evaluation threshold value W is compared with the risk evaluation index Fpzs for analysis, so that the risk degree of the postoperative complications of the current patient is comprehensively predicted.
The invention provides a method and a system for predicting complications after cardiothoracic surgery, which have the following beneficial effects:
The system can further realize multidirectional monitoring and accurate prediction of patients after cardiothoracic surgery by integrating the postoperative data monitoring module, the data processing module, the lung preliminary analysis module, the comprehensive analysis module and the prediction management module. The postoperative data monitoring module collects data information related to respiratory state, pulmonary abnormal distribution and pulmonary expansion degree through comprehensive physical examination of a patient, and provides basic support for subsequent data processing and analysis. Through the preliminary analysis module of lung, the system can construct postoperative oxygenation factor Yhyz to whether the oxygenation capacity of the lung of patient is impaired is preliminarily judged, the timely emission of complication prediction instruction is ensured, and the real-time response capability of the system is further enhanced. The comprehensive analysis module calculates the alveolar ventilation Ftqz and the pulmonary expansion capacity coefficient Fkxs of each pulmonary segment in detail, and fits and obtains the risk assessment index Fpzs by combining the trained complication prediction model, so that the high-precision prediction of postoperative complications is further realized. Finally, the prediction management module can comprehensively evaluate and predict the risk degree of postoperative complications of patients through the set evaluation threshold W, so that powerful support is provided for clinical decision, and the prevention and management level of the postoperative complications is improved as much as possible. In a word, through the application of the system, the probability of postoperative complications can be effectively reduced, and the overall treatment effect of a patient is improved.
The system further realizes accurate assessment of the postoperative pulmonary oxygenation capacity of the patient through the pulmonary primary analysis module, and the pulmonary primary analysis unit constructs postoperative oxygenation factors Yhyz by analyzing related respiratory state data information so as to reflect the pulmonary oxygenation capacity of the patient in the postoperative stage. The primary diagnostic unit further analyzes the pre-operative and intra-operative oxygenation factors of the patient using a statistical algorithm to obtain an ensemble average oxygenation factor. By comparing the postoperative oxygenation factor Yhyz of the patient with the overall average oxygenation factor of the patient, the system can preliminarily judge whether the pulmonary oxygenation capacity of the patient is damaged, and through dynamic analysis and comparison of the oxygenation factors, possible complications can be effectively early warned and data support is provided for subsequent treatment and management, so that postoperative care and management of the patient are optimized, and postoperative recovery quality is improved.
By analyzing the relevant pulmonary abnormality distribution data information, the alveolar ventilation Ftqz for each lung segment can be calculated. Specifically, the calculation of alveolar ventilation, which includes subtracting the void space ventilation Wtz from the total ventilation Mzz per minute to obtain an effective ventilation actually involved in gas exchange, enables a detailed description of the effective ventilation of each lung segment and the average alveolar ventilation obtained by counting the alveolar ventilation of each lung segment, and this detailed lung segment level analysis allows the physician to accurately identify the uneven distribution of pulmonary ventilation, providing reliable data support for further clinical decisions. By combining the analysis results of the two units, the comprehensive prediction unit can integrate the data of the alveolar ventilation and the pulmonary expansion capacity coefficient, and provide more comprehensive and accurate postoperative complication risk assessment. The implementation of the module not only improves the evaluation capability of the postoperative pulmonary function state, but also is beneficial to timely finding the potential complication risk and optimizing the postoperative management strategy of the patient. Through accurate data analysis and prediction, the pertinence and the effectiveness of clinical intervention can be further improved, and the postoperative prognosis and the quality of life of a patient are improved.
Drawings
FIG. 1 is a block diagram of a system for predicting complications after a chest surgery in accordance with the present invention;
fig. 2 is a flow chart of a method for predicting complications after cardiothoracic surgery according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: referring to fig. 1, the invention provides a system for predicting complications after cardiothoracic surgery, which comprises a postoperative data monitoring module, a data processing module, a lung preliminary analysis module, a comprehensive analysis module and a prediction management module;
The postoperative data monitoring module is used for carrying out physical examination on a patient after the chest surgery and acquiring relevant respiratory state data information, relevant pulmonary abnormal distribution data information and relevant expansion degree data information of the patient through a report acquired by the physical examination;
The data processing module is used for preprocessing the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information which are acquired in the postoperative data monitoring module, and constructing a postoperative complications data set after being processed by a dimensionless technique;
The lung preliminary analysis module is used for constructing an oxygenation factor Yhyz of a patient after operation according to the related respiratory state data information, preliminarily judging whether the current lung oxygenation capacity of the patient is damaged according to the numerical value of the oxygenation factor Yhyz, and if so, sending out a complication prediction instruction;
The comprehensive analysis module is used for respectively calculating the alveolar ventilation Ftqz and the pulmonary expansion capacity coefficient Fkxs of each pulmonary segment according to the related pulmonary abnormality distribution data information and the related expansion degree data information after receiving the complications prediction instruction, and fitting to obtain a risk assessment index Fpzs by combining the trained complications prediction model;
The prediction management module is used for presetting an evaluation threshold value W, and comparing the evaluation threshold value W with the risk evaluation index Fpzs for analysis so as to comprehensively predict the risk degree of postoperative complications of the current patient.
