A method and system for monitoring the care of hospitalized patients in the gastroenterology department based on big data

Abstract

This invention relates to the field of inpatient nursing technology and discloses a method and system for monitoring inpatient nursing care in gastroenterology departments based on big data. The method includes: collecting nursing data information of gastroenterology patients during their inpatient care, as well as collecting information on changes in the patients' conditions and nursing data for different nursing segments; processing the nursing data information to obtain patient nursing status information; extracting first nursing data information from the nursing data of different nursing segments based on the information on changes in the patients' conditions; predicting second nursing data information based on a constructed nursing model; comparing and analyzing the first and second nursing data information to obtain a first nursing early warning marker set; and collecting a standard nursing operation dataset and an executed nursing operation dataset based on the first nursing early warning marker set. This invention enables managers and nursing staff to accurately identify different levels of risk.

Description

Technical Field

[0001] This invention relates to the field of inpatient nursing technology, and in particular to a method and system for monitoring inpatient nursing care in the gastroenterology department based on big data. Background Technology

[0002] In the modern medical system, the conditions of patients in the gastroenterology department are often complex and variable, such as acute pancreatitis and gastrointestinal bleeding. The quality of their nursing care is directly related to the patient's recovery and safety. However, the special nature of gastroenterological diseases exacerbates the difficulty of nursing supervision. Taking patients with chronic diseases such as gastric ulcers and cirrhosis as an example, their nursing cycle is long and involves many procedures, including vital sign monitoring, medication management, dietary intervention, and other multi-dimensional nursing content. Manual supervision is difficult to fully cover all aspects.

[0003] For patients with acute gastrointestinal diseases such as gastrointestinal perforation, the condition changes rapidly, requiring more timely and standardized nursing procedures. Traditional supervision models, lacking real-time data comparison and early warning mechanisms, are unable to achieve early intervention for risks. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method and system for monitoring inpatient nursing care in the gastroenterology department based on big data, which can solve the problem that traditional monitoring models are difficult to intervene in advance due to the lack of real-time data comparison and early warning mechanisms.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for monitoring inpatient nursing care in gastroenterology departments based on big data, including:

[0008] Collect nursing data on patients in the gastroenterology department during their hospitalization, as well as information on changes in their condition and nursing data for different nursing areas.

[0009] Nursing data is processed to obtain patient nursing status information;

[0010] The nursing data of the nursing segment is extracted based on the information of changes in the patient's condition to obtain the first nursing data information; the nursing data is predicted based on the constructed nursing model to obtain the second nursing data information; the first nursing data information and the second nursing data information are compared and analyzed to obtain the first nursing early warning mark set.

[0011] A standard nursing operation dataset and an executed nursing operation dataset are collected based on a first nursing warning marker set. The standard nursing operation dataset and the executed nursing operation dataset are compared to obtain a segment information set. The segment information set includes a first nursing warning marker segment information set, a second nursing warning marker segment information set, and a nursing safety misjudgment segment result set.

[0012] The nursing supervision early warning information notification result is obtained by processing the early warning information based on the patient's nursing status information, the first nursing early warning marker segment information set, the second nursing early warning marker segment information set, and the nursing safety misjudgment segment result set.

[0013] As a preferred embodiment of the big data-based gastroenterology inpatient nursing supervision method described in this invention, a segment information set is obtained by comparing a standard nursing operation dataset and an executed nursing operation dataset; wherein, the segment information set includes a first nursing warning marker segment information set, a second nursing warning marker segment information set, and a nursing safety misjudgment segment result set, specifically:

[0014] Compare the standard nursing procedure dataset and the performed nursing procedure dataset;

[0015] If the same situation exists in the standard nursing operation dataset and the executed nursing operation dataset, the first nursing warning marker segment information set will be output.

[0016] If there are discrepancies between the standard nursing operation dataset and the executed nursing operation dataset, the results will be processed and analyzed to output a second nursing warning marker segment information set and a nursing safety misjudgment segment result set.

[0017] As a preferred embodiment of the big data-based inpatient nursing monitoring method for gastroenterology described in this invention, the method involves processing nursing data to obtain patient nursing status information, specifically including the following steps:

[0018] Nursing data of patients in the gastroenterology department are collected, and nursing status information is obtained by identifying the nursing status of the nursing data.

[0019] Pre-set matching nursing data based on nursing status information;

[0020] First and second executed nursing data are obtained by matching nursing data and nursing status information; wherein, the first and second executed nursing data are combined to form an executed nursing dataset;

[0021] The nursing condition information is compared with the preset standard nursing condition information to obtain the difference information and the same information;

[0022] The first and second data collection points are set based on the difference information section;

[0023] The first feedback nursing data from the first data collection point is statistically analyzed based on the matched nursing data, and the second feedback nursing data from the second data collection point is statistically analyzed based on the matched nursing data; wherein, the first feedback nursing data and the second feedback nursing data are combined to form a feedback nursing dataset;

[0024] Patient nursing status information is obtained by processing and analyzing nursing status information, executed nursing datasets, and feedback nursing datasets.

[0025] As a preferred embodiment of the big data-based inpatient nursing supervision method for gastroenterology described in this invention, the method involves processing and analyzing nursing status information, executed nursing datasets, and feedback nursing datasets to obtain patient nursing status information. Specifically, this includes the following steps:

[0026] If the first feedback nursing data is the same as the first executed nursing data and the second feedback nursing data is the same as the second executed nursing data, then the nursing status information is determined to be the patient's nursing status information.

[0027] If the first feedback nursing data is the same as the first executed nursing data and the second feedback nursing data is different from the second executed nursing data, or if the first feedback nursing data is different from the first executed nursing data and the second feedback nursing data is the same as the second executed nursing data, then output the compliant nursing data and non-compliant nursing data.

[0028] The patient's nursing status information is obtained by processing and analyzing the data of compliant nursing care, non-compliant nursing care, the first data collection point, the second data collection point, and the executed nursing care dataset.

[0029] As a preferred embodiment of the big data-based inpatient nursing supervision method for gastroenterology described in this invention, the patient's nursing status information is obtained by processing and analyzing the compliant nursing data, non-compliant nursing data, the first data collection point, the second data collection point, and the executed nursing dataset. Specifically, this includes the following steps:

[0030] Based on the substandard nursing data, select the data collection points that need to be adjusted from the first and second data collection points, and obtain the third feedback nursing data based on the adjusted data collection points;

[0031] Based on the non-compliance nursing data, the corresponding comparison nursing data is selected from the first and second execution nursing data. When the third feedback nursing data is the same as the comparison nursing data, the first comparison difference information is identified based on the third feedback nursing data and the compliant nursing data.

[0032] The first comparison difference information and the difference information part are integrated to obtain the first integrated difference information part. The patient care status information is obtained based on the first integrated difference information part and the same information part.

