Medical care information processing method and system based on big data

Abstract

The invention discloses a medical care information processing method and system based on big data, and belongs to the technical field of information processing. Calling the nursing operation type, dosage and physiological index information of the patient from a medical nursing system; the method comprises the steps of constructing a medical care set, constructing a three-dimensional patient care risk matrix, calculating a care risk probability, calculating a care risk weight of a patient, constructing a two-dimensional care risk image matrix of the patient, presetting a care risk weight threshold value, and obtaining a care operation type and a dosage of the care risk weight greater than or equal to the care risk weight threshold value. A high-risk combination is constructed; and constructing a patient-based high-risk combination set, calculating risk similarity among different patients, presetting a risk similarity threshold, and performing analysis and comprehensive management. According to the method, the nursing risk of a single patient can be accurately quantified, the risk similarity among multiple patients can be further identified, a high-risk combination set is formed, and comprehensive management decision support is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and particularly to a method and system for processing medical care information based on big data. Background Art

[0002] With the rapid development of global medical informatization, big data technology has gradually penetrated into the field of medical care. Providing more accurate and efficient nursing services for patients has become an important research direction. Most traditional methods for processing medical care information rely on the experience judgment and manual records of medical staff. This method is not only easily interfered by human factors, resulting in incomplete and inaccurate data records, but also difficult to quickly analyze and deeply mine the massive patient data. In recent years, data acquisition technologies based on electronic medical records, monitoring devices, and intelligent sensors have gradually become popular, and the amount of medical care information data has increased exponentially, making big data analysis and mining an important means to improve the quality of medical care. Researchers have explored various data analysis models, such as risk assessment models based on rule matching, machine learning prediction models, etc. These methods have improved the ability to identify nursing risks to a certain extent. However, since existing methods often only focus on the changes of single indicators and lack the comprehensive analysis ability of multi-dimensional and multi-level nursing data, it is difficult to accurately depict the patient risk characteristics in complex nursing scenarios.

[0003] The deficiencies of the existing technology are mainly reflected in the following aspects: First, traditional methods often treat the abnormal conditions of patients' physiological indicators as independent events, ignoring the interaction relationship among the types of nursing operations, the dosage of medications, and physiological indicators, resulting in inaccurate risk assessment results; Second, most existing models lack a dynamic risk management mechanism for individual patients and cannot adjust nursing strategies in real time to cope with sudden abnormal situations; Third, there are limitations in the analysis of the risk correlation among multiple patients in the existing technology, and it is unable to effectively mine the potential common risk characteristics among patients, restricting the optimal allocation of nursing resources. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for processing medical care information based on big data to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A medical care information processing method based on big data, the method comprising the following steps: Step S1: After obtaining the authorization of the patient, retrieve the patient's nursing operation type, medication dosage, and patient physiological index information from the medical care system; sort the medical care information according to the nursing operation type, and construct a medical care set; Step S2: Based on the medical care set of the patient, construct a three-dimensional patient care risk matrix, and calculate the care risk probability that a single nursing operation type of the patient causes a single patient physiological index data abnormality due to a single medication dosage; Step S3: Based on the care risk probability, calculate the care risk weight that a single nursing operation type of the patient causes all patient physiological index data abnormalities due to a single medication dosage; based on the care risk weight, construct a two-dimensional care risk image matrix of the patient; Step S4: Based on the two-dimensional care risk image matrix, preset a care risk weight threshold, obtain the nursing operation types and medication dosages with care risk weights greater than or equal to the care risk weight threshold, and construct a high-risk combination; construct a high-risk combination set based on the patient, calculate the risk similarity between different patients, preset a risk similarity threshold, and analyze and conduct comprehensive management.

[0006] As a preferred embodiment of the medical care information processing method based on big data according to the present invention, after obtaining the authorization of the patient, retrieve the medical care information of the patient from the medical care system, where the medical care information refers to the medical care operation information, medication dosage, and patient physiological index information of the patient when receiving medical care; the medical care operation information includes the nursing operation type; Sort the medical care information according to the nursing operation type, and construct a medical care set, denoted as , where represents the t-th nursing operation type, represents the nursing operation type corresponding to the i-th medication dosage, represents the medication dosage corresponding to the a-th patient physiological index data, T represents the total number of nursing operation types, I represents the total number of medication dosages, A represents the total number of patient physiological index data, represents the medical care set of the h-th patient.

