[go: up one dir, main page]

CN119274804A - A risk prediction and decision-making support system for postoperative pulmonary complications - Google Patents

A risk prediction and decision-making support system for postoperative pulmonary complications Download PDF

Info

Publication number
CN119274804A
CN119274804A CN202411785781.XA CN202411785781A CN119274804A CN 119274804 A CN119274804 A CN 119274804A CN 202411785781 A CN202411785781 A CN 202411785781A CN 119274804 A CN119274804 A CN 119274804A
Authority
CN
China
Prior art keywords
prediction model
complication
information
acquiring
score
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
Application number
CN202411785781.XA
Other languages
Chinese (zh)
Inventor
吴涛
陈蔚
任贺
夏星球
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Healsci Chuanglian Health Technology Co ltd
Original Assignee
Beijing Healsci Chuanglian Health Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Healsci Chuanglian Health Technology Co ltd filed Critical Beijing Healsci Chuanglian Health Technology Co ltd
Priority to CN202411785781.XA priority Critical patent/CN119274804A/en
Publication of CN119274804A publication Critical patent/CN119274804A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G06N5/025—Extracting rules from data
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
    • 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Pathology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Medicinal Chemistry (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Surgery (AREA)
  • Urology & Nephrology (AREA)
  • Chemical & Material Sciences (AREA)
  • Biophysics (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本发明涉及医疗保健信息学技术领域，更具体涉及一种术后肺部并发症风险预测及辅助决策系统。该系统包括：数据获取模块，用于获取患者的入院信息、术前信息和术后信息；模型训练模块，用于创建并训练入院预测模型、术前预测模型和术后预测模型；特征处理模块，用于从患者信息、术前信息和术后信息中提取第一特征、第二特征和第三特征，并进行预处理；风险预测模块，用于获取入院预测模型、术前预测模型和术后预测模型的输出结果及对应风险因子；干预手段推荐模块，用于获取每一预测肺部并发症的术前干预措施、术中干预措施和术后干预措施。本发明解决了术后肺部并发症预测不准及精准获取干预措施的问题，提高了预测精度和干预措施的精准度。

The present invention relates to the technical field of medical care informatics, and more specifically to a postoperative pulmonary complication risk prediction and decision-making support system. The system includes: a data acquisition module for acquiring the patient's admission information, preoperative information, and postoperative information; a model training module for creating and training an admission prediction model, a preoperative prediction model, and a postoperative prediction model; a feature processing module for extracting the first feature, the second feature, and the third feature from the patient information, the preoperative information, and the postoperative information, and performing preprocessing; a risk prediction module for acquiring the output results and corresponding risk factors of the admission prediction model, the preoperative prediction model, and the postoperative prediction model; an intervention means recommendation module for acquiring the preoperative intervention measures, intraoperative intervention measures, and postoperative intervention measures for each predicted pulmonary complication. The present invention solves the problem of inaccurate prediction of postoperative pulmonary complications and accurate acquisition of intervention measures, and improves the prediction accuracy and the accuracy of intervention measures.