In the system operation, through the synergistic effect of a plurality of functional modules, accurate prediction of the complication risk of the patient after the cardiothoracic surgery is further realized. Firstly, the postoperative data monitoring module can acquire key data such as the postoperative respiratory state, abnormal lung distribution, expansion degree and the like of a patient in multiple aspects and accurately, and provides sufficient data support for subsequent risk assessment. Through preprocessing and dimensionless technique processing of the data processing module, the data are standardized and structured, and a postoperative complication data set is constructed, so that subsequent analysis is more efficient and reliable. Further, the lung preliminary analysis module constructs an oxygenation factor Yhyz based on the respiratory state data information of the patient, and can quickly and preliminarily judge the damage condition of the oxygenation capacity of the lung of the patient. When the potential risk is found, a complication prediction instruction is timely sent out, so that early intervention is facilitated, and further development of complications is prevented; the comprehensive analysis module can further accurately fit the risk assessment index Fpzs through calculation of the alveolar ventilation Ftqz and the pulmonary expansion capacity coefficient Fkxs and combination of a trained prediction model, and provides an accurate complication risk quantification result. Finally, the prediction management module can effectively predict the risk degree of postoperative complications of the patient by comparing the risk evaluation index Fpzs with a preset evaluation threshold W, and the systematic prediction method can provide important decision basis in postoperative management and effectively reduce the occurrence probability of the complications, so that the postoperative recovery quality of the patient is improved.
Example 2: referring to fig. 1, the following details are: the postoperative data monitoring module comprises a physical examination unit and an acquisition unit;
The physical examination unit is used for checking the postoperative state of a patient subjected to cardiothoracic surgery through a plurality of groups of monitoring devices, wherein the plurality of groups of monitoring devices comprise an arterial blood gas analyzer, a breathing machine, a lung function tester and a pressure sensor;
The acquisition unit is used for acquiring and recording related respiratory state data information, related pulmonary abnormality distribution data information and related expansion degree data information of a patient according to patient reports acquired by a plurality of groups of monitoring equipment, wherein the related respiratory state data information comprises arterial blood oxygen partial pressure Dfy and suction oxygen concentration Xynd before, during and after operation of the patient;
The related pulmonary abnormality distribution data information includes total ventilation Mzz and dead space ventilation Wtz per minute for each pulmonary segment in the patient's lungs after surgery;
the relevant expansion degree data information includes tidal volume Cqz, positive end expiratory pressure Hmzy and plateau pressure Pty.
The data processing module comprises a preprocessing unit and an integrating unit;
The preprocessing unit is used for checking and identifying missing data, repeated data and data formats in the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information so as to remove the repeated data, correct the data formats and fill up missing values, wherein the missing value filling method comprises mean filling, median filling, interpolation filling and regression filling; the data is converted into a format suitable for further analysis. For example, data normalization, data encoding (e.g., converting category data into numeric data).
The integration unit is used for carrying out standardized processing on the preprocessed data information by utilizing a dimensionless processing technology so as to eliminate the dimensionality difference among different data sources, and combining the data from the different data sources into a unified view by combining a multi-sensor data fusion technology so as to construct a postoperative complication data set, for example, fusing the data from different sensors together so as to provide more comprehensive data information.
In this embodiment, this system has further realized the comprehensive, the accurate monitoring to patient postoperative state through the design of physical examination unit and collection unit. The physical examination unit integrates a plurality of groups of monitoring equipment, ensures dynamic tracking and examination of preoperative, intraoperative and postoperative states of a patient, can monitor and acquire multi-dimensional key data information in real time, and provides a solid data basis for predicting complications. In the data processing module, the preprocessing unit further ensures the integrity and accuracy of data through a series of strict data cleaning and preprocessing steps, and particularly further improves the quality of the data through filling in missing values, data format standardization and other methods. The integration unit performs standardized processing and integration on data from different data sources by using a dimensionless processing technology and a multi-sensor data fusion technology, so that dimensional differences are eliminated, a unified postoperative complication data set is constructed, high-quality input is provided for subsequent risk assessment and complication prediction by the data set, and the accuracy and reliability of a prediction model are improved as much as possible. In a word, can further effectively improve the prediction degree of accuracy of postoperative complication through this system to help medical team in time take corresponding counter measure, reduce postoperative complication's incidence, thereby promote patient's postoperative rehabilitation effect and whole treatment level.
