Big data-based hospitalization nursing supervision method and system for digestive department

Abstract

The invention relates to the technical field of hospitalization nursing, and discloses a big data-based digestive department hospitalization nursing supervision method and system, and the method comprises the steps: collecting the nursing data information of a digestive department patient in a hospitalization nursing process, and collecting the illness state change information of the digestive department patient and the nursing data of a nursing section; processing the nursing data information to obtain patient nursing state information; extracting nursing data of the nursing section according to the illness state change information to obtain first nursing data information; predicting the nursing data according to the constructed nursing model to obtain second nursing data information, and performing comparative analysis on the first nursing data information and the second nursing data information to obtain a first nursing early warning mark set; and collecting a standard nursing operation data set and an execution nursing operation data set according to the first nursing early warning mark set. According to the invention, managers and nursing personnel can accurately identify different levels of risks.

Description

Technical Field

[0001] The present invention relates to the technical field of inpatient care, and particularly to a method and system for supervising inpatient care in the digestive department based on big data. Background Art

[0002] In the modern medical system, the conditions of digestive department patients are often characterized by complexity and variability. For diseases such as acute pancreatitis and gastrointestinal bleeding, the quality of care is directly related to the rehabilitation effect and safety of patients. However, the particularity of digestive diseases exacerbates the difficulty of care supervision. Taking patients with chronic diseases such as gastric ulcer and liver cirrhosis as an example, their care cycle is long, the operation links are numerous, and it involves multi-dimensional care contents such as vital sign monitoring, medication management, and diet intervention. Manual supervision is difficult to fully cover all links.

[0003] For patients with acute digestive diseases such as gastrointestinal perforation, the condition changes rapidly, and higher requirements are placed on the timeliness and standardization of care operations. Due to the lack of real-time data comparison and early warning mechanisms in the traditional supervision mode, it is difficult to achieve early intervention in risks. Summary of the Invention

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

[0005] Therefore, the present invention provides a method and system for supervising inpatient care in the digestive department based on big data, which can solve the problem that it is difficult to achieve early intervention in risks due to the lack of real-time data comparison and early warning mechanisms in the traditional supervision mode.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides a method for supervising inpatient care in the digestive department based on big data, including: Collecting the nursing data information of digestive department patients during the inpatient care process, as well as collecting the information on the changes in the conditions of digestive department patients and the nursing data of the nursing sections; Processing the nursing data information to obtain the patient's nursing status information; Extracting the first nursing data information from the nursing data of the nursing section according to the information on the changes in the condition; predicting the nursing data according to the constructed nursing model to obtain the second nursing data information, and comparing and analyzing the first nursing data information and the second nursing data information to obtain the first nursing early warning mark set; Collecting the standard nursing operation data set and the executed nursing operation data set according to the first nursing early warning mark set, and comparing the standard nursing operation data set and the executed nursing operation data set to obtain the section information set; wherein, the section information set includes the first nursing early warning mark section information set, the second nursing early warning mark section information set, and the nursing safety misjudgment section result set; Early warning processing is performed based on patient care status information, the first set of nursing early warning marker section information, the second set of nursing early warning marker section information, and the nursing safety misjudgment section result set to obtain the result of the nursing supervision early warning information notification.

[0007] As a preferred solution of a method for inpatient nursing supervision in the digestive department based on big data according to the present invention, the standard nursing operation data set and the executed nursing operation data set are compared to obtain a section information set; wherein, the section information set includes the first set of nursing early warning marker section information, the second set of nursing early warning marker section information, and the nursing safety misjudgment section result set, specifically: Compare the standard nursing operation data set and the executed nursing operation data set; If there are the same situations in the standard nursing operation data set and the executed nursing operation data set, output the first set of nursing early warning marker section information.

[0008] If there are different situations in the comparison result between the standard nursing operation data set and the executed nursing operation data set, perform processing and analysis and then output the second set of nursing early warning marker section information and the nursing safety misjudgment section result set.

[0009] As a preferred solution of a method for inpatient nursing supervision in the digestive department based on big data according to the present invention, the nursing data information is processed to obtain patient care status information, which specifically includes the following steps: Collect the nursing data information of digestive department patients, and perform nursing status recognition on the nursing data information to obtain nursing status information; Preset matching nursing data according to the nursing status information; Obtain the first executed nursing data and the second executed nursing data according to the matching nursing data and the nursing status information; wherein, the first executed nursing data and the second executed nursing data form an executed nursing data set in combination; Compare the nursing status information with the preset standard nursing status information to obtain a difference information part and an identical information part; Set the first data collection point and the second data collection point according to the difference information part; Count the first feedback nursing data at the first data collection point according to the matching nursing data, and count the second feedback nursing data at the second data collection point according to the matching nursing data; wherein, the first feedback nursing data and the second feedback nursing data form a feedback nursing data set in combination; Process and analyze the nursing status information, the executed nursing data set, and the feedback nursing data set to obtain patient care status information.

[0010] As a preferred solution of a method for supervising inpatient care in the department of gastroenterology based on big data according to the present invention, the nursing status information, the executed nursing data set and the feedback nursing data set are processed and analyzed to obtain the patient care status information, which specifically includes 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, it is determined that the nursing status information is the patient care 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, the qualified nursing data and the unqualified nursing data are output; The qualified nursing data, the unqualified nursing data, the first data collection point, the second data collection point and the executed nursing data set are processed and analyzed to obtain the patient care status information.