Description

Postoperative pulmonary complications risk prediction and auxiliary decision making system
Technical Field
The invention relates to the technical field of medical health care informatics, in particular to a postoperative pulmonary complications risk prediction and auxiliary decision making system.
Background
Pulmonary complications, particularly pulmonary infections, remain a major cause of prolonged hospital stay and death in patients with chest surgery after surgery. Perioperative lung protection is an important component for accelerating rehabilitation surgery, and strengthening perioperative lung protection can obviously reduce occurrence of pulmonary complications and reduce death risk. Predicting postoperative pulmonary complications may potentially optimize therapeutic measures for some patients, and may also promote reasonable use of medical resources, thereby enhancing perioperative lung protection and promoting improvement of medical quality. A similar prior art has a patent application with publication number of CN112017783A, a prediction model of heart postoperative pulmonary infection and a construction method thereof are provided, in various clinical data of heart operation patient perioperation period are collected, evaluation indexes related to heart postoperative pulmonary infection are screened out, the evaluation indexes are brought into a Logistic regression model to analyze and calculate regression coefficients of risk factors for determining heart postoperative pulmonary infection, then risk scores are obtained through the regression coefficients of the risk factors, finally, the risk scores are combined with a pulmonary infection risk prediction function to calculate a pulmonary infection probability value, so that a risk prediction model based on a scoring system can be established, compared with the existing model abroad, better risk prediction capability is shown, the purpose of early screening postoperative pulmonary infection high-risk patients can be achieved, early prevention, early discovery and early treatment effects are achieved, and the incidence rate of heart postoperative pulmonary infection is reduced. A similar prior art also discloses US20230016569A1, which proposes a method for predicting whether a patient suffers from any of one or more advanced complications categories based on chest radiographs. Chest radiography is a low cost, minimally invasive source of visual information that accurately predicts whether a subject will suffer from diabetes and is associated with chronic complications, morbid obesity, congestive heart failure, specific cardiac arrhythmias, vascular disease or chronic obstructive pulmonary disease, among other advanced complications categories. Both patent applications solve the problem of predicting complications, but do not predict for different stages and have insufficient prediction accuracy, and do not propose a targeted intervention measure for each stage, and do not provide effective reference measures for medical staff, so that the effect of reducing or alleviating complications, particularly pulmonary complications is poor.
Disclosure of Invention
In order to better solve the above problems, the present invention provides a post-operative pulmonary complication risk prediction and decision-aiding system, the system comprising:
The data acquisition module is used for acquiring admission information of a patient when the patient is admitted, acquiring preoperative information of the patient in a first preset time period before the patient performs an operation, and acquiring postoperative information of the patient in a second preset time period after the patient performs the operation;
The model training module is used for creating and training an admission prediction model, a preoperative prediction model and a postoperative prediction model, and acquiring a first correlation factor, a second correlation factor and a third correlation factor based on the trained admission prediction model, the trained preoperative prediction model and the trained postoperative prediction model;
the feature processing module is used for extracting a first feature, a second feature and a third feature from the admission information, the preoperative information and the postoperative information respectively according to the first related factor, the second related factor and the third related factor respectively, and preprocessing the first feature, the second feature and the third feature;
The risk prediction module is used for inputting the first feature, the second feature and the third feature into the admission prediction model, the preoperative prediction model and the postoperative prediction model respectively, and obtaining a first output result, a second output result, a third output result, a first risk factor, a second risk factor and a third risk factor;
The intervention means recommending module is used for acquiring each predicted pulmonary complication and corresponding preoperative intervention measures, intraoperative dry pre-measures and postoperative intervention measures based on the first risk factor, the second risk factor, the third risk factor, the first output result, the second output result and the third output result.
As a preferable technical scheme, the system further comprises a result feedback module, wherein the result feedback module is used for sending each predicted lung complication and the predicted lung complication corresponding to the prediction score, the preoperative intervention measure, the intraoperative dry pre-measure and the postoperative intervention measure to a medical care terminal as output results.
The patient admission information comprises patient basic information, main complaints, prior medical history, personal medical history, complications and admission diagnosis information, the pre-operation information comprises examination information of the patient and the patient admission information obtained in the first preset time period before operation, and the post-operation information comprises operation time, blood loss and anesthesia medication information obtained in the second preset time period after operation.
The model training module is configured to train the admission prediction model, the preoperative prediction model and the postoperative prediction model based on the historical admission information, the historical preoperative information, the historical postoperative information and the corresponding multiple historical pulmonary complications and corresponding scores of other patients in chest surgery stored in the storage unit, take the historical admission information, each of the historical pulmonary complications and corresponding scores as the first training data, take the historical preoperative information, each of the historical pulmonary complications and corresponding scores as the second training data, take the historical postoperative information, each of the historical pulmonary complications and corresponding scores as the third training data, train the admission prediction model, the preoperative prediction model and the postoperative prediction model based on the first training data, the second training data and the third training data respectively, take the historical admission prediction model, each of the historical pulmonary complications and the corresponding scores as the second training data, take the historical admission prediction model, each of the historical pulmonary complications and the corresponding scores as the third training data, and take the historical admission prediction model, each of the historical pulmonary complications and corresponding scores as the third training data, set the third correlation factor and the third correlation factor from the trained admission prediction model, the output of the first correlation factor, the third correlation factor and the third correlation factor.
As a preferred solution, the risk prediction module is configured to:
Inputting the first features into the hospital admission prediction model, and acquiring a first output result, wherein the first output result comprises N1 first lung complications and first scores of each first lung complication, and further acquiring a contribution value of each first score corresponding to each feature in the first features, and taking N features which have the largest contribution value and can be intervened as first risk factors corresponding to the first lung complications, and similarly, acquiring the first risk factors of each first lung complication, wherein the value range of N and N1 is a positive integer greater than or equal to 1;