[0033] As a preferred embodiment of the gastroenterology inpatient nursing supervision method based on big data described in this invention, a first nursing early warning marker set is obtained by comparing and analyzing the first nursing data information and the second nursing data information, specifically as follows:

[0034] The nursing data comparison results are obtained by comparing the first nursing data information and the second nursing data information.

[0035] A preset nursing data difference range judgment value is set. The corresponding difference nursing data segments that are greater than or equal to the nursing data difference range judgment value are extracted from the nursing data comparison results. The difference nursing data segment set is output according to the corresponding difference nursing data segments, and the difference nursing data segment set is marked as the first nursing warning mark.

[0036] As a preferred embodiment of the big data-based gastroenterology inpatient nursing supervision method described in this invention, if there are discrepancies between the standard nursing operation dataset and the executed nursing operation dataset, the method is processed and analyzed to output a second nursing warning marker segment information set and a nursing safety misjudgment segment result set. Specifically, this includes the following steps:

[0037] The difference between corresponding data in the standard nursing operation dataset and the performed nursing operation dataset is calculated to obtain the set of operation data difference ranges.

[0038] A preset range of nursing operation data difference values ​​is defined. The nursing warning mark segment information set is obtained by extracting the nursing warning mark segment corresponding to the preset range of nursing operation data difference values ​​from the set of operation data difference values.

[0039] Extract the nursing warning marker segment that is not located in the preset nursing operation data difference range value to obtain the nursing safety misjudgment segment result set.

[0040] Secondly, the present invention provides a big data-based inpatient nursing monitoring system for gastroenterology departments, comprising:

[0041] Data collection module: Collects nursing data information of gastroenterology patients during hospitalization, as well as information on changes in the condition of gastroenterology patients and nursing data of nursing areas;

[0042] Processing module: Processes nursing data to obtain patient nursing status information;

[0043] Extraction and Analysis Module: Extracts nursing data from nursing segments based on changes in patient condition to obtain first nursing data information; predicts nursing data based on the constructed nursing model to obtain second nursing data information; compares and analyzes the first and second nursing data information to obtain a first nursing early warning marker set;

[0044] The data acquisition and comparison module acquires a standard nursing operation dataset and an executed nursing operation dataset based on the first nursing warning marker set, and compares the standard nursing operation dataset and the executed nursing operation dataset to obtain a segment information set; wherein, the segment information set includes a first nursing warning marker segment information set, a second nursing warning marker segment information set, and a nursing safety misjudgment segment result set;

[0045] Early warning module: Based on patient nursing status information, first nursing early warning marker segment information set, second nursing early warning marker segment information set, and nursing safety misjudgment segment result set, early warning processing is performed to obtain nursing supervision early warning information notification results.

[0046] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a big data-based method for monitoring inpatient nursing care in the gastroenterology department.

[0047] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention proposes a method and system for monitoring inpatient nursing care in gastroenterology based on big data. By calculating the difference between the standard and executed nursing operation datasets and determining the intervals, it accurately captures nursing operation deviations. In terms of risk stratification management, the solution constructs a clear risk differentiation mechanism. The second nursing warning marking segment focuses on scenarios where "deviations are controllable" to prompt nursing staff to pay continuous attention. The nursing safety misjudgment segment quickly marks high-risk operations for situations where "deviations exceed limits," enabling managers and nursing staff to accurately identify different levels of risk. Emergency verification and process rectification are immediately initiated for high-risk misjudgment segments. Routine monitoring of the warning segments is carried out to achieve efficient and stratified risk control and ensure the bottom line of patient safety. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This invention provides a step-by-step schematic diagram of a gastroenterology inpatient nursing supervision method based on big data.

[0050] Figure 2 This invention presents a schematic diagram of a big data-based inpatient nursing monitoring system for the gastroenterology department;

[0051] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0052] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0053] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0054] Example 1, referring to Figures 1-3 This is the first embodiment of the present invention, which provides a method for monitoring inpatient nursing care in a gastroenterology department based on big data, including:

[0055] Collect nursing data on patients in the gastroenterology department during their hospitalization, as well as information on changes in their condition and nursing data for different nursing areas.

[0056] Nursing data is processed to obtain patient nursing status information;

[0057] Clearly define the boundaries of data collection: Only collect data directly related to inpatient nursing care in the gastroenterology department, such as nursing operation records and disease monitoring indicators (body temperature, degree of abdominal pain, etc.), and do not collect additional personal information unrelated to diagnosis and treatment (such as patients' social media accounts, non-essential family information, etc.).

[0058] Authorization and notification: Upon patient admission, medical staff will explain the purpose of data collection (for nursing quality supervision, disease analysis and risk warning, and to improve the level of diagnosis and treatment services), scope, storage period (stored for [X] years from discharge, anonymized upon expiration), and usage method (only for analysis within the internal nursing supervision system of this medical institution, and not shared externally). Data collection will only begin after the patient signs the "Informed Consent Form for Data Collection and Use".

[0059] The nursing data of the nursing segment is extracted based on the information of changes in the patient's condition to obtain the first nursing data information; the nursing data is predicted based on the constructed nursing model to obtain the second nursing data information; the first nursing data information and the second nursing data information are compared and analyzed to obtain the first nursing early warning mark set.

[0060] Based on the first nursing warning marker set, standard nursing operation datasets and executed nursing operation datasets are collected. The standard nursing operation datasets and executed nursing operation datasets are compared to obtain the segment information set. The segment information set includes the first nursing warning marker segment information set, the second nursing warning marker segment information set, and the nursing safety misjudgment segment result set.

[0061] The nursing supervision early warning information notification result is obtained by processing the early warning information based on the patient's nursing status information, the first nursing early warning marker segment information set, the second nursing early warning marker segment information set, and the nursing safety misjudgment segment result set.

[0062] This application collects nursing data (such as vital sign monitoring data, nursing operation records, etc.), information on changes in the condition (changes in symptoms, changes in test results, etc.) and nursing data of nursing segments (nursing work data within a specific nursing stage or time interval) of patients hospitalized in the gastroenterology department through various medical equipment and nursing record systems, so as to provide basic data support for subsequent analysis.

[0063] The collected nursing data is used to determine the nursing status information based on the nursing condition. The nursing data is then matched according to the nursing status to obtain the first and second executed nursing data. The first and second executed nursing data are then combined to form the executed nursing dataset. The nursing status is compared with the standard nursing status to identify the differences and similarities. Data collection points are set for the differences to collect and feedback nursing data to form the feedback nursing dataset. Finally, the nursing status information, executed and feedback nursing datasets are comprehensively analyzed to determine the patient's nursing status information, thereby evaluating the effectiveness of the current nursing work.