Example 3: referring to fig. 1, the following details are: the lung preliminary analysis module comprises a lung preliminary analysis unit and a preliminary diagnosis unit;
The lung preliminary analysis unit is used for constructing an oxygenation factor Yhyz of a patient after operation according to the related respiratory state data information, and the oxygenation factor is obtained in the following manner: ; wherein Dfy represents an arterial blood oxygen partial pressure and Xynd represents an intake oxygen concentration.
The above-mentioned arterial blood oxygen partial pressure Dfy can be obtained by monitoring with an arterial blood gas analyzer (ABG analyzer), specifically by arterial blood sampling, and the blood sample is sent into the arterial blood gas analyzer for measurement;
inhalation oxygen concentration Xynd the oxygen concentration of the inhalation gas can be measured in real time by an oxygen concentration sensor onboard the ventilator.
The primary diagnosis unit is used for analyzing and acquiring the pre-operation oxygenation factors Yhyz and the intra-operation oxygenation factors Yhyz of the patient according to the mode of acquiring the post-operation oxygenation factors Yhyz of the patient in the lung primary analysis unit, and acquiring the overall average oxygenation factor of the patient through a statistical algorithmAnd by combining the post-operative oxygenation factor Yhyz of the patient with the average oxygenation factor of the patient as a wholeThe comparison is carried out to preliminarily judge whether the oxygenation capacity of the lung of the current patient is damaged, and the specific judgment content is as follows:
If the post-operative oxygenation factor Yhyz of the patient does not exceed the average oxygenation factor of the patient as a whole When the lung oxygenation capacity of the current patient is judged to be in a damaged state, a complication prediction instruction is sent outwards at the moment;
if the post-operative oxygenation factor Yhyz of the patient exceeds the average oxygenation factor of the patient as a whole And when the lung oxygenation capacity of the current patient is judged to be not in a damaged state, the lung oxygenation capacity of the current patient is judged preliminarily.
In this embodiment, the pulmonary primary analysis unit is responsible for constructing the postoperative oxygenation factor Yhyz of the patient according to the related respiratory state data information, specifically, the method can accurately evaluate the postoperative oxygenation state of the patient, and further ensures the scientificity and effectiveness of the monitoring result. The primary diagnosis unit obtains the overall average oxygenation factor of the patient by carrying out statistical analysis on the oxygenation factors before and during operationThen, the postoperative oxygenation factor Yhyz of the patient is compared with the overall average oxygenation factorA comparison is made to preliminarily determine the patient's pulmonary oxygenation capacity. If the post-operative oxygenation factor Yhyz is below the global average level, which indicates that there may be a loss of patient's pulmonary oxygenation capacity, the system will issue a complication prediction instruction to take timely intervention. In contrast, if the post-operative oxygenation factor Yhyz is greater than or equal to the global average level, the pulmonary oxygenation capacity is initially judged to be normal without additional intervention. Through the systematic analysis flow, the possible oxygenation capacity problem after operation can be rapidly and accurately identified, so that timeliness and accuracy of complication prediction are improved, safety and recovery quality of patients after operation are ensured, potential complication risks can be found in advance, precious decision basis can be provided for clinicians, and treatment scheme optimization and patient prognosis improvement are facilitated.
Example 4: referring to fig. 1, the following details are: the comprehensive analysis module comprises a local analysis unit, an expansion degree analysis unit and a comprehensive prediction unit;
The local analysis unit is used for calculating the alveolar ventilation Ftqz of each lung segment according to the related lung abnormal distribution data information after receiving the complications prediction instruction, and the alveolar ventilation Ftqz is obtained in the following manner: ; wherein Mzz represents the total ventilation per minute; wtz denotes dead space ventilation, which refers to airway ventilation without participation in gas exchange;
the total ventilation per minute Mzz mentioned above may be recorded in real time by the ventilator or calculated by the pulmonary function tester, and total ventilation per minute Mzz is typically the product of the tidal volume multiplied by the respiratory rate;
The dead space ventilation Wtz may be obtained by measuring the amount of anatomical dead space (e.g., by measuring the Bohr dead space equation) and functional dead space, which may be measured by nitrogen purging techniques (e.g., fowler method), and the functional dead space may be obtained by further evaluation of the volume exchange efficiency.