[0011] As a preferred solution of a method for supervising inpatient care in the department of gastroenterology based on big data according to the present invention, the qualified nursing data, the unqualified nursing data, the first data collection point, the second data collection point and the executed nursing data set are processed and analyzed to obtain the patient care status information, which specifically includes the following steps: The data collection points that need to be correspondingly adjusted are selected from the first data collection point and the second data collection point according to the unqualified nursing data, and the third feedback nursing data is obtained according to the adjusted data collection points; The corresponding comparison executed nursing data is selected from the first executed nursing data and the second executed nursing data according to the unqualified nursing data. When the third feedback nursing data is the same as the comparison executed nursing data, the first comparison difference information is identified according to the third feedback nursing data and the qualified nursing data; The first comparison difference information and the difference information part are integrally processed to obtain the first integrated difference information part, and the patient care status information is obtained according to the first integrated difference information part and the same information part.

[0012] As a preferred solution of a method for supervising inpatient care in the department of gastroenterology based on big data according to the present invention, the first nursing data information and the second nursing data information are compared and analyzed to obtain the first nursing warning mark set, specifically: The first nursing data information and the second nursing data information are compared to obtain the nursing data comparison result; Preset the determination value of the nursing data difference range, extract the corresponding differential nursing data section greater than or equal to the determination value of the nursing data difference range from the nursing data comparison result, output the differential nursing data section set according to the corresponding differential nursing data section, and mark the differential nursing data section set for nursing early warning as the first nursing early warning mark.

[0013] As a preferred solution of the method for supervising inpatient nursing in the digestive department based on big data according to the present invention, if there are differences in the comparison results between the standard nursing operation data set and the executed nursing operation data set, after processing and analysis, the second nursing early warning mark section information set and the nursing safety misjudgment section result set are output, which specifically includes the following steps: Calculate the difference between the corresponding data in the standard nursing operation data set and the executed nursing operation data set to obtain the operation data difference range set; Preset the range value of the operation data difference range of nursing operations, and extract the nursing early warning mark section corresponding to the operation data difference range set within the preset range value of the operation data difference range of nursing operations to obtain the second nursing early warning mark section information set; Extract the nursing early warning mark section corresponding to the operation data difference range set not within the preset range value of the operation data difference range of nursing operations to obtain the nursing safety misjudgment section result set.

[0014] In a second aspect, the present invention provides a system for supervising inpatient nursing in the digestive department based on big data, including: Collection module: Collect nursing data information of digestive department patients during inpatient nursing, as well as collect the condition change information of digestive department patients and the nursing data of nursing sections; Processing module: Process the nursing data information to obtain patient nursing status information; Extraction and analysis module: Extract the first nursing data information from the nursing data of the nursing section according to the condition change information; Predict the nursing data according to the constructed nursing model to obtain the second nursing data information, and compare and analyze the first nursing data information and the second nursing data information to obtain the first nursing early warning mark set; Collection and comparison module: Collect the standard nursing operation data set and the executed nursing operation data set according to the first nursing early warning mark set, and compare the standard nursing operation data set and the executed nursing operation data set to obtain the section information set; Among them, the section information set includes the first nursing early warning mark section information set, the second nursing early warning mark section information set and the nursing safety misjudgment section result set; Early warning module: Perform early warning processing according to the patient nursing status information, the first nursing early warning mark section information set, the second nursing early warning mark section information set and the nursing safety misjudgment section result set to obtain the nursing supervision early warning information notification result.

[0015] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, a big data-based inpatient nursing supervision method for the digestive department is implemented.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention proposes a big data-based inpatient nursing supervision method and system for the digestive department. By calculating the difference between the standard and the executed nursing operation data set and determining the interval, nursing operation deviations are captured. In risk stratified management, a clear risk differentiation mechanism is constructed in the solution. The second nursing warning mark section focuses on the "deviation controllable" scenario to prompt nurses to continuously pay attention; the nursing safety misjudgment section quickly marks high-risk operations for the "exceeding deviation" situation, enabling managers and nurses to accurately identify risks at different levels, immediately initiate emergency verification and process rectification for the high-risk misjudgment section; conduct regular monitoring of the warning section to achieve efficient and stratified control of risks and ensure the safety bottom line of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic diagram of the steps of a big data-based inpatient nursing supervision method for the digestive department proposed by the present invention; Figure 2 It is a schematic diagram of the modules of a big data-based inpatient nursing supervision system for the digestive department proposed by the present invention; Figure 3 It is a schematic diagram of the structure of the electronic device provided by the embodiment of the present invention.

[0019] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0021] Embodiment 1, referring to Figures 1 - 3, which is the first embodiment of the present invention. This embodiment provides a method for supervising inpatient care in the department of gastroenterology based on big data, including: Collect the nursing data information of patients in the department of gastroenterology during the inpatient care process, as well as the information on the changes in the patients' conditions and the nursing data of the nursing sections. Process the nursing data information to obtain the patient's nursing status information. Define the collection boundary: Only collect data directly related to inpatient care in the department of gastroenterology, such as nursing operation records, disease monitoring indicators (body temperature, degree of abdominal pain, etc.), and do not collect additional personal information unrelated to diagnosis and treatment (such as the patient's social account, unnecessary family situation, etc.).

[0022] Authorization and notification: When the patient is admitted to the hospital, the medical staff shall explain the purpose of data collection (for nursing quality supervision, disease analysis and risk warning, and improving the level of medical services), scope, storage period (saved for [X] years since discharge and anonymized after expiration), and usage method (only used for the analysis of the internal nursing supervision system of this medical institution and not shared externally) face to face. After the patient signs the "Informed Consent Form for Data Collection and Use", the data collection is started.

