Nursing data evaluation recording method and system for clinical nursing of old people

Abstract

The invention provides a nursing data evaluation recording method and system for elderly clinical nursing. The method comprises the steps of obtaining a medical history portrait and a basic portrait of a target elderly user; retrieving nursing index distribution intervals of healthy users in the same cluster and nursing index high-frequency discrete values of abnormal users in the same cluster, which meet the basic portrait, the disease type sequence, the disease age sequence and the diagnosis and treatment scheme sequence, and taking interval intersections of rated threshold intervals of the nursing indexes to obtain updated threshold intervals of the nursing indexes; and performing nursing data recording on the target elderly user based on the nursing index updating threshold interval. According to the method and the device, the technical problem that potential safety hazards are caused by trace errors due to the fact that individual difference requirements cannot be met when elderly nursing is carried out based on a unified medical standard index threshold in the prior art is solved, and the nursing index threshold interval is adjusted in a customized manner according to the individual characteristics of the elderly user; and the nursing accuracy and safety are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical health information, and in particular to a nursing data evaluation and recording method and system for elderly clinical nursing. BACKGROUND

[0002] The clinical nursing of the elderly population is increasingly valued by society and medical institutions. At present, the clinical nursing of the elderly mainly relies on unified medical standard index thresholds for monitoring and evaluation, such as using fixed standard ranges of blood pressure, blood sugar, body temperature, etc. as the reference basis for clinical nursing. However, the elderly population has large individual differences in age, medical history, physical condition, etc. Using unified medical standard index thresholds for nursing has limitations, ignoring the individualized characteristics of the elderly population, resulting in an inability to accurately grasp the actual health status of each elderly patient in clinical practice. Especially for elderly patients with multiple diseases and complex medication, even if the indicators only have a slight deviation, it may cause serious health and safety hazards. For example, even if the blood pressure, blood sugar, etc. of some elderly patients are slightly above or below the standard reference range, it may cause physical discomfort or exacerbate the existing disease, making it difficult to achieve personalized nursing and risk warning for elderly patients, thereby affecting the quality and safety of elderly care. SUMMARY

[0003] The present application provides a nursing data evaluation and recording method and system for elderly clinical nursing to solve the technical problems that the existing technology based on unified medical standard index thresholds for elderly nursing cannot meet the individual difference needs and may cause safety hazards due to slight errors.

[0004] The technical solution of the present application to solve the above technical problems is as follows: In a first aspect, the present application provides a nursing data evaluation and recording method for elderly clinical nursing, obtaining a medical history portrait of a target elderly user, wherein the medical history portrait includes a disease type sequence, an age of onset sequence, and a diagnosis and treatment scheme sequence; obtaining a basic portrait of the target elderly user; retrieving a nursing index distribution interval of a same cluster health user that meets the basic portrait, the disease type sequence, the age of onset sequence, and the diagnosis and treatment scheme sequence; retrieving a nursing index high-frequency discrete value of a same cluster abnormal user that meets the basic portrait, the disease type sequence, the age of onset sequence, and the diagnosis and treatment scheme sequence; taking an interval intersection of a nursing index rated threshold interval according to the nursing index distribution interval and the nursing index high-frequency discrete value, to obtain a nursing index updated threshold interval; and recording nursing data of the target elderly user based on the nursing index updated threshold interval.

[0005] In a second aspect, the present application provides a nursing data evaluation record system for elderly clinical care, comprising: a medical history image acquisition module for obtaining a medical history image of a target elderly user, wherein the medical history image comprises a disease type sequence, an age of onset sequence and a diagnosis and treatment scheme sequence; a basic image acquisition module for obtaining a basic image of the target elderly user; a healthy user retrieval module for retrieving a nursing index distribution interval of a same-cluster healthy user satisfying the basic image, the disease type sequence, the age of onset sequence and the diagnosis and treatment scheme sequence; an abnormal user retrieval module for retrieving a nursing index high-frequency discrete value of a same-cluster abnormal user satisfying the basic image, the disease type sequence, the age of onset sequence and the diagnosis and treatment scheme sequence; an index threshold optimization module for obtaining a nursing index updated threshold interval by taking an interval intersection of a nursing index rated threshold interval according to the nursing index distribution interval and the nursing index high-frequency discrete value; and a nursing data record module for recording nursing data of the target elderly user based on the nursing index updated threshold interval.

[0006] The present application has the following beneficial effects: The medical history image of the target elderly user is obtained, wherein the medical history image comprises a disease type sequence, an age of onset sequence and a diagnosis and treatment scheme sequence, thereby providing basic data support for subsequent personalized nursing evaluation. The basic image of the target elderly user is obtained, such as age, gender, height, weight, living habits, family medical history and other basic information, thereby providing matching conditions for subsequent same-cluster user retrieval. The nursing index distribution interval of a same-cluster healthy user satisfying the basic image, the disease type sequence, the age of onset sequence and the diagnosis and treatment scheme sequence is retrieved, thereby finding a user group with a good health status similar to the target elderly user in terms of basic characteristics and medical history characteristics through multi-dimensional feature matching, and statistically analyzing the normal distribution interval of each nursing index of these users, thereby establishing a reference benchmark for the target elderly user. The nursing index high-frequency discrete value of a same-cluster abnormal user satisfying the basic image, the disease type sequence, the age of onset sequence and the diagnosis and treatment scheme sequence is retrieved, thereby also finding a user group similar to the target elderly user in terms of basic characteristics and medical history characteristics but having abnormal health conditions through multi-dimensional feature matching, and statistically analyzing the nursing index discrete value of these users when the abnormal conditions occur, especially the high-frequency abnormal values, thereby identifying potential risk points. The interval intersection of a nursing index rated threshold interval is taken according to the nursing index distribution interval and the nursing index high-frequency discrete value, thereby obtaining a nursing index updated threshold interval, which not only avoids the limitations of traditional fixed thresholds, but also fully considers individual difference factors. The target elderly user is recorded for nursing data based on the nursing index updated threshold interval, the obtained personalized nursing index updated threshold interval is applied to the actual nursing process of the target elderly user, and the vital signs and drug reactions of the target elderly user are continuously monitored and recorded, so that timely warning and intervention can be performed once the index exceeds the personalized threshold interval, thereby improving the accuracy and safety of nursing.