[0064] Nursing data in nursing segments is filtered based on changes in patient condition to obtain first nursing data information; nursing data is predicted using a constructed nursing model (such as based on machine learning algorithms, combined with historical nursing and patient condition data training) to obtain second nursing data information; the two are compared with a preset nursing data difference judgment value, and nursing data segments with differences that reach or exceed the judgment value are extracted. Nursing warning marks are applied to these segments to form a first nursing warning mark set, thereby identifying abnormal fluctuations in nursing data.

[0065] The first nursing warning marker set is used to collect standard nursing operation datasets (established standard operating procedures, indicators, etc.) and executed nursing operation datasets (actually executed nursing operation data). The two datasets are compared: if there are similarities, the first nursing warning marker segment information set is output; if they are different, the corresponding data difference is calculated to obtain the operation data difference range set. The nursing operation data difference range range value is preset, and nursing warning marker segments that are located within and not within the range value are extracted respectively to form the second nursing warning marker segment information set and the nursing safety misjudgment segment result set, so as to clarify the execution status of nursing operation standards and possible misjudgment areas.

[0066] By integrating patient nursing status information, information sets of the first and second nursing early warning marker segments, and result sets of nursing safety misjudgment segments, nursing supervision early warning information notification results are generated, and issues that need attention and handling during the nursing process are promptly reported to medical staff, assisting in optimizing nursing decisions and workflows.

[0067] Patient nursing status information: Risk weights are set based on factors such as the ratio of compliant and non-compliant nursing data in the nursing status information and the key nursing links involved in the non-compliant nursing data. For example, if the non-compliant nursing data is concentrated in the medication nursing link and accounts for a large proportion, it indicates that the risk in this aspect is high and is given a higher weight.

[0068] The first nursing early warning marker segment information set: The weights are determined based on the number, severity, and potential risks to patient health of the differential nursing data segments. For example, differential segments involving abnormal fluctuations in patient vital sign monitoring data have a higher weight than segments with differences in general nursing operation time.

[0069] The second nursing early warning marker segment information set: The weight is determined by combining the degree to which the difference in operation data exceeds the reasonable range and the importance of the nursing operations involved. For example, if the difference in key therapeutic nursing operations is large, the weight will be increased accordingly.

[0070] Nursing safety misjudgment segment result set: The weights are determined according to the severity of the possible consequences of the misjudgment and the frequency of the misjudgment. If the misjudgment that may lead to medication errors occurs frequently, the weight is set higher.

[0071] The information from each part is quantified according to the set weights. For example, for patient nursing status information, a quantitative score can be obtained by multiplying the proportion of non-standard nursing data by the corresponding weight; for the first nursing warning marker segment information set, the score is calculated comprehensively based on the number and severity of the differential nursing data segments, and so on, to obtain the corresponding quantitative risk score for each part.

[0072] The overall risk score is obtained by summing up the quantitative scores of each part, which reflects the degree of risk in the overall nursing process.

[0073] Low risk: The overall risk score is in a low range, indicating that the nursing process is generally stable with only a few minor issues that do not affect the patient's health or the quality of care. In this case, the generated nursing monitoring and early warning information notification can remind nursing staff to pay close attention to the relevant situation, carry out nursing work according to routine procedures, and review the relevant data regularly.

[0074] Medium risk: When the comprehensive risk score reaches a certain range, it indicates that there are some issues in the nursing process that require attention and may have a potential impact on the patient's health. The warning notification will require nursing staff to conduct key investigations on specific issues (such as non-standard nursing procedures or abnormal nursing data in a certain area), adjust the nursing plan, and strengthen the observation and care of the patient.

[0075] High risk: A high overall risk score indicates serious problems or significant safety hazards in the nursing process. The early warning notification will immediately remind nursing management personnel and relevant nursing staff to comprehensively assess the nursing situation, adjust the nursing plan in a timely manner, and conduct multidisciplinary consultations when necessary to ensure patient safety.

[0076] Based on the classified warning levels, targeted nursing supervision warning information notifications are generated. The notification content includes the source of the risk (such as the failure of a certain nursing operation in the patient's nursing status to meet the standard, or the abnormal data in a certain nursing warning marker segment), the description of the risk level, and the recommended measures (such as strengthening the monitoring of vital signs during a certain period).

[0077] The hospital will promptly and accurately push early warning information to relevant nursing and management personnel through internal information systems (such as nursing management software and electronic medical record systems), SMS platforms, and mobile nursing terminals, so that they can respond and handle the situation quickly.

[0078] A segment information set is obtained by comparing the standard nursing operation dataset and the performed nursing operation dataset; the segment information set includes a first nursing warning marker segment information set, a second nursing warning marker segment information set, and a nursing safety misjudgment segment result set, specifically:

[0079] Compare the standard nursing procedure dataset and the performed nursing procedure dataset;

[0080] If the same situation exists in the standard nursing operation dataset and the executed nursing operation dataset, the first nursing warning marker segment information set will be output.

[0081] If there are discrepancies between the standard nursing operation dataset and the executed nursing operation dataset, the results will be processed and analyzed to output a second nursing warning marker segment information set and a nursing safety misjudgment segment result set.

[0082] This application generates the first nursing warning marker segment information set by comparing two datasets in detail. If, within a certain nursing operation segment, all data in the nursing operation dataset are completely consistent with the standard nursing operation dataset, for example, within a 24-hour period, the nurse accurately measures the vital signs of a patient with a gastric ulcer at 8-hour intervals, performs oral care exactly once, and the medication time and dosage are in accordance with the doctor's orders, thus meeting all standard requirements, then this nursing operation segment is identified as having the same situation, and the output is the first nursing warning marker segment information set. This means that the nursing operation in this part is strictly performed according to the standard, but it is still necessary to continuously monitor whether subsequent operations can maintain the standard.

[0083] The difference between the corresponding data in the standard nursing operation dataset and the actual nursing operation dataset is calculated. For example, the standard specifies that vital signs should be measured every 8 hours, while the actual measurement interval is 10 hours, resulting in a difference of 2 hours; the standard specifies that the dosage of a certain drug is 10mg each time, while the actual dosage used is 8mg, resulting in a difference of -2mg. These differences are summarized to form the operation data difference range set.

[0084] Determine the second nursing warning marker segment information set: Preset the range of deviation values ​​for nursing operation data. For example, for the time interval of vital sign measurement, the allowable reasonable deviation range is ±1 hour; for drug dosage, the allowable reasonable deviation range is ±1 mg. Extract the nursing warning marker segments that are within the preset range values ​​from the set of operation data deviation values ​​to obtain the second nursing warning marker segment information set. For example, if the deviation of a patient's vital sign measurement time interval is 0.5 hours and the deviation of drug dosage is 0.8 mg, these related nursing operation segments within the allowable range belong to the second nursing warning marker segment information set, indicating to the nursing staff that these operations have certain deviations but are still within the controllable range, and attention should be paid to whether they will exceed the range in the future.