The anatomical dead space refers to the part of the airway between the nasal cavity, oral cavity and terminal bronchioles, and these regions, while participating in the ingress and egress (ventilation) of air, do not have the ability to exchange gases, meaning that inhaled oxygen does not enter the blood at these sites and carbon dioxide is not expelled from the blood.
Alveolar ventilation Ftqz for each lung segment refers to the effective ventilation into the alveoli per minute;
Alveolar ventilation Ftqz for each lung segment was counted and an average alveolar ventilation calculated 。
The expansion degree analysis unit is used for constructing a lung expansion capacity coefficient Fkxs according to the related expansion degree data information, and the lung expansion capacity coefficient is obtained in the following manner: ; where Cqz denotes tidal volume, pty denotes plateau pressure, and Hmzy denotes positive end-tidal pressure.
The above mentioned tidal volume Cqz may directly measure the tidal volume of each breath by a ventilator or pulmonary function tester;
plateau pressure Pty refers to the airway pressure measured after a brief pause in airflow during mechanical ventilation, which the ventilator can automatically record at the end of inspiration for evaluation of the elastic compliance of the lungs.
Positive end-expiratory pressure Hmzy may be monitored and displayed in real time by a pressure sensor.
In the embodiment, the system further realizes deep evaluation of the lung state of the postoperative patient through the comprehensive analysis module, and the comprehensive analysis module comprises a local analysis unit, an expansion degree analysis unit and a comprehensive prediction unit, so that the lung state of the postoperative patient can be analyzed in multiple aspects and accurately, and powerful support is provided for clinical decision. After receiving the complication prediction instruction, the local analysis unit calculates the alveolar ventilation Ftqz of each lung segment according to the related pulmonary abnormality distribution data information, and obtains the effective alveolar ventilation of each lung segment by deducting the ineffective space ventilation from the total ventilation, and further calculates the average alveolar ventilation by statistics. The expansion degree analysis unit constructs a lung expansion capacity coefficient Fkxs through the related expansion degree data information so as to evaluate the expansion capacity of the lung in the respiratory process, and the analysis can provide important information about the compliance and functional state of the lung, so that the efficiency and degree of the expansion of the lung of the patient can be known. By combining the analysis results of the local alveolar ventilation and the lung expansion capacity coefficients, the comprehensive analysis module can evaluate the lung state of the patient in multiple dimensions, so that the prediction accuracy of postoperative complications is improved, and detailed data support is provided for further intervention and treatment. Through accurate alveolar ventilation and expansion capability assessment, the system can better guide clinical management, optimize postoperative recovery process, and improve overall health condition of patients.
Example 5: referring to fig. 1, the following details are: the comprehensive prediction unit is used for constructing a complication prediction model by utilizing a convolutional neural network technology and constructing an oxygenation factor Yhyz, a lung expansion capacity coefficient Fkxs and average alveolar ventilation after a patient operationInput into a complication prediction model to fit the acquired risk assessment index Fpzs, specifically by the following formula: ; wherein, C represents a correction constant, AndAre all weight values, wherein,，And (2) and。
Constructing an initial model by using a convolutional neural network technology, training and testing the initial model by using a complication data set, taking the trained initial model as a state recognition model, respectively acquiring characteristic information in the state recognition model, training and testing the state recognition model by using the acquired characteristic information, and taking the trained state recognition model as a complication prediction model by combining a complication prediction instruction;
The prediction management module comprises a comparison unit;
the comparison unit is used for presetting an evaluation threshold value W, and comprehensively predicting the risk degree of postoperative complications of the current patient by comparing the evaluation threshold value W with the risk evaluation index Fpzs, and comprises the following specific contents:
If the risk assessment index Fpzs is greater than the assessment threshold W, the risk of complications does not exist after the operation of the patient, at this time, the original planned postoperative care measures are continuously implemented, the regular monitoring of monitoring every 5 hours is kept, the mechanical ventilation support of the patient is gradually reduced on the premise of ensuring the condition stability of the patient, the restorative treatment and the rehabilitation training are started, and meanwhile, the patient is regularly rechecked, so that the risk assessment index is ensured to be continuously higher than the threshold;
If risk assessment index Fpzs =assessment threshold W, it indicates that there is a risk of complications after the patient operation, at this time, the frequency of regular monitoring will be adjusted to be once every 3 hours, so as to monitor the patient condition change in time, especially the dynamic change of key indexes such as lung function, oxygenation level, etc., and fine-tuning the treatment scheme according to the real-time monitoring result, where the specific fine-tuning device includes a ventilator;
if the risk assessment index Fpzs < the assessment threshold W, it indicates that there is a risk of complications after the patient operation, and emergency medical intervention is immediately taken at this time, where the specific emergency medical intervention includes: the mechanical ventilation parameters, up-regulation of the oxygen therapy intensity and the use of vasoactive drugs were adjusted, while the frequency of periodic monitoring was adjusted to once every 2 hours.