the intervention means recommending module is used for acquiring the preoperative intervention means based on the first causal relationship and the first score corresponding to the first lung complications by analyzing the first causal relationship between each first lung complication and the corresponding first risk factor.
The risk prediction module is further configured to input the second features into the pre-operation prediction model and obtain a second output result within the first preset time period before the chest surgery after the pre-operation intervention measure is implemented, wherein the second output result comprises N2 second lung complications and corresponding second scores, and the second risk factors corresponding to each second lung complication are obtained according to the contribution value of each feature in each second feature to each second score;
The intervention means recommending module is configured to obtain a first score and a second score of each first target complication by analyzing a second causal relationship between each second lung complication and the corresponding second risk factor, taking the first lung complication and the corresponding same condition as a first target complication when the first lung complication and the second lung complication correspond to the same condition, calculating a first difference value between the first score and the second score, weighting the first score and the second score to obtain a first target score, and obtaining an intra-operative dry pre-measure based on the second causal relationship and the first target score corresponding to each first target complication, wherein the weight of the first score is smaller than the weight of the second score, the greater the first difference value is, the smaller the weight of the first score is, and N2 of the first lung complications are included in N1.
As a preferred technical solution, the intervention means recommendation module is configured to input the third feature into the post-operation prediction model in the second preset time period after the operation, and obtain the third output result, where the third output result includes N3 third lung complications and corresponding third scores, and obtain a third risk factor corresponding to each third lung complication according to a contribution value of each feature in the third features to each third score, where N3 is less than or equal to N2;
The intervention means recommending module is configured to obtain a second target score corresponding to the second target complication by analyzing a third causal relationship between each third lung complication and the third risk factor, and obtaining the postoperative intervention measure based on the third causal relationship, and taking the third lung complication as a second target complication, where the first target complication includes the second target complication, calculate a second difference value between the first target score and the third score corresponding to each second target complication, set a weight of the first target score according to the second difference value, weight the first target score and the third score to obtain a second target score corresponding to the second target complication, and take the second target complication as the predicted lung complication, and take the second target score as the predicted score of the predicted lung complication, where the weight of the third score is greater than the weight of the first target score, and the second difference value is smaller than the first target score.
As a preferred embodiment, the first feature, the second feature, and the third feature each include a plurality of features and corresponding feature values.
The invention also provides a postoperative pulmonary complication risk prediction and auxiliary decision making method, which is realized based on the system, and comprises the following steps:
Step S1, creating and training an admission prediction model, a preoperative prediction model and a postoperative prediction model through a model training module, and acquiring a first correlation factor, a second correlation factor and a third correlation factor based on the trained admission prediction model, the trained preoperative prediction model and the trained postoperative prediction model;
S2, acquiring admission information of a patient during admission by a data acquisition module, acquiring first characteristics from the admission information according to the first related factors, inputting the first characteristics into the admission prediction model, acquiring a first output result, acquiring a first risk factor based on the first output result, and acquiring preoperative intervention measures of each first lung complication in the first output result based on the first risk factor and the first output result;
Step S3, acquiring preoperative information of a patient when the patient is admitted by a data acquisition module, acquiring a second characteristic from the preoperative information according to the second related factors, inputting the second characteristic into the preoperative prediction model, acquiring a second output result, acquiring a second risk factor based on the second output result, and acquiring preoperative intervention measures of each second pulmonary complications in the second output result based on the second risk factor, the second output result and the first output result;
And S4, acquiring postoperative information of a patient when the patient is admitted by a data acquisition module, acquiring a third characteristic from the preoperative information according to the third related factor, inputting the third characteristic into the preoperative prediction model, acquiring a third output result, acquiring a third risk factor based on the third output result, and acquiring postoperative intervention measures of each third pulmonary complication in the third output result based on the third risk factor, the second output result and the third output result, wherein the third pulmonary complication is the predicted pulmonary complication.
The invention also provides a computer storage medium, wherein the storage medium stores program instructions, and the program instructions control a device where the storage medium is located to execute the method when running.
Compared with the prior art, the invention has the following beneficial effects:
The invention acquires the admission information, preoperative information and postoperative information of the patient at the time of admission, and based on the first correlation factor, the second correlation factor and the third correlation factor extracted from the admission model, the preoperative model and the postoperative model after training, respectively extracts the first feature, the second feature and the third feature from the admission information, the preoperative information and the postoperative information, wherein the first correlation factor, the second correlation factor and the third correlation factor are the features with larger weights in the admission model, the preoperative model and the postoperative model output layer respectively, thereby laying a foundation for acquiring the first feature, the second feature and the third feature with higher accuracy, further acquiring the lung complications with higher accuracy, and inputting the first feature into the admission prediction model, and obtaining a first output result, obtaining the first risk factors according to each first lung complication and corresponding first score in the first output result, obtaining the preoperative intervention measures and corresponding intervention degrees based on each first lung complication and corresponding first risk factor and first score, inputting the second characteristic into the preoperative prediction model, obtaining a second output result and the second risk factors, obtaining the intraoperative intervention measures and corresponding intervention degrees through the first output result, the second output result and the second risk factors, and similarly obtaining the postoperative intervention measures and corresponding intervention degrees, fully considering the effect of each stage of intervention measures and recalculating the lung complications and corresponding scores of different stages through the mutual cooperation of the technical schemes, not only can the final postoperative multiple pulmonary complications and the score of each pulmonary complication be predicted more accurately, but also corresponding intervention measures can be given more pertinently, so that the occurrence of the pulmonary complications is reduced or lightened.
