CN112420201B - Deep cascading framework for ICU mortality prediction - Google Patents

Deep cascading framework for ICU mortality prediction Download PDF

Info

Publication number
CN112420201B
CN112420201B CN202011341957.4A CN202011341957A CN112420201B CN 112420201 B CN112420201 B CN 112420201B CN 202011341957 A CN202011341957 A CN 202011341957A CN 112420201 B CN112420201 B CN 112420201B
Authority
CN
China
Prior art keywords
network
sub
cascade
node
disease
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011341957.4A
Other languages
Chinese (zh)
Other versions
CN112420201A (en
Inventor
姜京池
王勃然
马林江
李雪
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.)
Harbin Institute Of Technology Institute Of Artificial Intelligence Co ltd
Original Assignee
Harbin Institute of Technology
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 Harbin Institute of Technology filed Critical Harbin Institute of Technology
Priority to CN202011341957.4A priority Critical patent/CN112420201B/en
Publication of CN112420201A publication Critical patent/CN112420201A/en
Application granted granted Critical
Publication of CN112420201B publication Critical patent/CN112420201B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention provides a deep cascading framework for ICU mortality prediction and an ICU mortality prediction method, wherein the deep cascading framework for the ICU mortality prediction comprises the following steps: the sign sub-network and the disease sub-network are connected in a cascade mode according to node failure conditions, and both the sign sub-network and the disease sub-network are used for outputting failure distribution so as to conduct ICU mortality prediction through the failure distribution. The invention has the beneficial effects that: the method can conveniently predict the death rate of ICU patients and can make the prediction interpretable.

