Nursing risk prediction system based on artificial intelligence

Abstract

The invention discloses a nursing risk prediction system based on artificial intelligence. The system comprises a nursing information acquisition module, a neighborhood accumulated risk construction module, a nursing risk response module, a target design module, a dynamic risk increment mapping module, a model training module and a nursing risk prediction module. The invention belongs to the field of risk prediction, and particularly relates to a nursing risk prediction system based on artificial intelligence. According to the scheme, risk timeliness is reflected through exponential decay weighted accumulation, accumulated nursing risks are smoothly quantified and accumulated through mean neighborhood accumulation, nonlinear mapping and a time interval sensitive kernel are introduced, and nonlinear interaction of nursing information is captured; dynamic risk capture is enhanced through a mean value neighborhood accumulated value, and the sensitivity to instantaneous high fluctuation is improved; filtering slight care fluctuations based on a threshold exempt function; event correlation weighting is introduced, an accompanying acute event is strengthened, risk increment is quantified through a risk development coefficient, and then the nursing risk prediction reliability is improved.

Description

Technical Field

[0001] The present invention relates to the field of risk prediction, and specifically refers to a nursing risk prediction system based on artificial intelligence. Background Art

[0002] Nursing risk prediction systems collect patient data, analyze potential risk factors, and convert clinical data into risk warning information to assist medical staff in reducing the incidence of adverse events. However, general nursing risk prediction systems ignore historical risk accumulation, fail to reflect patients' long-term risk accumulation, are sensitive to short-term nursing fluctuations, and easily filter out key transient signals, resulting in poor accuracy in nursing risk prediction. General nursing risk prediction systems also treat occasional acute events as outliers, lack sensitivity to key risk signals, and respond slowly to recent risk changes, leading to low reliability in nursing risk prediction. Summary of the Invention

[0003] In view of the above situation, in order to overcome the defects of the existing technology, the present invention provides a nursing risk prediction system based on artificial intelligence. In view of the problems that the general nursing risk prediction system ignores the historical risk accumulation, cannot reflect the long-term risk accumulation of patients, is sensitive to short-term nursing fluctuations, and easily filters out key instantaneous signals, which leads to poor accuracy of nursing risk prediction, this solution reflects the timeliness of risk through exponential decay weighted accumulation, avoids prediction bias caused by excessive interference from old nursing data; quantifies the accumulated nursing risk through smoothing of mean neighborhood accumulation, introduces nonlinear mapping and time-sensitive kernel, captures the nonlinear interaction of nursing information; enhances dynamic prediction through mean neighborhood accumulation value Dynamic risk capture improves sensitivity to transient high fluctuations such as short-term heart rate surges; thereby improving the accuracy of nursing risk prediction; in response to the problem that general nursing risk prediction systems regard occasional acute events as outliers, lack sensitivity to key risk signals, and respond slowly to recent risk changes, which leads to low reliability of nursing risk prediction, this solution filters daily minor nursing fluctuations based on a threshold exemption function; introduces event-related weighting to strengthen accompanying acute events, and avoids prediction bias caused by noise interference from ordinary nursing assessments; quantifies risk increments through risk development coefficients, and performs dynamic risk increment mapping, thereby improving the reliability of nursing risk prediction.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides an artificial intelligence-based nursing risk prediction system, which includes a nursing information acquisition module, a neighborhood cumulative risk construction module, a nursing risk response module, a target design module, a dynamic risk increment mapping module, a model training module and a nursing risk prediction module;

[0005] The nursing information acquisition module obtains patient nursing information and sets the quantitative indicators as an influencing factor sequence;

[0006] The neighborhood cumulative risk construction module generates a cumulative risk sequence and a cumulative index through exponential decay weighted accumulation to construct a mean neighborhood cumulative risk value;

[0007] The nursing risk response module introduces time-sensitive kernel processing to construct a nursing risk response function;

[0008] The target design module constructs a regularized risk loss target with event correlation weighting and obtains a risk development coefficient;

[0009] The dynamic risk increment mapping module generates an immediate risk score prediction value based on the risk development coefficient through kernelized response function and inverse accumulation;

[0010] The model training module uses patient nursing information as a data set and uses the nursing risk response module, the target design module and the dynamic risk increment mapping module as a nursing risk prediction model to establish a model;

[0011] The nursing risk prediction module performs nursing risk prediction on real-time patient nursing information based on the established nursing risk prediction model.

