A palliative care intervention method for hematologic malignancies based on potential profile analysis

Abstract

This invention discloses a method for palliative care intervention in hematologic malignancies based on potential profile analysis, belonging to the field of medical and health information analysis technology. The method includes the following steps: S1, constructing a multidimensional intervention feature dataset; S2, constructing a profile analysis model based on the feature dataset; S3, verifying the stability of categories based on the profile analysis results; S4, selecting intervention reference templates based on the stability verification results; S5, matching individual characteristics with the intervention reference templates to form a preset intervention path; and S6, using the preset intervention path to construct a profile-driven path execution and feedback control system. By setting a profile response function modeling model and combining it with a multi-intervention feature matrix to construct a high-resolution profile function, this method effectively solves the problem of insufficient ability of existing profile partitioning models to handle continuous variables, improves the expressive power of profile structure and the accuracy of individual heterogeneity characterization, and is suitable for the fine-grained hierarchical modeling needs driven by multidimensional intervention features.

Description

Technical Field

[0001] This invention relates to the field of medical and health information analysis technology, specifically to a method for palliative care intervention for hematologic malignancies based on potential profile analysis. Background Technology

[0002] With the increasing duration of disease progression and the growing demand for palliative care among patients with hematological malignancies, developing targeted interventions based on individual differences has become an important research direction. Traditional intervention pathways are mostly based on standardized procedures tailored to patients' overt characteristics, failing to fully identify the potential heterogeneity in intervention responses and needs among patient groups, resulting in significant differences in intervention efficacy.

[0003] 1. In the existing technology, existing models are usually based on classification features, ignoring the subtle changes and synergistic relationships of intervention features at continuous scales. The profile layering granularity is coarse and cannot meet the requirements of high-resolution intervention modeling. 2. In the existing technology, the current profile verification method cannot effectively reflect whether the profile has behavioral stability and intervention response consistency during the execution of the intervention path. It lacks a structured profile response function model, which affects the usability and decision support value of the profile in the actual intervention path. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method for palliative care intervention for hematologic malignancies based on potential profile analysis, in order to solve the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a method for palliative care intervention for hematologic malignancies based on potential profile analysis, comprising the following steps: S1. Construct a multidimensional intervention feature dataset; S2. Construct a profile analysis model based on the feature dataset; S3. Verify the stability of the category based on the profile analysis results; S4. Select intervention reference templates based on stability verification results; S5. Based on the intervention reference template, match individual characteristics to form a pre-set intervention path; S6. Construct a profile-driven path execution and feedback control system using intervention preset paths.

[0006] To further optimize this technical solution, the feature dataset in step S1 is represented by a standardized intervention feature matrix, which is: : ; in Indicates the first The patient in Numerical values ​​on each intervention feature dimension; Intervention Feature Set Based on the practice of palliative care for hematological malignancies, it mainly includes the following three categories: Physiological intervention characteristics: pain score, physiological tolerance score, sleep disorder index, data from clinical scales or vital sign monitoring systems; Characteristics of psychological intervention: anxiety index and amplitude of mood fluctuations; data are derived from standardized psychological assessment tools. Treatment process indicators: fluctuation coefficient of blood indicators and frequency of complications during the intervention period. Data are derived from laboratory test results and process event records.

[0007] To further optimize this technical solution, in step S1, all intervention features are Z-score standardized using a standardized formula to eliminate bias caused by differences in the numerical scale of the dependent variable itself. ; in, : No. The first patient One original intervention feature value; : No. The mean of each intervention feature across all patients; : No. The standard deviation of each intervention feature.

[0008] To further optimize this technical solution, in step S1, the intervention variables with discrete characteristics or discontinuous distributions are transformed using an isomorphic transformation mechanism, employing the discrete variable continuous mapping formula: ; The slope parameter of the mapping function reflects the sensitivity of the variable; The mapping center point is set based on clinical assessment thresholds.

[0009] To further optimize this technical solution, the profile analysis model constructed in step S2 adopts a cointegration mapping latent profile modeling mechanism, and its profile cointegration mapping model is as follows: ; in, : No. The first potential profile The mean of the basic profile of each feature; : No. The first cross-section The variable for the first The response coefficients of each cointegrated mapping function; :profile The Each cointegration mapping function reflects the nonlinear structural relationship between features; :profile Inner Individual residuals of variables.