[0007] As a preferred embodiment of the medical care information processing method based on big data according to the present invention, based on the medical care set of the h-th patient, construct a three-dimensional patient care risk matrix, where the row dimension, column dimension, and layer dimension of the three-dimensional patient care risk matrix are the nursing operation type, medication dosage, and patient physiological index data respectively; in the three-dimensional patient care risk matrix, a cell represents a care risk probability, and the care risk probability that the t-th nursing operation type of the h-th patient causes the a-th patient physiological index data abnormality due to the i-th medication dosage is denoted as , and the probability of nursing risk The calculation formula is as follows: ; Wherein, represents the standard value of the physiological index data of the a-th patient preset.

[0008] As a preferred solution of the medical nursing information processing method based on big data according to the present invention, according to the t-th nursing operation type and the i-th medication amount of the h-th patient, the corresponding row dimension and column dimension are matched in the three-dimensional patient nursing risk matrix, and according to the matched row dimension and column dimension, the nursing risk probability of all abnormal physiological index data of patients in the corresponding layer dimension is extracted, and the nursing risk weight caused by the i-th medication amount for the t-th nursing operation type of the h-th patient is calculated. The calculation formula is as follows: ; Wherein, represents the nursing risk weight caused by the i-th medication amount for the t-th nursing operation type of the h-th patient, and A represents all the physiological index data of patients in the corresponding layer dimension; Based on the nursing risk weight caused by the i-th medication amount for the t-th nursing operation type of the h-th patient , a two-dimensional nursing risk image matrix of the h-th patient is constructed, specifically as follows: ; Wherein, represents the nursing risk weight caused by the I-th medication amount for the T-th nursing operation type of the h-th patient.

[0009] As a preferred solution of the medical nursing information processing method based on big data according to the present invention, based on the two-dimensional nursing risk image matrix of the h-th patient, a nursing risk weight threshold is preset. If the nursing risk weight caused by the i-th medication amount for the t-th nursing operation type of the h-th patient is greater than or equal to the nursing risk weight threshold ; Based on the high-risk combination , a high-risk combination set based on the h-th patient is constructed, denoted as ; Based on the high-risk combination set of the h-th patient, the risk similarity between the h-th patient and the h + 1-th patient is calculated. The calculation formula is as follows: ; Wherein, Represents the risk similarity between the h-th patient and the (h + 1)-th patient, represents the high-risk combination set of the (h + 1)-th patient; a preset risk similarity threshold. If the risk similarity between the h-th patient and the (h + 1)-th patient is greater than or equal to the risk similarity threshold, it is determined that there is an association relationship between the h-th patient and the (h + 1)-th patient; Comprehensively manage different patients with an association relationship, and remind relevant staff to adjust the nursing operation types and drug dosages in the high-risk combination.

[0010] A medical nursing information processing system based on big data. This system includes: a data acquisition and set construction module, a three-dimensional matrix construction module, a weight calculation and matrix construction module, and a combination construction and analysis module; The data acquisition and set construction module: After obtaining the patient's authorization, retrieve the patient's nursing operation types, drug dosages, and patient physiological index information from the medical nursing system; sort the medical nursing information according to the nursing operation types, and construct a medical nursing set; The three-dimensional matrix construction module: Based on the patient's medical nursing set, construct a three-dimensional patient nursing risk matrix, and calculate the nursing risk probability that a single nursing operation type of a patient causes abnormal physiological index data of a single patient due to a single drug dosage; The weight calculation and matrix construction module: Based on the nursing risk probability, calculate the nursing risk weight that a single nursing operation type of a patient causes abnormal physiological index data of all patients due to a single drug dosage; Based on the nursing risk weight, construct a two-dimensional nursing risk image matrix of the patient; The combination construction and analysis module: Based on the two-dimensional nursing risk image matrix, preset a nursing risk weight threshold, obtain the nursing operation types and drug dosages with nursing risk weights greater than or equal to the nursing risk weight threshold, and construct a high-risk combination; construct a high-risk combination set based on the patient, calculate the risk similarity between different patients, preset a risk similarity threshold, and analyze and conduct comprehensive management.