Description

Deep cascading framework for ICU mortality prediction
Technical Field
The invention relates to the field of ICU mortality prediction, in particular to a deep cascade framework for ICU mortality prediction.
Background
Medical risk detection is an important topic for improving the clinical practice capability of the ICU, and many biometric learning methods and deep learning methods based on quantitative tables and characteristics can predict the mortality rate of a specific patient and assist physicians in making corresponding clinical decisions. However, current methods not only require experts to manually define risk factors but also rely heavily on the effectiveness of the pre-training features. From the model perspective, the end-to-end prediction model lacks interpretability, and the black box type neural network structure is difficult to obtain an inference path.
Disclosure of Invention
The problem addressed by the present invention is how to facilitate the prediction of ICU patient mortality and render the prediction interpretable.
The invention provides a deep cascading framework for ICU mortality prediction, which comprises the following steps: the sign sub-network and the disease sub-network are connected in a cascade mode according to node failure conditions, and both the sign sub-network and the disease sub-network are used for outputting failure distribution so as to conduct ICU mortality prediction through the failure distribution.
Further, the node failure condition comprises a failure set, and the failure set comprises the front part with the maximum failure risk in the cascade stagenAnd (4) each node.
Further, the node failure condition further includes network connectivity, the network connectivity includes an effective edge probability of the interaction edge, the effective edge probability represents a probability that one interaction edge is randomly selected and the edge connects two effective nodes, and the effective edge probability generated in the current cascade stage is used for updating the effective edge probability in the next cascade stage.
Further, the sign sub-network and the disease sub-network each include a degree distribution unit and an excess degree distribution unit, the sign sub-network and the disease sub-network each determine the failure set through the degree distribution unit, and the sign sub-network and the disease sub-network each determine an effective edge probability of a next cascade stage through the excess degree distribution unit according to the effective edge probability of a current cascade stage.
Further, the degree distribution unit includes a degree distribution generating function, the excess distribution unit includes an excess distribution generating function, and the recursive relation of the depth cascade framework includes:
Figure DEST_PATH_IMAGE001
in the first placelIn the secondary cascade, the effective node proportions of the disease sub-network and the sign sub-network are respectively as follows:
Figure 146755DEST_PATH_IMAGE002
(ii) a Or the like, or, alternatively,
Figure DEST_PATH_IMAGE003
in the first placelIn the secondary cascade, the effective node proportions of the sign sub-network and the disease sub-network are respectively as follows:
Figure 470420DEST_PATH_IMAGE004
；
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE005
a sub-network of a disease is represented,
Figure 781316DEST_PATH_IMAGE006
a sub-network of signs is represented,
Figure DEST_PATH_IMAGE007
and
Figure 832318DEST_PATH_IMAGE008
a degree distribution generating function representing the disease sub-network and the signs sub-network respectively,
Figure DEST_PATH_IMAGE009
and
Figure 177848DEST_PATH_IMAGE010
a hyperdynamic distribution generating function representing the disease sub-network and the signs sub-network respectively,lthe number of cascades is indicated,
Figure DEST_PATH_IMAGE011
represents the number of cascades asl-1 a hypernym distribution generation function of the vital sign sub-network,
Figure 734732DEST_PATH_IMAGE012
represents the number of cascades asl-1 a hyperdistribution generating function of the disease sub-network,
Figure DEST_PATH_IMAGE013
represents the number of cascades aslGenerating a function of the hyperdistribution of the disease sub-network,
Figure 939448DEST_PATH_IMAGE014
represents the number of cascades aslOf the sign sub-networkThe degree distribution is generated as a function of,
Figure DEST_PATH_IMAGE015
represents the number of cascades aslA function is generated of the degree distribution of the disease sub-network,
Figure 794140DEST_PATH_IMAGE016
represents the number of cascades aslThe degree distribution of the sign sub-network of (1) generates a function,
Figure DEST_PATH_IMAGE017
the probability of the valid edge is represented,
Figure 994178DEST_PATH_IMAGE018
represents the number of cascades aslOf the disease sub-network,
Figure DEST_PATH_IMAGE019
represents the number of cascades aslThe effective edge probability of the sign subnetwork.
Further, the sign sub-network and the disease sub-network both determine the failure distribution according to the effective probabilities of the nodes, wherein the failure distribution of the current cascade stage is generated by normalizing the effective probabilities of all the nodes of the cascade stage.
Further, in the sign sub-network and the disease sub-network, the effective probability of the node is determined according to the number of failed nodes in each node neighborhood, wherein the failure set generated in the current cascade stage is used for updating the number of failed nodes in each node neighborhood in the next cascade stage.
Further, the calculation formula of the effective probability of the node is as follows:
Figure 394066DEST_PATH_IMAGE020
；
wherein, the first and the second end of the pipe are connected with each other,
Figure DEST_PATH_IMAGE021
the nodes are represented as a list of nodes,mrepresenting the number of failed nodes in the neighborhood of nodes,
Figure 679554DEST_PATH_IMAGE022
which represents the number of neighbors of the node,
Figure DEST_PATH_IMAGE023
indicating the number of valid neighbors of the node,
Figure 902436DEST_PATH_IMAGE024
it is shown that the distribution is tolerated,
Figure DEST_PATH_IMAGE025
which represents the tolerance factor of the current signal,Xrepresenting the signs subnetwork or the diseases subnetwork.
Further, each node of the signs sub-network and the diseases sub-network has a personalized tolerance distribution
Figure 956980DEST_PATH_IMAGE024
Wherein:
Figure 58928DEST_PATH_IMAGE026
Figure DEST_PATH_IMAGE027
；
the tolerance coefficient is calculated by the formula:
Figure 831712DEST_PATH_IMAGE028
；
wherein, the first and the second end of the pipe are connected with each other,
Figure DEST_PATH_IMAGE029
representing the importance weight of the node's neighbors to the node.
Further, in the sign sub-network and the disease sub-network, when the number of nodes connected with valid nodes is greater than or equal to a first preset number, the nodes are valid, otherwise, the nodes are invalid.
The invention has the beneficial effects that: the sign sub-network and the disease sub-network are used for constructing a deep cascade framework, physiological domino effect is established through a cascade failure theory, the sign sub-network and the disease sub-network are cascaded according to node failure conditions, in cascade failure, the failure conditions of the nodes, such as failure between the nodes or interaction edges of two node connections, can cause other nodes to also fail through coupling relations between the nodes, so that cascade effect is generated, therefore, the sign sub-network and the disease sub-network generate failure distribution in respective cascade stages to integrally react on failure conditions of disease types and sign types in the sub-networks, finally, the ICU death rate of a patient can be determined according to the output, and due to the interrelations between the sign types and the disease types, the death rate prediction has interpretability.
The present invention also provides a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the following steps:
acquiring an examination type of a patient, wherein the examination type comprises a disease type of the patient or an abnormal sign type in signs of examination of the patient;
generating an initial failure set according to the inspection type;
inputting the initial failure set into a deep cascading framework for ICU mortality prediction as described above for cascading;
sequentially inputting failure distribution output by each cascading stage during cascading into a serialization model;
and obtaining the mortality prediction result of the patient according to the last hidden state of the serialization model at the end of the cascade.
Further, the processor, when executing the computer program, is further configured to implement the following steps:
generating importance weights through the graph attention network;
determining the effective probability of each node of each cascade stage during cascade connection according to the importance weight;
normalizing the effective probabilities of all nodes in the cascade stage to generate the failure distribution.
The computing device of the present invention has similar benefits to the above-described deep cascading framework for ICU mortality prediction compared to the prior art, and will not be described herein again.
The invention also proposes a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of:
acquiring an examination type of a patient, wherein the examination type comprises a disease type of the patient or an abnormal sign type in signs of examination of the patient;
generating an initial failure set according to the inspection type;
inputting the initial failure set into a deep cascading framework for ICU mortality prediction as described above for cascading;
sequentially inputting failure distribution output by each cascading stage during cascading into a serialization model;
and obtaining the mortality prediction result of the patient according to the last hidden state of the serialization model at the end of the cascade.
Further, the computer program, when executed by the processor, is adapted to perform the steps of:
generating importance weights through the graph attention network;
determining the effective probability of each node of each cascade stage during cascade connection according to the importance weight;