Drawings
FIG. 1 is a block diagram of a post-operative pulmonary complications risk prediction and decision-aid system according to the present invention;
Fig. 2 is a flowchart of a method for predicting and assisting decision-making of postoperative pulmonary complications risk according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides a postoperative pulmonary complication risk prediction and auxiliary decision making system, as shown in fig. 1, comprising:
The data acquisition module is used for acquiring admission information of a patient when the patient is admitted, acquiring preoperative information of the patient in a first preset time period before the patient performs an operation, and acquiring postoperative information of the patient in a second preset time period after the patient performs the operation;
The model training module is used for creating and training an admission prediction model, a preoperative prediction model and a postoperative prediction model, and acquiring a first correlation factor, a second correlation factor and a third correlation factor based on the trained admission prediction model, the trained preoperative prediction model and the trained postoperative prediction model;
the feature processing module is used for extracting a first feature, a second feature and a third feature from the admission information, the preoperative information and the postoperative information respectively according to the first related factor, the second related factor and the third related factor respectively, and preprocessing the first feature, the second feature and the third feature;
The risk prediction module is used for inputting the first feature, the second feature and the third feature into the admission prediction model, the preoperative prediction model and the postoperative prediction model respectively, and obtaining a first output result, a second output result, a third output result, a first risk factor, a second risk factor and a third risk factor;
The intervention means recommending module is used for acquiring each predicted pulmonary complication and corresponding preoperative intervention measures, intraoperative dry pre-measures and postoperative intervention measures based on the first risk factor, the second risk factor, the third risk factor, the first output result, the second output result and the third output result.
Specifically, the first, second and third characteristics are extracted from the admission information, the preoperative information and the postoperative information respectively based on the first, second and third correlation factors extracted from the admission model, the preoperative model and the postoperative model after training, wherein the first, second and third correlation factors are the characteristics with larger weights in the admission model, the preoperative model and the postoperative model output layer respectively, so as to lay a foundation for obtaining the more accurate first, second and third characteristics, further obtain more accurate predicted pulmonary complications, and input the first characteristics into the admission prediction model, and obtaining a first output result, obtaining the first risk factors according to each first lung complication and corresponding first score in the first output result, obtaining the preoperative intervention measures and corresponding intervention degrees based on each first lung complication and corresponding first risk factor and corresponding first score, inputting the second characteristic into the preoperative prediction model, obtaining a second output result and the second risk factors, obtaining the intraoperative intervention measures and corresponding intervention degrees through the first output result, the second output result and the second risk factors, and obtaining the postoperative intervention measures and corresponding intervention degrees through the mutual cooperation of the technical proposal, fully considering the effect of the intervention measures of each stage and recalculating the predicted lung complications and corresponding prediction scores of different stages of the patient, not only can the final postoperative multiple pulmonary complications and the score of each pulmonary complication be predicted more accurately, but also corresponding intervention measures can be given more pertinently, so that the occurrence of the pulmonary complications is reduced or lightened.
Further, the system also comprises a result feedback module, which is used for sending each predicted lung complication and the predicted lung complication corresponding to the predicted score, the preoperative intervention measure, the intraoperative dry pre-measure and the postoperative intervention measure to a medical care terminal as output results.
Specifically, by sending each predicted pulmonary complication and a corresponding predicted score to the medical care terminal, medical care personnel can know the predicted pulmonary complications and the corresponding predicted scores, wherein the predicted pulmonary complications comprise a first pulmonary complication, a second pulmonary complication and a third pulmonary complication, and the preoperative intervention measure, the intraoperative dry pre-measure and the postoperative intervention measure corresponding to each predicted pulmonary complication are also sent to the medical care terminal as output results, so that the medical care personnel can refer to the predicted pulmonary complications conveniently, and the occurrence of the pulmonary complications is reduced or lightened.
Further, the admission information of the patient comprises patient basic information, main complaints, past medical history, personal medical history, complications and admission diagnosis information, the pre-operation information comprises examination information of the patient and the admission information of the patient obtained in the first preset time period before operation, and the post-operation information comprises operation time length, blood loss and anesthesia medication information obtained in the second preset time period after operation.
Further, the model training module is configured to train the admission prediction model, the preoperative prediction model and the postoperative prediction model based on historical admission information, historical preoperative information, historical postoperative information and corresponding multiple historical lung complications and corresponding scores of other patients of chest surgery stored in a storage unit, and take the historical admission information, each of the historical lung complications and corresponding scores as the first training data, the historical preoperative information, each of the historical lung complications and corresponding scores as the second training data, the historical postoperative information, each of the historical lung complications and corresponding scores as the third training data, and train the admission prediction model, the preoperative prediction model and the postoperative prediction model based on the first training data, the second training data and the third training data respectively, wherein the admission prediction model, the preoperative prediction model and the postoperative prediction model are neural network models; and extracting the first correlation factor, the second correlation factor and the third correlation factor with weights greater than a set threshold from the trained output layers of the admission prediction model, the preoperative prediction model and the postoperative prediction model, wherein each of the first correlation factor, the second correlation factor and the third correlation factor respectively comprises a plurality of factors.