[0085] Determine the nursing safety misjudgment segment result set: Extract nursing warning marker segments whose operation data difference range is not located within the preset interval value to obtain the nursing safety misjudgment segment result set. For example, if the deviation of the vital sign measurement time interval reaches 3 hours and the drug dosage deviation is -3mg, which exceeds the allowable range, these nursing operation segments belong to the nursing safety misjudgment segment result set, indicating that these nursing operations may have a large risk and the cause needs to be investigated and corrective measures taken immediately.

[0086] The process of processing nursing data to obtain patient nursing status information includes the following steps:

[0087] Nursing data of patients in the gastroenterology department are collected, and nursing status information is obtained by identifying the nursing status of the nursing data.

[0088] Pre-set matching nursing data based on nursing status information;

[0089] First and second executed nursing data are obtained by matching nursing data and nursing status information; wherein, the first and second executed nursing data are combined to form an executed nursing dataset;

[0090] The nursing condition information is compared with the preset standard nursing condition information to obtain the difference information and the same information;

[0091] The first and second data collection points are set based on the difference information section;

[0092] The first feedback nursing data from the first data collection point is statistically analyzed based on the matched nursing data, and the second feedback nursing data from the second data collection point is statistically analyzed based on the matched nursing data; wherein, the first feedback nursing data and the second feedback nursing data are combined to form a feedback nursing dataset;

[0093] Patient nursing status information is obtained by processing and analyzing nursing status information, executed nursing datasets, and feedback nursing datasets.

[0094] Using various medical devices (such as monitors, blood glucose meters, etc.) and nursing record forms, we collect nursing data information of patients in the gastroenterology department, including vital signs (body temperature, blood pressure, heart rate, etc.), dietary status, medication records, nursing operation time, etc.

[0095] The collected nursing data is transformed into nursing status information through nursing status identification. For example, for a patient with peptic ulcer, based on data such as the frequency of pain attacks, medication adherence, and stability of vital signs, the nursing status may be judged as "the condition is stable but dietary care needs attention".

[0096] The identified nursing status information is matched with pre-set nursing data based on clinical nursing standards and experience. For example, for the above-mentioned peptic ulcer patients, if it is determined that "the condition is stable but dietary care needs attention", the pre-set matching nursing data may include: providing 3-4 light and easily digestible meals per day, controlling the amount of food at each meal within a certain range, and asking the patient about their dietary feelings at regular intervals.

[0097] Based on matching nursing data and nursing status information, the first set of executed nursing data (such as basic vital sign monitoring operation data) and the second set of executed nursing data (such as specific operation data for dietary care) are determined. The two together constitute the executed nursing dataset. For example, the first set of executed nursing data is measuring blood pressure and heart rate every 4 hours; the second set of executed nursing data is providing a specified diet for three meals a day on time.

[0098] The nursing status information is compared with the preset standard nursing status information, which is the ideal nursing state established based on authoritative clinical guidelines. After comparison, the difference information (the inconsistencies between actual nursing and standard nursing) and the similarity information (the parts of actual nursing that conform to the standard) are obtained. For example, the standard nursing requires that the vital signs of patients with peptic ulcers be measured every 2 hours during the pain attack, while in reality they are measured every 4 hours. This is the difference information. If the number of meals and diet of the actual dietary care conform to the standard, this is the similarity information.

[0099] Based on the difference information section, the first data collection point and the second data collection point are set. These collection points are key nodes or time periods for subsequent key monitoring and data collection. For example, for differences in the frequency of vital sign measurement, every 2 hours will be used as the first data collection point; for other potential problems in dietary care, specific dietary feedback time points will be set as the second data collection points.

[0100] Based on the matched nursing data, first feedback nursing data and second feedback nursing data are statistically analyzed at the set data collection points. Thus, a feedback nursing dataset is formed based on the first feedback nursing data and the second feedback nursing data. For example, at the set vital sign measurement time points every 2 hours, the actual measured blood pressure and heart rate values ​​are recorded as first feedback nursing data; at the dietary feedback time points, the patient's satisfaction with the diet and whether there are any adverse reactions are recorded as second feedback nursing data.

[0101] The nursing status information, the executed nursing dataset, and the feedback nursing dataset are comprehensively processed and analyzed. If the first feedback nursing data is the same as the first executed nursing data and the second feedback nursing data is the same as the second executed nursing data, the current nursing status information is directly determined as the patient's nursing status information. If there are some inconsistencies, further analysis is conducted on the compliant nursing data and the non-compliant nursing data to finally determine the patient's nursing status information. For example, if the actual vital sign measurement data is consistent with the executed data, but the patient reports dietary discomfort, it indicates that the dietary care part has not met the standards, and a comprehensive assessment of the patient's nursing status is required based on these factors.

[0102] The patient's nursing status information is obtained by processing and analyzing nursing status information, executed nursing datasets, and feedback nursing datasets, specifically including the following steps:

[0103] If the first feedback nursing data is the same as the first executed nursing data and the second feedback nursing data is the same as the second executed nursing data, then the nursing status information is determined to be the patient's nursing status information.

[0104] If the first feedback nursing data is the same as the first executed nursing data and the second feedback nursing data is different from the second executed nursing data, or if the first feedback nursing data is different from the first executed nursing data and the second feedback nursing data is the same as the second executed nursing data, then output the compliant nursing data and non-compliant nursing data.

[0105] The patient's nursing status information is obtained by processing and analyzing the data of compliant nursing care, non-compliant nursing care, the first data collection point, the second data collection point, and the executed nursing care dataset.

[0106] The first set of nursing data execution was to measure and record body temperature every 2 hours. The first set of feedback nursing data was consistent with the actual temperature measurement operation and data recorded at the collection points every 2 hours. The second set of nursing data execution was to ask the patient about abdominal pain scores every hour and record them, while ensuring that the patient had not eaten or drunk any water. The second set of feedback nursing data was consistent with the questioning operation, abdominal pain scores, and patient's lack of food and water intake recorded at the corresponding collection points. At this point, it can be directly determined that the nursing status information obtained earlier, "the condition is unstable, and close attention should be paid to changes in abdominal pain and vital signs. Strict adherence to fasting and water restriction" is the patient's current nursing status information, indicating that the nursing work was executed well and the nursing measures were in place.

[0107] The following situations apply: First feedback nursing data is the same as first executed nursing data, but second feedback nursing data is different from second executed nursing data; or first feedback nursing data is different from first executed nursing data, but second feedback nursing data is the same as second executed nursing data.