normalizing the effective probabilities of all nodes in the cascade stage to generate the failure distribution.
The advantages of the computer-readable storage medium of the present invention over the prior art are similar to the above-described deep cascading framework for ICU mortality prediction, and are not described herein again.
Drawings
FIG. 1 is a schematic representation of a prediction model for ICU mortality prediction using a deep cascade framework in accordance with the present invention;
FIG. 2 is a flow chart of a method for ICU mortality prediction in an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
It is noted that the terms first, second and the like in the description and in the claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein.
Referring to fig. 1, a deep cascading framework for ICU mortality prediction includes a sign sub-network and a disease sub-network, where the sign sub-network includes a plurality of nodes corresponding to sign types, the disease sub-network includes a plurality of nodes corresponding to disease types, the sign sub-network and the disease sub-network have interaction edges, and the interaction edges are connection edges between the nodes corresponding to the disease types and the nodes corresponding to the sign types, where the sign sub-network and the disease sub-network cascade according to node failure conditions, and both the sign sub-network and the disease sub-network are used for outputting failure distributions to perform ICU mortality prediction through the failure distributions.
Medical risk detection is an important topic for improving the clinical practice capability of the ICU, and many biometric learning methods and deep learning methods based on quantitative tables and characteristics can predict the mortality of a specific patient and assist a physician to make corresponding clinical decisions. However, current methods not only require experts to manually define risk factors but also overly rely on the effectiveness of pre-training features. From the model perspective, the end-to-end prediction model lacks interpretability, and the black box type neural network structure is difficult to obtain an inference path.
In embodiments of the invention, the body system is considered to be a complex dynamic network, the interaction between physiological functions maintaining the balance of the network. Once a part or a function of the physiological network fails, the steady state is broken, resulting in a more serious and dangerous functional failure, even a breakdown of the entire physiological network until death, for example: complications, infections, immune disorders, and the like.
Abnormalities in vital signs are the internal cause of disease, while diseases are the external manifestations of abnormal signs. One disease is indicative of some related signs being marginal or abnormal, and if the severity of these abnormal signs exceeds a tolerable threshold for other diseases, more physiological functional failure can occur, even resulting in a cascade. Therefore, there is a typical interaction between signs and diseases, which together maintain the balance of the physiological system. Based on this, the deep cascade framework for ICU mortality prediction of the present application, hereinafter referred to as deep cascade framework, includes: sign subnetwork
Figure 841256DEST_PATH_IMAGE030
And disease sub-network
Figure DEST_PATH_IMAGE031
Sign subnetwork
Figure 140519DEST_PATH_IMAGE032
Comprising a plurality of nodes representing types of physical signs, a disease sub-network
Figure DEST_PATH_IMAGE033
The node comprises a plurality of disease types, wherein the sign types are basic physiological characteristics of human beings, such as urine osmotic pressure, plasma albumin parameters and the like, and correspondingly, the disease types are external manifestations of abnormal signs, such as renal failure disease characteristics related to the urine osmotic pressure and the plasma albumin parameters and the like. Thus a two-part network is constructed,
Figure 678948DEST_PATH_IMAGE034
Figure DEST_PATH_IMAGE035
in which
Figure 939028DEST_PATH_IMAGE036
And
Figure DEST_PATH_IMAGE037
individual disease sub-networks
Figure 673635DEST_PATH_IMAGE033
Sign and sign sub-network
Figure 906033DEST_PATH_IMAGE038
The set of nodes of (a) is,
Figure DEST_PATH_IMAGE039
is a collection of interacting edges between two sub-networks,
Figure 208838DEST_PATH_IMAGE040
representing a set of triples
Figure DEST_PATH_IMAGE041
Weight, sign sub-network of
Figure 566001DEST_PATH_IMAGE042
And disease sub-networks
Figure 245245DEST_PATH_IMAGE031
With interacting edges, i.e. connecting edges of nodes of disease type and nodes of sign type, i.e. representing the interrelation between two sub-networks, for sign sub-networks
Figure 332149DEST_PATH_IMAGE038
And disease sub-network
Figure 196069DEST_PATH_IMAGE031
And the nodes in the network have no edge connection, and only the sign sub-network and the disease sub-network interact with each other. On-sign subnetwork
Figure 368424DEST_PATH_IMAGE042
In (1), failure of a certain node representing the type of physical sign may cause disease, and the corresponding disease sub-network
Figure 585779DEST_PATH_IMAGE031
One or more nodes representing the disease type may fail, and correspondingly, the disease subnetwork
Figure 792769DEST_PATH_IMAGE031
In (1), failure of a certain node representing the disease type may result in a sign sub-network
Figure 906219DEST_PATH_IMAGE042
Wherein one or more nodes representing a type of a sign may fail, thereby producing a chain reaction, and thus referring to fig. 1, the sign subnetwork
Figure 503553DEST_PATH_IMAGE042
And disease sub-network
Figure 462282DEST_PATH_IMAGE031
Interact with each other to generate cascade failure, and in time period, sign sub-network
Figure 320517DEST_PATH_IMAGE038
And disease sub-networks
Figure 339288DEST_PATH_IMAGE033
The method has a plurality of cascading stages, and in each cascading process, the failure condition of a node is used as a main factor influencing the subsequent cascading stage.
Thus, the present embodiment passes through the sign subnetwork
Figure DEST_PATH_IMAGE043
And disease sub-network
Figure 407607DEST_PATH_IMAGE005
Constructing deep cascadesFramework, physiological domino effect and physical sign sub-network established by cascade failure theory
Figure 966765DEST_PATH_IMAGE043
And disease sub-network
Figure 820451DEST_PATH_IMAGE033
Cascading is carried out according to node failure conditions, in cascading failure, the failure conditions of nodes, such as the failure between the nodes or the interaction edges of the connection of the two nodes, can cause other nodes to also fail through the coupling relation between the nodes, so that a cascading effect is generated, and therefore, in each stage of cascading by utilizing a deep cascading framework, a physical sign sub-network can be output
Figure 744545DEST_PATH_IMAGE043
And disease sub-network
Figure 441105DEST_PATH_IMAGE033
In this embodiment, in particular, the sign subnetwork
Figure 741637DEST_PATH_IMAGE043
And disease sub-network
Figure 964677DEST_PATH_IMAGE031
Generating failure distributions in respective cascade stages to integrally react to failure conditions of disease types and sign types in respective sub-networks, and finally determining the ICU death rate of the patient according to the output, in an optional embodiment of the present embodiment, as shown in FIG. 1, when ICU death rate prediction is performed, the failure distributions are processed through a serialization model, and based on the sign sub-networks in time period
Figure 59672DEST_PATH_IMAGE043
Or disease subnetwork
Figure 243528DEST_PATH_IMAGE031
Alternately cascading, and outputting fail-overCloth, sign subnetwork
Figure 613330DEST_PATH_IMAGE043
Failure distribution and disease subnetwork of
Figure 910450DEST_PATH_IMAGE033
The failure distribution is integrally input into the serialization model to be processed so as to control the input dimensionality to be unchanged, and the final hidden state of the serialization model can be classified by a classifier to directly obtain an ICU mortality prediction result. Thus, based on the deep cascade framework constructed in the embodiment, when applied to ICU mortality prediction, the potential failure risk of all physiological functions in each clinical stage can be predicted. In contrast to other feature-based or scale-based models, the deep cascade framework in this embodiment, when applied to ICU mortality prediction, the sign subnetwork
Figure 441925DEST_PATH_IMAGE030
And disease sub-network
Figure 847499DEST_PATH_IMAGE031
The nodes which are mutually influenced mutually influence each other to carry out cascade failure and output failure distribution for ICU mortality prediction, the output of a deep cascade framework and the cascade process have strong corresponding relations and are different from a black box type neural network structure, and an inference path can be obtained by applying the deep cascade framework in the embodiment to carry out ICU mortality prediction, so that the deep cascade framework has the characteristic of interpretability, is suitable for various prediction tasks and can be continuously learned from medical common sense and clinical experience.
The interaction between the physical signs and the physiological function of the disease can be learned or summarized from medical practice.
In an alternative embodiment of the invention, in the sign subnetwork
Figure 755412DEST_PATH_IMAGE030
And disease sub-network
Figure 766093DEST_PATH_IMAGE033
When the number of the nodes connected with the effective nodes is larger than or equal to a first preset number, the nodes are effective, otherwise, the nodes are invalid.
For a sub-network, if a node in the sub-network
Figure 655421DEST_PATH_IMAGE044
Number of active nodes connected to another sub-network
Figure DEST_PATH_IMAGE045
Greater than or equal to a first preset number
Figure 282711DEST_PATH_IMAGE046
Then degree is
Figure DEST_PATH_IMAGE047
Node (a) of
Figure 400840DEST_PATH_IMAGE044
Is set to
Figure 449DEST_PATH_IMAGE048
I.e. indicating that the node remains active, otherwise the state is set to
Figure DEST_PATH_IMAGE049
I.e. indicating node failure, to judge the validity and failure of the node in the sub-network.
Thus, for the node
Figure 670464DEST_PATH_IMAGE050
Formalizing nodes
Figure 175264DEST_PATH_IMAGE050
Tolerance coefficient of
Figure DEST_PATH_IMAGE051
Is a conditional probability