[0010] To further optimize this technical solution, the cointegration mapping function... For standard feature set The nonlinear structure mapping function, used to identify the interaction mechanism of latent variables within the profile, is defined as follows: ; in, For the first The cointegration function in the first profile Item to the first The response factor of each variable.

[0011] To further optimize this technical solution, the profile analysis model includes the following steps when in use: Initialize the number of profiles Set the initial number of profiles; Estimated profile parameters In fixed In this case, perform minimum residual fitting on all samples, using the minimum objective function: ; Profile attribution determination: Each individual Substitute the values ​​into the profile models, calculate the sum of squared residuals, and assign it to the profile with the smallest residual. ; Output profile structure information: Output the mean vector for each profile. Mapping response coefficients Cointegration function parameters .

[0012] To further optimize this technical solution, in step S3, based on the profile modeling mechanism of step S2, the profile mapping function is obtained: ; The profile classification is based on the maximum response. Corresponding value; The profile response deviation function is introduced for disturbance response analysis, with the initial input being... Considering patient characteristic perturbations ,in For the first The magnitude of the disturbance of each intervention feature: ; Further response bias function: ; in, This is the original profile response value; This function reflects the first under the intervention feature perturbation. The patient in The degree of response change under the cross-section.

[0013] To further optimize this technical solution, in step S3, an innovative profile stability index function is used to represent the classification stability of patients under multi-profile response bias: ; in, : indicates the patient The profile category to which it belongs when there is no disturbance, i.e., the largest Corresponding ; : Represents the space of intervention and perturbation, each dimension , The permissible disturbance range; : Represents the minimum response difference between the profile classification and the suboptimal profile under the worst perturbation condition; when This indicates that regardless of the disturbance, the patient remained stably classified into the profile. It possesses cross-sectional stability; when This indicates that the profile classification results are volatile; when , indicating a critical classification, sensitive to profile assignment, and prone to instability.

[0014] To further optimize this technical solution, the simultaneous use of the model in step S3 includes: Constructing a Disturbance Space: For Each Patient This generates a perturbation space. Random perturbation, gradient perturbation, or system perturbation path can be used; Calculate the profile deviation function: for each profile after disturbance Recalculate ,structure ; Output stability value Assess the profile stability of each patient; Statistical distribution analysis: Further analysis of the entire population is possible. The distribution is used to identify unstable regions in the profile model, which serve as input conditions for step S4.

[0015] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of a hematologic malignancy palliative care intervention method based on potential profile analysis as described in the first aspect of the present invention.

[0016] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a method for palliative care intervention for hematologic malignancies based on potential profile analysis as described in the first aspect of the present invention.

[0017] Compared with existing technologies, this invention provides a method for palliative care intervention for hematologic malignancies based on potential profile analysis, which has the following beneficial effects: This intervention method for palliative care in hematological malignancies based on potential profile analysis effectively addresses the shortcomings of existing profile segmentation models in handling continuous variables by setting up a profile response function model and constructing a high-resolution profile function in conjunction with a multi-intervention feature matrix. It enhances the expressive power of profile structure and the accuracy of individual heterogeneity characterization, making it suitable for the fine-grained hierarchical modeling needs driven by multi-dimensional intervention features. Furthermore, the introduction of a profile behavior response function and a profile intervention feedback offset function forms a measurable and adjustable profile stability assessment mechanism, resolving the lack of profile stability response feedback in existing validation methods. This provides stability support for the construction of the path execution system, improving the continuous effectiveness of the profile-adapted path and the closed-loop control capability of the intervention feedback. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the structure of a palliative care intervention method for hematologic malignancies based on potential profile analysis proposed in this invention; Figure 2 This is a schematic diagram of the profile analysis process for a palliative care intervention method for hematologic malignancies based on potential profile analysis proposed in this invention. Figure 3 This is a schematic diagram of the category stability verification process for a hematologic malignancy palliative care intervention method based on potential profile analysis proposed in this invention. Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments. Example 1