[0108] Scenario 1: The first feedback nursing data (measure and record body temperature every 2 hours) is the same as the first executed nursing data, but the second feedback nursing data (records that the patient has been stealing food) is different from the second executed nursing data (requires strict prohibition of the patient from eating and drinking). In this case, the body temperature measurement nursing operation corresponding to the first executed nursing data is considered to be in compliance with the nursing standard; the fasting and water restriction nursing operation corresponding to the second executed nursing data is considered to be in compliance with the nursing standard.

[0109] Scenario 2: Suppose that the first feedback nursing data (a temperature measurement was delayed by half an hour) is different from the first executed nursing data (temperature is measured every 2 hours), while the second feedback nursing data (the patient has not eaten or drunk anything and the abdominal pain score is normal) is the same as the second executed nursing data (the patient's abdominal pain score is checked every hour and the patient has not eaten or drunk anything). In this case, the nursing operation corresponding to the second executed nursing data is considered to be in compliance with the nursing standard, while the nursing operation corresponding to the first executed nursing data is considered to be in non-compliance with the nursing standard.

[0110] After obtaining the data on compliant and non-compliant nursing care, further analysis is conducted by combining the first data collection point (a 2-hour collection point set for differences in body temperature measurement), the second data collection point (a 4-hour checkpoint set for fasting and water restriction), and the executed nursing dataset. For example, for the nursing procedures corresponding to non-compliant nursing care data, it is analyzed whether they are occasional errors or systemic problems. Based on the settings of the first and second data collection points, it is determined whether the non-compliant situation is within the acceptable error range or whether it needs special attention. After comprehensive evaluation, the patient's final nursing status information is determined, such as "the condition is unstable, vital signs monitoring is basically up to standard, but there are loopholes in the fasting and water restriction care, and supervision needs to be strengthened."

[0111] Let the first nursing data be... The first feedback nursing data is The second set of nursing data is The second feedback nursing data is .

[0112] The formula for determining whether the first feedback nursing data and the first executed nursing data are the same is: ;in This represents the logical AND operation. This indicates that the first feedback nursing data is the same as the first executed nursing data; This indicates that the first feedback nursing data is different from the first executed nursing data.

[0113] Similarly, the formula for determining whether the second feedback nursing data is the same as the second executed nursing data is: , This indicates that the second feedback nursing data is the same as the second executed nursing data; This indicates that the second feedback nursing data is different from the second executed nursing data.

[0114] The patient's nursing status information is obtained by processing and analyzing the data of compliant nursing care, non-compliant nursing care, the first data collection point, the second data collection point, and the executed nursing care dataset. This process includes the following steps:

[0115] Based on the substandard nursing data, select the data collection points that need to be adjusted from the first and second data collection points, and obtain the third feedback nursing data based on the adjusted data collection points;

[0116] Based on the non-compliance nursing data, the corresponding comparison nursing data is selected from the first and second execution nursing data. When the third feedback nursing data is the same as the comparison nursing data, the first comparison difference information is identified based on the third feedback nursing data and the compliant nursing data.

[0117] The first comparison difference information and the difference information part are integrated to obtain the first integrated difference information part. The patient care status information is obtained based on the first integrated difference information part and the same information part.

[0118] It is known that there are substandard nursing data (patients have been eating secretly) in the fasting and water restriction nursing procedure. The first data collection point is a collection point every 2 hours set for the difference in body temperature measurement, and the second data collection point is a check point every 4 hours set for the fasting and water restriction. At this time, since the substandard nursing data comes from the fasting and water restriction, the second data collection point is selected as the data collection point that needs to be adjusted accordingly. It is adjusted to check the patient's mouth and surrounding area for signs of eating once every 2 hours. Data is collected according to the adjusted data collection point to obtain the third feedback nursing data, such as recording that the patient still has a small amount of eating traces in a certain check after the adjustment.

[0119] Based on the non-compliance nursing data (fasting and water restriction not properly implemented), the corresponding comparative nursing data was selected from the second executed nursing data (questioning the patient's abdominal pain score every hour and ensuring the patient has not eaten or drunk anything), i.e. ensuring the patient has not eaten or drunk anything. When the third feedback nursing data (the patient has a small amount of food traces) differs from the comparative executed nursing data (requiring the patient not to eat or drink anything), it is analyzed in conjunction with the compliant nursing data (such as temperature measurement nursing procedures being compliant). It was found that, in addition to the patient having eating behavior, there may be insufficient frequency and intensity of supervision of dietary care. This is the first comparative difference information identified.

[0120] The patient's nursing status information is obtained by comparing the nursing status information with the preset standard nursing status information in the early stage (such as differences in the frequency of vital sign measurement). This information is then integrated with the newly identified first comparison difference information (insufficient supervision of dietary care) to obtain the first integrated difference information. This is then combined with the same information (such as the temperature measurement nursing operation meeting the standard) to make a comprehensive judgment to obtain the patient's nursing status information, such as "the condition is unstable, the vital sign monitoring is basically up to standard, but there are significant loopholes in the fasting and water restriction and related dietary care, and supervision and nursing measures need to be strengthened and adjusted."

[0121] The first nursing data information is compared and analyzed with the second nursing data information to obtain the first nursing early warning mark set, specifically:

[0122] The nursing data comparison results are obtained by comparing the first nursing data information and the second nursing data information.

[0123] A preset nursing data difference range judgment value is set. The corresponding difference nursing data segments that are greater than or equal to the nursing data difference range judgment value are extracted from the nursing data comparison results. The difference nursing data segment set is output according to the corresponding difference nursing data segments, and the difference nursing data segment set is marked as the first nursing warning mark.

[0124] The first nursing data information is nursing data extracted based on changes in the patient's condition. For example, in the nursing segment where the patient's abdominal pain worsened, data such as the measurement of vital signs (body temperature, blood pressure, heart rate) every hour, as well as the corresponding medication dosage and time, were recorded.

[0125] The second nursing data is data predicted by the constructed nursing model. It is assumed that the nursing model predicts that vital signs will be measured every 30 minutes in the nursing period when abdominal pain intensifies, based on factors such as the patient's basic condition and past symptom fluctuation patterns, and that the medication dosage needs to be fine-tuned according to blood pressure fluctuations.

[0126] Comparing these two types of data yields nursing data comparison results. For example, there is a time interval difference between the actual measurement of vital signs every hour and the predicted measurement every 30 minutes; there is a difference between the actual medication dosage not adjusted according to blood pressure fluctuations and the predicted need for fine-tuning.

[0127] To ensure the accuracy and reliability of the secondary nursing data generated by the nursing model predictions, validation was conducted through a combination of clinical controlled trials and statistical verification. The process is as follows:

[0128] 1: Experimental Design

[0129] Grouping: Gastroenterology patients hospitalized during the same period were selected and divided into an experimental group (nursing procedures were guided by model-predicted second nursing data) and a control group (nursing plans were developed by senior nurses based on clinical experience). Each group included at least 50 patients (covering different disease types and age groups) to ensure that the baseline between groups was consistent (e.g., no significant differences in underlying disease conditions and complications).