Figure 956138DEST_PATH_IMAGE052
And determining the failure risk of the nodes in the sub-network, wherein the piecewise function expression is as follows:
Figure DEST_PATH_IMAGE053
；
the linear function is expressed as
Figure 675832DEST_PATH_IMAGE054
；
The nonlinear function is expressed as
Figure DEST_PATH_IMAGE055
Figure 392116DEST_PATH_IMAGE056
。
In an optional embodiment of the invention, the node failure condition comprises a failure set, and the failure set comprises the nodes before the maximum failure risk in the cascade stagenAnd (4) each node.
In ICU mortality prediction, a sub-network based on signs is required
Figure 259578DEST_PATH_IMAGE043
And disease sub-network
Figure 47405DEST_PATH_IMAGE005
The overall failure condition of (a) is judged for mortality. In an alternative embodiment, in the cascade stage, the first stage will benAnd adding the node with the maximum failure risk into the failure set input in the current cascade stage to update the failure set to be output. Referring to fig. 1, when the mortality of an ICU is predicted through a deep cascade framework, an initial failure set is usually input, the initial failure set includes a disease detection type or a sign abnormality type when the ICU is input, and in the first cascade process, the failure set output at this stage is added to the initial failure set in the current cascadenThe node with the largest failure risk fails in the subsequent cascade processThe set is updated in this way and is used as input in the later cascading stages, so that the failure condition of the whole in each cascading stage can be finally determined through the failure set, such as determining the failure distribution of the sub-networks.
In an optional embodiment of the present invention, the node failure condition further includes network connectivity, the network connectivity includes effective edge probability of the interaction edge, the effective edge probability represents a probability that one interaction edge is randomly selected and the edge connects two effective nodes, and the effective edge probability generated in the current cascade stage is used to update the effective edge probability in the next cascade stage, so as to update the effective edge probability in the sign sub-network
Figure 548837DEST_PATH_IMAGE043
And disease sub-network
Figure 826234DEST_PATH_IMAGE031
In the cascade process, the sign sub-network is measured by the effective edge probability
Figure 118675DEST_PATH_IMAGE043
And disease sub-network
Figure 710194DEST_PATH_IMAGE033
Connectivity of the constructed physiological network.
In an optional embodiment of the present invention, the sign sub-network and the disease sub-network each include a degree distribution unit and an excess degree distribution unit, and both the sign sub-network and the disease sub-network determine the failure set through the degree distribution unit, and both the sign sub-network and the disease sub-network determine the effective edge probability of the next cascade stage according to the effective edge probability of the current cascade stage through the excess degree distribution unit.
When one of two connected nodes fails, the interaction edge between them will also be removed, for example: the kidney loses the physiological function of detoxification due to the occurrence of renal failure, and then the supply interaction of urine osmotic pressure and physical stability of plasma albumin is no longer realized, and the cascade frequency is changedWill continuously impair the robustness of the physiological network, and therefore, in this embodiment, referring to fig. 1, the sign subnetwork
Figure 76584DEST_PATH_IMAGE043
And disease sub-network
Figure 462566DEST_PATH_IMAGE033
The degree distribution generating unit based on the degree distribution generating function and the excess degree distribution generating unit based on the excess degree distribution generating function are both arranged in the computer. Sign subnetwork
Figure 304620DEST_PATH_IMAGE043
And disease sub-network
Figure 434250DEST_PATH_IMAGE031
Each cascade stage sign sub-network is measured and determined by a degree distribution generating function
Figure 904415DEST_PATH_IMAGE043
And disease sub-networks
Figure 726877DEST_PATH_IMAGE033
The effective probability distribution of the middle nodes, and further the node with the maximum failure risk can be determined through the effective probability of the effective nodes, so as to determine the failure setnAdding the node with the maximum failure risk into the failure set input in the current cascade stage to update the failure set, and correspondingly, adding the sign sub-network into the failure set
Figure 790648DEST_PATH_IMAGE032
And disease sub-network
Figure 723969DEST_PATH_IMAGE033
The effective edge probability is determined through an excess distribution generating function, so that the connectivity of the network is determined, and the robustness is improved.
In an alternative embodiment of the invention, the sign subnetwork
Figure 799372DEST_PATH_IMAGE042
And disease sub-network
Figure 792736DEST_PATH_IMAGE033
Degree distribution generating function of
Figure DEST_PATH_IMAGE057
The expression of (a) is:
Figure 343803DEST_PATH_IMAGE058
；
whereinXRepresenting the sign sub-network
Figure 815236DEST_PATH_IMAGE042
Or the disease subnetwork
Figure 259993DEST_PATH_IMAGE031
，
Figure DEST_PATH_IMAGE059
Is that
Figure 220995DEST_PATH_IMAGE060
The degree distribution of the network is such that,
Figure 931462DEST_PATH_IMAGE017
the probability that an interaction edge is randomly selected and the edge connects two effective nodes, namely the effective edge probability, is used for measuring the effective probability distribution of each cascade stage node by using a degree distribution generating function.
Excess distribution generating function
Figure 144269DEST_PATH_IMAGE061
Is a function of generating a distribution of degree of contrast
Figure 522161DEST_PATH_IMAGE062
According to the effective edge probability of the current cascade stage
Figure 654065DEST_PATH_IMAGE017
Calculating effective edge probability of network of next stage
Figure 117407DEST_PATH_IMAGE017
Over-distribution generating function
Figure 117593DEST_PATH_IMAGE061
The expression of (a) is:
Figure 349991DEST_PATH_IMAGE063
Figure DEST_PATH_IMAGE064
；
wherein, the first and the second end of the pipe are connected with each other,
Figure 387217DEST_PATH_IMAGE065
representing sub-networksXSo as to measure the connectivity of the network by using the over-distribution generating function.
Thus, in an alternative embodiment of the present invention, the recursive relationship of the depth cascade framework comprises:
Figure DEST_PATH_IMAGE066
，
Figure 275539DEST_PATH_IMAGE067
representing the probability of valid nodes, inlIn the secondary cascade, the effective node proportions of the disease sub-network and the sign sub-network are respectively as follows:
Figure DEST_PATH_IMAGE068
(ii) a Or the like, or, alternatively,
Figure 689203DEST_PATH_IMAGE003
in the first placelIn the secondary cascade, the effective node proportions of the sign sub-network and the disease sub-network are respectively as follows:
Figure 776107DEST_PATH_IMAGE004
；
wherein the content of the first and second substances,
Figure 640027DEST_PATH_IMAGE031
a sub-network of a disease is represented,
Figure 812383DEST_PATH_IMAGE006
a sub-network of signs is represented,
Figure 29737DEST_PATH_IMAGE069
and
Figure DEST_PATH_IMAGE070
a degree distribution generating function representing the disease sub-network and the signs sub-network respectively,
Figure 908832DEST_PATH_IMAGE071
and
Figure 491123DEST_PATH_IMAGE072
a hyperdynamic distribution generating function representing the disease sub-network and the signs sub-network respectively,lthe number of cascades is indicated,
Figure DEST_PATH_IMAGE073
represents the number of cascades asl-1 a hypernym distribution generation function of the vital sign sub-network,
Figure 947512DEST_PATH_IMAGE012
represents the number of cascades asl-1 a hyperdistribution generating function of the disease sub-network,
Figure 171820DEST_PATH_IMAGE013
represents the number of cascades aslOver-distribution generation function of the disease sub-network,
Figure 420267DEST_PATH_IMAGE014
represents the number of cascades aslThe superscale distribution of sign sub-networks of (a) to (b) generate a function,
Figure 439039DEST_PATH_IMAGE015
represents the number of cascades aslA function is generated of the degree distribution of the disease sub-network,
Figure 648303DEST_PATH_IMAGE016
represents the number of cascades aslThe degree distribution of the physical sign sub-networks of (1) generates a function,
Figure 145144DEST_PATH_IMAGE017
the probability of the valid edge is represented,
Figure 998830DEST_PATH_IMAGE018
represents the number of cascades aslOf the disease sub-network,
Figure 188503DEST_PATH_IMAGE019
represents the number of cascades aslThe effective edge probability of the sign subnetwork.
It will be appreciated that in the deep cascade framework described in this embodiment, cascades may be derived from disease subnetworks
Figure 885064DEST_PATH_IMAGE033
Starting or starting from a sign subnetwork
Figure 185595DEST_PATH_IMAGE074
Starting with sub-networks, starting with cascades of different sub-networks, with some distinction in cascade recursion relationships
Figure 143056DEST_PATH_IMAGE031
Initially, the recursive relationship for the depth cascade framework includes:
Figure DEST_PATH_IMAGE075
in the first placelIn the secondary cascade, the disease subnetwork
Figure 300367DEST_PATH_IMAGE031
And the sign subnetwork
Figure 421907DEST_PATH_IMAGE074
The effective node ratios of (1) are respectively as follows:
Figure DEST_PATH_IMAGE077
。
but in the sign sub-network
Figure 729392DEST_PATH_IMAGE078
At the beginning, the recursive relationship of the depth cascade framework includes:
Figure 619987DEST_PATH_IMAGE003
in the first placelIn the secondary cascade, the sign subnetwork
Figure 72834DEST_PATH_IMAGE078
And the disease subnetwork
Figure 478408DEST_PATH_IMAGE031
The effective node ratios are respectively as follows:
Figure 386321DEST_PATH_IMAGE004
。
generally, patients usually suffer from a small number of diseases at the beginning of their hospitalization, so in this embodiment, the sub-networks of diseases are cascaded
Figure 69106DEST_PATH_IMAGE031
Starting with an example, for a disease sub-network
Figure 771483DEST_PATH_IMAGE031
Node set of
Figure 664353DEST_PATH_IMAGE079