[0007] By the technical scheme, the nursing index threshold personalization customization based on the individual characteristics and the medical history information of the old user is realized, the technical problem that the unified threshold standard in the traditional nursing cannot meet the individual difference is solved, and the security hidden danger caused by the trace error is effectively avoided. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 A flowchart of a nursing data evaluation record method of the old clinical nursing provided by the present application is shown in the figure. Figure 2 A structure diagram of a nursing data evaluation record system of the old clinical nursing provided by the present application is shown in the figure.

[0009] In the figure, the components represented by the numbers are as follows: The medical history image acquisition module 11, the basic image acquisition module 12, the healthy user retrieval module 13, the abnormal user retrieval module 14, the index threshold optimization module 15, and the nursing data record module 16. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0011] In the description of the present application, the terms "first", "second" are only used for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0012] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0013] Example 1, as Figure 1 As shown, an embodiment of the present invention provides a nursing data evaluation and recording method for elderly clinical nursing, comprising: S100: Obtain a medical history portrait of a target elderly user, wherein the medical history portrait includes a sequence of symptom types, a sequence of ages at onset, and a sequence of diagnosis and treatment plans.

[0014] Specifically, by systematically collecting the target elderly user's medical history information from their electronic medical record system, a medical history profile of the target elderly user is formed, providing data support for subsequent precision nursing care. The medical history profile includes a sequence of symptom type, age at onset, and diagnosis and treatment plan.

[0015] Among them, the disease type sequence records the various diseases that the target elderly users have suffered in history, arranged in chronological order, and reflects the user's disease development trajectory; the disease age sequence records the specific age of the target elderly users when they suffer from various diseases, providing a time dimension reference for evaluating the long-term impact of the disease on the user's physiological state; the diagnosis and treatment plan sequence records in detail the treatment measures and medication plans taken for each disease, including but not limited to drug treatment, surgical intervention, physical therapy and other treatment methods, as well as the duration of treatment and efficacy evaluation.

[0016] By obtaining the medical history portraits of target elderly users, we can fully understand the health history and disease characteristics of target elderly users, laying the foundation for subsequent nursing indicators based on individual differences, thus breaking through the limitations of using unified standards for evaluation in traditional elderly clinical care, and being able to better adapt to the individual differences in the physical constitution of the elderly population and improve the accuracy and safety of nursing.

[0017] S200: Obtain a basic profile of target elderly users.

[0018] Specifically, by collecting key indicators of the target elderly user's basic physiological characteristics and physical condition, a basic profile of the target elderly user is formed, providing a reference for personalized care assessment. The basic profile includes basic physiological indicators such as gender, age, height, weight, and body fat percentage, as well as relevant data reflecting the target elderly user's physical function status.

[0019] Basic profiles can be obtained through hospital physical examinations and smart device monitoring to ensure data accuracy and comprehensiveness. Basic demographic characteristics such as gender and age, combined with physical indicators such as height and weight, can provide a preliminary assessment of the target elderly user's basic physical condition. Metabolic-related indicators such as body fat percentage further reflect the elderly user's body composition and metabolic characteristics, providing a basis for assessing their health risks.

[0020] By combining basic portraits with medical history portraits, a comprehensive and accurate description of the health status of target elderly users can be formed, providing a basis for the subsequent personalized threshold setting of nursing indicators, thereby achieving precise care tailored to individual differences in the elderly and effectively improving the safety and effectiveness of clinical care for the elderly.

[0021] S300: Retrieve the distribution interval of nursing indicators of healthy users in the same cluster who meet the basic portrait, the symptom type sequence, the disease age sequence and the diagnosis and treatment plan sequence.

[0022] Specifically, by searching the medical big data platform for healthy users with similar basic profiles, symptom types, ages at onset, and treatment plans as the target elderly user, we identify clusters of healthy users. We then obtain the distribution ranges of nursing indicators for these healthy users, and establish personalized nursing indicator reference standards for the target elderly user. The medical big data platform is a comprehensive information system that integrates a vast amount of medical and health data. It brings together clinical data such as electronic medical records, medical examination results, medication records, and nursing records from medical institutions, as well as health management data such as physical examinations and wearable device monitoring. This platform covers a vast amount of user information across different age groups and disease types, providing a rich data source. Healthy users in the cluster are users who are highly similar to the target elderly user in terms of basic physiological characteristics and disease progression, but are currently in a healthy state. By analyzing the nursing indicator data of these users, we can obtain the distribution ranges of indicators that reflect the normal physiological status of this type of user. These indicators include, but are not limited to, the normal fluctuation ranges of key physiological parameters such as blood pressure, heart rate, blood sugar, body temperature, respiratory rate, and blood oxygen saturation.

[0023] In the retrieval process, a multi-dimensional index condition is constructed according to the basic portrait and medical history portrait of the target elderly user, and a cluster of healthy user samples that meet the conditions are screened out in the medical big data platform. By statistically analyzing the nursing indicators of these samples, the distribution characteristics of each indicator are determined, and the nursing indicator distribution interval is formed, reflecting the normal range of physiological indicators of the healthy population similar to the target elderly user's conditions, providing a basis for determining the subsequent personalized nursing threshold.

[0024] By obtaining the nursing indicator distribution interval based on the cluster of healthy users, the limitations of using a unified standard threshold in traditional nursing are broken through, and the normal range of physiological indicators of the elderly population with specific basic characteristics and disease history can be more accurately reflected, laying the foundation for realizing personalized precision nursing.