[0130] Data collection: Nursing care data (frequency / time of vital sign measurement, medication dosage adjustment, etc.) and disease outcome indicators (time to relief of abdominal pain, length of hospital stay, incidence of complications) of the two groups of patients were recorded simultaneously as a basis for verification.

[0131] 2. Accuracy Verification

[0132] Indicator comparison:

[0133] Vital signs measurement: Compare the "model predicted measurement time interval" of the experimental group with the "first nursing data information" actually performed, and calculate the time interval deviation rate (deviation rate = |predicted interval - actual interval| / predicted interval × 100%). The deviation rate should be ≤ [X]% (set in combination with the clinically acceptable range, such as 15%).

[0134] Medication dosage adjustment: Calculate the deviation between the "model predicted dose" and the actual dose in the experimental group (deviation = |predicted dose - actual dose|), and compare it with the deviation of the dose adjustment by nurses in the control group based on their experience to verify that the model prediction accuracy is not lower than the level of clinical experience.

[0135] 3. Reliability Verification

[0136] Stability test:

[0137] Cross-case validation: Select historical gastroenterology cases from different years and seasons (e.g., 100 retrospective cases), input them into the nursing model to generate second nursing data, compare them with the real nursing records (first nursing data), and calculate MAE (mean absolute error) and RMSE (root mean square error). The indicators are required to be within the clinically acceptable range (e.g., MAE ≤ deviation of the preset judgment value).

[0138] Real-time verification: When the patient's condition suddenly fluctuates (such as increased abdominal pain or sudden change in blood pressure), the test model's predicted response time (the time from receiving information about changes in the patient's condition to outputting the second nursing data) is required to be ≤[X] minutes (to meet the timeliness requirements of clinical nursing intervention).

[0139] 4. Result Determination

[0140] If there is no significant difference in the disease outcome indicators between the experimental group and the control group (P>0.05, determined by chi-square test and t-test), and the deviation rate and error value between the model-predicted data and the first nursing data are within the preset judgment value range, it can be proven that the second nursing data information predicted by the nursing model has the accuracy and reliability in clinical scenarios and can provide an effective reference for nursing supervision.

[0141] Through the above verification, the practicality of the model is verified from the perspective of clinical practice (controlled trial), and the accuracy of the model is quantified through statistical indicators (bias rate, MAE, etc.), thus constructing a dual verification system of "practice + data" to ensure that the second nursing data is "usable and reliable" in the nursing supervision process.

[0142] Preset judgment values ​​for the range of differences in nursing data. For example, for the time interval of vital sign measurement, the preset judgment value is an allowable deviation of ±15 minutes; for medication dosage, the preset judgment value is an allowable deviation of ±10%.

[0143] Extract the corresponding differential nursing data segments from the nursing data comparison results that are greater than or equal to the nursing data difference range judgment value. In the example above, the difference in the time interval of vital sign measurement is 30 minutes, which is greater than the preset deviation of 15 minutes. The data segment related to this vital sign measurement belongs to the differential nursing data segment. If the actual value of medication dosage deviates from the predicted value by more than 10%, the data segment related to medication dosage also belongs to the differential nursing data segment. These differential nursing data segments are grouped together to form a differential nursing data segment set.

[0144] Nursing warning labels are applied to the differential nursing data segments to obtain the first nursing warning label set. For example, specific warning labels are applied to data segments with abnormal intervals in vital sign measurement and abnormal medication dosage to indicate to medical staff that there may be risks in these nursing processes and that they need to be closely monitored and investigated.

[0145] If discrepancies are found between the standard nursing procedure dataset and the executed nursing procedure dataset, the analysis and processing will be performed to output a second nursing warning marker segment information set and a nursing safety misjudgment segment result set. This includes the following steps:

[0146] The difference between corresponding data in the standard nursing operation dataset and the performed nursing operation dataset is calculated to obtain the set of operation data difference ranges.

[0147] A preset range of nursing operation data difference values ​​is defined. The nursing warning mark segment information set is obtained by extracting the nursing warning mark segment corresponding to the preset range of nursing operation data difference values ​​from the set of operation data difference values.

[0148] Extract the nursing warning marker segment that is not located in the preset nursing operation data difference range value to obtain the nursing safety misjudgment segment result set.

[0149] Standard nursing procedures require vital signs to be measured every 8 hours, but in practice the measurement interval is 10 hours. According to the formula d1=10-8=2 hours, the difference between the vital signs measurement intervals can be obtained.

[0150] The standard specifies that the dosage of a certain drug is 10mg per dose, but the actual dosage used is 8mg. The difference in drug dosage is calculated using the formula d2=8-10=-2mg. These differences are then summarized to obtain the operational data difference range set.

[0151] The preset range of deviation values ​​for nursing operation data is set. For the time interval of vital sign measurement, the allowable reasonable deviation range is ±1 hour; for drug dosage, the allowable reasonable deviation range is ±1 mg.

[0152] Judging from the range of operational data differences, if the deviation of the time interval for measuring a patient's vital signs is 0.5 hours, since -1≤0.5≤1; and the deviation of the drug dosage is 0.8mg, since -1≤0.8≤1, these related nursing operation segments belong to the second nursing warning marker segment information set, indicating that the nursing staff's operation has deviations but is controllable, and the subsequent situation needs to be monitored.

[0153] If the deviation of the vital signs measurement time interval is 3 hours, which does not meet the condition -1≤d≤1; or the deviation of the drug dosage is -3mg, which does not meet the condition -1≤d≤1, these nursing warning marker segments that are not within the preset interval values ​​belong to the nursing safety misjudgment segment result set, indicating that the corresponding nursing operation may have a large risk and needs to be investigated and corrected in time.

[0154] Table 1: Comparison of Technical Scheme for Inpatient Nursing Supervision in the Gastroenterology Department with Traditional Manual Supervision Data

[0155]

[0156] Table 1 above selects two wards (30 beds in each ward) in the gastroenterology department of the same hospital, which serve as the experimental group (using the technical solution) and the control group (traditional manual supervision), respectively, with an experimental period of 6 months.

[0157] In terms of identifying deviations in vital sign measurement intervals, the experimental group identified 28 deviations, including subtle time interval differences such as 0.5 hours; the control group identified only 12 deviations, most of which were significant deviations of more than 2 hours. This indicates that the technical solution of this application can accurately capture subtle deviations that are easily overlooked by humans through data difference calculation and preset interval determination, and discover potential risks in advance (such as measurement intervals that are not up to standard), thus avoiding small problems from accumulating into major hidden dangers.