Removing a proportion of disease nodes, e.g., removing a proportion of
Figure 844798DEST_PATH_IMAGE080
Correspondingly, another sign subnetwork
Figure 625498DEST_PATH_IMAGE078
Is not influenced by cascade connection in the first cascade connection stage, and is integrated
Figure 764356DEST_PATH_IMAGE081
The remaining effective node proportion
Figure 144521DEST_PATH_IMAGE082
Will decide on the current disease sub-network
Figure 128658DEST_PATH_IMAGE031
And sign subnetwork
Figure 786035DEST_PATH_IMAGE078
Connectivity of two physiological networks formed, in which case the effective edge probability
Figure DEST_PATH_IMAGE083
Generating a degree distribution into a function
Figure 626952DEST_PATH_IMAGE084
Application to sign subnetwork
Figure 432097DEST_PATH_IMAGE078
Then sign subnetwork
Figure DEST_PATH_IMAGE085
The ratio of the middle effective node will be
Figure 141296DEST_PATH_IMAGE086
Figure DEST_PATH_IMAGE087
And (6) updating. Since the disease subnetwork at this time
Figure 512235DEST_PATH_IMAGE088
The network connectivity cannot be reflected according to the proportion of the effective nodes because the network connectivity is destroyed by the initial failure nodes, that is, the inequality exists:
Figure DEST_PATH_IMAGE089
. At this time, according to the physical meaning of the super distribution, there is
Figure 399419DEST_PATH_IMAGE090
Thus, it can be determined that in the present embodiment, slave disease subnetworks are cascaded
Figure 691860DEST_PATH_IMAGE031
The recursive relation of the recursion starts. Correspondingly, this determination can be made to cascade slave sign subnetworks
Figure 345695DEST_PATH_IMAGE078
The recursive relation of the recursion is started to achieve the corresponding technical effect, and the description is omitted here.
In an optional embodiment of the present invention, the sign subnetwork and the disease subnetwork both determine the failure distribution by the effective probabilities of the nodes, wherein the failure distribution of the current cascade stage is generated by normalizing the effective probabilities of all nodes of the cascade stage.
Efficient probability means that there are neighbors of a nodemThe probability that an individual node has failed, itself remains valid.
In this embodiment, when the mortality is predicted by using the deep cascade framework, in each cascade stage, the deep cascade framework outputs failure distribution for mortality prediction, the failure distribution is generated by normalizing the effective probability of all nodes, and the effective probability is calculated by the following formula:
Figure DEST_PATH_IMAGE091
；
wherein the content of the first and second substances,
Figure 695774DEST_PATH_IMAGE021
the nodes are represented as a list of nodes,mindicating sectionThe number of failed nodes in the neighborhood of a point,
Figure 81756DEST_PATH_IMAGE022
which represents the number of neighbors of the node,
Figure 923810DEST_PATH_IMAGE092
indicating the number of valid neighbors of the node,
Figure 53440DEST_PATH_IMAGE024
it is shown that the distribution is tolerated,
Figure 274337DEST_PATH_IMAGE025
the value of the tolerance factor is represented,Xrepresenting the sign sub-network
Figure 96800DEST_PATH_IMAGE043
Or the disease subnetwork
Figure 160571DEST_PATH_IMAGE031
。
In this embodiment, in the cascade stage, the effective probabilities of all the nodes are obtained
Figure DEST_PATH_IMAGE093
Then, all the effective probabilities can be matched
Figure 749684DEST_PATH_IMAGE094
Normalization is performed so that a failure distribution can be obtained
Figure 152983DEST_PATH_IMAGE095
And further as output of the deep cascade framework for ICU mortality prediction, see fig. 1, in the deep cascade framework, the sign subnetwork
Figure 208664DEST_PATH_IMAGE030
And disease sub-network
Figure 431835DEST_PATH_IMAGE033
Cascading and outputting failure distribution
Figure DEST_PATH_IMAGE096
And failure distribution
Figure 106530DEST_PATH_IMAGE097
To the serialization model, as sign subnetwork
Figure 364336DEST_PATH_IMAGE030
And disease sub-network
Figure 325339DEST_PATH_IMAGE033
Are all carried outnWhen the secondary cascade then ends, the serialization model receives 2nAnd distributing the failures, and classifying the last hidden state of the serialized model through a classifier to obtain an ICU mortality prediction result.
In an alternative embodiment of the invention, each node of the signs sub-network and the diseases sub-network has a personalized tolerance distribution
Figure 301385DEST_PATH_IMAGE024
Wherein:
Figure 763459DEST_PATH_IMAGE026
Figure 875772DEST_PATH_IMAGE027
；
the tolerance coefficient is calculated by the formula:
Figure 273255DEST_PATH_IMAGE028
；
wherein the content of the first and second substances,
Figure 471018DEST_PATH_IMAGE029
representing the importance weight of the node's neighbors to the node.
Degree distribution generating function
Figure DEST_PATH_IMAGE098
The method can be used for measuring the proportion of effective nodes in the interaction network in each cascade stage, and because each node has difference, the uniform tolerance coefficient is adopted for each node with the same degree
Figure 221936DEST_PATH_IMAGE099
This can lead to inaccuracies and heterogeneity that violates physiological functions. For example, assume that at some cascade stage a diabetic node and a hypertensive node have the same number of neighbors
Figure 516652DEST_PATH_IMAGE022
And the same number of valid neighbors
Figure DEST_PATH_IMAGE100
Then both disease nodes have the same risk of failure when cascading without regard to node variability. However, since the two physiological functions differ in risk tolerance and pathological characteristics, the risk of failure is significantly different between the two.
Therefore, in the embodiment, as for the degree distribution generating function and the over-degree distribution generating function, the degree distribution generating function is generated by fusing the node characteristics
Figure 678512DEST_PATH_IMAGE101
And an over-distribution generating function
Figure DEST_PATH_IMAGE102
Conversion to node personalization form, generating function for degree distribution
Figure 425888DEST_PATH_IMAGE098
And an over-distribution generating function
Figure 42814DEST_PATH_IMAGE103
Decomposing degree distribution in function
Figure DEST_PATH_IMAGE104
Wherein
Figure 801822DEST_PATH_IMAGE105
Is at a degree ofkThe set of nodes of (a) is,
Figure DEST_PATH_IMAGE106
thus, the two generating functions can be redefined as:
Figure 275529DEST_PATH_IMAGE107
；
wherein:
Figure 447884DEST_PATH_IMAGE108
and
Figure DEST_PATH_IMAGE109
i.e. the effective probability, the specific formula is:
Figure 789873DEST_PATH_IMAGE110
。
in this embodiment, a personalized tolerance profile is generated for each node
Figure DEST_PATH_IMAGE111
Tolerant of distribution
Figure 528022DEST_PATH_IMAGE024
Is a tolerance factor
Figure 313575DEST_PATH_IMAGE112
With the effective number of neighbor nodes of the node
Figure DEST_PATH_IMAGE113
Increase of (2), tolerance factor thereof
Figure 769964DEST_PATH_IMAGE114
Will also rise, provided that
Figure DEST_PATH_IMAGE115
Is a node
Figure 650064DEST_PATH_IMAGE021
Is/are as follows
Figure 711561DEST_PATH_IMAGE116
The neighbor nodes which have failed are provided with mutual independence assumption among the neighbors in the bipartite network, so that the nodes
Figure 792650DEST_PATH_IMAGE021
Equal to each neighbor node and node
Figure 674018DEST_PATH_IMAGE021
Sum of causal probabilities between, i.e.
Figure 374121DEST_PATH_IMAGE117
And satisfy
Figure DEST_PATH_IMAGE118
Therefore, for the tolerance coefficient, the calculation formula is:
Figure 290124DEST_PATH_IMAGE119
；
distinguished from tolerance factor
Figure 542114DEST_PATH_IMAGE120
The calculation method of the piecewise, linear or polynomial function, the tolerance coefficient in this embodiment
Figure 176358DEST_PATH_IMAGE112
Conversion from simple quantitative statistics to AND-nodes
Figure 669699DEST_PATH_IMAGE021
Thereby more accurately confirming the failure risk of the sub-network.
Wherein, referring to FIG. 1, the importance weight may be generated by a graph attention network (GAT)
Figure 440209DEST_PATH_IMAGE121
Thereby facilitating reflection of the interaction weights of a pair of nodes.
The invention also provides an ICU mortality prediction method, which comprises the following steps:
s1, obtaining the examination type of the patient, wherein the examination type comprises the disease type of the patient or the abnormal sign type in the signs of the examination of the patient;
s2, generating an initial failure set according to the check type;
s3, inputting the initial failure set into the deep cascading framework for cascading;
s4, sequentially inputting failure distribution output by each cascade stage during cascade connection into a serialization model;
and S5, obtaining a mortality prediction result of the patient according to the last hidden state of the serialization model at the end of the cascade.
In this embodiment, when the patient's ICU mortality is predicted according to the deep cascade framework, the examination type of the patient is obtained, the examination type may include a disease diagnosis type when entering the ICU or a sign examination type within a certain time after entering the ICU, and for a certain patient, there is usually a certain disease when entering the ICU, and a part with abnormality in the sign type can be detected, and correspondingly, the part with abnormality or a disease item can be used as a sign sub-network
Figure 863100DEST_PATH_IMAGE078
Or disease subnetwork
Figure 719061DEST_PATH_IMAGE033
The initial failure node is used to construct the initial failure set and serve as the initial input of the deep cascading framework, referring to fig. 1, in this embodiment, the sign sub-network is used to cascade failure
Figure 760966DEST_PATH_IMAGE078
In the first cascade, the patient is usually suffering from the initial hospitalizationA small number of diseases, hence the disease sub-network
Figure 651562DEST_PATH_IMAGE031
A certain proportion of disease nodes need to be removed, e.g., the removal proportion is
Figure 245354DEST_PATH_IMAGE122
Correspondingly, another sign subnetwork
Figure 588611DEST_PATH_IMAGE078
The disease subnetwork will not be affected by cascade in the first cascade stage
Figure 417895DEST_PATH_IMAGE033
Remaining effective node proportion
Figure 162997DEST_PATH_IMAGE082
Will decide the current disease sub-network
Figure 927691DEST_PATH_IMAGE031
Sign and sign sub-network