In this embodiment, the comprehensive prediction unit and the prediction management module in the system further improve the accuracy of the prediction of postoperative complications and the personalized care level of the patient through the convolutional neural network technology and the detailed risk assessment mechanism. The comprehensive prediction unit utilizes a complication prediction model constructed by a convolutional neural network technology, can comprehensively consider an oxygenation factor Yhyz, a lung expansion capacity coefficient Fkxs and average alveolar ventilation of a patient after operation, calculates an accurate risk assessment index Fpzs, and weights different physiological indexes through dynamically adjusted weights and correction constants C by the deep learning model, so that a multidimensional and accurate postoperative complication risk assessment is provided, potential risk points can be effectively identified by the prediction method based on data driving, and a reliable decision basis is provided for a clinician. The prediction management module performs comparison analysis on the risk assessment index Fpzs and a preset assessment threshold W through the comparison unit, so that corresponding nursing measures can be adopted under different risk levels. Specifically: if the risk assessment index Fpzs > the assessment threshold W, which indicates that the risk of postoperative complications of the patient is low, in this case, the system suggests to continue to perform the originally planned postoperative care measures, maintain periodic monitoring every 5 hours, gradually reduce mechanical ventilation support, and start restorative treatment and rehabilitation training, and at the same time, periodically review, which can effectively optimize the recovery process of the patient and advance the rehabilitation process while ensuring stable conditions. If the risk assessment index Fpzs =the assessment threshold W indicates that there is a certain risk of complications after the patient operation, the system will adjust the frequency of regular monitoring to once every 3 hours, ensure to track the patient's condition changes in time, especially key indicators such as lung function and oxygenation level, and fine tune the treatment plan, and this measure can cope with potential problems in time, reducing the occurrence probability of complications. If the risk assessment index Fpzs is smaller than the assessment threshold W, the risk assessment index indicates that the postoperative complication risk of the patient is higher. At this time, the system will immediately take urgent medical intervention measures including adjusting mechanical ventilation parameters, increasing oxygen therapy intensity and using vasoactive drugs, and at the same time, increasing the monitoring frequency to once every 2 hours, the urgent response mechanism can rapidly cope with acute complications, and ensure the safety of patients. Overall, the implementation of the system improves the prediction and management efficiency of postoperative complications, further improves the postoperative care quality and safety of patients through accurate risk assessment and timely adjustment measures, and effectively reduces the possibility of occurrence of complications.
Example 6: referring to fig. 2, the following details are: a method for predicting complications after cardiothoracic surgery comprises the following steps,
Step one: performing physical examination on a patient after the chest and heart surgery, and acquiring related respiratory state data information, related pulmonary abnormal distribution data information and related expansion degree data information of the patient through a report acquired by the physical examination;
step two: preprocessing the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information which are acquired in the postoperative data monitoring module, and constructing a postoperative complications data set after dimensionless technical processing;
Step three: constructing an oxygenation factor Yhyz of the patient after operation according to the related respiratory state data information, primarily judging whether the current pulmonary oxygenation capacity of the patient is damaged according to the numerical value of the oxygenation factor Yhyz, and if so, sending out a complication prediction instruction;
Step four: after a complication prediction instruction is received, respectively calculating alveolar ventilation Ftqz and a lung expansion capacity coefficient Fkxs of each lung segment according to related lung abnormal distribution data information and related expansion degree data information, and fitting to obtain a risk assessment index Fpzs by combining a trained complication prediction model;
step five: an evaluation threshold value W is preset, and the evaluation threshold value W is compared with the risk evaluation index Fpzs for analysis, so that the risk degree of the postoperative complications of the current patient is comprehensively predicted.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The heart and chest surgical postoperative complications prediction system is characterized by comprising a postoperative data monitoring module, a data processing module, a lung preliminary analysis module, a comprehensive analysis module and a prediction management module;