[0012] Furthermore, the nursing information acquisition module obtains patient nursing information; the nursing risk score is regarded as a target sequence, and the target sequence Expressed as: ;in, is the risk score corresponding to the number of nursing assessments; n is the maximum number of assessments; defines the factors affecting patient nursing information , expressed as: ;in, is the quantitative indicator of category u corresponding to the number of nursing assessment days; N is the total number of indicators.

[0013] Furthermore, the neighborhood cumulative risk building module introduces exponential decay weighted accumulation to perform exponential decay weighted accumulation, which is expressed as: ; ; ;in, is the risk score sequence obtained after one accumulation; is the attenuation factor; is the cumulative risk score at the corresponding number of nursing assessments, k is the number of nursing assessments; v is the cumulative index; is the cumulative risk index of category u on the corresponding number of nursing assessment days; the cumulative risk value is expressed as: ;in, It is the cumulative risk value of the mean neighborhood during the corresponding number of assessments; it is more sensitive to transient high fluctuations including brief heart rate surges, indicating potential acute events.

[0014] Furthermore, the nursing risk response module constructs a nursing risk response function, which is expressed as: ; ; Where d is the risk development coefficient; B is the weight parameter vector, corresponding to the impact intensity of the u-th cumulative indicator after nonlinear mapping; d and B are unknown; T is the matrix transpose; is the cumulative risk indicator vector; It is a nonlinear mapping, introducing a time-sensitive kernel , expressed as: ;A and R are auxiliary vectors; and is the kernel width parameter; and is the time interval between the nursing assessment of A and R and the last nursing assessment; and They are the cumulative risk indicators of Category 2 and Category N corresponding to the number of nursing assessment days.

[0015] Furthermore, the target design module combines empirical risk with structural complexity to construct a regularized target for risk loss, and introduces event correlation weighting. The objective function is expressed as: ;in, ; ; Where C is the penalty coefficient; M is the total number of training samples; is the threshold exemption function, z is an auxiliary parameter; is the exemption threshold; 、 and are the i-th patient 、 and ; and are the patient’s negative penalty multiplier and positive penalty multiplier, respectively; is the event-related weight. If the i-th patient has an acute event during the k-th care, then ,otherwise , is the event correlation factor; Lagrange multipliers are introduced to construct the dual problem, which is expressed as: ; ; Among them, u and v are the nursing times index; and are the positive penalty multipliers for the patient at the u-th care and the v-th care respectively; and are the negative penalty multipliers for the patient during the u-th and v-th care, respectively.

[0016] Furthermore, the dynamic risk increment mapping module solves the candidate risk development coefficient for each patient based on the complementary relaxation condition. ,like ,but ;like ,but ; Take the arithmetic mean of all candidate risk development coefficients as the final risk development coefficient d, and calculate the cumulative prediction of nursing risk, which is expressed as: ;in, is the cumulative risk prediction value corresponding to the number of nursing times; and through inverse accumulation, the cumulative prediction value is restored to a single-step risk increment to obtain the patient's specific nursing risk score at the next moment, which is expressed as: ;in, is the immediate risk score prediction value.

[0017] Furthermore, the model training module is based on the acquired patient nursing information as a data set, and uses the nursing risk response module, target design module and dynamic risk increment mapping module as a nursing risk prediction model. The nursing risk prediction model is trained through the real-time risk score prediction value obtained through the data set to obtain a completed nursing risk prediction model.