Specifically, the history admission information, the history preoperative information, and the history postoperative information of the other patient in the chest surgery stored in the storage unit are identical to the contents of the admission information, preoperative information, and postoperative information of the patient for whom post-operative pulmonary complications are to be predicted, and the history admission information and each of the history pulmonary complications and the corresponding scores are used as the first training data, and the admission prediction model is trained using the first training data, since the admission prediction model is a neural network model, and since the history admission information includes patient basic information, a main complaint, a history, a personal history, complications, and admission diagnostic information, but not the contents of each of the history admission information are related to the history pulmonary complications, extracting key information with weight greater than the set threshold value from an output layer of the admission prediction model, namely, key information in the admission information related to each of the historical pulmonary complications, taking the key information as the first related factor, taking the historical preoperative information and each of the historical complications and corresponding scores as the second training data, taking the historical postoperative information and each of the historical complications and corresponding scores as the third training data, respectively training the preoperative prediction model and the postoperative prediction model by using the second training data and the third training data, and acquiring the second related factor and the third related factor by adopting an acquisition mode same as the first related factor, the preoperative prediction model and the postoperative prediction model lay a foundation for obtaining accurate postoperative pulmonary complications.
Further, the risk prediction module is configured to:
Inputting the first features into the hospital admission prediction model, and acquiring a first output result, wherein the first output result comprises N1 first lung complications and first scores of each first lung complication, and further acquiring a contribution value of each first score corresponding to each feature in the first features, and taking N features which have the largest contribution value and can be intervened as first risk factors corresponding to the first lung complications, and similarly, acquiring the first risk factors of each first lung complication, wherein the value range of N and N1 is a positive integer greater than or equal to 1;
the intervention means recommending module is used for acquiring the preoperative intervention means based on the first causal relationship and the first score corresponding to the first lung complications by analyzing the first causal relationship between each first lung complication and the corresponding first risk factor.
Specifically, since the first feature is feature information related to the first pulmonary complications extracted from the admission prediction model based on the first related factor, and the first output result is obtained by inputting the first feature into the admission prediction model, the first output result includes N1 different types of the first pulmonary complications and a first score of each of the first pulmonary complications, and the higher the first score, the higher the occurrence probability and the greater the severity of the first pulmonary complications, in order to maximally reduce the occurrence of the first pulmonary complications by means of an accurate pre-operative intervention measure before performing the first intervention, the first pulmonary complications can be obtained by means of a first pre-operative intervention factor based on a first risk-based on a first aspect of the first intervention, and therefore, when the first output result is outputted by means of the admission prediction model, the first feature is required to be able to intervene, for example, age, history, although the first pulmonary complications related to the first pulmonary complications can not be acquired by means of an accurate pre-operative intervention measure before performing the first intervention, the first pulmonary complications can be obtained by means of an accurate pre-operative intervention factor, the first pulmonary intervention factor can be obtained by means of an accurate pre-operative intervention factor, and the first pulmonary intervention factor can be obtained by means of an accurate pre-operative intervention factor according to a first aspect of the first intervention factor before performing the first intervention factor, the first pulmonary intervention factor can be obtained by means of the first pre-operative intervention factor according to the first aspect of the first intervention factor before performing the first intervention factor, and the first aspect of the first intervention factor can be obtained by means of the first feature before the first feature factors by means of the first feature before the first intervention factor, and the first factors can be obtained by the first factors, as an intervention factor, and can factors, though factors, and can, thereby reducing the occurrence probability of the first pulmonary complications.
Further, the risk prediction module is further configured to input the second features into the pre-operation prediction model and obtain a second output result within the first preset time period before the chest surgery after the pre-operation intervention measure is implemented, wherein the second output result comprises N2 second lung complications and corresponding second scores, and the second risk factors corresponding to each second lung complication are obtained according to the contribution value of each feature in each second feature to each second score;
The intervention means recommending module is configured to obtain a first score and a second score of each first target complication by analyzing a second causal relationship between each second lung complication and the corresponding second risk factor, taking the first lung complication and the corresponding same condition as a first target complication when the first lung complication and the second lung complication correspond to the same condition, calculating a first difference value between the first score and the second score, weighting the first score and the second score to obtain a first target score, and obtaining an intra-operative dry pre-measure based on the second causal relationship and the first target score corresponding to each first target complication, wherein the weight of the first score is smaller than the weight of the second score, the greater the first difference value is, the smaller the weight of the first score is, and N2 of the first lung complications are included in N1.
Specifically, before the chest surgery, the second feature is input into the pre-surgery prediction model and the second output result is obtained, wherein the second output result includes a plurality of different types of the second pulmonary complications and corresponding second scores, and the second risk factor corresponding to each of the second pulmonary complications is obtained based on the contribution value of each feature in the second feature to the second scores, wherein the second risk factor is obtained in the same manner as the first risk factor, and because the pre-surgery prediction model can predict the occurrence of the first pulmonary complications relatively accurately and intervenes through the relatively accurate pre-surgery, the occurrence of the first pulmonary complications or the score decrease, i.e., N1 of the first pulmonary complications includes N2 of the second pulmonary complications, is avoided, and the first score is set according to the first score, the better the first score indicates the better the first pulmonary complications than the second risk factors, i.e., the better the first score indicates the better the first pulmonary complications, and the better the first score indicates the better the first pulmonary complications, therefore, the second lung complication is more accurate and smaller than the first score, so that the weight of the second score is greater than that of the first score, the first target score is obtained by weighting the first score and the second score, the first target score reflects the occurrence probability of the first target complication, the intervention degree of the intraoperative dry pre-measure corresponding to the first target complication is set through the first target score, for example, when the medicine intervention is needed, the medicine dosage is adjusted within a proper range through the intervention degree, the score of each first target complication can be accurately obtained through the technical scheme, and the accurate intraoperative dry pre-measure can be obtained for each first target complication.