The postoperative data monitoring module is used for carrying out physical examination on a patient after the chest surgery and acquiring relevant respiratory state data information, relevant pulmonary abnormal distribution data information and relevant expansion degree data information of the patient through a report acquired by the physical examination;
The data processing module is used for preprocessing the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information which are acquired in the postoperative data monitoring module, and constructing a postoperative complications data set after being processed by a dimensionless technique;
The lung preliminary analysis module is used for constructing an oxygenation factor Yhyz of a patient after operation according to the related respiratory state data information, preliminarily judging whether the current lung oxygenation capacity of the patient is damaged according to the numerical value of the oxygenation factor Yhyz, and if so, sending out a complication prediction instruction;
The comprehensive analysis module is used for respectively calculating the alveolar ventilation Ftqz and the pulmonary expansion capacity coefficient Fkxs of each pulmonary segment according to the related pulmonary abnormality distribution data information and the related expansion degree data information after receiving the complications prediction instruction, and fitting to obtain a risk assessment index Fpzs by combining the trained complications prediction model;
The comprehensive analysis module comprises a local analysis unit, an expansion degree analysis unit and a comprehensive prediction unit;
The local analysis unit is used for calculating the alveolar ventilation Ftqz of each lung segment according to the related lung abnormal distribution data information after receiving the complications prediction instruction, and the alveolar ventilation Ftqz is obtained in the following manner:
；
wherein Mzz represents the total ventilation per minute; wtz denotes dead space ventilation;
Alveolar ventilation Ftqz for each lung segment was counted and an average alveolar ventilation calculated ；
The comprehensive prediction unit is used for constructing a complication prediction model by utilizing a convolutional neural network technology and constructing an oxygenation factor Yhyz, a lung expansion capacity coefficient Fkxs and average alveolar ventilation after a patient operationInput into a complication prediction model to fit the acquired risk assessment index Fpzs, specifically by the following formula:
；
Wherein, C represents a correction constant, AndAll are weight values;
The prediction management module is used for presetting an evaluation threshold value W, and comparing the evaluation threshold value W with the risk evaluation index Fpzs for analysis so as to comprehensively predict the risk degree of postoperative complications of the current patient.
2. The system for predicting complications after cardiothoracic surgery according to claim 1, wherein the postoperative data monitoring module comprises a physical examination unit and an acquisition unit;
The physical examination unit is used for checking the postoperative state of a patient subjected to cardiothoracic surgery through a plurality of groups of monitoring devices, wherein the plurality of groups of monitoring devices comprise an arterial blood gas analyzer, a breathing machine, a lung function tester and a pressure sensor;
The acquisition unit is used for acquiring and recording related respiratory state data information, related pulmonary abnormality distribution data information and related expansion degree data information of a patient according to patient reports acquired by a plurality of groups of monitoring equipment, wherein the related respiratory state data information comprises arterial blood oxygen partial pressure Dfy and suction oxygen concentration Xynd before, during and after operation of the patient;
The related pulmonary abnormality distribution data information includes total ventilation Mzz and dead space ventilation Wtz per minute for each pulmonary segment in the patient's lungs after surgery;
the relevant expansion degree data information includes tidal volume Cqz, positive end expiratory pressure Hmzy and plateau pressure Pty.
3. The post-cardiac and thoracic surgical complication prediction system of claim 1 wherein the data processing module comprises a preprocessing unit and an integration unit;
The preprocessing unit is used for checking and identifying missing data, repeated data and data formats in the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information so as to remove the repeated data, correct the data formats and fill the missing values;
The integration unit is used for carrying out standardized processing on the preprocessed data information by utilizing a dimensionless processing technology so as to eliminate the dimensionality difference among different data sources, and combining the data from the different data sources into a unified view by combining a multi-sensor data fusion technology so as to construct a postoperative complication data set.
4. The post-cardiac and thoracic surgical complication prediction system of claim 2 wherein the pulmonary primary analysis module comprises a pulmonary primary analysis unit and a primary diagnosis unit;
The lung preliminary analysis unit is used for constructing an oxygenation factor Yhyz of a patient after operation according to the related respiratory state data information, and the oxygenation factor is obtained in the following manner:
；
wherein Dfy represents an arterial blood oxygen partial pressure and Xynd represents an intake oxygen concentration.