[0023] Reference Figures 1-3 This is the first embodiment of the present invention, which provides a method for palliative care intervention for hematologic malignancies based on potential profile analysis, including the following steps: S1. Construct a multidimensional intervention feature dataset; In step S1, the feature dataset is represented by a standardized intervention feature matrix, which is: : ; in Indicates the first The patient in Numerical values ​​on each intervention feature dimension; Intervention Feature Set Based on the practice of palliative care for hematological malignancies, it mainly includes the following three categories: Physiological intervention characteristics: pain score, physiological tolerance score, sleep disorder index, data from clinical scales or vital sign monitoring systems; Characteristics of psychological intervention: anxiety index and amplitude of mood fluctuations; data are derived from standardized psychological assessment tools. Treatment process indicators: fluctuation coefficient of blood indicators and frequency of complications during the intervention period. Data are derived from laboratory test results and process event records. In step S1, all intervention features are Z-score standardized using a standardization formula to eliminate bias caused by differences in the numerical scale of the dependent variable itself. ; in, : No. The first patient One original intervention feature value; : No. The mean of each intervention feature across all patients; : No. Standard deviation of each intervention feature; In step S1, the intervention variables with discrete characteristics or discontinuous distributions are transformed using an isomorphic transformation mechanism, employing the continuous mapping formula for discrete variables: ; The slope parameter of the mapping function reflects the sensitivity of the variable; The mapping center point is set based on clinical assessment thresholds.

[0024] S2. Construct a profile analysis model based on the feature dataset; In step S2, the profile analysis model is constructed using a cointegration mapping latent profile modeling mechanism, and its profile cointegration mapping model is as follows: ; in, : No. The first potential profile The mean of the basic profile of each feature; : No. The first cross-section The variable for the first The response coefficients of each cointegrated mapping function; :profile The Each cointegration mapping function reflects the nonlinear structural relationship between features; :profile Inner Individual residuals of the variable; The cointegration mapping function For standard feature set The nonlinear structure mapping function, used to identify the interaction mechanism of latent variables within the profile, is defined as follows: ; in, For the first The cointegration function in the first profile Item to the first Response factors for each variable; The profile analysis model includes the following steps when used: Initialize the number of profiles Set the initial number of profiles; Estimated profile parameters In fixed In this case, perform minimum residual fitting on all samples, using the minimum objective function: ; Profile attribution determination: Each individual Substitute the values ​​into the profile models, calculate the sum of squared residuals, and assign it to the profile with the smallest residual. ; Output profile structure information: Output the mean vector for each profile. Mapping response coefficients Cointegration function parameters ; S3. Verify the stability of the category based on the profile analysis results; In step S3, the profile mapping function is obtained based on the profile modeling mechanism of step S2: ; The profile classification is based on the maximum response. Corresponding value; The profile response deviation function is introduced for disturbance response analysis, with the initial input being... Considering patient characteristic perturbations ,in For the first The magnitude of the disturbance of each intervention feature: ; Further response bias function: ; in, This is the original profile response value; This function reflects the first under the intervention feature perturbation. The patient in The degree of response change under the cross-section; In step S3, an innovative profile stability index function is used to represent the patient's classification stability under multi-profile response bias: ; in, : indicates the patient The profile category to which it belongs when there is no disturbance, i.e., the largest Corresponding ; : Represents the space of intervention and perturbation, each dimension , The permissible disturbance range; : Represents the minimum response difference between the profile classification and the suboptimal profile under the worst perturbation condition; when This indicates that regardless of the disturbance, the patient remained stably classified into the profile. It possesses cross-sectional stability; when This indicates that the profile classification results are volatile; when , indicating a critical classification, sensitive to profile assignment, and prone to instability; The simultaneous use of the model in step S3 includes: Constructing a Disturbance Space: For Each Patient This generates a perturbation space. Random perturbation, gradient perturbation, or system perturbation path can be used; Calculate the profile deviation function: for each profile after disturbance Recalculate ,structure ; Output stability value Assess the profile stability of each patient; Statistical distribution analysis: Further analysis of the entire population is possible. The distribution is used to identify unstable regions in the profile model, which serve as input conditions for step S4.

[0025] S4. Select intervention reference templates based on stability verification results; After completing the profile stability assessment, this step selects highly stable profiles based on the mean scores in the consistency factor matrix, which serve as the standard intervention reference category. These reference profiles are used to establish the structural baseline for intervention implementation and are not further modeled; instead, the profile mean vector and the key value ranges for each indicator are saved in a parameter table format for subsequent intervention parameter matching and pathway development.

[0026] S5. Based on the intervention reference template, match individual characteristics to form a pre-set intervention path; Based on the profile reconstruction results, establish a profile intervention path matrix. , indicating the first The first section in the Pre-defined intervention paths for each intervention stage.