[0158] In terms of the number of drug dosage deviations identified, the experimental group identified 22 cases of dosage deviations (including small dose differences of 0.8 mg), while the control group only identified 8 cases (most of which were deviations of more than 2 mg). This indicates that the application has significantly improved the ability to identify small deviations in drug dosage, which can reduce fluctuations in treatment effect or adverse reactions (such as insufficient medication affecting efficacy) caused by dosage errors.

[0159] In terms of the average response time in the second nursing warning zone, the experimental group was 18 minutes (nurses intervened quickly after the system automatically marked the warnings), while the control group was 75 minutes (responded after manual screening to find the deviations). This shows that the technical solution shortens the response time through automated marking, enabling nursing resources to be allocated more efficiently to potential risk points.

[0160] Regarding the average handling time for misjudged nursing safety areas, the experimental group had a time of 25 minutes (rapid handling after the system accurately located high-risk areas); the control group had a time of 90 minutes (manual investigation of problems took longer). This indicates that the technical solution can quickly pinpoint the source of the problem, shorten the handling cycle, and reduce patient safety risks (such as delayed monitoring of the condition due to measurement delays).

[0161] Regarding the standardization rate of nursing operations, the experimental group had a rate of 93% (standardization rate of 100 monthly sampled operations); the control group had a rate of 76%. This indicates that this technical solution promotes the standardization of nursing operations, reduces human error (such as performing measurements and medication according to standard procedures) and improves the overall standardization of nursing care through closed-loop management of "deviation identification - process optimization - training verification".

[0162] Regarding the incidence of adverse events caused by nursing deviations, the experimental group had a rate of 3% (100 patients were counted quarterly), while the control group had a rate of 11%. This indicates that the application significantly reduced adverse events caused by non-standard nursing procedures (such as vomiting caused by dosage errors and delays in observation of the patient's condition due to untimely measurements), thereby improving the safety and experience of patients seeking medical treatment. Example

[0163] The following technical features are added based on Embodiment 1:

[0164] A big data-based inpatient nursing monitoring system for gastroenterology departments includes:

[0165] Data collection module: Collects nursing data information of gastroenterology patients during hospitalization, as well as information on changes in the condition of gastroenterology patients and nursing data of nursing areas;

[0166] Processing module: Processes nursing data to obtain patient nursing status information;

[0167] Extraction and Analysis Module: Extracts nursing data from nursing segments based on changes in patient condition to obtain first nursing data information; predicts nursing data based on the constructed nursing model to obtain second nursing data information; compares and analyzes the first and second nursing data information to obtain a first nursing early warning marker set;

[0168] The training process for the nursing model used to predict nursing data is as follows:

[0169] Data source: Historical inpatient data from the gastroenterology department were extracted from the Hospital Information System (HIS) and Nursing Information System (NIS), including basic data of nursing segments (such as frequency of nursing operations and duration of nursing care), data on changes in the patient's condition (such as the evolution of abdominal pain and fluctuations in digestive indicators), and basic patient information (age, underlying diseases, etc.) as the training dataset for the model.

[0170] Encoding conversion: One-hot encoding is used for categorical data (such as nursing operation type and disease severity level), and Z-score standardization is used for numerical data (such as body temperature and white blood cell count) to unify the data format.

[0171] Model selection: LSTM (Long Short-Term Memory Network) was adopted as the core model to adapt to the temporal nature of gastroenterology nursing data (changes in patient condition and dynamic evolution of nursing operations over time) and capture long-term data dependencies; XGBoost was combined to supplement feature importance analysis to optimize the model's prediction accuracy.

[0172] Feature engineering: From the preprocessed data, features strongly correlated with nursing outcomes, such as "frequency of abdominal pain in the past 3 hours", "timeliness of nursing operation execution", and "trend of patient nutritional indicators", are selected to construct a feature set; redundant features are eliminated and the model complexity is reduced by using Pearson correlation coefficient and mutual information method.

[0173] Data set partitioning: The preprocessed data is divided into training set, validation set, and test set in a 7:2:1 ratio;

[0174] Hyperparameter optimization: Use grid search + cross-validation (5-fold cross-validation) to adjust the number of hidden layer neurons and learning rate of LSTM, and tree depth and regularization coefficient of XGBoost, etc.

[0175] Model training: Input the training set data into the model, monitor the validation set loss through "early stopping" to avoid overfitting; iterate the training until the model converges, and output the preliminary trained model.

[0176] Validation metrics: MAE (mean absolute error) is used to measure the deviation between predicted and actual values ​​of nursing data, and R² (coefficient of determination) is used to assess the explanatory power of the model and validate the model's generalization ability on the test set.

[0177] Optimization and iteration: If the validation metrics do not meet expectations (e.g., MAE is higher than 0.2, R² is lower than 0.7), go back to the data preprocessing stage and supplement with extreme case data to enhance the robustness of the model; or adjust the model structure (e.g., increase the depth of the LSTM layer, integrate the attention mechanism) and retrain until the accuracy requirements are met.

[0178] The trained nursing model is deployed to the "extraction and analysis module" of the nursing monitoring system to receive nursing segment data and information on changes in patient condition in real time for prediction. At the same time, a model update mechanism is set up: after accumulating nursing data for every 100 newly admitted patients in the gastroenterology department, incremental training is automatically triggered to incorporate new data features and continuously adapt to changes in clinical nursing scenarios.

[0179] Through the above training process, the nursing model can accurately learn the patterns of gastroenterology nursing data, providing reliable predictive support for the comparative analysis of "first nursing data information" and "second nursing data information", ensuring the accuracy of the nursing early warning label set, and helping to facilitate the efficient operation of gastroenterology inpatient nursing supervision.

[0180] Data Acquisition and Comparison Module: Based on the first nursing warning marker set, the module collects the standard nursing operation dataset and the executed nursing operation dataset, and compares the standard nursing operation dataset and the executed nursing operation dataset to obtain the segment information set; wherein, the segment information set includes the first nursing warning marker segment information set, the second nursing warning marker segment information set, and the nursing safety misjudgment segment result set;

[0181] Early warning module: Based on patient nursing status information, first nursing early warning marker segment information set, second nursing early warning marker segment information set, and nursing safety misjudgment segment result set, early warning processing is performed to obtain nursing supervision early warning information notification results.

[0182] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a big data-based method for monitoring inpatient nursing care in the gastroenterology department.

[0183] like Figure 3 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630, and a communication bus 640. The processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call the logical instructions in the memory 630 to execute a big data-based inpatient nursing supervision method for the gastroenterology department.

[0184] Furthermore, when the logical instructions in the aforementioned memory 630 can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0185] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program that can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute a big data-based method for monitoring inpatient nursing care in the gastroenterology department.