[0018] Furthermore, the nursing risk prediction module is based on the established nursing risk prediction model, collects patient nursing information in real time and inputs it into the nursing risk prediction model, and uses the obtained instant risk score prediction value as the prediction result.

[0019] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0020] (1) In view of the problems that general nursing risk prediction systems ignore historical risk accumulation, cannot reflect the long-term risk accumulation of patients, are sensitive to short-term nursing fluctuations, and easily filter out key instantaneous signals, which leads to poor accuracy in nursing risk prediction, this scheme reflects the timeliness of risk through exponential decay weighted accumulation to avoid prediction bias caused by excessive interference from old nursing data; quantifies the accumulated nursing risk through mean neighborhood accumulation smoothing, introduces nonlinear mapping and time-sensitive kernels to capture the nonlinear interaction of nursing information; enhances dynamic risk capture through mean neighborhood accumulation values, and improves sensitivity to transient high fluctuations such as short-term heart rate surges; thereby improving the accuracy of nursing risk prediction.

[0021] (2) In response to the problem that the general nursing risk prediction system regards occasional acute events as outliers, is not sensitive enough to key risk signals, and responds slowly to recent risk changes, which leads to low reliability of nursing risk prediction, this solution filters daily minor nursing fluctuations based on a threshold exemption function; introduces event-related weighting to strengthen accompanying acute events to avoid prediction bias caused by noise interference from ordinary nursing assessments; quantifies risk increments through risk development coefficients, and performs dynamic risk increment mapping to improve the reliability of nursing risk prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of the process of a nursing risk prediction system based on artificial intelligence provided by the present invention.

[0023] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0025] In the description of the present invention, it should be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0026] Example 1, see Figure 1 , the present invention provides an artificial intelligence-based nursing risk prediction system, which includes a nursing information acquisition module, a neighborhood cumulative risk construction module, a nursing risk response module, a target design module, a dynamic risk increment mapping module, a model training module and a nursing risk prediction module;

[0027] The nursing information acquisition module obtains patient nursing information, sets the quantitative indicators as the influencing factor sequence; and sends the data to the neighborhood cumulative risk construction module;

[0028] The neighborhood cumulative risk construction module generates a cumulative risk sequence and a cumulative index through exponential decay weighted accumulation, constructs a mean neighborhood cumulative risk value, and sends the data to the nursing risk response module;

[0029] The nursing risk response module introduces time-sensitive kernel processing to construct a nursing risk response function; and sends the data to the target design module;

[0030] The target design module constructs a regularized risk loss target with event-related weighting and obtains a risk development coefficient; and sends the data to the dynamic risk increment mapping module;

[0031] The dynamic risk increment mapping module generates an immediate risk score prediction value based on the risk development coefficient through kernelized response function and inverse accumulation; and sends the data to the model training module;

[0032] The model training module uses patient nursing information as a data set, and uses the nursing risk response module, the target design module, and the dynamic risk increment mapping module as a nursing risk prediction model to establish a model; and sends the data to the nursing risk prediction module;

[0033] The nursing risk prediction module performs nursing risk prediction on real-time patient nursing information based on the established nursing risk prediction model.

[0034] Example 2, see Figure 1 This embodiment is based on the above embodiment. The nursing information acquisition module obtains the patient nursing information. The nursing risk score is regarded as the target sequence, and the historically accumulated comprehensive risk assessment value is used to reflect the patient's potential risk level. Let the target sequence Expressed as: ;in, is the risk score corresponding to the number of nursing assessments, the true label marked, in percentages; n is the maximum number of assessments, that is, the total number of historical nursing assessments considered; defines the influencing factors of patient nursing information , expressed as: ;in, is the u-th quantitative indicator corresponding to the number of nursing assessment days; N is the total number of indicators; the quantitative indicators of patient nursing information include: average blood pressure, pain score, number of steps, average body temperature, blood albumin level, medication completion rate and number of nighttime awakenings; quantitative indicators require feature engineering processing.