5. The system according to claim 4, wherein the preliminary diagnosis unit is configured to analyze and obtain the pre-operative and intra-operative oxygenation factors Yhyz of the patient according to the method of obtaining the post-operative oxygenation factor Yhyz of the patient in the pulmonary preliminary analysis unit, and obtain the average oxygenation factor of the whole patient by a statistical algorithmAnd by combining the post-operative oxygenation factor Yhyz of the patient with the average oxygenation factor of the patient as a wholeThe comparison is carried out to preliminarily judge whether the oxygenation capacity of the lung of the current patient is damaged, and the specific judgment content is as follows:
If the post-operative oxygenation factor Yhyz of the patient does not exceed the average oxygenation factor of the patient as a whole When the lung oxygenation capacity of the current patient is judged to be in a damaged state, a complication prediction instruction is sent outwards at the moment;
if the post-operative oxygenation factor Yhyz of the patient exceeds the average oxygenation factor of the patient as a whole And when the lung oxygenation capacity of the current patient is judged to be not in a damaged state, the lung oxygenation capacity of the current patient is judged preliminarily.
6. The post-cardiac and thoracic surgical complication prediction system of claim 5, wherein the expansion degree analysis unit is configured to construct a lung expansion capacity coefficient Fkxs according to the related expansion degree data information, and specifically obtain the lung expansion capacity coefficient according to the following manner:
；
where Cqz denotes tidal volume, pty denotes plateau pressure, and Hmzy denotes positive end-tidal pressure.
7. The post-cardiac and thoracic surgical complication prediction system of claim 1 wherein the prediction management module comprises an alignment unit;
the comparison unit is used for presetting an evaluation threshold value W, and comprehensively predicting the risk degree of postoperative complications of the current patient by comparing the evaluation threshold value W with the risk evaluation index Fpzs, and comprises the following specific contents:
If the risk assessment index Fpzs is larger than the assessment threshold W, the risk of complications does not exist after the operation of the patient, at the moment, the original planned postoperative care measures are continuously implemented, the regular monitoring of monitoring every 5 hours is kept, the mechanical ventilation support of the patient is gradually reduced on the premise of ensuring the condition stability of the patient, the restorative treatment and rehabilitation training are started, and meanwhile, the patient is regularly rechecked;
If risk assessment index Fpzs =assessment threshold W, it indicates that there is a risk of complications after the patient operation, at this time, the frequency of regular monitoring will be adjusted to once every 3 hours, and the treatment scheme is fine-tuned according to the real-time monitoring result, and the specific fine-tuning device includes a ventilator;
if the risk assessment index Fpzs < the assessment threshold W, it indicates that there is a risk of complications after the patient operation, and emergency medical intervention is immediately taken at this time, where the specific emergency medical intervention includes: the mechanical ventilation parameters, up-regulation of the oxygen therapy intensity and the use of vasoactive drugs were adjusted, while the frequency of periodic monitoring was adjusted to once every 2 hours.
8. A method for predicting complications after cardiothoracic surgery, for implementing the system for predicting complications after cardiothoracic surgery according to any one of claims 1 to 7, comprising the steps of:
Step one: performing physical examination on a patient after the chest and heart surgery, and acquiring related respiratory state data information, related pulmonary abnormal distribution data information and related expansion degree data information of the patient through a report acquired by the physical examination;
step two: preprocessing the related respiratory state data information, the related pulmonary abnormal distribution data information and the related expansion degree data information which are acquired in the postoperative data monitoring module, and constructing a postoperative complications data set after dimensionless technical processing;
Step three: constructing an oxygenation factor Yhyz of the patient after operation according to the related respiratory state data information, primarily judging whether the current pulmonary oxygenation capacity of the patient is damaged according to the numerical value of the oxygenation factor Yhyz, and if so, sending out a complication prediction instruction;
Step four: after a complication prediction instruction is received, respectively calculating alveolar ventilation Ftqz and a lung expansion capacity coefficient Fkxs of each lung segment according to related lung abnormal distribution data information and related expansion degree data information, and fitting to obtain a risk assessment index Fpzs by combining a trained complication prediction model;