Further, the intervention means recommending module is configured to input the third feature into the post-operation prediction model in the second preset time period after the operation, and obtain the third output result, where the third output result includes N3 third lung complications and corresponding third scores, and obtain a third risk factor corresponding to each third lung complication according to a contribution value of each feature in the third feature to each third score, where N3 is less than or equal to N2;
The intervention means recommending module is configured to obtain the post-operative intervention measure based on a third causal relationship between each third lung complication and the third risk factor, and use the third lung complication as a second target complication, where the first target complication includes the second target complication, calculate a second difference value between the first target score and the third score corresponding to each second target complication, set a weight of the first target score according to the second difference value, and weight the first target score and the third score to obtain a second target score corresponding to the second target complication, where the weight of the third score is greater than the weight of the first target score, and the second difference value is greater the weight of the first target score is, the smaller the second difference value is, and the weight of the first target score is greater the weight of the first target score is.
Specifically, the third feature is input into the post-operation prediction model in the second preset time period after operation, the third output result is obtained, according to the contribution value of each feature in the third feature to each third lung complication corresponding to the third score in the third output result, the third lung complication corresponding to the third risk factor is obtained according to the method of obtaining the first risk factor, and the third weight is obtained by analyzing the third causal relation between each third lung complication and the third risk factor, and based on the third causal relation, the post-operation intervention measure is obtained, and the third score can more accurately reflect the occurrence probability and the severity of each second target complication because the first target score of the second target complication is the lung complication condition after the post-operation pre-measurement is adopted, the weight of the second target complication is more accurately compared with the weight of the patient, and the second target score can not be accurately obtained by the method of the second target score, and the second target score can be accurately obtained.
The invention also provides a postoperative pulmonary complication risk prediction and auxiliary decision making method, which is realized based on the system, as shown in fig. 2, and comprises the following steps:
Step S1, creating and training an admission prediction model, a preoperative prediction model and a postoperative prediction model through a model training module, and acquiring a first correlation factor, a second correlation factor and a third correlation factor based on the trained admission prediction model, the trained preoperative prediction model and the trained postoperative prediction model;
S2, acquiring admission information of a patient during admission by a data acquisition module, acquiring first characteristics from the admission information according to the first related factors, inputting the first characteristics into the admission prediction model, acquiring a first output result, acquiring a first risk factor based on the first output result, and acquiring preoperative intervention measures of each first lung complication in the first output result based on the first risk factor and the first output result;
Step S3, acquiring preoperative information of a patient when the patient is admitted by a data acquisition module, acquiring a second characteristic from the preoperative information according to the second related factors, inputting the second characteristic into the preoperative prediction model, acquiring a second output result, acquiring a second risk factor based on the second output result, and acquiring preoperative intervention measures of each second pulmonary complications in the second output result based on the second risk factor, the second output result and the first output result;
And S4, acquiring postoperative information of a patient when the patient is admitted by a data acquisition module, acquiring a third characteristic from the preoperative information according to the third related factor, inputting the third characteristic into the preoperative prediction model, acquiring a third output result, acquiring a third risk factor based on the third output result, and acquiring postoperative intervention measures of each third pulmonary complication in the third output result based on the third risk factor, the second output result and the third output result, wherein the third pulmonary complication is the predicted pulmonary complication.
The invention also provides a computer storage medium, wherein the storage medium stores program instructions, and the program instructions control a device where the storage medium is located to execute the method when running.
In summary, the present invention establishes a basis for obtaining accurate first, second and third features to obtain accurate predicted pulmonary complications based on the first, second and third correlation factors extracted from the trained admission model, the preoperative model and the postoperative model, and the first, second and third correlation factors extracted from the admission information, preoperative information and postoperative information, respectively, by inputting the first feature into the admission prediction model, obtaining a first output result, and obtaining the first risk factor according to each first pulmonary complication and a corresponding first score in the first output result, and based on each of the first pulmonary complications and the corresponding first risk factors and first scores, the preoperative intervention measures and corresponding scores are obtained, the second characteristics are input into the preoperative prediction model, the second output results and the second risk factors are obtained, the intraoperative dry pre-measure and corresponding scores are obtained through the first output results, the second output results and the second risk factors, the intraoperative intervention measures and corresponding scores are obtained, the intraoperative intervention measures and corresponding scores are also obtained through the mutual coordination of the technical proposal, the effect of each stage of intervention measures is fully considered, the pulmonary complications and corresponding scores of different stages of the patient are recalculated, the scores of a plurality of pulmonary complications and each pulmonary complication after the final operation can be more accurately predicted, the corresponding intervention measures can be given out more pertinently, thereby reducing or alleviating the occurrence of pulmonary complications.
The technical features of the above embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as the scope of the description of the present specification as long as there is no contradiction between the combinations of the technical features.
The foregoing examples have been presented to illustrate only a few embodiments of the invention and are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.