[0035] Example 3, see Figure 1 This embodiment is based on the above embodiment. The neighborhood cumulative risk construction module introduces exponential decay weighted accumulation. Nursing risks often accumulate over time, including prolonged decubitus ulcers and long-term low protein levels, which can cause infection. Accumulation is used to smooth out random fluctuations in the score sequence and factor sequence. However, the historical accumulation of nursing risks is not equally weighted. Unlike long-term risks such as prolonged decubitus ulcers, more recent falls and low protein levels will have a more direct impact on the current risk level. Therefore, exponential decay weighted accumulation is performed, which can be expressed as: ; ; ;in, is the risk score sequence obtained after one accumulation; is the attenuation factor; is the cumulative risk score at the corresponding number of nursing assessments, k is the number of nursing assessments; v is the cumulative index; is the cumulative risk index of category u on the corresponding number of nursing assessment days; and the mean of the previous and next moments is used to construct equivalent smooth nodes to enhance the fitting accuracy of time series evolution and facilitate the physical interpretation of the subsequent risk development coefficient d, that is, the average increase in risk between each assessment. The cumulative risk value is expressed as: ;in, It is the cumulative risk value of the mean neighborhood during the corresponding number of assessments; it is more sensitive to transient high fluctuations including brief heart rate surges, indicating potential acute events.

[0036] Example 4, see Figure 1 This embodiment is based on the above embodiment. The nursing risk response module linearly combines the risk increment and the original risk score on the left side, and linearly weights the multidimensional factors after nonlinear mapping φ on the right side. This can simultaneously capture the complex nonlinear interaction of various factors on the risk. The nursing risk response function is expressed as: ; ; Where d is the risk development coefficient; B is the weight parameter vector, corresponding to the impact intensity of the u-th cumulative indicator after nonlinear mapping; d and B are unknown; T is the matrix transpose; is the cumulative risk indicator vector; It is a nonlinear mapping, introducing a time-sensitive kernel , expressed as: ;A and R are auxiliary vectors; and is the kernel width parameter; and It is the time interval between the nursing assessment where A and R are located and the last nursing assessment; it is used to handle unequal interval nursing sampling and is more sensitive to sudden events; and They are the cumulative risk indicators of Category 2 and Category N corresponding to the number of nursing assessment days.

[0037] By performing the above operations, the general nursing risk prediction system ignores historical risk accumulation, cannot reflect the long-term risk accumulation of patients, is sensitive to short-term nursing fluctuations, and easily filters out key instantaneous signals, which leads to poor accuracy in nursing risk prediction. This solution reflects the timeliness of risk through exponential decay weighted accumulation to avoid prediction bias caused by excessive interference from old nursing data; quantifies the accumulated nursing risk through mean neighborhood accumulation smoothing, introduces nonlinear mapping and time-sensitive kernels to capture the nonlinear interaction of nursing information; enhances dynamic risk capture through mean neighborhood accumulation values, and increases sensitivity to short-term high fluctuations such as heart rate surges, thereby improving the accuracy of nursing risk prediction.

[0038] Example 5, see Figure 1This embodiment is based on the above embodiment. The target design module combines empirical risk with structural complexity to construct a regularized target for risk loss. It does not penalize prediction errors less than the threshold, but only penalizes abnormal differences. It enhances the robustness of the model to occasional nursing events, including an accidental fall that leads to a very high score. It also introduces event-related weighting. In the nursing scenario, different evaluation points may be accompanied by known acute events, and the prediction errors at these moments should be punished. The objective function is expressed as: ;in, ; ; Where C is the penalty coefficient; M is the total number of training samples; is the threshold exemption function, z is an auxiliary parameter; is the exemption threshold; 、 and are the i-th patient 、 and ; and are the patient’s negative penalty multiplier and positive penalty multiplier, respectively; is the event-related weight. If the i-th patient has an acute event during the k-th care, then ,otherwise , is the event correlation factor; Lagrange multipliers are introduced to construct the dual problem, which is expressed as: ; ; Among them, u and v are the nursing times index; and are the positive penalty multipliers for the patient at the u-th care and the v-th care respectively; and are the negative penalty multipliers for the patient at the u-th and v-th care visits, respectively; the kernel function is used to flexibly capture the nonlinear interactions between multidimensional clinical indicators, thereby improving the ability to identify complex risk signal patterns; the Lagrange multiplier and support vector index are obtained by calling the general quadratic programming solver.