[0027] S6. Construct a profile-driven path execution and feedback control system using intervention preset paths; In this step, a response feedback offset control system is constructed to dynamically assess the degree of deviation between the execution path and the patient's actual state, and to fine-tune the path accordingly, thereby achieving closed-loop execution control of the path. Construct the response feedback offset function: ; in, : This is a nonlinear response offset function used to reflect the sensitivity to offset. ; : No. The patient in Phase 1 The actual response of each intervention feature; : The first in the corresponding profile path The intervention feature in the first Preset values ​​for the stage (from S5); : indicates that the patient was on the Overall offset response of the stage; Constructing dynamic path adjustment functions: ; in, Path feedback adjustment rate (set by path fault tolerance); : Mean offset direction estimation term based on patient population: ; : No. Patient assembly in cross-section; The number of patients in this cross-section; The adjustment function is then applied to the next stage of path construction, forming a feedback closed-loop execution flow: ; The formulas used in this step include: Path execution phase The system is based on Intervention; Response feedback collection: Obtaining the true response of each patient. ; Offset function calculation: obtained Assess the degree of execution deviation; Path calibration judgment: If the average offset of the population exceeds the threshold, perform path correction; Path adjustment execution: Constructing the next stage path This forms a closed-loop control system. Example 2

[0028] Based on Embodiment 1, this embodiment provides a hematologic malignancy palliative care intervention system based on potential profile analysis, including the following modules: Feature quantification module: Corresponding to step S1, it transforms the variable into a standardized intervention variable matrix. This is used for subsequent modeling and analysis; Profile modeling module: Corresponding to step S2, this module constructs a patient profile classification model based on a continuous variable latent profile analysis mechanism. This enables the identification and profile division of the latent structure of the intervention object; Profile stability verification module: corresponding to step S3, based on the profile response function stability verification model. The stability, robustness, and internal consistency of the profile division results are analyzed to provide a basis for profile usability in subsequent path construction. Profile feature extraction module: Corresponding to step S4, this module filters, sorts, and performs differential analysis on key intervention features within each profile, extracting the core vector of the profile intervention features. As the foundation for path construction; Profile path construction module: Corresponding to step S5, construct the profile feature intervention path matrix. Define the execution sequence and target value for each intervention stage to provide a standardized basis for path execution; Path execution and feedback control module: Corresponding to step S6, it uses the feedback response offset function. With dynamic path adjustment function Establish a closed-loop feedback mechanism for path execution to achieve automated adjustment and optimization of the path execution process. Example 3

[0029] This embodiment also provides a computer device applicable to a hematologic malignancy palliative care intervention method based on potential profile analysis, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the hematologic malignancy palliative care intervention method based on potential profile analysis as proposed in the above embodiment.

[0030] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a hematologic malignancy palliative care intervention method based on potential profile analysis as proposed in the above embodiments.

[0031] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0032] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0033] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0034] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0035] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0036] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for palliative care intervention in hematologic malignancies based on potential profile analysis, characterized in that, Includes the following steps: S1. Construct a multidimensional intervention feature dataset; S2. Construct a profile analysis model based on the feature dataset; S3. Perform category stability verification based on the profile analysis results; category stability verification includes obtaining the profile mapping function based on the profile modeling mechanism in step S2: ； The profile classification is based on the maximum response. Corresponding k value; The profile response deviation function is introduced for disturbance response analysis, with the initial input being... x i,j , x i,j This represents the value of the i-th patient on the j-th intervention feature dimension. i =1, 2, ..., n Considering patient characteristic perturbations ,in For the first j The magnitude of the perturbation of each intervention feature: ; Represents the cointegration mapping function. j =1, 2, ..., p ; Further response bias function: ； in, This is the original profile response value; This function reflects the first under the intervention feature perturbation. i The patient in k The degree of response change under the cross-section; It also includes using a profile stability index function to represent the classification stability of patients under multi-profile response bias: ； in, k* : indicates the patient i The profile category to which it belongs when there is no disturbance, i.e., the largest Corresponding k ; : Represents the space of intervention and perturbation, each dimension , The permissible disturbance range; S i : Represents the minimum response difference between the profile classification and the suboptimal profile under the worst perturbation condition; when S i A value greater than 0 indicates that the patient remains stably classified into the profile regardless of any disturbance. k* It possesses cross-sectional stability; when S i <0 indicates that the profile classification results are volatile; when S i =0 indicates a critical classification, which is sensitive to profile assignment and prone to instability; S4. Select intervention reference templates based on stability verification results; S5. Based on the intervention reference template, match individual characteristics to form a pre-set intervention path; S6. Construct a profile-driven path execution and feedback control system using an intervention preset path, and construct a response feedback offset function: ； in, : This is a non-linear response offset function used to reflect the sensitivity to offset. ； : No. i The patient in t Phase 1 j The actual response of each intervention feature; : The first in the corresponding profile path j The intervention feature in the first t Preset values ​​for the stage; : indicates that the patient was on the t Overall offset response of the stage; Reconstruct the dynamic path adjustment function: ； in, η Path feedback regulation rate; : Mean offset direction estimation term based on patient population: ； : No. k Patient assembly in cross-section; n k The number of patients in this cross-section; The adjustment function is applied to the next stage of path construction, forming a feedback closed-loop execution process.