[0023] Extract the nursing data of the nursing section according to the information on the changes in the condition to obtain the first nursing data information; predict the nursing data according to the constructed nursing model to obtain the second nursing data information, and compare and analyze the first nursing data information and the second nursing data information to obtain the first nursing warning mark set. Collect the standard nursing operation data set and the executed nursing operation data set according to the first nursing warning mark set, and compare the standard nursing operation data set and the executed nursing operation data set to obtain the section information set; among them, the section information set includes the first nursing warning mark section information set, the second nursing warning mark section information set, and the nursing safety misjudgment section result set. Perform warning processing according to the patient's nursing status information, the first nursing warning mark section information set, the second nursing warning mark section information set, and the nursing safety misjudgment section result set to obtain the nursing supervision warning information notification result.

[0024] This application collects the nursing data information (such as vital sign monitoring data, nursing operation records, etc.), the information on the changes in the condition (symptom changes, changes in test results, etc.), and the nursing section nursing data (nursing work data within a specific nursing stage or time interval) of patients in the department of gastroenterology during hospitalization through various medical devices, nursing record systems, etc., providing basic data support for subsequent analysis.

[0025] The collected nursing data information is judged according to the nursing status to obtain the nursing condition information. Based on the preset matching of the nursing condition with the nursing data, the first executed nursing data and the second executed nursing data are obtained. Thus, the first executed nursing data and the second executed nursing data are composed into an executed nursing data set. The nursing condition is compared with the standard nursing condition to find the different and identical information parts. For the differences, data collection points are set to statistically feedback the nursing data to form a feedback nursing data set. Finally, the nursing condition information, the executed and feedback nursing data sets are comprehensively analyzed to determine the patient's nursing status information, so as to evaluate the effectiveness of the current nursing work.

[0026] The nursing section nursing data is screened according to the disease condition change information to obtain the first nursing data information; the nursing data is predicted by means of a constructed nursing model (such as trained based on machine learning algorithms, combined with historical nursing and disease condition data) to obtain the second nursing data information. The two are compared with the preset nursing data difference amplitude judgment value, and the differential nursing data sections with the difference reaching or exceeding the judgment value are extracted, and these sections are marked with nursing early warning to form the first nursing early warning mark set, so as to find the abnormal fluctuations in the nursing data.

[0027] According to the first nursing early warning mark set, the standard nursing operation data set (data such as established standard operation procedures and indicators) and the executed nursing operation data set (nursing operation data actually executed) are collected, and these two data sets are compared: if there are the same situations, the first nursing early warning mark section information set is output; if they are different, the corresponding data differences are calculated to obtain the operation data difference amplitude set, and the preset nursing operation data difference amplitude interval value is set. The nursing early warning mark sections located and not located in this interval value are respectively extracted to form the second nursing early warning mark section information set and the nursing safety misjudgment section result set, so as to clarify the implementation situation of the nursing operation specifications and the possible misjudgment areas.

[0028] Based on the patient's nursing status information, the first and second nursing early warning mark section information sets, and the nursing safety misjudgment section result set, the nursing supervision early warning information notification result is generated, and the problems that need attention and handling in the nursing process are timely feedback to the medical staff, so as to assist in optimizing the nursing decision-making and work process.

[0029] Patient's nursing status information: Risk weights are set according to factors such as the proportion of qualified nursing data and unqualified nursing data in the nursing status information, and the key nursing links involved in the unqualified nursing data. For example, if the unqualified nursing data is concentrated in the medication nursing link and the proportion is relatively large, it indicates a high risk in this aspect and a higher weight is given.

[0030] The first nursing early warning mark section information set: The weights are determined according to the number, severity of the differential nursing data sections and the potential risks to the patient's health. For example, the weight of the differential section involving abnormal fluctuations in the patient's vital sign monitoring data is higher than that of the section with differences in general nursing operation time.

[0031] Second nursing warning mark section information set: Determine the weight by combining the degree to which the concentration of the operation data difference amplitude exceeds the reasonable range and the importance of the involved nursing operations. For example, if the difference amplitude of key therapeutic nursing operations is large, the weight is correspondingly increased.

[0032] Nursing safety misjudgment section result set: Determine the weight according to the severity of the consequences that the misjudgment may cause, the frequency of the misjudgment occurrence, etc. If misjudgments that may lead to medication errors in patients frequently occur, the weight is set higher.

[0033] Quantitatively calculate the above-mentioned various parts of information according to the set weights. For example, for the patient care status information, a quantitative score can be obtained by multiplying the proportion of unqualified care data by the corresponding weight; for the first nursing warning mark section information set, calculate the score comprehensively according to the number and severity of the differential care data sections, and so on, to obtain the corresponding quantitative risk scores for each part.

[0034] Summarize the quantitative scores of each part to obtain the comprehensive risk score, which reflects the risk degree in the overall nursing process.

[0035] Low risk: The comprehensive risk score is in a lower range, indicating that the overall nursing process is stable, and there are only a few minor problems that do not affect the patient's health and nursing quality. At this time, the generated nursing supervision warning information notification result can prompt the nursing staff to continuously pay attention to the relevant situation, carry out nursing work according to the routine process, and regularly review the relevant data.

[0036] Medium risk: The comprehensive risk score reaches a certain range, indicating that there are some problems that need to be paid attention to in the nursing process, which may have a potential impact on the patient's health. The warning notification result will require the nursing staff to conduct key investigations on specific problems (such as non-standardization of a certain type of nursing operation, abnormal nursing data in a certain section), adjust the nursing plan, and strengthen the observation and care of the patient.