Claims (10)

1. A post-operative pulmonary complications risk prediction and decision-making aid system, the system comprising:
The data acquisition module is used for acquiring admission information of a patient when the patient is admitted, acquiring preoperative information of the patient in a first preset time period before the patient performs an operation, and acquiring postoperative information of the patient in a second preset time period after the patient performs the operation;
The model training module is used for creating and training an admission prediction model, a preoperative prediction model and a postoperative prediction model, and acquiring a first correlation factor, a second correlation factor and a third correlation factor based on the trained admission prediction model, the trained preoperative prediction model and the trained postoperative prediction model;
the feature processing module is used for extracting a first feature, a second feature and a third feature from the admission information, the preoperative information and the postoperative information respectively according to the first related factor, the second related factor and the third related factor respectively, and preprocessing the first feature, the second feature and the third feature;
The risk prediction module is used for inputting the first feature, the second feature and the third feature into the admission prediction model, the preoperative prediction model and the postoperative prediction model respectively, and obtaining a first output result, a second output result, a third output result, a first risk factor, a second risk factor and a third risk factor;
The intervention means recommending module is used for acquiring each predicted pulmonary complication and corresponding preoperative intervention measures, intraoperative dry pre-measures and postoperative intervention measures based on the first risk factor, the second risk factor, the third risk factor, the first output result, the second output result and the third output result.
2. The system of claim 1, further comprising a result feedback module for transmitting each of the predicted pulmonary complications and the predicted pulmonary complications corresponding prediction scores, the pre-operative intervention, the intra-operative dry pre-measure, and the post-operative intervention as output results to a healthcare terminal.
3. The system of claim 1, wherein the admission information of the patient includes patient basic information, complaints, past medical history, personal medical history, complications, admission diagnostic information, the pre-operative information includes examination information of the patient acquired during the first preset time period before the operation and the admission information of the patient, and the post-operative information includes operation duration, blood loss amount, and anesthesia medication information acquired during the second preset time period after the operation.
4. The system of claim 1, wherein the model training module is configured to train the admission prediction model, the pre-operative prediction model, and the post-operative prediction model based on historical admission information, historical pre-operative information, historical post-operative information, and corresponding multiple historical pulmonary complications and corresponding scores of other patients of chest surgery stored in the storage unit, and to take the historical admission information, each of the historical pulmonary complications and corresponding scores as first training data, take the historical pre-operative information, each of the historical pulmonary complications and corresponding scores as second training data, take the historical post-operative information, each of the historical pulmonary complications and corresponding scores as third training data, and train the admission prediction model, the pre-operative prediction model, and the post-operative prediction model based on the first training data, the second training data, and the third training data, respectively, wherein the admission prediction model, the pre-operative prediction model, and the post-operative prediction model are all neural network models, and the trained admission prediction model, the pre-operative prediction model, and the post-operative prediction model, respectively, and the third correlation factor, the first correlation factor, the third correlation factor, and the third correlation factor are respectively, and the third correlation factor are set from the trained admission prediction model, the pre-operative prediction model, the pre-and the pre-correlation factor.
5. The system of claim 1, wherein the risk prediction module is configured to:
Inputting the first features into the hospital admission prediction model, and acquiring a first output result, wherein the first output result comprises N1 first lung complications and first scores of each first lung complication, and further acquiring a contribution value of each first score corresponding to each feature in the first features, and taking N features which have the largest contribution value and can be intervened as first risk factors corresponding to the first lung complications, and similarly, acquiring the first risk factors of each first lung complication, wherein the value range of N and N1 is a positive integer greater than or equal to 1;
the intervention means recommending module is used for acquiring the preoperative intervention means based on the first causal relationship and the first score corresponding to the first lung complications by analyzing the first causal relationship between each first lung complication and the corresponding first risk factor.
6. The system of claim 5, wherein the risk prediction module is further configured to input the second features into the pre-operative prediction model and obtain second output results within the first preset time period prior to chest surgery after the pre-operative intervention is performed, wherein the second output results comprise N2 second lung complications and corresponding second scores, and the second risk factors corresponding to each of the second lung complications are obtained according to the contribution value of each of the second features to each of the second scores;
The intervention means recommending module is configured to obtain a first score and a second score of each first target complication by analyzing a second causal relationship between each second lung complication and the corresponding second risk factor, taking the first lung complication and the corresponding same condition as a first target complication when the first lung complication and the second lung complication correspond to the same condition, calculating a first difference value between the first score and the second score, weighting the first score and the second score to obtain a first target score, and obtaining an intra-operative dry pre-measure based on the second causal relationship and the first target score corresponding to each first target complication, wherein the weight of the first score is smaller than the weight of the second score, the greater the first difference value is, the smaller the weight of the first score is, and N2 of the first lung complications are included in N1.
7. The system of claim 6, wherein the intervention means recommendation module is configured to input the third feature into the post-operation prediction model during the second preset period of time after the operation, and obtain the third output result, where the third output result includes N3 third lung complications and corresponding third scores, and obtain a third risk factor corresponding to each third lung complication according to a contribution value of each feature in the third features to each third score, where N3 is less than or equal to N2;
The intervention means recommending module is configured to obtain a second target score corresponding to the second target complication by analyzing a third causal relationship between each third lung complication and the third risk factor, and obtaining the postoperative intervention measure based on the third causal relationship, and taking the third lung complication as a second target complication, where the first target complication includes the second target complication, calculate a second difference value between the first target score and the third score corresponding to each second target complication, set a weight of the first target score according to the second difference value, weight the first target score and the third score to obtain a second target score corresponding to the second target complication, and take the second target complication as the predicted lung complication, and take the second target score as the predicted score of the predicted lung complication, where the weight of the third score is greater than the weight of the first target score, and the second difference value is smaller than the first target score.
8. The system of claim 1, wherein the first feature, the second feature, and the third feature each comprise a plurality of features and corresponding feature values.
9. A method of post-operative pulmonary complication risk prediction and aid decision making, the method being implemented based on the system of any of claims 1-8, the method comprising:
Step S1, creating and training an admission prediction model, a preoperative prediction model and a postoperative prediction model through a model training module, and acquiring a first correlation factor, a second correlation factor and a third correlation factor based on the trained admission prediction model, the trained preoperative prediction model and the trained postoperative prediction model;
S2, acquiring admission information of a patient during admission by a data acquisition module, acquiring first characteristics from the admission information according to the first related factors, inputting the first characteristics into the admission prediction model, acquiring a first output result, acquiring a first risk factor based on the first output result, and acquiring preoperative intervention measures of each first lung complication in the first output result based on the first risk factor and the first output result;
Step S3, acquiring preoperative information of a patient when the patient is admitted by a data acquisition module, acquiring a second characteristic from the preoperative information according to the second related factors, inputting the second characteristic into the preoperative prediction model, acquiring a second output result, acquiring a second risk factor based on the second output result, and acquiring intraoperative dry pre-measures of each second pulmonary complications in the second output result based on the second risk factor, the second output result and the first output result;
And S4, acquiring postoperative information of a patient when the patient is admitted by a data acquisition module, acquiring a third characteristic from the preoperative information according to the third related factor, inputting the third characteristic into the preoperative prediction model, acquiring a third output result, acquiring a third risk factor based on the third output result, and acquiring postoperative intervention measures of each third pulmonary complication in the third output result based on the third risk factor, the second output result and the third output result, wherein the third pulmonary complication is the predicted pulmonary complication.
10. A computer storage medium, characterized in that the storage medium stores program instructions, wherein the program instructions, when run, control a device on which the storage medium is located to perform the method of claim 9.
CN202411785781.XA 2024-12-06 2024-12-06 A risk prediction and decision-making support system for postoperative pulmonary complications Pending CN119274804A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411785781.XA CN119274804A (en) 2024-12-06 2024-12-06 A risk prediction and decision-making support system for postoperative pulmonary complications