[0011] Furthermore, the data acquisition and set construction module includes a data acquisition unit and a set construction unit; The data acquisition unit: After obtaining the patient's authorization, retrieve the patient's medical nursing information from the medical nursing system. The medical nursing information refers to the medical nursing operation information, drug dosage, and patient physiological index information when the patient receives medical nursing; The medical nursing operation information includes nursing operation types; The set construction unit: Sort the medical nursing information according to the nursing operation types, and construct a medical nursing set.

[0012] Further, the three-dimensional matrix construction module includes a three-dimensional matrix construction unit; The three-dimensional matrix construction unit: Based on the medical care set of the patient, construct a three-dimensional patient care risk matrix, where the row dimension, column dimension, and layer dimension of the three-dimensional patient care risk matrix are the nursing operation type, the dosage of medicine, and the patient's physiological index data respectively; in the three-dimensional patient care risk matrix, a cell represents a nursing risk probability.

[0013] Further, the weight calculation and matrix construction module includes a weight calculation unit and a matrix construction unit; The weight calculation unit: According to the single nursing operation type and single dosage of medicine of a single patient, match the corresponding row dimension and column dimension in the three-dimensional patient care risk matrix, and according to the matched row dimension and column dimension, extract the nursing risk probabilities with abnormal physiological index data of all patients in the corresponding layer dimension, and calculate the nursing risk weight caused by the single dosage of medicine for the single nursing operation type of a single patient; The matrix construction unit: Based on the nursing risk weight of the single nursing operation type of a single patient due to the single dosage of medicine, construct a two-dimensional nursing risk image matrix of a single patient.

[0014] Further, the combination construction and analysis module includes a combination construction unit and an analysis unit; The combination construction unit: Based on the two-dimensional nursing risk image matrix of a single patient, preset a nursing risk weight threshold. If the nursing risk weight of the single nursing operation type of a single patient due to the single dosage of medicine is greater than or equal to the nursing risk weight threshold, then record the single nursing operation type and the single dosage of medicine as a high-risk combination; The analysis unit: Based on the high-risk combinations, construct a high-risk combination set for a single patient; based on the high-risk combination set of a single patient, calculate the risk similarity between different patients; preset a risk similarity threshold. If the risk similarity between different patients is greater than or equal to the risk similarity threshold, then determine that there is an association relationship between different patients; conduct comprehensive management on different patients with an association relationship, and remind relevant staff to adjust the nursing operation type and dosage of medicine in the high-risk combination.

[0015] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In the medical care information processing method and system based on big data provided by the present invention, through constructing a three-dimensional patient care risk matrix and a two-dimensional nursing risk image matrix, multi-dimensional correlation analysis of the nursing operation type, dosage of medicine, and patient's physiological index data is realized. It can not only accurately quantify the nursing risk of a single patient, but also further identify the risk similarity between multiple patients, form a high-risk combination set, and provide comprehensive management decision support; the present invention solves the problem of how to realize multi-dimensional nursing risk quantification and comprehensive management of the relevance between multiple patients based on big data. Description of the Drawings

[0016] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention.

[0017] Figure 1 is a schematic diagram of the steps of a method for processing medical care information based on big data according to the present invention; Figure 2 is a schematic structural diagram of a system for processing medical care information based on big data according to the present invention. Detailed Embodiments

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] Please refer to Figure 1 , in the first embodiment: A method for processing medical care information based on big data is provided, and the method includes the following steps: Step S1: After the patient's authorization, retrieve the patient's nursing operation type, medication dosage, and patient physiological index information from the medical care system; sort the medical care information according to the nursing operation type, and construct a medical care set.