[0025] S400: Retrieve the high-frequency discrete values of the nursing indicators of the cluster of abnormal users that meet the basic portrait, the sequence of disease types, the sequence of ages of onset, and the sequence of diagnosis and treatment schemes.

[0026] Specifically, by retrieving a cluster of abnormal users with similar basic portraits, disease type sequences, age of onset sequences, and diagnosis and treatment scheme sequences to the target elderly user in the medical big data platform, a cluster of abnormal users is formed, and the high-frequency discrete values of the nursing indicators of these cluster of abnormal users are obtained, providing a reference basis for identifying potential abnormal risk points for the target elderly user. Among them, the cluster of abnormal users refers to a user group that is highly similar to the target elderly user in terms of basic physiological characteristics and disease development history, but is currently in an abnormal or disease state. By analyzing the nursing indicator data of these users, characteristic indicator values that reflect the possible abnormal state of this type of user can be obtained. These high-frequency discrete values usually represent the abnormal aggregation of certain nursing indicators in a specific interval, and are important signals for early warning of potential health risks.

[0027] The retrieval process uses the same indexing method as step S300, but the screening object is users in an abnormal health state. By statistically analyzing the nursing indicators of these cluster of abnormal users, the frequently occurring discrete indicator values in the abnormal state are identified, and the high-frequency discrete values of the nursing indicators are formed. These high-frequency discrete values of the nursing indicators reflect the typical indicator characteristics of people similar to the target elderly user when they are in a healthy abnormal state, providing an important reference for determining the subsequent personalized early warning threshold.

[0028] By obtaining the high-frequency discrete values of the nursing indicators based on the cluster of abnormal users, it can help identify the indicator abnormal patterns with early warning significance in a specific population, improve the early identification ability of the target elderly user's health risks, and create conditions for realizing personalized precision early warning.

[0029] S500: Taking the intersection of the rated threshold intervals of the nursing indicator according to the nursing indicator distribution interval and the high-frequency discrete value of the nursing indicator to obtain an updated threshold interval of the nursing indicator.

[0030] Specifically, the rated threshold interval of the nursing indicators is modified by combining the distribution interval of the nursing indicators of healthy users in the same cluster and the high-frequency discrete values ​​of the nursing indicators of abnormal users in the same cluster, so as to obtain the updated threshold interval of the nursing indicators that meets the individual characteristics of the target elderly users. The rated threshold interval of the nursing indicators refers to the normal range of various physiological indicators stipulated in traditional medical standards, such as the standard range of normal blood pressure, normal blood sugar, normal body temperature, etc. for adults. Specifically, according to the distribution interval of the nursing indicators and the high-frequency discrete values ​​of the nursing indicators, the intersection of the rated threshold interval of the nursing indicators is taken to form a personalized updated threshold interval of the nursing indicators for the target elderly users. This not only meets the basic requirements of the general medical standards, but also fully considers the physiological characteristics and potential risk points of the target elderly users, and can provide a more accurate evaluation basis for the clinical care of the target elderly users.

[0031] By combining the distribution characteristics of healthy users in the same cluster with the discrete characteristics of abnormal users, the threshold interval updating method overcomes the limitation of the lack of personalization of traditional nursing indicator thresholds, and can provide more precise nursing standards for elderly users with different individual characteristics, thereby improving the accuracy and pertinence of nursing assessments.

[0032] S600: Recording nursing data for the target elderly user based on the nursing indicator update threshold interval.

[0033] Specifically, based on the obtained nursing indicator update threshold intervals, the real-time physiological indicators of the target elderly user are monitored, recorded, and evaluated to achieve personalized nursing data management. Specifically, the nursing data records for the target elderly user are no longer simply based on the fixed thresholds of traditional medical standards, but are based on the obtained nursing indicator update threshold intervals. By comparing the target elderly user's indicator monitoring values ​​with their personalized nursing indicator update threshold intervals, normal fluctuations and abnormal deviations can be accurately identified, thereby improving the accuracy and pertinence of nursing monitoring.

[0034] Personalized nursing data recording can effectively distinguish between indicator fluctuations due to individual differences and true health abnormalities, reduce false positives and omissions caused by standardized standards, and provide caregivers with a more reliable basis for decision-making. Furthermore, it can record indicator trends and predict potential health risks, enabling a shift in care from reactive response to proactive prevention, thereby improving the safety and effectiveness of clinical nursing for the elderly.

[0035] Furthermore, the distribution intervals of nursing indicators of healthy users in the same cluster that meet the basic profile, the sequence of symptom types, the sequence of age at onset, and the sequence of diagnosis and treatment plans are retrieved, including: S310: constructing a strict indexing rule based on the basic portrait of the target elderly user; S320: constructing a primary fault-tolerant indexing rule based on the disease type sequence, the age of onset sequence, and the diagnosis and treatment scheme sequence of the target elderly user; S330: retrieving a primary same-cluster healthy user satisfying the strict indexing rule and the primary fault-tolerant indexing rule; S340: constructing a secondary fault-tolerant indexing rule based on the primary disease type sequence, the primary age of onset sequence, and the primary diagnosis and treatment scheme sequence of the primary same-cluster healthy user; S350: retrieving a secondary same-cluster healthy user satisfying the strict indexing rule and the secondary fault-tolerant indexing rule; S360: counting the care index distribution interval of the primary same-cluster healthy user and the secondary same-cluster healthy user.

[0036] In a feasible implementation, a multi-level indexing retrieval strategy is adopted, and a strict indexing combined with a fault-tolerant indexing is used to achieve efficient and accurate user screening, so as to accurately retrieve a same-cluster healthy user having similar characteristics to the target elderly user.