[0039] Example 6, see Figure 1 This embodiment is based on the above embodiment. The dynamic risk increment mapping module solves the candidate risk development coefficient for each patient based on the complementary relaxation condition. ,like ,but ;like ,but ; Take the arithmetic mean of all candidate risk development coefficients as the final risk development coefficient d, and calculate the cumulative prediction of nursing risk, which is expressed as: ;in, is the cumulative risk prediction value corresponding to the number of nursing cares. Through the kernelized response function, the cumulative value of nursing risk at future moments is expressed as the weighted kernel inner product of the historical support vector and the new factor vector, which has both nonlinear fitting and time decay characteristics. By integrating decay memory, the longer the measurement, the less influence it has on the current prediction, which is consistent with the experience that proximal nursing operations determine the recent risk. Through inverse accumulation, the cumulative prediction value is restored to a single-step risk increment to obtain the patient's specific nursing risk score at the next moment, which is expressed as: ;in, is the immediate risk score prediction value.

[0040] By performing the above operations, we can address the problem that general nursing risk prediction systems regard occasional acute events as outliers, lack sensitivity to key risk signals, and respond slowly to recent risk changes, which leads to low reliability of nursing risk prediction. This solution filters daily minor nursing fluctuations based on a threshold exemption function; introduces event-related weighting to strengthen accompanying acute events to avoid prediction bias caused by noise interference from ordinary nursing assessments; quantifies risk increments through risk development coefficients, and performs dynamic risk increment mapping to improve the reliability of nursing risk prediction.

[0041] Example 7, see Figure 1 This embodiment is based on the above embodiment. The model training module is based on the acquired patient nursing information as a data set, and the nursing risk response module, the target design module and the dynamic risk increment mapping module are used as nursing risk prediction models. The nursing risk prediction model is trained by the real-time risk score prediction value obtained by the data set to obtain a completed nursing risk prediction model.

[0042] Example 8, see Figure 1 This embodiment is based on the above embodiment. The nursing risk prediction module is based on the established nursing risk prediction model. It collects patient nursing information in real time and inputs it into the nursing risk prediction model. The obtained immediate risk score prediction value is used as the prediction result; a risk score threshold is set. If the immediate risk score prediction value is higher than the risk score threshold, an early warning is issued to the management personnel.

[0043] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0044] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. A nursing risk prediction system based on artificial intelligence, characterized by: The system includes a nursing information acquisition module, a neighborhood cumulative risk construction module, a nursing risk response module, a target design module, a dynamic risk increment mapping module, a model training module, and a nursing risk prediction module; The nursing information acquisition module obtains patient nursing information and sets the quantitative indicators as an influencing factor sequence; The neighborhood cumulative risk construction module generates a cumulative risk sequence and a cumulative index through exponential decay weighted accumulation to construct a mean neighborhood cumulative risk value; The nursing risk response module introduces time-sensitive kernel processing to construct a nursing risk response function; The target design module constructs a regularized risk loss target with event correlation weighting and obtains a risk development coefficient; The dynamic risk increment mapping module generates an immediate risk score prediction value based on the risk development coefficient through kernelized response function and inverse accumulation; The model training module uses patient nursing information as a data set and uses the nursing risk response module, the target design module and the dynamic risk increment mapping module as a nursing risk prediction model to establish a model; The nursing risk prediction module performs nursing risk prediction on real-time patient nursing information based on the established nursing risk prediction model.