[0186] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform a big data-based method for monitoring inpatient nursing care in the gastroenterology department.

[0187] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0188] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platform, or of course by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0189] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0190] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for monitoring inpatient nursing care in the gastroenterology department based on big data, characterized in that, include: Collect nursing data on patients in the gastroenterology department during their hospitalization, as well as information on changes in their condition and nursing data for different nursing areas. The process of processing nursing data to obtain patient nursing status information includes the following steps: Nursing data of patients in the gastroenterology department are collected, and nursing status information is obtained by identifying the nursing status of the nursing data. Pre-set matching nursing data based on nursing status information; First and second executed nursing data are obtained by matching nursing data and nursing status information; wherein, the first and second executed nursing data are combined to form an executed nursing dataset; The nursing condition information is compared with the preset standard nursing condition information to obtain the difference information and the same information; The first and second data collection points are set based on the difference information section; The first feedback nursing data from the first data collection point is statistically analyzed based on the matched nursing data, and the second feedback nursing data from the second data collection point is statistically analyzed based on the matched nursing data; wherein, the first feedback nursing data and the second feedback nursing data are combined to form a feedback nursing dataset; The patient's nursing status information is obtained by processing and analyzing nursing status information, executed nursing datasets, and feedback nursing datasets, specifically including the following steps: If the first feedback nursing data is the same as the first executed nursing data and the second feedback nursing data is the same as the second executed nursing data, then the nursing status information is determined to be the patient's nursing status information. If the first feedback nursing data is the same as the first executed nursing data and the second feedback nursing data is different from the second executed nursing data, or if the first feedback nursing data is different from the first executed nursing data and the second feedback nursing data is the same as the second executed nursing data, then output the compliant nursing data and non-compliant nursing data. The patient's nursing status information is obtained by processing and analyzing the data of compliant nursing care, non-compliant nursing care, the first data collection point, the second data collection point, and the executed nursing care dataset. This process includes the following steps: Based on the substandard nursing data, select the data collection points that need to be adjusted from the first and second data collection points, and obtain the third feedback nursing data based on the adjusted data collection points; Based on the non-compliance nursing data, the corresponding comparison nursing data is selected from the first and second execution nursing data. When the third feedback nursing data is the same as the comparison nursing data, the first comparison difference information is identified based on the third feedback nursing data and the compliant nursing data. The first comparison difference information and the difference information part are integrated to obtain the first integrated difference information part. The patient care status information is obtained based on the first integrated difference information part and the same information part. The nursing data of the nursing area is extracted based on the information of changes in the patient's condition to obtain the first nursing data information; the nursing data is predicted based on the constructed nursing model to obtain the second nursing data information; the first nursing data information and the second nursing data information are compared and analyzed to obtain the first nursing early warning mark set. A standard nursing operation dataset and an executed nursing operation dataset are collected based on a first nursing warning marker set. The standard nursing operation dataset and the executed nursing operation dataset are compared to obtain a segment information set. The segment information set includes a first nursing warning marker segment information set, a second nursing warning marker segment information set, and a nursing safety misjudgment segment result set. The nursing supervision early warning information notification result is obtained by processing the early warning information based on the patient's nursing status information, the first nursing early warning marker segment information set, the second nursing early warning marker segment information set, and the nursing safety misjudgment segment result set.

2. The method for monitoring inpatient nursing care in the gastroenterology department based on big data as described in claim 1, characterized in that, A segment information set is obtained by comparing the standard nursing operation dataset and the performed nursing operation dataset; wherein, the segment information set includes a first nursing warning marker segment information set, a second nursing warning marker segment information set, and a nursing safety misjudgment segment result set, specifically: Compare the standard nursing procedure dataset and the performed nursing procedure dataset; If the standard nursing operation dataset and the executed nursing operation dataset have the same situation, output the first nursing warning marker segment information set; If there are discrepancies between the standard nursing operation dataset and the executed nursing operation dataset, the results will be processed and analyzed to output a second nursing warning marker segment information set and a nursing safety misjudgment segment result set.

3. The method for monitoring inpatient nursing care in the gastroenterology department based on big data as described in claim 2, characterized in that, The first nursing data information is compared and analyzed with the second nursing data information to obtain the first nursing early warning mark set, specifically: The nursing data comparison results are obtained by comparing the first nursing data information and the second nursing data information. A preset nursing data difference range judgment value is set. The corresponding difference nursing data segments that are greater than or equal to the nursing data difference range judgment value are extracted from the nursing data comparison results. The difference nursing data segment set is output according to the corresponding difference nursing data segments, and the difference nursing data segment set is marked as the first nursing warning mark.

4. The method for monitoring inpatient nursing care in the gastroenterology department based on big data as described in claim 3, characterized in that, If discrepancies are found between the standard nursing procedure dataset and the executed nursing procedure dataset, the analysis and processing will be performed to output a second nursing warning marker segment information set and a nursing safety misjudgment segment result set. This includes the following steps: The difference between corresponding data in the standard nursing operation dataset and the performed nursing operation dataset is calculated to obtain the set of operation data difference ranges. A preset range of nursing operation data difference values ​​is defined. The nursing warning mark segment information set is obtained by extracting the nursing warning mark segment corresponding to the preset range of nursing operation data difference values ​​from the set of operation data difference values. Extract the nursing warning marker segment that is not located in the preset nursing operation data difference range value to obtain the nursing safety misjudgment segment result set.

5. A big data-based inpatient nursing monitoring system for gastroenterology, applied to the big data-based inpatient nursing monitoring method for gastroenterology as described in any one of claims 1-4, characterized in that, include: Data collection module: Collects nursing data information of gastroenterology patients during hospitalization, as well as information on changes in the condition of gastroenterology patients and nursing data of nursing areas; Processing module: Processes nursing data to obtain patient nursing status information; Extraction and Analysis Module: Extracts nursing data from nursing areas based on changes in patient condition to obtain primary nursing data information; The nursing data is predicted based on the constructed nursing model to obtain the second nursing data information. The first nursing data information and the second nursing data information are compared and analyzed to obtain the first nursing early warning mark set. The data acquisition and comparison module acquires a standard nursing operation dataset and an executed nursing operation dataset based on the first nursing warning marker set, and compares the standard nursing operation dataset and the executed nursing operation dataset to obtain a segment information set; wherein, the segment information set includes a first nursing warning marker segment information set, a second nursing warning marker segment information set, and a nursing safety misjudgment segment result set; Early warning module: Based on patient nursing status information, first nursing early warning marker segment information set, second nursing early warning marker segment information set, and nursing safety misjudgment segment result set, early warning processing is performed to obtain nursing supervision early warning information notification results.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements a big data-based inpatient nursing supervision method for gastroenterology departments as described in any one of claims 1 to 4.

Images