[0037] Firstly, a strict indexing rule is constructed based on the basic portrait of the target elderly user. This rule mainly sets strict matching conditions for the basic physiological characteristics of the target elderly user such as gender, age, height, weight, and body fat rate, to ensure that the retrieval result is highly consistent with the target elderly user in basic physiological characteristics. Secondly, a primary fault-tolerant indexing rule is constructed based on the disease type sequence, the age of onset sequence, and the diagnosis and treatment scheme sequence of the target elderly user. This rule allows a certain degree of difference in disease history, which provides the possibility of expanding the effective sample range. Then, the above two rules are applied to retrieve a primary same-cluster healthy user satisfying the strict indexing rule and the primary fault-tolerant indexing rule. These users are highly similar to the target elderly user in basic physiological characteristics and maintain a certain similarity in disease history, which can expand the retrieval range, increase the number of effective samples, and improve the reliability of statistical results while ensuring clinical relevance.

[0038] Then, based on the retrieved disease characteristics of the first-level same-cluster healthy users, i.e., the first-level disease type sequence, the first-level age sequence, and the first-level diagnosis and treatment scheme sequence, a second-level fault-tolerant index rule is constructed to further relax the requirements for disease history matching. This second-level fault-tolerant index rule dynamically constructed according to the first-level same-cluster healthy users can adaptively adjust the fault-tolerant parameters according to the feature distribution of the existing samples, improving the flexibility and pertinence of the retrieval. Subsequently, the strict index rule and the second-level fault-tolerant index rule are applied to retrieve second-level same-cluster healthy users, expanding the sample coverage. Although the second-level same-cluster healthy users have a low similarity in disease history with the target elderly user, they maintain a high consistency in basic physiological characteristics, which can provide supplementary samples for index analysis and enhance the representativeness of statistical results. Then, the nursing indexes of the retrieved first-level same-cluster healthy users and second-level same-cluster healthy users are statistically analyzed to obtain the nursing index distribution interval, laying a data foundation for setting the personalized nursing index update threshold interval.

[0039] Further, the nursing index distribution interval of the first-level same-cluster healthy users and the second-level same-cluster healthy users is statistically analyzed, including: S361: Grouping the second-level same-cluster healthy users based on the first-level same-cluster healthy users to obtain multiple groups of second-level same-cluster healthy users; S362: Performing attribute index box plot evaluation on the multiple groups of second-level same-cluster healthy users to obtain multiple groups of second-level nursing index box distribution intervals; S363: Performing attribute interval intersection analysis on the multiple groups of second-level nursing index box distribution intervals to obtain a second-level nursing index distribution interval; S364: Performing attribute index box plot evaluation on the first-level same-cluster healthy users to obtain a first-level nursing index box distribution interval; S365: Performing intersection analysis on the second-level nursing index distribution interval and the first-level nursing index box distribution interval to obtain the nursing index distribution interval.

[0040] In a preferred embodiment, a statistical method based on multi-level user grouping and box plot analysis is proposed to ensure that the statistical analysis of the nursing index distribution interval is more accurate.

[0041] Firstly, based on the primary cluster healthy users, the secondary cluster healthy users are grouped to obtain multiple groups of secondary cluster healthy users. Specifically, for each primary cluster healthy user, the secondary cluster healthy users corresponding to the primary cluster healthy user are retrieved to form a group of secondary cluster healthy users. Since there are multiple primary cluster healthy users, the secondary cluster healthy users can be grouped to obtain multiple groups of secondary cluster healthy users, each corresponding to a primary cluster healthy user. This one-to-many grouping method ensures that there is a clear correspondence between the secondary cluster healthy users and the primary cluster healthy users, providing a basis for subsequent hierarchical analysis. Secondly, the multiple groups of secondary cluster healthy users are traversed, and the care indicators of each group of secondary cluster healthy users are evaluated by the same attribute indicator box plot to obtain multiple groups of secondary care indicator box distribution intervals. Box plot evaluation can calculate the statistical distribution characteristics of each group of secondary cluster healthy users on blood pressure, heart rate, blood glucose and other care indicators, including minimum value, first quartile, median, third quartile and maximum value, forming multiple groups of secondary care indicator box distribution intervals.

[0042] Then, the multiple groups of secondary care indicator box distribution intervals are analyzed by the same attribute interval intersection to obtain a secondary care indicator distribution interval. Specifically, the intersection of the distribution intervals of different groups of secondary cluster healthy users on the same care indicator is calculated, the common normal fluctuation range between groups is extracted, and the extreme distribution unique to individual groups is excluded to form a more universal secondary care indicator distribution interval. Next, the primary cluster healthy users are evaluated by the same attribute indicator box plot to obtain a primary care indicator box distribution interval. Specifically, all primary cluster healthy users are taken as a whole, and their care indicators are statistically analyzed by box plot to obtain a care indicator distribution interval reflecting the overall characteristics of the primary cluster healthy users. Then, the intersection of the secondary care indicator distribution interval and the primary care indicator box distribution interval is analyzed to obtain the final care indicator distribution interval. Specifically, the intersection of the secondary care indicator distribution interval and the primary care indicator box distribution interval is calculated, which considers the indicator characteristics of the primary cluster healthy users highly similar to the target elderly user, and also takes into account the statistical stability of the larger sample size of the secondary cluster healthy users, thereby obtaining a precise and reliable care indicator distribution interval.

[0043] Further, the retrieval of the care indicator high-frequency discrete value of the cluster abnormal user satisfying the basic portrait, the disease type sequence, the age of onset sequence and the diagnosis and treatment scheme sequence includes: S410: obtaining a predefined care indicator outlier factor threshold; S420: evaluating the same attribute indicator outlier factor of the cluster abnormal user to obtain a set of care indicator outlier factors; S430: extracting a selected nursing index outlier factor set with outlier factors less than or equal to the nursing index outlier factor threshold value based on the nursing index outlier factor set; S440: extracting nursing index record values of the selected nursing index outlier factor set and adding them into the nursing index high-frequency discrete value.