[0037] High risk: When the comprehensive risk score is relatively high, it means that there are serious problems or major safety hazards in the nursing process. The warning notification result will immediately remind the nursing management staff and relevant nursing staff to comprehensively evaluate the nursing situation, adjust the nursing plan in a timely manner, and conduct multidisciplinary consultations if necessary to ensure the safety of the patient.

[0038] Generate targeted nursing supervision warning information notification results according to the divided warning levels. The notification content includes the risk source (such as a certain nursing operation not meeting the standard in the patient care status, abnormal data in a certain nursing warning mark section, etc.), the description of the risk degree, and the recommended measures to be taken (such as strengthening the monitoring of vital signs at a certain time period, etc.).

[0039] Through the hospital's internal information system (such as nursing management software, electronic medical record system), SMS platform, mobile nursing terminal and other channels, early warning information will be pushed to relevant nursing staff and managers in a timely and accurate manner so that they can respond and handle it quickly.

[0040] The standard nursing operation data set and the executed nursing operation data set are compared to obtain a segment information set; wherein the segment information set includes a first nursing warning mark segment information set, a second nursing warning mark segment information set and a nursing safety misjudgment segment result set, specifically: Compare the standard nursing practice data set with the performed nursing practice data set; If the same situation exists in the standard nursing operation data set and the executed nursing operation data set, the first nursing warning mark section information set is output.

[0041] If there are differences in the comparison results between the standard nursing operation data set and the executed nursing operation data set, they are processed and analyzed and then output as the second nursing warning mark segment information set and the nursing safety misjudgment segment result set.

[0042] The first nursing warning mark segment information set of this application is generated: the two data sets are compared in detail. If, within a certain nursing operation segment, the data of the nursing operation data set are completely consistent with the standard nursing operation data set, for example, within a certain 24-hour period, the nurse measures the vital signs of the gastric ulcer patient at an interval of exactly 8 hours, oral care is performed exactly once, and the medication time and dosage are also in line with the doctor's orders, that is, all standard requirements are met. At this time, the nursing operation segment is identified as having the same situation and is output as the first nursing warning mark segment information set, which means that the nursing operations in this part are strictly performed in accordance with the standards, but it is still necessary to continue to pay attention to whether the subsequent operations can maintain the standards.

[0043] The difference between the corresponding data in the standard nursing operation data set and the executed nursing operation data set is calculated. For example, the standard stipulates that vital signs should be measured every 8 hours, but the actual measurement interval is 10 hours, and the difference is 2 hours; the standard stipulates that the dose of a certain drug is 10 mg each time, and the actual dose is 8 mg, and the difference is -2 mg. These differences are summarized to form the operation data difference amplitude set.

[0044] Determine the second set of nursing warning marker section information: Preset the range value of the nursing operation data difference amplitude. For example, for the vital sign measurement time interval, the allowable reasonable deviation range is ±1 hour; for the drug dosage, the allowable reasonable deviation range is ±1 mg. Extract the nursing warning marker sections within the preset range value from the set of operation data difference amplitudes to obtain the second set of nursing warning marker section information. For example, if the deviation of a patient's vital sign measurement time interval is 0.5 hour and the drug dosage deviation is 0.8 mg, these relevant nursing operation sections within the allowable range belong to the second set of nursing warning marker section information, indicating to the nursing staff that these operations have certain deviations but are still within the controllable range, and they need to pay attention to whether they will exceed the range in the future.

[0045] Determine the result set of nursing safety misjudgment sections: Extract the nursing warning marker sections in the set of operation data difference amplitudes that are not within the preset range value to obtain the result set of nursing safety misjudgment sections. For example, if the deviation of the vital sign measurement time interval reaches 3 hours and the drug dosage deviation is -3 mg, exceeding the allowable range, these nursing operation sections belong to the result set of nursing safety misjudgment sections, indicating that these nursing operations may have greater risks and it is necessary to immediately investigate the reasons and take corrective measures.

[0046] Process the nursing data information to obtain the patient's nursing status information, which specifically includes the following steps: Collect the nursing data information of patients in the digestive department, and identify the nursing status of the nursing data information to obtain the nursing status information; Preset and match the nursing data according to the nursing status information; Obtain the first execution nursing data and the second execution nursing data according to the matched nursing data and the nursing status information; among them, the first execution nursing data and the second execution nursing data form the execution nursing data set in combination; Compare the nursing status information with the preset standard nursing status information to obtain the difference information part and the same information part; Set the first data collection point and the second data collection point according to the difference information part; Statistically obtain the first feedback nursing data at the first data collection point according to the matched nursing data, and statistically obtain the second feedback nursing data at the second data collection point according to the matched nursing data; among them, the first feedback nursing data and the second feedback nursing data form the feedback nursing data set in combination; Process and analyze the nursing status information, the execution nursing data set, and the feedback nursing data set to obtain the patient's nursing status information.

[0047] Use various medical devices (such as monitors, blood glucose meters, etc.) and nursing record forms to collect the nursing data information of patients in the digestive department, covering vital signs (body temperature, blood pressure, heart rate, etc.), diet, medication records, nursing operation time, etc.

[0048] The collected nursing data information is used to identify the nursing status and convert it into nursing condition information. For example, for a patient with peptic ulcer, based on data such as the frequency of pain attacks, medication compliance, and vital sign stability, it is determined that the nursing condition may be "stable condition but diet nursing needs attention".

[0049] For the identified nursing condition information, nursing data is pre-set and matched according to clinical nursing standards and experience. For example, for the above-mentioned peptic ulcer patient, if it is determined as "stable condition but diet nursing needs attention", the pre-set and matched nursing data may include: providing 3-4 light and easily digestible meals per day, controlling the amount of food per meal within a certain range, and regularly asking the patient about their feelings about the diet, etc.