Figure 23823DEST_PATH_IMAGE078
Connectivity of two physiological networks formed, in which case the effective edge probability
Figure DEST_PATH_IMAGE123
Whereby said physical sign subnetwork
Figure 141952DEST_PATH_IMAGE078
And cascading according to the initial failure set.
Referring to FIG. 1, the present embodiment utilizes the above described deep cascading framework for ICU mortality prediction, in which cascading failures are in sign sub-networks
Figure 7140DEST_PATH_IMAGE006
Initially, at this point, an initial failure set is entered, which includes abnormalities in the signs corresponding to the patient examinationIs determined, whereby the initial failed node passes through the sign subnetwork
Figure 942735DEST_PATH_IMAGE006
Degree distribution unit and excess distribution unit to obtain maximum failure risknEach node updates the failure set to obtain the effective edge probability representing the connectivity of the network at the next stage, and the failure set and the effective edge probability are used as the second cascade of the whole deep cascade framework, namely the disease subnetwork
Figure 995004DEST_PATH_IMAGE031
The first cascade of input, disease subnetworks
Figure 431671DEST_PATH_IMAGE033
Cascading is also performed according to the input to obtain a failure set and effective edge probability for the next cascading stage, so that the failure set and the effective edge probability are input into the sign sub-network again
Figure 151365DEST_PATH_IMAGE006
To perform the physical sign sub-network
Figure 257861DEST_PATH_IMAGE006
Thereby carrying out sign subnetwork
Figure 797427DEST_PATH_IMAGE006
And disease sub-networks
Figure 522938DEST_PATH_IMAGE031
And, during the cascade, sign subnetworks
Figure 97138DEST_PATH_IMAGE006
And disease sub-network
Figure 374536DEST_PATH_IMAGE033
The failure distributions are output in their respective cascade stages as outputs of a deep cascade framework, in particular, in fig. 1, the sign subnetwork
Figure 666977DEST_PATH_IMAGE006
First cascade output failure distribution
Figure 179867DEST_PATH_IMAGE124
And sign subnetwork
Figure 874153DEST_PATH_IMAGE006
And disease sub-network
Figure 322452DEST_PATH_IMAGE033
Are all carried outlFailure distribution of output after secondary cascade
Figure DEST_PATH_IMAGE125
And
Figure 508714DEST_PATH_IMAGE126
and with disease subnetworks
Figure 638344DEST_PATH_IMAGE031
Cascade connectionnFailure distribution of output at sub-end
Figure DEST_PATH_IMAGE127
Due to physical signs subnetwork
Figure 983875DEST_PATH_IMAGE006
And disease sub-network
Figure 462129DEST_PATH_IMAGE031
Alternately cascaded, the cascaded outputs of each stage are also input into the serialized neural network as a whole, corresponding to the serialized neural network in FIG. 1h1…h2l-1、h2l…h2nThe input of each stage is processed by a serialized neural network, and the final hidden state can obtain the result of ICU mortality prediction by a classifier.
When the disease diagnosis type is used as the examination type, the disease diagnosis type is used as the initial failure set, i.e., the diagnosis type is used as the initial failure set
Figure 729163DEST_PATH_IMAGE128
Correspondingly, when the sign inspection type is taken as the inspection type, the abnormal item of the sign inspection type can be taken as an initial failure set.
In the cascade process, disease subnetworks
Figure 724801DEST_PATH_IMAGE031
And sign subnetwork
Figure 128100DEST_PATH_IMAGE074
Output failure distribution
Figure 793568DEST_PATH_IMAGE126
And
Figure 282318DEST_PATH_IMAGE129
in which the failure distribution is determined by the effective probability of all nodes in the cascade stage
Figure DEST_PATH_IMAGE130
Is normalized based on the disease sub-network
Figure 816067DEST_PATH_IMAGE033
Sign and sign sub-network
Figure 260824DEST_PATH_IMAGE074
Cascaded in sequence, failure distribution
Figure 159510DEST_PATH_IMAGE131
And
Figure 197873DEST_PATH_IMAGE096
referring to fig. 1, that is, in the input serialized neural network, the serialized model may use transform, LSTM, or GRU, and when the number of cascading times reaches a set threshold or no node fails, it indicates that the cascading is finished, and when the cascading is finished, the last hidden state of the serialized model may pass through a classifier, such as a softmax classifier, so as to obtain the patient suffering from the diseaseICU mortality prediction in the subject.
In an alternative embodiment of the present invention, the ICU mortality prediction method further comprises:
generating importance weights through the graph attention network;
determining the effective probability of each node of each cascade stage during cascade connection according to the importance weight;
normalizing the effective probabilities of all nodes in the cascade stage to generate the failure distribution.
Referring to fig. 1, in the present embodiment, importance weights are generated by the graph attention network to generate personalized tolerance distributions for each node, as in fig. 1, with sign sub-networks
Figure 145101DEST_PATH_IMAGE078
The cascade is started, and the sign sub-network
Figure 257413DEST_PATH_IMAGE078
Performing various stages of the cascade, the graph attention network each generating weights for generating individualized tolerance distributions with tolerance coefficients
Figure 858159DEST_PATH_IMAGE132
In the disease subnetwork
Figure 852660DEST_PATH_IMAGE031
In each stage of the cascade, the graph attention network generates weights for generating personalized tolerance distributions with tolerance coefficients
Figure 118425DEST_PATH_IMAGE133
Thus, to physical sign sub-network
Figure 85244DEST_PATH_IMAGE078
And disease sub-network
Figure 653628DEST_PATH_IMAGE031
The determination of the effective probabilities of the nodes of (A) each have a corresponding tolerance coefficient, e.g.Figure 1 shows a sign subnetwork
Figure 338687DEST_PATH_IMAGE078
No. 1 …lSub-cascaded stages, each having a tolerance factor
Figure 893297DEST_PATH_IMAGE134
…
Figure 980201DEST_PATH_IMAGE135
Etc., and a disease sub-network as shown in figure 1
Figure 719487DEST_PATH_IMAGE031
To (1) al…nSub-cascaded stages, each having a tolerance factor
Figure 891843DEST_PATH_IMAGE136
…
Figure 499410DEST_PATH_IMAGE137
Etc. it should be noted that, in fig. 1, the sub-network is due to physical signs
Figure 440822DEST_PATH_IMAGE078
And disease sub-network
Figure 351009DEST_PATH_IMAGE033
Alternatively cascaded, thus in a sign subnetwork
Figure 276239DEST_PATH_IMAGE078
Figure 276239DEST_PATH_IMAGE078
1 st 1 …lBetween the secondary cascade stages, there is also a 1 st 1 … not shown in fig. 1lSub-disease sub-network
Figure 234968DEST_PATH_IMAGE031
Corresponding to the 1 st 1 … not shown in fig. 1lSub-disease sub-network
Figure 234148DEST_PATH_IMAGE033
Has tolerance coefficients corresponding to the cascade stages of (2), and in addition, in a disease subnetwork
Figure 987341DEST_PATH_IMAGE031
To (1) al…nBetween the secondary cascade stages, there is also a second stage which is not shown in FIG. 1l…nSub-sign sub-network
Figure 196605DEST_PATH_IMAGE078
While also corresponding to the second stage not shown in fig. 1l…nSub-sign sub-network
Figure 959025DEST_PATH_IMAGE078
The tolerance coefficient of the tolerance distribution is converted from simple quantitative statistics to the node
Figure 813978DEST_PATH_IMAGE138
Thereby more accurately confirming the failure risk of the sub-network.
The present invention also provides a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the following steps:
acquiring an examination type of a patient, wherein the examination type comprises a disease type of the patient or an abnormal sign type in signs of examination of the patient;
generating an initial failure set according to the inspection type;
inputting the initial failure set into a deep cascading framework for ICU mortality prediction as described above for cascading;
sequentially inputting failure distribution output by each cascading stage during cascading into a serialization model;
and obtaining the mortality prediction result of the patient according to the last hidden state of the serialization model at the end of the cascade.
In an alternative embodiment of the present invention, when the processor executes the computer program, the processor is further configured to implement the following steps:
generating importance weights through the graph attention network;
determining the effective probability of each node of each cascade stage during cascade connection according to the importance weight;
normalizing the effective probabilities of all nodes in the cascade stage to generate the failure distribution.
The computing device of this embodiment is similar to the above-described deep cascading framework for ICU mortality prediction in comparison with the prior art, and will not be described herein again.
A computer-readable storage medium of another embodiment of the invention, having a computer program stored thereon, which, when executed by a processor, performs the steps of:
acquiring an examination type of a patient, wherein the examination type comprises a disease type of the patient or an abnormal sign type in signs of examination of the patient;
generating an initial failure set according to the inspection type;
inputting the initial failure set into a deep cascading framework for ICU mortality prediction as described above for cascading;
sequentially inputting failure distribution output by each cascading stage during cascading into a serialization model;
and obtaining the mortality prediction result of the patient according to the last hidden state of the serialization model at the end of the cascade.
In an alternative embodiment of the invention, the computer program, when executed by the processor, is further adapted to perform the steps of:
generating importance weights by the graph attention network;
determining the effective probability of each node of each cascade stage during cascade connection according to the importance weight;
normalizing the effective probabilities of all nodes in the cascade stage to generate the failure distribution.
The advantages of the computer-readable storage medium of this embodiment over the prior art are similar to the above-described deep cascading framework for ICU mortality prediction, and are not described herein again.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the disclosure, and it is intended that all such changes and modifications fall within the scope of the invention.