[0044] In a preferred embodiment, a high-frequency discrete value extraction method based on outlier factor analysis is proposed. By outlier value screening and statistical analysis, the nursing index characteristic values with early warning significance in the same cluster abnormal user are accurately identified.

[0045] First, a predefined nursing index outlier factor threshold value is obtained. This threshold value is pre-set through a large amount of clinical data analysis and expert evaluation, and is used to judge the abnormality degree of a nursing index value. It is an important reference standard for screening effective outlier values. Different nursing indexes have different outlier factor thresholds to adapt to the differences in characteristics of each index. Second, the same attribute index outlier factor of the same cluster abnormal user is evaluated to obtain a nursing index outlier factor set. Specifically, for each nursing index of the same cluster abnormal user, the outlier factor is calculated to quantify the degree of deviation of the index value from the normal range. For example, based on the nursing index data of the same cluster healthy user, the reference statistical value of each nursing index is calculated, including the mean and the standard deviation, which represents the distribution characteristics of the index in the normal state. For a nursing index value of the same cluster abnormal user, the absolute difference between the value and the mean of the reference statistical value is calculated, and the difference is divided by the standard deviation of the reference statistical value to obtain the outlier factor of the index value, which reflects the standardized degree of deviation of the index value from the normal range. The larger the value, the more significant the deviation. The same cluster abnormal user is retrieved in the same way as the same cluster healthy user, that is, based on the target elderly user's basic portrait, disease type sequence, age sequence and diagnosis and treatment scheme sequence, but the health state of the user group is abnormal.

[0046] Then, based on the nursing index outlier factor set, a selected nursing index outlier factor set with outlier factors less than or equal to the nursing index outlier factor threshold value is extracted, so as to screen out index values whose outlier degree reaches or exceeds the threshold requirement, ensuring that the selected outlier values have sufficient abnormal significance, and the misjudgment result caused by significant fluctuations. After that, the nursing index record values corresponding to the selected nursing index outlier factor set are extracted and added into the nursing index high-frequency discrete value. By statistically analyzing the frequency and distribution characteristics of these significant outlier index values in the same cluster abnormal user, the abnormal index value mode with high incidence can be identified, and the nursing index high-frequency discrete value is formed, which provides an important reference for subsequent personalized nursing index update threshold interval setting.

[0047] By extracting high-frequency discrete values ​​based on outlier factor analysis, it is possible to accurately identify characteristic indicator values ​​with early warning significance from a large amount of abnormal user data, improve the sensitivity and specificity of abnormal monitoring, and create conditions for achieving personalized and accurate early warnings.

[0048] Furthermore, according to the nursing indicator distribution interval and the nursing indicator high-frequency discrete value, the interval intersection of the nursing indicator rated threshold interval is taken to obtain the nursing indicator update threshold interval, including: S510: Obtain a first nursing indicator update threshold interval by taking an interval intersection of the nursing indicator distribution interval and the nursing indicator rated threshold interval; S520: When the high-frequency discrete value of the nursing indicator does not belong to the first nursing indicator update threshold interval, setting the first nursing indicator update threshold interval as the nursing indicator update threshold interval; S530: When the high-frequency discrete value of the nursing indicator belongs to the first nursing indicator update threshold interval, the high-frequency discrete value of the nursing indicator is deleted from the first nursing indicator update threshold interval, and a second nursing indicator update threshold interval is obtained, which is set as the nursing indicator update threshold interval.

[0049] In a feasible implementation, a personalized care indicator update threshold interval for the target elderly user is formed through interval calculation and optimization processing.

[0050] First, the first nursing indicator update threshold interval is obtained by taking the intersection of the nursing indicator distribution interval and the nursing indicator rated threshold interval. Specifically, the nursing indicator distribution interval is obtained through statistical analysis of healthy users in the same cluster and reflects the normal range of indicators for a population with similar characteristics to the target elderly user; while the nursing indicator rated threshold interval is the normal range specified by traditional medical standards. By calculating the intersection of these two intervals, the scientific validity of universal medical standards is preserved while incorporating individual differences among specific populations, forming a preliminary personalized threshold interval, namely the first nursing indicator update threshold interval.

[0051] Secondly, it is judged whether the high-frequency discrete value of the nursing index belongs to the first nursing index updating threshold interval. When the high-frequency discrete value of the nursing index does not belong to the first nursing index updating threshold interval, it is indicated that the high-frequency abnormal value has been excluded from the initially determined normal range, and there is no need for further processing, and the first nursing index updating threshold interval is directly set as the final nursing index updating threshold interval. When the high-frequency discrete value of the nursing index belongs to the first nursing index updating threshold interval, it is indicated that the characteristic value frequently appearing in the same cluster of abnormal users is contained in the initially determined normal range, and there is a possibility that the potential risk point is misjudged as a normal state. At this time, the high-frequency discrete value of the nursing index is deleted from the first nursing index updating threshold interval, a second nursing index updating threshold interval is obtained, and it is set as the final nursing index updating threshold interval. For example, if the first nursing index updating threshold interval is [A, B], the high-frequency discrete value of the nursing index is c, and A < c < B, the deletion operation will convert the continuous interval [A, B] into two discontinuous intervals [A, c) and (c, B]. This processing method can accurately exclude the abnormal index value with early warning significance, and improve the early warning sensitivity of the threshold interval.

[0052] Through the above steps, the individual optimization of the nursing index threshold interval is realized, the physiological characteristics of the target elderly user are considered, and the high-frequency abnormal value with early warning significance is excluded, so that a more accurate nursing index updating threshold interval is formed, which provides a basis for subsequent individualized nursing monitoring.