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411785781.XA CN119274804A (en) 2024-12-06 2024-12-06 A risk prediction and decision-making support system for postoperative pulmonary complications

Publications (1)

Publication Number Publication Date
CN119274804A true CN119274804A (en) 2025-01-07

Family

ID=94124786

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411785781.XA Pending CN119274804A (en) 2024-12-06 2024-12-06 A risk prediction and decision-making support system for postoperative pulmonary complications

Country Status (1)

Country Link
CN (1) CN119274804A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108364689A (en) * 2018-02-24 2018-08-03 西安时代基因健康科技股份有限公司 A kind of hyperuricemia and gout non-drug targeting interfering system based on molecule parting
JP2020057053A (en) * 2018-09-28 2020-04-09 学校法人慶應義塾 Postoperative complication prediction method, postoperative complication prediction program, and postoperative complication prediction device
CN115223679A (en) * 2022-08-05 2022-10-21 华中科技大学同济医学院附属同济医院 Perioperative period risk early warning method based on machine learning
CN115579107A (en) * 2022-09-21 2023-01-06 上海市第一人民医院 An intelligent auxiliary decision-making model based on the optimal behavior of perioperative doctors and nurses
CN116030986A (en) * 2022-12-30 2023-04-28 复旦大学附属中山医院 Model, method and electronic device for predicting risk of delirium after cardiac surgery
WO2023198065A1 (en) * 2022-04-11 2023-10-19 北京优理医疗器械有限公司 Physiological data collecting apparatus and method, physiological data processing apparatus and method and physiological data presenting apparatus and method for handling crisis and non-crisis situations
CN117995355A (en) * 2024-01-12 2024-05-07 沈阳医学院附属第二医院 Method, equipment and system for assisting in decision making of acute myocardial infarction PCI (peripheral component interconnect) operation
CN118213075A (en) * 2024-03-19 2024-06-18 华东师范大学附属芜湖医院(芜湖市第二人民医院) Multi-mode prediction and identification system for postoperative delirium syndrome of senile general anesthesia patient
CN118522473A (en) * 2021-12-27 2024-08-20 武庆平 Method, system, electronic device and medium for predicting postoperative pulmonary complications

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108364689A (en) * 2018-02-24 2018-08-03 西安时代基因健康科技股份有限公司 A kind of hyperuricemia and gout non-drug targeting interfering system based on molecule parting
JP2020057053A (en) * 2018-09-28 2020-04-09 学校法人慶應義塾 Postoperative complication prediction method, postoperative complication prediction program, and postoperative complication prediction device
CN118522473A (en) * 2021-12-27 2024-08-20 武庆平 Method, system, electronic device and medium for predicting postoperative pulmonary complications
WO2023198065A1 (en) * 2022-04-11 2023-10-19 北京优理医疗器械有限公司 Physiological data collecting apparatus and method, physiological data processing apparatus and method and physiological data presenting apparatus and method for handling crisis and non-crisis situations
CN115223679A (en) * 2022-08-05 2022-10-21 华中科技大学同济医学院附属同济医院 Perioperative period risk early warning method based on machine learning
CN115579107A (en) * 2022-09-21 2023-01-06 上海市第一人民医院 An intelligent auxiliary decision-making model based on the optimal behavior of perioperative doctors and nurses
CN116030986A (en) * 2022-12-30 2023-04-28 复旦大学附属中山医院 Model, method and electronic device for predicting risk of delirium after cardiac surgery
CN117995355A (en) * 2024-01-12 2024-05-07 沈阳医学院附属第二医院 Method, equipment and system for assisting in decision making of acute myocardial infarction PCI (peripheral component interconnect) operation
CN118213075A (en) * 2024-03-19 2024-06-18 华东师范大学附属芜湖医院(芜湖市第二人民医院) Multi-mode prediction and identification system for postoperative delirium syndrome of senile general anesthesia patient

Similar Documents

Publication Publication Date Title
Jollis et al. Treatment time and in-hospital mortality among patients with ST-segment elevation myocardial infarction, 2018-2021
Inohara et al. Association of renin-angiotensin inhibitor treatment with mortality and heart failure readmission in patients with transcatheter aortic valve replacement
Fonarow et al. The hospital readmission reduction program is associated with fewer readmissions, more deaths: time to reconsider
Varacallo et al. Ten-year trends and independent risk factors for unplanned readmission following elective total joint arthroplasty at a large urban academic hospital
Pagidipati et al. Sex differences in functional and CT angiography testing in patients with suspected coronary artery disease
Chimukangara et al. The impact of frailty on outcomes of paraesophageal hernia repair
Arce et al. The American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator does not accurately predict risk of 30-day complications among patients undergoing microvascular head and neck reconstruction
KR20190132290A (en) Method, server and program of learning a patient diagnosis
Ullrich et al. Coronary venous pressure and microvascular hemodynamics in patients with microvascular angina: a randomized clinical trial
Abrahamyan et al. Long-term outcomes after atrial septal defect transcatheter closure by age and against population controls
Burns et al. Prevalence of pulmonary hypertension in pediatric patients with obstructive sleep apnea and a cardiology evaluation: a retrospective analysis
JP2018534697A (en) System and method for facilitating health monitoring based on personalized predictive models
US20240274297A1 (en) Surgical warning
JP2022520750A (en) How to assess muscle-related disorders
Song et al. Combined cardiac, lung, and diaphragm ultrasound for predicting weaning failure during spontaneous breathing trial
Siontis et al. Patient-Level Artificial Intelligence–Enhanced Electrocardiography in Hypertrophic Cardiomyopathy: Longitudinal Treatment and Clinical Biomarker Correlations
Kline et al. Derivation and validation of a Bayesian network to predict pretest probability of venous thromboembolism
Caller et al. Atherosclerotic cardiovascular diseases are associated with incident metastatic and nonmetastatic cancer
Hariharan et al. Association between the Pulmonary Embolism Severity Index (PESI) and short-term clinical deterioration
Li et al. Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery: a multi-center cohort study
Li et al. Predicting inferior vena cava filter complications using machine learning
CN119274804A (en) A risk prediction and decision-making support system for postoperative pulmonary complications
Klimitz et al. The five-item Modified Frailty Index (mFI-5) predicts adverse short-term outcomes in patients undergoing mastectomy: a propensity score-matched analysis of 252,054 cases
Colvin et al. Left ventricular recovery in young patients with myocardial infarction: How much is enough?
Zembala et al. Clinical characteristics of patients undergoing surgical ventricular reconstruction by choice and by randomization

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