Claims (13)

1. A deep cascade framework for ICU mortality prediction comprising: the sign sub-network and the disease sub-network are connected in a cascade mode according to node failure conditions, and the sign sub-network and the disease sub-network are both used for outputting failure distribution so as to conduct ICU mortality prediction through the failure distribution;
the sign sub-network and the disease sub-network both comprise a degree distribution unit and a super degree distribution unit, the degree distribution unit comprises a degree distribution generating function, the super degree distribution unit comprises a super degree distribution generating function, and the recursive relation of the deep cascade framework comprises:
Figure DEST_PATH_IMAGE002
，
Figure DEST_PATH_IMAGE004
represents the effective node ratio, inlIn the secondary cascade, the effective node proportions of the disease sub-network and the sign sub-network are respectively as follows:
Figure DEST_PATH_IMAGE006
(ii) a Or the like, or, alternatively,
Figure DEST_PATH_IMAGE008
in the first placelIn the secondary cascade, the effective node proportions of the sign sub-network and the disease sub-network are respectively as follows:
Figure DEST_PATH_IMAGE010
；
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE012
a sub-network of diseases is represented,
Figure DEST_PATH_IMAGE014
a sub-network of physical signs is represented,
Figure DEST_PATH_IMAGE016
and
Figure DEST_PATH_IMAGE018
a degree distribution generating function representing the disease sub-network and the signs sub-network respectively,
Figure DEST_PATH_IMAGE020
and
Figure DEST_PATH_IMAGE022
a hyperdynamic distribution generating function representing the disease sub-network and the signs sub-network respectively,lthe number of cascades is indicated,
Figure DEST_PATH_IMAGE024
represents the number of cascades asl-1 an overarching distribution generation function of the sub-network of signs,
Figure DEST_PATH_IMAGE026
represents the number of cascades asl-1 a hyperdistribution generating function of the disease sub-network,
Figure DEST_PATH_IMAGE028
represents the number of cascades aslGenerating a function of the hyperdistribution of the disease sub-network,
Figure DEST_PATH_IMAGE030
represents the number of cascades aslThe superscale distribution of sign sub-networks of (a) to (b) generate a function,
Figure DEST_PATH_IMAGE032
represents the number of cascades aslA function is generated of the degree distribution of the disease sub-network,
Figure DEST_PATH_IMAGE034
represents the number of cascades aslThe degree distribution of the sign sub-network of (1) generates a function,
Figure DEST_PATH_IMAGE036
the probability of a valid edge is represented,
Figure DEST_PATH_IMAGE038
represents the number of cascades aslOf the disease sub-network,
Figure DEST_PATH_IMAGE040
represents the number of cascades aslThe effective edge probability of the sign subnetwork.
2. The deep cascading framework for ICU mortality prediction of claim 1, wherein the node failure condition comprises a failure set comprising pre-stage failures with the greatest risk in cascading stagesnAnd (4) each node.
3. The deep cascading framework for ICU mortality prediction of claim 2, wherein the node failure condition further comprises network connectivity comprising effective edge probabilities of the interacting edges, the effective edge probabilities representing a probability of randomly selecting an interacting edge and connecting two effective nodes, the effective edge probabilities generated in a current cascading stage being used to update the effective edge probabilities in a next cascading stage.
4. The deep cascading framework for ICU mortality prediction of claim 3, wherein the sign sub-network and the disease sub-network each determine the failure set through a degree distribution unit, the sign sub-network and the disease sub-network each determine a valid edge probability of a next cascade stage according to a valid edge probability of a current cascade stage through a super degree distribution unit.
5. The deep cascading framework for ICU mortality prediction according to any of claims 2-4, wherein the sign subnetwork and the disease subnetwork each determine the failure distribution by an effective probability of a node, wherein the failure distribution of a current cascade stage is generated by normalizing the effective probabilities of all nodes of the cascade stage.
6. The deep cascading framework for ICU mortality prediction of claim 5, wherein in the signs subnetwork and the diseases subnetwork, the significance probability of the node is determined according to the number of failed nodes in each neighborhood of nodes, wherein the failure set generated in the current cascading stage is used to update the number of failed nodes in each neighborhood of nodes in the next cascading stage.
7. The deep cascading framework for ICU mortality prediction of claim 6, wherein the effective probability of the node is calculated by:
Figure DEST_PATH_IMAGE042
；
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE044
a node is represented by a plurality of nodes,mrepresenting the number of failed nodes in the neighborhood of nodes,
Figure DEST_PATH_IMAGE046
which represents the number of neighbors of the node,
Figure DEST_PATH_IMAGE048
indicating the number of valid neighbors of the node,
Figure DEST_PATH_IMAGE050
it is shown that the distribution is tolerated,
Figure DEST_PATH_IMAGE052
which represents the tolerance factor of the current signal,Xrepresenting the signs subnetwork or the diseases subnetwork.
8. The deep cascade framework for ICU mortality prediction of claim 7, wherein each node of the signs sub-network and the diseases sub-network has a personalized tolerance distribution
Figure 158749DEST_PATH_IMAGE050
Wherein:
Figure DEST_PATH_IMAGE054
Figure DEST_PATH_IMAGE056
；
the tolerance coefficient is calculated by the formula:
Figure DEST_PATH_IMAGE058
；
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE060
representing the importance of a node's neighbors to the nodeAnd (4) weighting.
9. A deep cascading framework for ICU mortality prediction according to any of claims 1-4, wherein in the signs sub-network and the diseases sub-network, a node is active when the number of nodes connecting active nodes is greater than or equal to a first preset number, and otherwise the node is inactive.
10. A computing device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring an examination type of a patient, wherein the examination type comprises a disease type of the patient or an abnormal sign type in signs of examination of the patient;
generating an initial failure set according to the inspection type;
cascading said initial failure set into the deep cascading framework for ICU mortality prediction of any of claims 1-9;
sequentially inputting failure distribution output by each cascading stage during cascading into a serialization model;
and obtaining the mortality prediction result of the patient according to the last hidden state of the serialization model at the end of the cascade.
11. The computing device of claim 10, wherein the processor, when executing the computer program, is further configured to:
generating importance weights through the graph attention network;
determining the effective probability of each node of each cascade stage during cascade connection according to the importance weight;
normalizing the effective probabilities of all nodes in the cascade stage to generate the failure distribution.
12. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of:
acquiring an examination type of a patient, wherein the examination type comprises a disease type of the patient or an abnormal sign type in signs of examination of the patient;
generating an initial failure set according to the inspection type;
cascading said initial failure set into the deep cascading framework for ICU mortality prediction of any of claims 1-9;
sequentially inputting failure distribution output by each cascading stage during cascading into a serialization model;
and obtaining the mortality prediction result of the patient according to the last hidden state of the serialization model at the end of the cascade.
13. The computer-readable storage medium according to claim 12, wherein the computer program, when executed by the processor, is further configured to perform the steps of:
generating importance weights by the graph attention network;
determining the effective probability of each node of each cascade stage during cascade connection according to the importance weight;
normalizing the effective probabilities of all nodes in the cascade stage to generate the failure distribution.
CN202011341957.4A 2020-11-25 2020-11-25 Deep cascading framework for ICU mortality prediction Active CN112420201B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011341957.4A CN112420201B (en) 2020-11-25 2020-11-25 Deep cascading framework for ICU mortality prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011341957.4A CN112420201B (en) 2020-11-25 2020-11-25 Deep cascading framework for ICU mortality prediction

Publications (2)

Publication Number Publication Date
CN112420201A CN112420201A (en) 2021-02-26
CN112420201B true CN112420201B (en) 2022-09-30

Family

ID=74843546

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011341957.4A Active CN112420201B (en) 2020-11-25 2020-11-25 Deep cascading framework for ICU mortality prediction

Country Status (1)

Country Link
CN (1) CN112420201B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112967816B (en) * 2021-04-26 2023-08-15 四川大学华西医院 Acute pancreatitis organ failure prediction method, computer equipment and system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106777935A (en) * 2016-12-05 2017-05-31 广东石油化工学院 A kind of disease dynamic prediction method based on network structure
CN107463796B (en) * 2017-07-12 2019-10-18 北京航空航天大学 Early stage virulence factor detection method based on gene co-expressing Internet communication analysis
CN107491638A (en) * 2017-07-28 2017-12-19 深圳和而泰智能控制股份有限公司 A kind of ICU user's prognosis method and terminal device based on deep learning model
CN109119155B (en) * 2018-07-03 2022-01-28 厦门大学 ICU death risk assessment system based on deep learning

Also Published As

Publication number Publication date
CN112420201A (en) 2021-02-26

Similar Documents

Publication Publication Date Title
Sailasya et al. Analyzing the performance of stroke prediction using ML classification algorithms
Haq et al. A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms
Ismaeel et al. Using the Extreme Learning Machine (ELM) technique for heart disease diagnosis
Luengo et al. A study on the use of statistical tests for experimentation with neural networks: Analysis of parametric test conditions and non-parametric tests
Nour et al. Automatic classification of hypertension types based on personal features by machine learning algorithms
Ziasabounchi et al. ANFIS based classification model for heart disease prediction
US11600387B2 (en) Control method and reinforcement learning for medical system
Ranganath et al. Multiple causal inference with latent confounding
Ribeiro et al. Multi-step ahead meningitis case forecasting based on decomposition and multi-objective optimization methods
WO2011060314A1 (en) Method and system for optimal estimation in medical diagnosis
Anouncia et al. Design of a diabetic diagnosis system using rough sets
CN112420201B (en) Deep cascading framework for ICU mortality prediction
Azar et al. Linguistic hedges fuzzy feature selection for differential diagnosis of Erythemato-Squamous diseases
Santhanam et al. Machine learning and blood pressure
Jahangir et al. Auto-MeDiSine: an auto-tunable medical decision support engine using an automated class outlier detection method and AutoMLP
Fatemidokht et al. Development of a hybrid neuro-fuzzy system as a diagnostic tool for Type 2 Diabetes Mellitus
Roversi et al. A Dynamic Bayesian Network model for simulating the progression to diabetes onset in the ageing population
Prasad et al. Chronic Kidney Disease Risk Prediction Using Machine Learning Techniques
Qiu et al. HFS‐LightGBM: A machine learning model based on hybrid feature selection for classifying ICU patient readmissions
Kubus et al. The use of fuzzy cognitive maps in evaluation of prognosis of chronic heart failure patients
Karahoca et al. Diagnosis of diabetes by using adaptive neuro fuzzy inference systems
Muibideen et al. A Fast Algorithm for Heart Disease Prediction using Bayesian Network Model
Abdellatif et al. Computational detection and interpretation of heart disease based on conditional variational auto-encoder and stacked ensemble-learning framework
WO2021196239A1 (en) Network representation learning algorithm across medical data sources
Nisha et al. Interpretable Machine Learning Models for Assisting Clinicians in the Analysis of Physiological Data.

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
TR01 Transfer of patent right

Effective date of registration: 20230918

Address after: Building 1, Kechuang headquarters, Shenzhen (Harbin) Industrial Park, 288 Zhigu street, Songbei District, Harbin City, Heilongjiang Province

Patentee after: Harbin Institute of Technology Institute of artificial intelligence Co.,Ltd.

Address before: 150001 No. 92 West straight street, Nangang District, Heilongjiang, Harbin

Patentee before: HARBIN INSTITUTE OF TECHNOLOGY

TR01 Transfer of patent right