[0053] Further, the nursing data record of the target elderly user is based on the nursing index updating threshold interval, including: S610: obtaining the nursing index monitoring data of the target elderly user; S620: when the nursing index monitoring data belongs to the nursing index updating threshold interval, performing health identification on the nursing index monitoring data; S630: when the nursing index monitoring data does not belong to the nursing index updating threshold interval, performing abnormal identification on the nursing index monitoring data; S640: when the abnormal identification triggering frequency exceeds the pre-defined number of times for a continuous preset time length, sending a prompt information to the nurse station.

[0054] In a feasible implementation manner, based on the individualized nursing index updating threshold interval, a set of nursing data record and abnormal warning mechanism is established, and through real-time monitoring, intelligent judgment and timely warning, the precise nursing management of the target elderly user is realized.

[0055] First, obtain the target elderly user's care index monitoring data. These data can be obtained through vital sign monitoring devices, wearable health monitoring devices, or regular manual measurements, including real-time or regular measurements of key physiological parameters such as blood pressure, heart rate, blood oxygen, body temperature, etc. Preprocess and standardize these raw care index monitoring data to ensure data quality meets the subsequent evaluation requirements. When the care index monitoring data belongs to the care index update threshold interval, the health identification is performed on the care index monitoring data. Health identification indicates that the index value is within the personalized normal range and does not need special attention. Record these health-identified data in the target elderly user's care database as historical records and trend analysis basis data for health status.

[0056] When the care index monitoring data does not belong to the care index update threshold interval, the abnormal identification is performed on the care index monitoring data. Abnormal identification indicates that the index value is outside the personalized normal range and may have health risks. At the same time, record the degree, duration and occurrence environment of the abnormality, etc. to provide multi-dimensional basis for subsequent analysis and early warning. When the frequency of abnormal identification exceeds the pre-defined number within a continuous pre-set time period, send a prompt message to the nurse station. Among them, the continuous pre-set time period is set according to the characteristics of different indexes, such as 5 minutes for blood pressure, 3 minutes for heart rate, and 2 minutes for blood oxygen, etc. to ensure timely and effective intervention on the abnormal state of various indexes, while avoiding false positives caused by temporary fluctuations. Through this early warning mechanism based on frequency and duration, it can effectively distinguish between occasional fluctuations and sustained abnormalities, avoid false positives caused by transient fluctuations, and ensure timely intervention on sustained abnormal states. The prompt message contains key information such as abnormal index type, abnormal degree, duration, etc. to help nursing staff quickly assess the situation and take appropriate measures.

[0057] Through personalized care data recording and early warning methods, precise monitoring and evaluation can be performed based on the individual characteristics of the target elderly user, potential health risks can be effectively identified, and the safety and effectiveness of elderly clinical care can be improved, providing more accurate and safe medical care services for the elderly population.

[0058] Further, based on the disease type sequence, the disease age sequence, and the diagnosis and treatment scheme sequence, a first fault-tolerant index rule is constructed, including: S321: Send the disease type sequence to the expert end and receive the first disease fault-tolerant type set to the Mth disease fault-tolerant type set of the disease type sequence; S322: Send the disease age sequence and the diagnosis and treatment scheme sequence to the expert end and receive the disease age deviation fault-tolerant threshold and the diagnosis and treatment scheme fault-tolerant threshold; S323: constructing the primary fault-tolerant index rule based on the first disease fault-tolerant type set to the Mth disease fault-tolerant type set, the disease age deviation fault-tolerant threshold, and the diagnosis and treatment scheme fault-tolerant threshold.

[0059] In a preferred embodiment, to construct the primary fault-tolerant index rule, first, the disease type sequence of the target elderly user is sent to the expert terminal, and the fault-tolerant expansion set of each disease type provided by the expert is received, that is, the first disease fault-tolerant type set to the Mth disease fault-tolerant type set. Specifically, for each disease type in the disease type sequence of the target elderly user, the expert provides a set of disease types similar to the original disease type in clinical manifestations, pathological mechanisms, or treatment methods according to the medical relevance principle, forming the fault-tolerant type set of the disease. For example, for type 2 diabetes, its fault-tolerant type set may include metabolic syndrome, impaired glucose tolerance, and other related diseases. These diseases may have differences from the original disease, but they have similarities in clinical characteristics and physiological effects.

[0060] Secondly, the disease age sequence and the diagnosis and treatment scheme sequence of the target elderly user are sent to the expert terminal, and the disease age deviation fault-tolerant threshold and the diagnosis and treatment scheme fault-tolerant threshold set by the expert are received. The disease age deviation fault-tolerant threshold defines the allowable error range in age matching, such as ±5 years; the diagnosis and treatment scheme fault-tolerant threshold defines the allowable difference in treatment methods, drug types, or treatment effects, ensuring that the search range is expanded while maintaining clinical relevance. Then, based on the received first disease fault-tolerant type set to the Mth disease fault-tolerant type set, the disease age deviation fault-tolerant threshold, and the diagnosis and treatment scheme fault-tolerant threshold, the primary fault-tolerant index rule is constructed. This rule considers the similar substitution of disease types, the reasonable fluctuation of disease age, and the equivalent change of diagnosis and treatment schemes, forming a set of search conditions that have both medical professionalism and practical flexibility, providing a basis for subsequent screening of users in the same cluster.

[0061] Through this expert-assisted fault-tolerant rule construction method, medical professional knowledge and data retrieval technology can be effectively combined to ensure the effectiveness of the search results in medicine and the sufficiency of the data, laying a reliable foundation for personalized nursing assessment.