[0050] Based on the matched nursing data and nursing condition information, the first execution nursing data (such as data related to basic vital sign monitoring operations) and the second execution nursing data (such as specific operation data for diet nursing) are determined. The two together constitute the execution nursing data set. For example, the first execution nursing data is to measure blood pressure and heart rate every 4 hours; the second execution nursing data is to provide the specified recipe diet on time for three meals a day.

[0051] The nursing condition information is compared with the pre-set standard nursing condition information. The standard nursing condition information is the ideal nursing state formulated based on authoritative clinical guidelines, etc. After comparison, the different information part (the places where the actual nursing is inconsistent with the standard nursing) and the same information part (the parts where the actual nursing meets the standard) are obtained. For example, the standard nursing requires measuring vital signs every 2 hours for peptic ulcer patients during the pain attack period, while actually it is measured every 4 hours, and this is the different information part; if the number of meals and recipes of the actual diet nursing meet the standard, this is the same information part.

[0052] According to the different information part, the first data collection point and the second data collection point are set. These collection points are the key nodes or time periods for subsequent key monitoring and data collection. For example, for the difference in the frequency of vital sign measurement, every 2 hours is set as the first data collection point; for other potential problems that may exist in diet nursing, a specific diet feedback time point is set as the second data collection point.

[0053] According to the matched nursing data, the first feedback nursing data and the second feedback nursing data are statistically obtained at the set data collection points, and thus a feedback nursing data set is formed based on the first feedback nursing data and the second feedback nursing data. For example, at the set vital sign measurement time point every 2 hours, the actually measured blood pressure and heart rate values are recorded as the first feedback nursing data; at the diet feedback time point, the patient's satisfaction with the diet and whether there are discomfort reactions, etc. are recorded as the second feedback nursing data.

[0054] Comprehensively process and analyze the nursing status information, the executed nursing data set, and the feedback nursing data set. 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, directly determine the current nursing status information as the patient's nursing status information. If there are partial inconsistencies, further analyze the qualified nursing data and unqualified nursing data, etc., and finally determine the patient's nursing status information. For example, if the actual data of vital sign measurement is consistent with the executed data, but the patient feedbacks discomfort in diet, it indicates that the diet nursing part is unqualified, and it is necessary to comprehensively evaluate the patient's nursing status based on these situations.

[0055] Process and analyze the nursing status information, the executed nursing data set, and the feedback nursing data set to obtain the patient's nursing status information, which specifically includes 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 determine that the nursing status information is 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 qualified nursing data and unqualified nursing data; Process and analyze the qualified nursing data, unqualified nursing data, the first data collection point, the second data collection point, and the executed nursing data set to obtain the patient's nursing status information.

[0056] The first executed nursing data is set to measure the body temperature every 2 hours and record it, and the first feedback nursing data is consistent with the actual body temperature measurement operation and data at the 2-hour collection point; the second executed nursing data is set to ask the patient about the abdominal pain score every hour and record it, and at the same time ensure that the patient does not eat or drink water. The second feedback nursing data is also consistent with the inquiry operation, abdominal pain score, and the patient's situation of not eating or drinking water recorded at the corresponding collection point. At this time, directly determine that the previously obtained nursing status information "The condition is unstable, it is necessary to closely monitor the changes in abdominal pain and vital signs, and strictly implement fasting and water deprivation" is the patient's current nursing status information, indicating that the nursing work is well executed and the nursing measures are in place.

[0057] The situation where 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 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: Case 1: The first feedback nursing data (taking and recording body temperature every 2 hours) is the same as the first executed nursing data, but the second feedback nursing data (recording that the patient has the behavior of stealing food) is different from the second executed nursing data (strictly prohibiting the patient from eating and drinking). At this time, the body temperature measurement nursing operation corresponding to the first executed nursing data belongs to the qualified nursing data; the fasting and water deprivation nursing operation corresponding to the second executed nursing data belongs to the unqualified nursing data.

[0058] Case 2: Suppose the first feedback nursing data (the time of a certain body temperature measurement is delayed by half an hour) is different from the first executed nursing data (taking body temperature every 2 hours), while the second feedback nursing data (the patient has not eaten or drunk water and the abdominal pain score record is normal) is the same as the second executed nursing data (asking the patient about the abdominal pain score every hour and ensuring that the patient has not eaten or drunk water). Then, the nursing operation corresponding to the second executed nursing data belongs to the qualified nursing data, and the nursing operation corresponding to the first executed nursing data belongs to the unqualified nursing data.

[0059] After obtaining the qualified nursing data and unqualified nursing data, combined with the first data collection point (the every 2-hour collection point set for body temperature measurement differences), the second data collection point (the every 4-hour check point set for fasting and water deprivation), and the executed nursing data set for further analysis. For example, for the nursing operation corresponding to the unqualified nursing data, analyze whether it is an occasional mistake or there is a systematic problem; judge whether the unqualified situation is within the acceptable error range or needs to be focused on according to the settings of the first and second data collection points; comprehensively evaluate and determine the patient's final nursing status information, such as "the condition is unstable, the vital sign monitoring is basically qualified but there are loopholes in the fasting and water deprivation nursing, and supervision needs to be strengthened".

[0060] Let the first executed nursing data be , the first feedback nursing data be , the second executed nursing data be , and the second feedback nursing data be .