[0020] Specifically, after the patient's authorization, retrieve the patient's medical care information from the medical care system. The medical care information refers to the medical care operation information, medication dosage, and patient physiological index information when the patient receives medical care; the medical care operation information includes the nursing operation type. Further, sort the medical care information according to the nursing operation type, and construct a medical care set, denoted as , where represents the t-th nursing operation type, represents the i-th medication dosage corresponding to the nursing operation type , represents the a-th patient physiological index data corresponding to the medication dosage , T represents the total number of nursing operation types, I represents the total number of medication dosages, A represents the total number of patient physiological index data, represents the medical care set of the h-th patient.

[0021] ​It should be noted that this step forms a structured nursing data set, providing a unified data basis for subsequent analysis. Specifically, by obtaining medical nursing information with the patient's authorization, the legality and integrity of the data are ensured, laying a foundation for precise nursing analysis. Sorting by nursing operation type, the originally chaotic nursing data is classified and organized according to the operation type, improving the orderliness of the data and facilitating subsequent extraction and analysis. Constructing a medical nursing set, associating the nursing operation type, the dosage of medicine, and the patient's physiological index information, establishing a personalized nursing file for the patient, realizing the structuring of the data, and providing multi-dimensional data support for further risk assessment; this step realizes the standardized modeling of the patient's nursing data, laying a data foundation for the construction of the subsequent risk matrix, avoiding misjudgment caused by incomplete and non-standard data in the traditional analysis process, and thus improving the accuracy of nursing decisions.

[0022] Step S2: Based on the medical nursing set of the patient, construct a three-dimensional patient nursing risk matrix, and calculate the nursing risk probability that the physiological index data of a single patient is abnormal due to a single dosage of medicine for a single nursing operation type of the patient.

[0023] Specifically, based on the medical nursing set of the h-th patient , construct a three-dimensional patient nursing risk matrix. The row dimension, column dimension, and layer dimension of the three-dimensional patient nursing risk matrix are the nursing operation type, the dosage of medicine, and the patient's physiological index data respectively; in the three-dimensional patient nursing risk matrix, a cell represents a nursing risk probability. Denote the nursing risk probability that the a-th patient's physiological index data is abnormal due to the i-th dosage of medicine for the t-th nursing operation type of the h-th patient as , and the nursing risk probability is calculated as follows: ; where represents the preset standard value of the a-th patient's physiological index data.

[0024] It should be noted that this step transforms the complex nursing relationship into a three-dimensional matrix, establishes specific risk probability mappings for each operation, each medication, and each physiological index, quantifies the nursing risks. Specifically, a three-dimensional nursing risk matrix is constructed, binding the nursing operation types, medication dosages, and patient physiological indices together to form a data cube, facilitating the analysis of risk changes in each dimension layer by layer. Each cell corresponds to a specific risk probability, accurately quantifying the risk degree of each nursing operation and medication on the physiological indices of a specific patient, achieving a refined expression of risks and avoiding errors caused by empirical judgments. By introducing a comparison with standard values, the real-time physiological indices of the patient are compared with the preset standard values to dynamically evaluate the nursing risks, enhancing the timeliness and scientific nature of risk assessment. This step realizes a refined quantitative expression of nursing risks, enabling the risks of each nursing operation and medication to be captured at a fine-grained level, providing strong data support for the subsequent comprehensive analysis of risk weights, and enhancing the sensitivity of risk identification.

[0025] Step S3: Based on the nursing risk probabilities, calculate the nursing risk weight for a single nursing operation type of a patient due to a single medication dosage resulting in abnormal physiological index data of all patients; based on the nursing risk weights, construct a two-dimensional nursing risk image matrix for the patient.

[0026] Specifically, according to the t-th nursing operation type and the i-th medication dosage of the h-th patient, match the corresponding row dimension and column dimension in the three-dimensional patient nursing risk matrix. According to the matched row dimension and column dimension, extract the nursing risk probabilities of abnormal physiological index data of all patients in the corresponding layer dimension, and calculate the nursing risk weight for the t-th nursing operation type of the h-th patient due to the i-th medication dosage. The calculation formula is as follows: ; where, represents the nursing risk weight for the t-th nursing operation type of the h-th patient due to the i-th medication dosage, and A represents all the physiological index data of patients in the corresponding layer dimension; Furthermore, based on the nursing risk weight for the t-th nursing operation type of the h-th patient due to the i-th medication dosage, construct the two-dimensional nursing risk image matrix for the h-th patient, specifically as follows: ; where, represents the nursing risk weight for the T-th nursing operation type of the h-th patient due to the I-th medication dosage.

[0027] It should be noted that this step expands the single-point risk probability into a comprehensive risk weight, breaks through the limitations of single indicators, and realizes the comprehensive risk assessment from single-dimensional anomalies to multi-dimensional anomalies. Specifically, it extracts the abnormal risks of all physiological index data, no longer limited to a single indicator, expands the coverage of risk assessment, and improves the comprehensiveness of risk identification. It calculates the comprehensive risk weight of nursing operation types and medications, combines the anomalies of multiple indicators into a single weight value, which is convenient for subsequent screening and management of high-risk combinations, and improves the intuitiveness and efficiency of risk assessment. It constructs a two-dimensional nursing risk image matrix, visualizes the nursing operation types and medications in matrix form, which is convenient for quickly identifying risk aggregation areas and helping medical staff more intuitively judge high-risk points. This step realizes the weighted comprehensive assessment of multi-index risks, forms an intuitive risk image matrix, breaks through the dependence of traditional nursing plans on single-point indicators, improves the integrity and usability of risk assessment, and provides a more accurate basis for subsequent screening of high-risk combinations.

[0028] Step S4: Based on the two-dimensional nursing risk image matrix, preset the nursing risk weight threshold, obtain the nursing operation types and medication amounts with nursing risk weights greater than or equal to the nursing risk weight threshold, and construct high-risk combinations; construct a high-risk combination set based on patients, calculate the risk similarity between different patients, preset the risk similarity threshold, and analyze and conduct comprehensive management.

[0029] Specifically, based on the two-dimensional nursing risk image matrix of the h-th patient, preset the nursing risk weight threshold , if the nursing risk weight of the t-th nursing operation type of the h-th patient due to the i-th medication amount is greater than or equal to the nursing risk weight threshold , then record the t-th nursing operation type and the i-th medication amount as a high-risk combination, denoted as ; Furthermore, based on the high-risk combination , construct a high-risk combination set based on the h-th patient, denoted as ; Based on the high-risk combination set of the h-th patient, calculate the risk similarity between the h-th patient and the (h + 1)-th patient. The calculation formula is as follows: ; Among them, represents the risk similarity between the h-th patient and the (h + 1)-th patient, represents the high-risk combination set of the (h + 1)-th patient; Even further, preset the risk similarity threshold. If the risk similarity between the h-th patient and the (h + 1)-th patient If it is greater than or equal to the risk similarity threshold, it is determined that there is an association relationship between the h-th patient and the (h + 1)-th patient; Comprehensively manage different patients with an association relationship, and remind relevant staff of high-risk combinations to adjust the nursing operation types and medication dosages in them.

[0030] It should be noted that this step introduces the multi-patient risk similarity assessment, forms a cross-patient risk association network, and realizes the collaborative risk management of the patient group. Specifically, it screens high-risk combinations, quickly locates high-risk operations and medications, pre-identifies potential nursing risks, and effectively prevents the spread of risks. Construct a high-risk combination set, package and manage high-risk nursing operations and medication combinations, which is convenient for the medical team to quickly identify and respond in actual operations, and improve the emergency response speed. Introduce risk similarity calculation, compare the high-risk combinations of different patients, quantify the degree of risk association between patients, help the medical team identify patient groups with similar risk patterns, and achieve early detection and early intervention. Comprehensive management and adjustment, for patient groups with high-risk associations, remind medical staff to timely adjust the nursing plan, avoid the spread of risks, and realize the pre-emptive management of risk prevention and control. This step breaks through the traditional single-patient management mode, realizes the group management of cross-patient risks, further improves the medical nursing risk warning ability, and provides a more systematic risk control plan for large-scale medical nursing scenarios.

[0031] Please refer to Figure 2 , in the second embodiment: Provide a medical nursing information processing system based on big data, which includes: a data acquisition and set construction module, a three-dimensional matrix construction module, a weight calculation and matrix construction module, and a combination construction and analysis module; The data acquisition and set construction module: After obtaining the authorization of the patient, retrieve the nursing operation types, medication dosages, and patient physiological index information of the patient from the medical nursing system; sort the medical nursing information according to the nursing operation types, and construct a medical nursing set; The three-dimensional matrix construction module: Based on the medical nursing set of the patient, construct a three-dimensional patient nursing risk matrix, and calculate the nursing risk probability that a single nursing operation type of the patient causes abnormal physiological index data of a single patient due to a single medication dosage; The weight calculation and matrix construction module: Based on the nursing risk probability, calculate the nursing risk weight that a single nursing operation type of the patient causes abnormal physiological index data of all patients due to a single medication dosage; based on the nursing risk weight, construct a two-dimensional nursing risk image matrix of the patient; The combined construction and analysis module: Based on the two-dimensional nursing risk image matrix, preset the nursing risk weight threshold, obtain the nursing operation types and medication dosages with nursing risk weights greater than or equal to the nursing risk weight threshold, and construct a high-risk combination; construct a high-risk combination set based on patients, calculate the risk similarity between different patients, preset the risk similarity threshold, and analyze and conduct comprehensive management.

[0032] Furthermore, the data acquisition and set construction module includes a data acquisition unit and a set construction unit; The data acquisition unit: After obtaining the patient's authorization, retrieve the patient's medical nursing information from the medical nursing system. The medical nursing information refers to the medical nursing operation information, medication dosage, and patient physiological index information when the patient receives medical nursing; the medical nursing operation information includes the nursing operation type. The set construction unit: Sort the medical nursing information according to the nursing operation type and construct a medical nursing set.

[0033] Furthermore, the three-dimensional matrix construction module includes a three-dimensional matrix construction unit; The three-dimensional matrix construction unit: Based on the patient's medical nursing set, construct a three-dimensional patient nursing risk matrix. The row dimension, column dimension, and layer dimension of the three-dimensional patient nursing risk matrix are the nursing operation type, medication dosage, and patient physiological index data respectively; in the three-dimensional patient nursing risk matrix, a cell represents a nursing risk probability.

[0034] Furthermore, the weight calculation and matrix construction module includes a weight calculation unit and a matrix construction unit; The weight calculation unit: According to the single nursing operation type and single medication dosage of a single patient, match the corresponding row dimension and column dimension in the three-dimensional patient nursing risk matrix. According to the matched row dimension and column dimension, extract the nursing risk probabilities with all abnormal patient physiological index data in the corresponding layer dimension, and calculate the nursing risk weight caused by the single medication dosage for the single nursing operation type of the single patient. The matrix construction unit: Based on the nursing risk weight of the single nursing operation type of a single patient due to the single medication dosage, construct a two-dimensional nursing risk image matrix for the single patient.

[0035] Furthermore, the combined construction and analysis module includes a combined construction unit and an analysis unit; The combined construction unit: Based on the two-dimensional nursing risk image matrix of a single patient, preset the nursing risk weight threshold. If the nursing risk weight of the single nursing operation type of the single patient due to the single medication dosage is greater than or equal to the nursing risk weight threshold, record the single nursing operation type and the single medication dosage as a high-risk combination; The analysis unit: Based on the high-risk combination, construct a high-risk combination set for each individual patient; Based on the high-risk combination set for each individual patient, calculate the risk similarity between different patients; Preset a risk similarity threshold. If the risk similarity between different patients is greater than or equal to the risk similarity threshold, it is determined that there is an association relationship between different patients; Comprehensively manage different patients with an association relationship, and remind relevant staff to adjust the nursing operation types and medication dosages in the high-risk combination.

[0036] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0037] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for processing medical care information based on big data, characterized in that, The method includes the following steps: Step S1: After obtaining the authorization from the patient, retrieve the patient's nursing operation type, medication dosage, and patient physiological index information from the medical care system; sort the medical care information according to the nursing operation type, and construct a medical care set; Step S2: Based on the patient's medical care set, construct a three-dimensional patient care risk matrix, and calculate the care risk probability that a single nursing operation type of the patient causes abnormal physiological index data of a single patient due to a single medication dosage; Step S3: Based on the care risk probability, calculate the care risk weight that a single nursing operation type of the patient causes abnormal physiological index data of all patients due to a single medication dosage; based on the care risk weight, construct a two-dimensional care risk image matrix of the patient; Step S4: Based on the two-dimensional care risk image matrix, preset a care risk weight threshold, obtain the nursing operation types and medication dosages with care risk weights greater than or equal to the care risk weight threshold, and construct a high-risk combination; construct a high-risk combination set based on the patient, calculate the risk similarity between different patients, preset a risk similarity threshold, and analyze and conduct comprehensive management.

2. The method for processing medical care information based on big data according to claim 1, wherein, The specific implementation process of step S1 includes: After obtaining the authorization from the patient, retrieve the patient's medical care information from the medical care system, where the medical care information refers to the medical care operation information, medication dosage, and patient physiological index information when the patient receives medical care; the medical care operation information includes the nursing operation type; Sort the medical care information according to the described nursing operation type, and construct a medical care set, denoted as , where represents the t-th nursing operation type, represents the nursing operation type corresponding to the i-th dosage of medicine, represents the dosage of medicine corresponding to the a-th patient physiological index data. T represents the total number of nursing operation types, I represents the total number of dosages of medicine, A represents the total number of patient physiological index data, represents the medical care set of the h-th patient.

3. The method for processing medical care information based on big data according to claim 2, wherein The specific implementation process of step S2 includes: Medical care set based on the h-th patient , a three-dimensional patient care risk matrix is constructed. The row dimension, column dimension, and layer dimension of the three-dimensional patient care risk matrix are the types of nursing operations, the dosage of medications, and the patient's physiological index data respectively; in the three-dimensional patient care risk matrix, a cell represents a nursing risk probability, and the nursing risk probability that the t-th type of nursing operation of the h-th patient causes the a-th patient's physiological index data to be abnormal due to the i-th dosage of medication is denoted as , and the nursing risk probability is calculated as follows: ； Among them, represents the standard value of the physiological index data of the a-th patient preset.

4. A method for processing medical care information based on big data according to claim 3, characterized in that, The specific implementation process of step S3 includes: According to the t-th nursing operation type and the i-th medication dosage of the h-th patient, match the corresponding row dimension and column dimension in the three-dimensional patient care risk matrix, and according to the matched row dimension and column dimension, extract the care risk probability of abnormal physiological index data of all patients in the corresponding layer dimension, and calculate the care risk weight caused by the t-th nursing operation type of the h-th patient due to the i-th medication dosage. The calculation formula is as follows: ； Among them, represents the nursing risk weight of the t-th type of nursing operation for the h-th patient due to the i-th dosage of medication, and A represents all the physiological index data of the patients in the corresponding layer dimension; Nursing risk weight for the t-th type of nursing operation based on the h-th patient due to the i-th drug dosage , construct a two-dimensional nursing risk image matrix for the h-th patient, specifically as follows: ； Among them, represents the nursing risk weight of the T-th type of nursing operation for the h-th patient due to the I-th dosage of medication.

5. A method for processing medical care information based on big data according to claim 4, characterized in that The specific implementation process of step S4 includes: Based on the two-dimensional nursing risk image matrix of the h-th patient, a preset nursing risk weight threshold , if the nursing risk weight of the t-th nursing operation type of the h-th patient due to the i-th dosage of medicine is greater than or equal to the nursing risk weight threshold , then the t-th nursing operation type and the i-th dosage of medicine are recorded as a high-risk combination, denoted as ; Based on the high-risk portfolio , construct a high-risk portfolio set based on the h-th patient, denoted as ; Based on the high-risk combination set of the h-th patient, calculate the risk similarity between the h-th patient and the h+1-th patient. The calculation formula is as follows: ； Among them, represents the risk similarity between the h-th patient and the (h + 1)-th patient, represents the high-risk combination set of the (h + 1)-th patient; Preset a risk similarity threshold. If the risk similarity between the h-th patient and the (h + 1)-th patient is greater than or equal to the risk similarity threshold, it is determined that there is an association relationship between the h-th patient and the (h + 1)-th patient; Comprehensively manage different patients with associated relationships and remind relevant staff to adjust the types of nursing operations and medication dosages in the high-risk combination.

6. A medical care information processing system based on big data, which executes a medical care information processing method based on big data as described in any one of claims 1-5, characterized in that, The system includes: a data acquisition and set construction module, a three-dimensional matrix construction module, a weight calculation and matrix construction module, and a combination construction and analysis module; The data acquisition and set construction module: After obtaining the authorization from the patient, retrieve the patient's nursing operation type, medication dosage, and patient physiological index information from the medical care system; sort the medical care information according to the nursing operation type, and construct a medical care set; The three-dimensional matrix construction module: Based on the patient's medical care set, construct a three-dimensional patient care risk matrix, and calculate the care risk probability that a single nursing operation type of the patient causes abnormal physiological index data of a single patient due to a single medication dosage; The weight calculation and matrix construction module: Based on the care risk probability, calculate the care risk weight that a single nursing operation type of the patient causes abnormal physiological index data of all patients due to a single medication dosage; based on the care risk weight, construct a two-dimensional care risk image matrix of the patient; The combined construction and analysis module: Based on the two-dimensional nursing risk image matrix, preset the nursing risk weight threshold, obtain the nursing operation types and drug dosages with nursing risk weights greater than or equal to the nursing risk weight threshold, and construct a high-risk combination; construct a high-risk combination set based on patients, calculate the risk similarity between different patients, preset the risk similarity threshold, and analyze and conduct comprehensive management.

7. The medical care information processing system based on big data according to claim 6, wherein: The data acquisition and set construction module includes a data acquisition unit and a set construction unit; The data acquisition unit: After obtaining the patient's authorization, retrieve the patient's medical nursing information from the medical nursing system. The medical nursing information refers to the medical nursing operation information, drug dosage, and patient physiological index information when the patient receives medical nursing; the medical nursing operation information includes the nursing operation type. The set construction unit: Sort the medical nursing information according to the nursing operation type and construct a medical nursing set.

8. A medical care information processing system based on big data according to claim 7, characterized in that: The three-dimensional matrix construction module includes a three-dimensional matrix construction unit; The three-dimensional matrix construction unit: Based on the patient's medical nursing set, construct a three-dimensional patient nursing risk matrix. The row dimension, column dimension, and layer dimension of the three-dimensional patient nursing risk matrix are the nursing operation type, drug dosage, and patient physiological index data respectively. In the three-dimensional patient nursing risk matrix, a cell represents a nursing risk probability.

9. The medical care information processing system based on big data according to claim 8, characterized in that: The weight calculation and matrix construction module includes a weight calculation unit and a matrix construction unit; The weight calculation unit: According to the single nursing operation type and single drug dosage of a single patient, match the corresponding row dimension and column dimension in the three-dimensional patient nursing risk matrix. According to the matched row dimension and column dimension, extract the nursing risk probabilities with all patient physiological index data abnormal in the corresponding layer dimension, and calculate the nursing risk weight caused by the single drug dosage for the single nursing operation type of the single patient. The matrix construction unit: Based on the nursing risk weight of the single nursing operation type of a single patient due to the single drug dosage, construct a two-dimensional nursing risk image matrix for the single patient.

10. A medical care information processing system based on big data according to claim 9, characterized in that: The combined construction and analysis module includes a combined construction unit and an analysis unit; The combined construction unit: Based on the two-dimensional nursing risk image matrix of a single patient, preset the nursing risk weight threshold. If the nursing risk weight of the single nursing operation type of a single patient due to the single drug dosage is greater than or equal to the nursing risk weight threshold, record the single nursing operation type and single drug dosage as a high-risk combination. The analysis unit: Based on the high-risk combination, construct a high-risk combination set based on a single patient; based on the high-risk combination set of a single patient, calculate the risk similarity between different patients; Preset the risk similarity threshold. If the risk similarity between different patients is greater than or equal to the risk similarity threshold, determine that there is an association relationship between different patients; conduct comprehensive management on different patients with an association relationship, and remind relevant staff to adjust the nursing operation types and drug dosages in the high-risk combination.

Images