[0062] Embodiment two, as shown in Figure 2 based on the same inventive concept of the nursing data evaluation record method for elderly clinical nursing provided in embodiment one, the present embodiment also provides a nursing data evaluation record system for elderly clinical nursing, comprising: a medical history image acquisition module 11 for obtaining a medical history image of a target elderly user, wherein the medical history image includes a disease type sequence, a disease age sequence, and a diagnosis and treatment scheme sequence; a basic image acquisition module 12 for obtaining a basic image of the target elderly user; a health user searching module 13 configured to search for a health user cluster satisfying the basic profile, the disease type sequence, the disease age sequence, and the treatment scheme sequence, and obtain a nursing index distribution interval of the health user cluster; an abnormal user searching module 14 configured to search for an abnormal user cluster satisfying the basic profile, the disease type sequence, the disease age sequence, and the treatment scheme sequence, and obtain a high-frequency discrete value of a nursing index of the abnormal user cluster; an index threshold optimization module 15 configured to obtain a nursing index update threshold interval by taking an interval intersection of a nursing index rated threshold interval according to the nursing index distribution interval and the high-frequency discrete value of the nursing index; a nursing data recording module 16 configured to record nursing data of the target elderly user based on the nursing index update threshold interval.

[0063] Further, the health user searching module 13 comprises the following execution steps: constructing a strict index rule based on the basic profile; constructing a first-level fault-tolerant index rule based on the disease type sequence, the disease age sequence, and the treatment scheme sequence; searching for a first-level health user cluster satisfying the strict index rule and the first-level fault-tolerant index rule; constructing a second-level fault-tolerant index rule based on a first-level disease type sequence, a first-level disease age sequence, and a first-level treatment scheme sequence of the first-level health user cluster; searching for a second-level health user cluster satisfying the strict index rule and the second-level fault-tolerant index rule; statistically obtaining the nursing index distribution interval of the first-level health user cluster and the second-level health user cluster.

[0064] Further, the health user searching module 13 further comprises the following execution steps: grouping the second-level health user cluster based on the first-level health user cluster to obtain a plurality of second-level health user clusters; performing a same attribute index box plot evaluation on the plurality of second-level health user clusters to obtain a plurality of second-level nursing index box distribution intervals; performing a same attribute interval intersection analysis on the plurality of second-level nursing index box distribution intervals to obtain a second-level nursing index distribution interval; performing a same attribute index box plot evaluation on the first-level health user cluster to obtain a first-level nursing index box distribution interval; performing an intersection analysis on the second-level nursing index distribution interval and the first-level nursing index box distribution interval to obtain the nursing index distribution interval.

[0065] Further, the abnormal user retrieval module 14 comprises the following execution steps: obtaining a predefined nursing index outlier factor threshold value; performing attribute index outlier factor evaluation on the same cluster abnormal users to obtain a nursing index outlier factor set; based on the nursing index outlier factor set, extracting a selected nursing index outlier factor set with outlier factors less than or equal to the nursing index outlier factor threshold value; extracting nursing index record values of the selected nursing index outlier factor set and adding them to the nursing index high-frequency discrete values.

[0066] Further, the index threshold value optimization module 15 comprises the following execution steps: obtaining a first nursing index update threshold value interval by taking interval intersection between the nursing index distribution interval and the nursing index rated threshold value interval; when the nursing index high-frequency discrete value does not belong to the first nursing index update threshold value interval, setting the first nursing index update threshold value interval as the nursing index update threshold value interval; when the nursing index high-frequency discrete value belongs to the first nursing index update threshold value interval, deleting the nursing index high-frequency discrete value from the first nursing index update threshold value interval, obtaining a second nursing index update threshold value interval, and setting it as the nursing index update threshold value interval.

[0067] Further, the nursing data record module 16 comprises the following execution steps: obtaining nursing index monitoring data of the target elderly user; when the nursing index monitoring data belongs to the nursing index update threshold value interval, performing health identification on the nursing index monitoring data; when the nursing index monitoring data does not belong to the nursing index update threshold value interval, performing abnormal identification on the nursing index monitoring data; when the abnormal identification trigger frequency exceeds the predefined number of times for a continuous preset time length, sending a prompt information to the nurse station.

[0068] Further, the healthy user retrieval module 13 further comprises the following execution steps: sending the disease type sequence to the expert end to receive a first disease fault tolerance type set to an Mth disease fault tolerance type set of the disease type sequence; sending the disease age sequence and the diagnosis and treatment scheme sequence to the expert end to receive disease age deviation fault tolerance threshold value and diagnosis and treatment scheme fault tolerance threshold value; Based on the first disease fault tolerance type set to the Mth disease fault tolerance type set, the diseased age bias fault tolerance threshold and the treatment scheme fault tolerance threshold, the first-level fault tolerance index rule is constructed.

[0069] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0070] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0071] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in one or more blocks.

[0072] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in one or more blocks.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in one or more blocks.

[0074] While the preferred embodiments of the application have been described, additional variations and modifications can be made to these embodiments by those skilled in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application.

[0075] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims, the application can be practiced otherwise than as specifically described herein.

Claims

1. A nursing data evaluation and recording method for elderly clinical nursing, characterized in that: include: Obtaining a medical history profile of a target elderly user, wherein the medical history profile includes a sequence of symptom types, a sequence of ages at onset, and a sequence of diagnosis and treatment plans; Obtain a basic profile of target elderly users; Retrieving the distribution interval of nursing indicators of healthy users in the same cluster that meet the basic profile, the sequence of symptom types, the sequence of age at onset, and the sequence of diagnosis and treatment plans; Retrieving high-frequency discrete values ​​of nursing indicators of abnormal users in the same cluster that meet the basic profile, the disease type sequence, the disease age sequence, and the diagnosis and treatment plan sequence; Taking the intersection of the rated threshold intervals of the nursing indicator according to the nursing indicator distribution interval and the high-frequency discrete value of the nursing indicator to obtain the updated threshold interval of the nursing indicator; Nursing data is recorded for the target elderly user based on the nursing indicator update threshold interval.

2. The method according to claim 1, wherein Retrieving the distribution interval of nursing indicators of healthy users in the same cluster who meet the basic profile, the sequence of symptom types, the sequence of age at onset, and the sequence of diagnosis and treatment plans, including: Based on the basic profile, strict indexing rules are constructed; Constructing a first-level fault-tolerant index rule based on the disease type sequence, the age sequence, and the diagnosis and treatment plan sequence; Retrieving first-level healthy users in the same cluster that meet the strict indexing rule and the first-level fault-tolerant indexing rule; Constructing a second-level fault-tolerant index rule based on the first-level disease type sequence, the first-level disease age sequence, and the first-level diagnosis and treatment plan sequence of the first-level healthy users in the same cluster; Retrieving secondary healthy users in the same cluster that meet the strict indexing rule and the secondary fault-tolerant indexing rule; The distribution intervals of the nursing indicators of the first-level healthy users in the same cluster and the second-level healthy users in the same cluster are counted.

3. The method according to claim 2, wherein Counting the distribution intervals of the nursing indicators of the first-level healthy users in the same cluster and the second-level healthy users in the same cluster includes: Based on the first-level healthy users in the same cluster, grouping the second-level healthy users in the same cluster to obtain multiple groups of second-level healthy users in the same cluster; Traversing the plurality of groups of secondary healthy users in the same cluster to perform box plot evaluation of the same attribute indicators, and obtaining the box distribution intervals of the plurality of groups of secondary nursing indicators; Performing a same-attribute interval intersection analysis on the multiple groups of secondary nursing indicator box distribution intervals to obtain the secondary nursing indicator distribution intervals; Performing a box plot evaluation of the same attribute indicators for the first-level healthy users in the same cluster to obtain the box distribution interval of the first-level nursing indicator; The intersection of the secondary nursing indicator distribution interval and the primary nursing indicator box distribution interval is analyzed to obtain the nursing indicator distribution interval.

4. The method according to claim 1, wherein Retrieving high-frequency discrete values ​​of nursing indicators of abnormal users in the same cluster who meet the basic profile, the disease type sequence, the disease age sequence, and the diagnosis and treatment plan sequence, including: Obtain predefined nursing indicator outlier factor thresholds; Performing outlier factor evaluation on the same attribute indicators of the abnormal users in the same cluster to obtain a set of outlier factors of the nursing indicators; Extracting, based on the nursing indicator outlier factor set, a selected nursing indicator outlier factor set having an outlier factor less than or equal to the nursing indicator outlier factor threshold; The nursing indicator record values ​​of the selected nursing indicator outlier factor set are extracted and added to the nursing indicator high-frequency discrete values.

5. The method according to claim 1, wherein According to the nursing indicator distribution interval and the nursing indicator high-frequency discrete value, the interval intersection of the nursing indicator rated threshold interval is taken to obtain the nursing indicator update threshold interval, including: Obtaining a first nursing indicator update threshold interval by taking an interval intersection of the nursing indicator distribution interval and the nursing indicator rated threshold interval; When the high-frequency discrete value of the nursing indicator does not belong to the first nursing indicator update threshold interval, setting the first nursing indicator update threshold interval as the nursing indicator update threshold interval; When the high-frequency discrete value of the nursing indicator belongs to the first nursing indicator update threshold interval, the high-frequency discrete value of the nursing indicator is deleted from the first nursing indicator update threshold interval to obtain a second nursing indicator update threshold interval, which is set as the nursing indicator update threshold interval.

6. The method according to claim 1, wherein Recording nursing data for the target elderly user based on the nursing indicator updating threshold interval includes: Obtaining nursing indicator monitoring data of the target elderly user; When the nursing indicator monitoring data falls within the nursing indicator update threshold interval, performing a health mark on the nursing indicator monitoring data; When the nursing indicator monitoring data does not fall within the nursing indicator update threshold interval, marking the nursing indicator monitoring data as abnormal; When the abnormal flag trigger frequency exceeds the predefined number of times for a continuous preset time period, a prompt message is sent to the nurse station.

7. The method according to claim 2, wherein Based on the disease type sequence, the age sequence and the diagnosis and treatment plan sequence, a first-level fault-tolerant index rule is constructed, including: Sending the disease type sequence to an expert terminal, and receiving the first disease fault tolerance type set to the Mth disease fault tolerance type set of the disease type sequence; Sending the disease age sequence and the diagnosis and treatment plan sequence to the expert end, and receiving the disease age deviation tolerance threshold and the diagnosis and treatment plan error tolerance threshold; Based on the first disease fault tolerance type set up to the Mth disease fault tolerance type set, the disease age deviation fault tolerance threshold and the diagnosis and treatment plan fault tolerance threshold, the first-level fault tolerance index rule is constructed.

8. A nursing data evaluation and recording system for elderly clinical nursing, characterized by: For implementing the method according to any one of claims 1 to 7, comprising: A medical history portrait acquisition module is used to obtain the medical history portrait of the target elderly user, wherein the medical history portrait includes a sequence of symptom type, a sequence of age at onset, and a sequence of diagnosis and treatment plans; Basic portrait acquisition module, used to obtain the basic portrait of target elderly users; A healthy user retrieval module is used to retrieve the nursing indicator distribution intervals of healthy users in the same cluster that meet the basic profile, the disease type sequence, the disease age sequence, and the diagnosis and treatment plan sequence; An abnormal user retrieval module is used to retrieve high-frequency discrete values ​​of nursing indicators of abnormal users in the same cluster that meet the basic profile, the disease type sequence, the age sequence of the patient, and the diagnosis and treatment plan sequence; An indicator threshold optimization module, configured to obtain an interval intersection of the nursing indicator rated threshold interval based on the nursing indicator distribution interval and the nursing indicator high-frequency discrete value, and obtain a nursing indicator update threshold interval; A nursing data recording module is used to record nursing data for the target elderly user based on the nursing indicator update threshold interval.

Images