[0061] The formula for judging whether the first feedback nursing data is the same as the first executed nursing data is: ; where represents the logical AND operation, when it indicates that the first feedback nursing data is the same as the first executed nursing data; when it indicates that the first feedback nursing data is different from the first executed nursing data.

[0062] Similarly, the formula for judging whether the second feedback nursing data is the same as the second executed nursing data is: , when it indicates that the second feedback nursing data is the same as the second executed nursing data; It indicates that the second feedback nursing data is different from the second executed nursing data.

[0063] Process and analyze the qualified nursing data, unqualified nursing data, the first data collection point, the second data collection point, and the executed nursing data set to obtain the patient's nursing status information, which specifically includes the following steps: Select the data collection points that need to be correspondingly adjusted from the first data collection point and the second data collection point according to the unqualified nursing data, and obtain the third feedback nursing data based on the adjusted data collection points; Select the corresponding comparison executed nursing data from the first executed nursing data and the second executed nursing data according to the unqualified nursing data. When the third feedback nursing data is the same as the comparison executed nursing data, identify the first comparison difference information based on the third feedback nursing data and the qualified nursing data; Integrate and process the first comparison difference information and the difference information part to obtain the first integrated difference information part, and obtain the patient's nursing status information based on the first integrated difference information part and the same information part.

[0064] It is known that there is unqualified nursing data (the patient has the behavior of stealing food) in the fasting and water deprivation nursing operation. The first data collection point is the collection point set for the body temperature measurement difference every 2 hours, and the second data collection point is the inspection point set for fasting and water deprivation every 4 hours. At this time, since the unqualified nursing data comes from the fasting and water deprivation link, the second data collection point is selected as the data collection point that needs to be correspondingly adjusted, and it is adjusted to check the patient's mouth and the surrounding area for signs of eating every 2 hours. Collect data according to the adjusted data collection point to obtain the third feedback nursing data. For example, it is recorded that the patient still has a small amount of eating traces in a certain inspection after the adjustment.

[0065] Select the corresponding comparison executed nursing data from the second executed nursing data (ask the patient about the abdominal pain score every hour and ensure that the patient has not eaten or drunk water) according to the unqualified nursing data (the fasting and water deprivation is not done well), that is, the part of ensuring that the patient has not eaten or drunk water. When the third feedback nursing data (the patient has a small amount of eating traces) is different from the comparison executed nursing data (requiring the patient not to eat or drink water), analyze in combination with the qualified nursing data (such as the body temperature measurement nursing operation is qualified), and it is found that there may be deficiencies in the supervision frequency and intensity of diet nursing in addition to the patient's eating behavior. This is the identified first comparison difference information.

[0066] The difference information part obtained by comparing the nursing status information with the preset standard nursing status information in the early stage (such as the difference in the frequency of vital sign measurements, etc.) is integrated with the newly identified first comparison difference information (insufficient supervision of diet nursing) to obtain the first integrated difference information part, and then combined with the same information part (such as the nursing operation of body temperature measurement conforms to the standard) to comprehensively judge and obtain the patient's nursing status information, such as "the patient's condition is unstable, the monitoring of vital signs is basically up to standard, but there are major loopholes in fasting, water deprivation and related diet nursing, and supervision and nursing measures need to be strengthened and adjusted".

[0067] The first nursing data information and the second nursing data information are compared and analyzed to obtain the first nursing warning mark set, specifically: The first nursing data information and the second nursing data information are compared to obtain the nursing data comparison result; A preset nursing data difference amplitude determination value is set. The corresponding differential nursing data sections greater than or equal to the nursing data difference amplitude determination value are extracted from the nursing data comparison result, and a differential nursing data section set is output according to the corresponding differential nursing data sections. The differential nursing data section set is marked with a nursing warning as the first nursing warning mark.

[0068] The first nursing data information is the nursing section nursing data extracted according to the patient's condition change information. For example, in the nursing section where the patient's abdominal pain intensifies, the vital signs (body temperature, blood pressure, heart rate) are measured once an hour, and the corresponding medication dosage and time and other data are recorded.

[0069] The second nursing data information is the data predicted by the constructed nursing model. It is assumed that the nursing model predicts that the vital signs are measured every 30 minutes in the nursing section where the abdominal pain intensifies according to factors such as the patient's basic condition and the past symptom fluctuation law, and the medication dosage needs to be fine-tuned according to the blood pressure fluctuation.

[0070] These two types of data information are compared to obtain the nursing data comparison result. For example, there is a time interval difference between the actual measurement of vital signs once an hour and the predicted measurement every 30 minutes; there is a dosage difference between the actual medication dosage not being adjusted according to the blood pressure fluctuation and the predicted need for fine-tuning, etc.

[0071] To ensure the accuracy and reliability of the second nursing data information generated by the prediction of the nursing model, it is verified through the method of clinical controlled trial + statistical verification. The process is as follows: 1: Experimental design Grouping: Select inpatients in the digestive department during the same period and divide them into an experimental group (using the second nursing data predicted by the model to guide nursing operations) and a control group (formulating a nursing plan by senior nurses based on clinical experience). Each group includes at least 50 patients (covering different disease types and age groups), and ensure that the baseline between groups is consistent (such as there is no significant difference in the basic condition and complication situation).

[0072] Data collection: Synchronously record the nursing execution data of two groups of patients (frequency / time of vital sign measurement, dosage adjustment of medications, etc.) and the indicators of disease progression (time to relieve abdominal pain, length of hospital stay, incidence of complications) as the verification basis.

[0073] 2. Accuracy verification Index comparison: Vital sign measurement: Compare the "model-predicted measurement time interval" of the experimental group with the "first nursing data information" actually executed, and calculate the time interval deviation rate (deviation rate = |predicted interval - actual interval| / predicted interval × 100%). It is required that the deviation rate ≤ [X]% (set in combination with the clinically acceptable range, such as 15%); Dosage adjustment of medications: Calculate the deviation value between the "model-predicted dosage" and the actually executed dosage in the experimental group (deviation value = |predicted dosage - actual dosage|), and compare it with the deviation of the dosage adjusted by the nurses in the control group to verify that the prediction accuracy of the model is not lower than the clinical experience level.

[0074] 3. Reliability verification Stability test: Cross-case verification: Select historical cases in the department of gastroenterology in different years and seasons (such as 100 retrospective data), input them into the nursing model to generate the second nursing data, compare it with the real nursing records (the first nursing data), and calculate MAE (mean absolute error) and RMSE (root mean square error). It is required that the indicators are within the clinically acceptable range (such as MAE ≤ the corresponding deviation of the preset judgment value); Real-time verification: When the patient's condition suddenly fluctuates (such as sudden exacerbation of abdominal pain or sudden change in blood pressure), test the model prediction response time (the duration from receiving the information of the condition change to outputting the second nursing data), and it is required that ≤ [X] minutes (meeting the time limit requirements for clinical nursing intervention).

[0075] 4. Result determination If there is no significant difference in the indicators of disease progression 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 both within the preset judgment value range, it can be proved that: the second nursing data information predicted by the nursing model has accuracy and reliability in the clinical scenario and can provide an effective reference for nursing supervision.

[0076] Through the above verification, the practicality of the model is verified from the clinical practice (control trial) level, and the model accuracy is quantified through statistical indicators (deviation rate, MAE, etc.), constructing a double verification system of "practice + data" to ensure that the second nursing data is "usable and trustworthy" in the nursing supervision process.

[0077] Preset the determination value of the nursing data difference range. For example, for the vital sign measurement time interval, the preset determination value is an allowable deviation of ±15 minutes; for the medication dosage, the preset determination value is an allowable deviation of ±10%.

[0078] Extract the corresponding differential nursing data segments greater than or equal to the determination value of the nursing data difference range from the nursing data comparison results. In the above example, the difference in the vital sign measurement time interval is 30 minutes, which is greater than the preset deviation of 15 minutes. The data segment related to the vital sign measurement belongs to the differential nursing data segment; if the deviation between the actual value and the predicted value of the medication dosage exceeds 10%, the data segment related to the medication dosage also belongs to the differential nursing data segment. These differential nursing data segments are concentrated to form a differential nursing data segment set.

[0079] Perform nursing warning markings on the differential nursing data segment set to obtain the first nursing warning marking set. For example, specific warning identifiers are added to the data segments related to abnormal vital sign measurement time intervals and abnormal medication dosages to prompt medical staff that there may be risks in these nursing links and require key attention and investigation.

[0080] If there are differences in the comparison results between the standard nursing operation data set and the executed nursing operation data set, after processing and analysis, output the second nursing warning marking segment information set and the nursing safety misjudgment segment result set, which specifically includes the following steps: Calculate the difference between the corresponding data in the standard nursing operation data set and the executed nursing operation data set to obtain the operation data difference range set; Preset the interval value of the nursing operation data difference range, and extract the nursing warning marking segments corresponding to the operation data difference range set within the preset nursing operation data difference range interval value to obtain the second nursing warning marking segment information set; Extract the nursing warning marking segments corresponding to the operation data difference range set not within the preset nursing operation data difference range interval value to obtain the nursing safety misjudgment segment result set.

[0081] The standard nursing operation stipulates that vital signs should be measured every 8 hours. In actual execution, the measurement time interval is 10 hours. According to the formula d1 = 10 - 8 = 2 hours, the difference in the vital sign measurement time interval is obtained.

[0082] The standard stipulates that the dosage of a certain drug is 10 mg each time, and the actual dosage used is 8 mg. Through the formula d2 = 8 - 10 = -2 mg, the difference in the drug dosage is calculated. These differences are summarized to obtain the operation data difference range set.

[0083] Preset the differential range value of nursing operation data. 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.

[0084] Judge whether each difference is within the range from the concentration of the operation data difference amplitude. If the deviation of the time interval for measuring the vital signs of a certain patient is 0.5 hour, because -1 ≤ 0.5 ≤ 1; the drug dosage deviation is 0.8 mg, since -1 ≤ 0.8 ≤ 1, these relevant nursing operation sections belong to the second nursing warning mark section information set, indicating that the operation of the nursing staff has deviations but is controllable, and the subsequent situation needs to be concerned.

[0085] If the deviation of the time interval for measuring vital signs is 3 hours, it does not satisfy -1 ≤ d ≤ 1; the drug dosage deviation is -3 mg, which does not satisfy -1 ≤ d ≤ 1. These nursing warning mark sections that are not within the preset interval values belong to the nursing safety misjudgment section result set, indicating that there may be greater risks in the corresponding nursing operations and timely investigation and correction are required.

[0086] Table 1: Comparison data of the inpatient nursing supervision technical plan in the digestive department and traditional manual supervision

[0087] The above Table 1 selects 2 groups of wards (30 beds in each group) in the digestive department of the same hospital, and they are respectively used as the experimental group (adopting the technical plan) and the control group (traditional manual supervision), and the experimental period is 6 months.

[0088] In terms of the number of identified deviations in the vital sign measurement interval, the experimental group identified 28 deviations, including subtle time interval differences such as 0.5 hour; the control group only identified 12 cases, mostly obvious deviations of more than 2 hours, indicating that through the data difference calculation and preset interval determination of the technical plan of this application, it can accurately capture subtle deviations that are easily overlooked by manual work, discover potential risks in advance (such as the extension of the measurement interval not meeting the standard), and avoid small problems from accumulating into major hidden dangers.