2. The method for palliative care intervention for hematologic malignancies based on potential profile analysis according to claim 1, characterized in that, In step S1, the feature dataset is represented by a standardized intervention feature matrix to obtain a continuous variable feature set. The feature matrix is ​​as follows: ； in x i，j Indicates the first i The patient in j Numerical values ​​on each intervention feature dimension; Intervention Feature Set Based on the practice of palliative care for hematological malignancies, it is determined to include the following three categories: Physiological intervention characteristics: pain score, physiological tolerance score, sleep disorder index, data from clinical scales or vital sign monitoring systems; Characteristics of psychological intervention: anxiety index and amplitude of mood fluctuations; data are derived from standardized psychological assessment tools. Treatment process indicators: fluctuation coefficient of blood indicators and frequency of complications during the intervention period. Data are derived from laboratory test results and process event records.

3. The method for palliative care intervention for hematologic malignancies based on potential profile analysis according to claim 2, characterized in that, In step S1, all intervention features are Z-score standardized using a standardization formula to eliminate bias caused by differences in the numerical scale of the dependent variable itself. ； in, : No. i The first patient j One original intervention feature value; : No. j The mean of each intervention feature across all patients; : No. j The standard deviation of each intervention feature.

4. The method for palliative care intervention for hematologic malignancies based on potential profile analysis according to claim 3, characterized in that, In step S1, the intervention variables with discrete characteristics or discontinuous distributions are transformed using an isomorphic transformation mechanism, employing the continuous mapping formula for discrete variables: ； The slope parameter of the mapping function reflects the sensitivity of the variable; The mapping center point is set based on clinical assessment thresholds.

5. A method for palliative care intervention in hematologic malignancies based on potential profile analysis according to claim 1, characterized in that, In step S2, the profile analysis model is constructed using a cointegration mapping latent profile modeling mechanism, and its profile cointegration mapping model is as follows: ； in, μ k,j : No. k The first potential profile j The mean of the basic profile of each feature; : No. k The first cross-section j The variable for the first r The response coefficients of each cointegrated mapping function; :profile k The r Each cointegration mapping function reflects the nonlinear structural relationship between features; :profile k Inner j Individual residuals of variables.

6. A method for palliative care intervention in hematologic malignancies based on potential profile analysis according to claim 5, characterized in that, The cointegration mapping function For standard feature set The nonlinear structure mapping function, used to identify the interaction mechanism of latent variables within the profile, is defined as follows: ； in, For the first k The cointegration function in the first profile r Item to the first s The response factor of each variable.

7. A method for palliative care intervention in hematologic malignancies based on potential profile analysis according to claim 5, characterized in that, The profile analysis model includes the following steps when used: Initialize the number of profiles K Set the initial number of profiles; Estimated profile parameters Under fixed conditions, perform minimum residual fitting on all samples, using the minimum objective function: ； Profile attribution determination: Each individual i Substitute the values ​​into the profile models, calculate the sum of squared residuals, and assign them to the profile with the smallest residual. k ; Output profile structure information: Output the mean vector for each profile. μ k,j Mapping response coefficients Cointegration function parameters η k,rs .

8. A method for palliative care intervention in hematologic malignancies based on potential profile analysis according to claim 1, characterized in that, The simultaneous use of the model in step S3 includes: Constructing a Disturbance Space: For Each Patient i This generates a perturbation space. The perturbation path can be random, gradient, or system perturbation. Calculate the profile deviation function: for each profile after disturbance k Recalculate ,structure ; Output stability value Assess the profile stability of each patient; Statistical distribution analysis: Further analysis of the entire population The distribution is used to identify unstable regions in the profile model, which serve as input conditions for step S4.

Images