step five: an evaluation threshold value W is preset, and the evaluation threshold value W is compared with the risk evaluation index Fpzs for analysis, so that the risk degree of the postoperative complications of the current patient is comprehensively predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411288140.3A CN118800458B (en) | 2024-09-14 | 2024-09-14 | Method and system for predicting complications after cardiothoracic surgery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411288140.3A CN118800458B (en) | 2024-09-14 | 2024-09-14 | Method and system for predicting complications after cardiothoracic surgery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118800458A CN118800458A (en) | 2024-10-18 |
| CN118800458B true CN118800458B (en) | 2024-11-15 |
Family
ID=93031508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411288140.3A Active CN118800458B (en) | 2024-09-14 | 2024-09-14 | Method and system for predicting complications after cardiothoracic surgery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118800458B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119153075A (en) * | 2024-11-12 | 2024-12-17 | 大连玖柒医疗科技有限公司 | Data analysis-based method and system for evaluating complications after cardiothoracic surgery |
| CN119151934B (en) * | 2024-11-19 | 2025-01-28 | 山东衡昊信息技术有限公司 | Extracardiac operation monitoring system and method based on image processing |
| CN119207828A (en) * | 2024-11-26 | 2024-12-27 | 吉林大学第一医院 | Real-time monitoring system and method for infection cases |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105288217A (en) * | 2015-11-20 | 2016-02-03 | 冯连桂 | Drug for comprehensive intervention after cardiothoracic surgery |
| WO2021064426A1 (en) * | 2019-10-04 | 2021-04-08 | Imperial College Innovations Limited | Screening with mass spectrometry for mycobacteria prior to cardiothoracic surgery |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2379353C (en) * | 2002-03-28 | 2012-07-31 | Joseph Fisher | A new method for continuous measurement of flux of gases in the lungs during breathing |
| CN105377274A (en) * | 2012-12-12 | 2016-03-02 | 麦瑟布莱斯特公司 | Methods of treating or preventing respiratory conditions |
| CN105288216A (en) * | 2015-11-20 | 2016-02-03 | 庞大斌 | Preparation method of atomized inhaling liquid used after cardiac surgery |
| CN116864119B (en) * | 2023-05-22 | 2024-03-05 | 中国医学科学院北京协和医院 | A pneumonia risk prediction method, equipment, system and storage medium based on the infection period |
-
2024
- 2024-09-14 CN CN202411288140.3A patent/CN118800458B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105288217A (en) * | 2015-11-20 | 2016-02-03 | 冯连桂 | Drug for comprehensive intervention after cardiothoracic surgery |
| WO2021064426A1 (en) * | 2019-10-04 | 2021-04-08 | Imperial College Innovations Limited | Screening with mass spectrometry for mycobacteria prior to cardiothoracic surgery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118800458A (en) | 2024-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118800458B (en) | Method and system for predicting complications after cardiothoracic surgery | |
| US10314515B2 (en) | Capnography device and method | |
| US6997880B2 (en) | Waveform interpreter for respiratory analysis | |
| Kline et al. | Alveolar dead space as a predictor of severity of pulmonary embolism | |
| Modrykamien et al. | Detection of upper airway obstruction with spirometry results and the flow-volume loop: a comparison of quantitative and visual inspection criteria | |
| AU2018315253B2 (en) | A method for the early identification of recurrences of chronic obstructive pulmonary disease | |
| JP2014526926A (en) | Event sequencing and method using acoustic breathing markers | |
| Morris et al. | Analysis of expiratory tidal flow patterns as a diagnostic tool in airflow obstruction | |
| EP4295884B1 (en) | System for alleviating hyperventilation based on ventilator | |
| Chao et al. | Determining the best threshold of rapid shallow breathing index in a therapist-implemented patient-specific weaning protocol | |
| Zannin et al. | Early respiratory system reactance predicts respiratory outcomes in preterm infants: a retrospective, multicentre study | |
| Zannin et al. | Oscillatory mechanics in very preterm infants on continuous positive airway pressure support: reference values | |
| Sticher et al. | Computerized Anesthesia Record Keeping in Thoracic Surgery–Suitability of Electronic Anesthesia Records in Evaluating Predictors for Hypoxemia During One-lung Ventilation | |
| CN210903016U (en) | Device for evaluating airflow limitation of subject | |
| Kazemi et al. | Assessment on methods used to detect asthmatic and non-asthmatic conditions using capnogram signal | |
| Todur et al. | Utility of arterial to end-tidal carbon dioxide difference [P (a–ET) CO2] as a weaning index | |
| WO2022223676A1 (en) | System for identifying a condition of a user | |
| Balakrishnan et al. | A review of capnography in asthma: A new approach on assessment of capnogram | |
| CN118452881A (en) | Method for detecting vital capacity | |
| US20150005591A1 (en) | Tissue to end tidal co2 monitor | |
| WO2025012843A1 (en) | System and methods for automatically identifying a breath variability event from patient respiratory data associated with a mechanical ventilator | |
| CN118155830A (en) | A multivariate prediction system for hypoxemia during painless bronchoscopy | |
| KR20240158489A (en) | mart spirometer capable of measuring expiratory temperature (EBT) and COPD patient screening system using the same | |
| Scanlan et al. | Pulmonary Function Testing | |
| CN109431509A (en) | A kind of method and apparatus for assessing subject's flow limitation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |