CN-122000053-A - Network analysis and risk identification method for emotion trouble of gynecological cancer patient

CN122000053ACN 122000053 ACN122000053 ACN 122000053ACN-122000053-A

Abstract

The invention provides a network analysis and risk identification method for emotion trouble of a gynecological cancer patient, which comprises the following steps of S1, collecting emotion symptom data and psychosocial variable data from a plurality of gynecological cancer patients, S2, constructing an expanded Gaussian graph model network comprising emotion symptom nodes and psychosocial variable nodes, wherein the emotion symptom nodes are selected based on a brief version of a concise mood state table, and the psychosocial variable at least comprises a nerve and the like, S3, calculating and analyzing centrality indexes, bridge indexes and the like of each node in the network.

Inventors

HUANG HAOWEN
XIA LING

Assignees

黄昊雯

Dates

Publication Date: 20260508
Application Date: 20260121

Claims (8)

1. A network analysis and risk identification method for mood trouble of a gynecological cancer patient, comprising the steps of: step S1, collecting emotion symptom data and psychosocial variable data from a plurality of gynecological cancer patients; Step S2, an extended Gaussian graph model network comprising emotion symptom nodes and psychosocial variable nodes is constructed, wherein the emotion symptom nodes are selected based on simple version of a concise mood state table, and the psychosocial variables at least comprise nerves, self-perception burden, disease cognition, economic toxicity and psychological capital; Step S3, calculating and analyzing the centrality index and the bridge index of each node in the network to identify the core emotion symptoms and key psychology social cut points in the network; and S4, generating an identification report for individuation psychosocial risk assessment and intervention strategy formulation based on the core emotion symptoms and the key psychosocial cut points.
2. The network analysis and risk identification method of mood plagues in a gynaecological cancer patient according to claim 1, wherein the mood symptom data comprises specific item scores in five dimensions of tension-anxiety, depression-depression, anger-hostility, fatigue-burnout and confusion-confused, and the psychosocial variable data is obtained as a total score by a corresponding standardized scale.
3. The network analysis and risk recognition method for mood troubles of gynecological cancer patients according to claim 1, wherein when the expanded Gaussian diagram model network is constructed, a EBICglasso regularization method is adopted to estimate the partial correlation coefficient between nodes to form a network edge, and a non-parametric self-service method is used to evaluate the accuracy of the network edge and the stability of the node centrality index.
4. The method of claim 1, wherein the step of identifying the mood symptom comprises calculating the intensity centrality and expected impact centrality of nodes, and identifying the mood symptom node with the highest centrality index as the core node of the mood symptom maintaining network.
5. The method of claim 1, wherein identifying key psychosocial cut-in points comprises calculating bridge intensity and expected influence of the nodes, and identifying the psychosocial variable node with the highest bridge centrality index as the key bridge node connecting the external stress source and the internal emotion symptom network.
6. The network analysis and risk recognition method for mood troubles of gynecological cancer patients according to claim 1, wherein prior to constructing a network model, the collected continuous variable data is subjected to non-parametric normal conversion based on rank, and mood symptom data is subjected to regression analysis on demographics and clinical covariates to obtain residual, and a residual symptom network after controlling covariates is constructed based on the residual.
7. The method for analyzing and identifying the risk of the mood disorder of a patient with gynecological cancer according to claim 1, further comprising the step of comparing the network by dividing the patient into a high risk group and a low risk group according to the median of at least one psychosocial variable, respectively constructing symptom networks thereof, and analyzing the difference between the two groups in the overall strength of the network and the network structure by using a network comparison test method.
8. The method of claim 1, wherein generating the identification report includes listing the identified core emotional symptoms and their connection patterns in the network, indicating key psychosocial cut-in points and their strength of association with specific emotional symptoms, and recommending targeted hierarchical psychological interventions or care strategies accordingly.

Description

Network analysis and risk identification method for emotion trouble of gynecological cancer patient Technical Field The invention relates to the technical field of mental health assessment, in particular to a network analysis and risk identification method for emotion disturbance of a gynecological cancer patient. Background Gynaecological cancer is an important threat to global female health, and its course of treatment is often accompanied by significant emotional distress, such as anxiety, depression, fatigue, etc. These emotional symptoms not only affect the quality of life of the patient, but may also reduce treatment compliance, worsening clinical prognosis. At present, standardized questionnaire total score or sub-scale score is mostly adopted in clinical practice to evaluate emotional trouble, and although the method is simple and convenient, the dynamic association between symptoms cannot be revealed, and it is difficult to identify which symptoms play a key role in maintaining emotional trouble network. Psychological-social factors such as nervous matter, self-perceived burden, economic toxicity, etc. have interacted with emotional symptoms, and there is no systematic, fine-grained analysis. Disclosure of Invention In view of this, the present invention proposes a network analysis and risk identification method for mood disturbance of gynecological cancer patients in order to solve the problems existing in the technical background. The method specifically comprises the following steps: A network analysis and risk identification method for mood trouble of a gynecological cancer patient, comprising the following steps: step S1, collecting emotion symptom data and psychosocial variable data from a plurality of gynecological cancer patients; Step S2, an extended Gaussian graph model network comprising emotion symptom nodes and psychosocial variable nodes is constructed, wherein the emotion symptom nodes are selected based on simple version of a concise mood state table, and the psychosocial variables at least comprise nerves, self-perception burden, disease cognition, economic toxicity and psychological capital; Step S3, calculating and analyzing the centrality index and the bridge index of each node in the network to identify the core emotion symptoms and key psychology social cut points in the network; and S4, generating an identification report for individuation psychosocial risk assessment and intervention strategy formulation based on the core emotion symptoms and the key psychosocial cut points. In one embodiment of the invention, the mood symptom data includes specific item scores in five dimensions of tension-anxiety, depression-depression, anger-hostility, fatigue-burnout, and confusion-confused, and the psychosocial variable data is given a total score by a corresponding standardized scale. In one embodiment of the invention, when the extended Gaussian graph model network is constructed, a EBICglasso regularization method is adopted to estimate the partial correlation coefficient between nodes to form a network edge, and a non-parametric self-service method is used to evaluate the accuracy of the network edge and the stability of the node centrality index. In one embodiment of the invention, the process of identifying a core emotional symptom includes calculating the intensity centrality and expected impact centrality of the nodes, identifying the emotional symptom node with the highest centrality index as the core node of the maintained emotion puzzlement network. In one embodiment of the invention, the process of identifying key psychosocial cut-in points includes calculating bridge intensity and expected bridge impact of the nodes, identifying the psychosocial variable node with the highest bridge centrality index as the key bridge node connecting the external stress source with the internal emotional symptom network. In one embodiment of the invention, prior to constructing the network model, the collected continuous variable data is subjected to non-parametric normal conversion based on rank, and the emotional symptom data is subjected to regression analysis on demographics and clinical covariates to obtain residual errors, and a residual symptom network after controlling covariates is constructed based on the residual errors. In one embodiment of the present invention, the method further comprises a network comparison step of dividing the patient into a high risk group and a low risk group according to the median of at least one psycho-social variable, constructing symptom networks thereof respectively, and analyzing the difference between the two groups in terms of overall network strength and network structure using a network comparison test method. In one embodiment of the invention, the generation of the identification report includes listing the identified core emotional symptoms and their connection patterns in the network, indicating key psychosocial cut-in points and their stre