2. The artificial intelligence-based nursing risk prediction system according to claim 1, characterized in that: The nursing information acquisition module obtains patient nursing information; the nursing risk score is regarded as the target sequence, and the target sequence Expressed as: ;in, is the risk score corresponding to the number of nursing assessments; n is the maximum number of assessments; defines the factors affecting patient nursing information , expressed as: ;in, is the quantitative indicator of category u corresponding to the number of nursing assessment days; N is the total number of indicators.

3. The artificial intelligence-based nursing risk prediction system according to claim 2, characterized in that: The neighborhood cumulative risk building module introduces exponential decay weighted accumulation and performs exponential decay weighted accumulation, which is expressed as: ; ; ;in, is the risk score sequence obtained after one accumulation; is the attenuation factor; is the cumulative risk score at the corresponding number of nursing assessments, k is the number of nursing assessments; v is the cumulative index; is the cumulative risk index of category u on the corresponding number of nursing assessment days; the cumulative risk value is expressed as: ;in, It is the cumulative risk value of the mean neighborhood during the corresponding number of assessments; it is more sensitive to transient high fluctuations including brief heart rate surges, indicating potential acute events.

4. The artificial intelligence-based nursing risk prediction system according to claim 3, characterized in that: The nursing risk response module constructs a nursing risk response function, which is expressed as: ; ; Where d is the risk development coefficient; B is the weight parameter vector, corresponding to the impact intensity of the u-th cumulative indicator after nonlinear mapping; d and B are unknown; T is the matrix transpose; is the cumulative risk indicator vector; It is a nonlinear mapping, introducing a time-sensitive kernel , expressed as: ;A and R are auxiliary vectors; and is the kernel width parameter; and is the time interval between the nursing assessment of A and R and the last nursing assessment; and They are the cumulative risk indicators of Category 2 and Category N corresponding to the number of nursing assessment days.

5. The artificial intelligence-based nursing risk prediction system according to claim 4, characterized in that: The target design module combines empirical risk with structural complexity to construct a regularized target for risk loss and introduces event-related weighting. The target function is expressed as: ;in, ; ; Where C is the penalty coefficient; M is the total number of training samples; is the threshold exemption function, z is an auxiliary parameter; is the exemption threshold; 、 and are the i-th patient 、 and ; and are the patient’s negative penalty multiplier and positive penalty multiplier, respectively; is the event-related weight. If the i-th patient has an acute event during the k-th care, then ,otherwise , is the event correlation factor; Lagrange multipliers are introduced to construct the dual problem, which is expressed as: ; ; Among them, u and v are the nursing times index; and are the positive penalty multipliers for the patient at the u-th care and the v-th care respectively; and are the negative penalty multipliers for the patient during the u-th and v-th care, respectively.

6. The artificial intelligence-based nursing risk prediction system according to claim 5, characterized in that: The dynamic risk increment mapping module solves the candidate risk development coefficient for each patient based on the complementary relaxation condition. ,like ,but ;like ,but ; Take the arithmetic mean of all candidate risk development coefficients as the final risk development coefficient d, and calculate the cumulative prediction of nursing risk, which is expressed as: ;in, is the cumulative risk prediction value corresponding to the number of nursing times; and through inverse accumulation, the cumulative prediction value is restored to a single-step risk increment to obtain the patient's specific nursing risk score at the next moment, which is expressed as: ;in, is the immediate risk score prediction value.

7. The artificial intelligence-based nursing risk prediction system according to claim 6, characterized in that: The model training module is based on the acquired patient nursing information as a data set, and uses the nursing risk response module, the target design module and the dynamic risk increment mapping module as the nursing risk prediction model. The nursing risk prediction model is trained through the real-time risk score prediction value obtained from the data set to obtain a completed nursing risk prediction model.

8. The artificial intelligence-based nursing risk prediction system according to claim 7, characterized in that: The nursing risk prediction module is based on the established nursing risk prediction model, collects patient nursing information in real time and inputs it into the nursing risk prediction model, and uses the obtained instant risk score prediction value as the prediction result.

Images