[0089] In terms of the number of identified drug dosage deviations, the experimental group identified 22 cases of dosage deviations (including small dosage differences of 0.8 mg), and the control group only identified 8 cases (mostly deviations of more than 2 mg), indicating that the ability of this application to identify small deviations in drug dosage has been significantly improved, and it can reduce the fluctuations in treatment effects or adverse reactions caused by dosage errors (such as insufficient medication affecting the curative effect).

[0090] In terms of the average response time in the second nursing warning section, the experimental group was 18 minutes (the nurse intervened quickly after the system automatically marked); the control group was 75 minutes (the response after manual investigation found the deviation), indicating that this technical plan shortens the response time through automatic marking, enabling more efficient allocation of nursing resources to potential risk points.

[0091] In terms of the average handling time in the nursing safety misjudgment section, the experimental group took 25 minutes (rapid handling after the system accurately locates the high-risk section); the control group took 90 minutes (long time-consuming for manual problem detection), indicating that this technical solution can quickly lock the source of the problem, shorten the handling cycle, and reduce the patient safety risk (such as the lag in condition monitoring due to measurement delay).

[0092] In terms of the nursing operation standardization rate, the experimental group was 93% (the standardization rate of 100 monthly sampled operations); the control group was 76%, indicating that this technical solution promotes the standardization of nursing operations through the closed-loop management of "deviation identification - process optimization - training verification", reduces manual omissions (such as performing measurements and administering medications according to the standard process), and improves the overall nursing standardization.

[0093] In terms of the incidence rate of adverse events caused by nursing deviations in patients, the experimental group was 3% (statistics of 100 patients per quarter); the control group was 11%, indicating that this application significantly reduces the adverse events of patients caused by non-standard nursing operations (such as vomiting caused by dosage errors and delay in condition observation due to untimely measurement), and improves the safety and experience of patients seeking medical treatment. Embodiment

[0094] Based on Embodiment 1, the following technical features are added: A digestive department inpatient nursing supervision system based on big data, including: Collection module: Collect nursing data information of digestive department patients during inpatient nursing, as well as collect the condition change information of digestive department patients and the nursing data of nursing sections; Processing module: Process the nursing data information to obtain patient nursing status information; Extraction and analysis module: Extract the first nursing data information from the nursing data of the nursing section according to the condition change information; Predict the nursing data according to the constructed nursing model to obtain the second nursing data information, and compare and analyze the first nursing data information with the second nursing data information to obtain the first nursing warning mark set; The training process of the nursing model for predicting nursing data is as follows: Data source: Extract the historical inpatient data of digestive department patients in the hospital information system (HIS) and nursing information system (NIS), covering the basic data of nursing sections (such as nursing operation frequency, nursing duration), condition change data (such as the evolution of abdominal pain degree, fluctuation of digestive indicators), and patient basic information (age, basic diseases, etc.) as the model training data set.

[0095] Coding conversion: Perform one-hot encoding (One-Hot Encoding) on categorical data (such as nursing operation type, condition grade), and perform standardization processing (Z-Score standardization) on numerical data (such as body temperature, white blood cell count) to unify the data format.

[0096] Model Selection: The LSTM (Long Short-Term Memory Network) is adopted as the core model to adapt to the temporal characteristics of nursing data in the digestive department (the changes in the condition and the dynamic evolution of nursing operations over time), and capture the long-term data dependency relationships. The XGBoost is combined to supplement the feature importance analysis and optimize the prediction accuracy of the model.

[0097] Feature Engineering: From the preprocessed data, features strongly related to the nursing effect are screened, such as "abdominal pain frequency in the past 3 hours", "punctuality rate of nursing operation execution", "trend of patient nutrition indicators", etc., to construct a feature set. Through the Pearson correlation coefficient and mutual information method, redundant features are removed to reduce the complexity of the model.

[0098] Dataset Division: The preprocessed data is divided into a training set, a validation set, and a test set according to the ratio of 7:2:1. Hyperparameter Optimization: Use Grid Search + 5-fold cross-validation to adjust the hyperparameters such as the number of hidden layer neurons and learning rate of LSTM, and the tree depth and regularization coefficient of XGBoost. Model Training: Input the training set data into the model, and monitor the loss of the validation set through the "Early Stopping" method to avoid overfitting. Iteratively train until the model converges and output the preliminary trained model.

[0099] Validation Metrics: The MAE (Mean Absolute Error) is used to measure the deviation between the predicted value and the true value of nursing data, and R² (Coefficient of Determination) is used to evaluate the explanatory power of the model to verify the generalization ability of the model on the test set.

[0100] Optimization and Iteration: If the validation metrics do not meet the expectations (such as MAE higher than 0.2 and R² lower than 0.7), trace back to the data preprocessing link to supplement extreme case data to enhance the robustness of the model; or adjust the model structure (such as increasing the depth of the LSTM layer and integrating the attention mechanism), and retrain until the accuracy requirements are met.

[0101] The trained nursing model is deployed to the "extraction and analysis module" of the nursing supervision system to receive nursing section data and information on the changes in the condition in real time for prediction. At the same time, a model update mechanism is set: after every 100 cases of nursing data of newly admitted patients in the digestive department are accumulated, incremental training is automatically triggered to integrate new data features and continuously adapt to the changes in the clinical nursing scenario.

[0102] Through the above training process, the nursing model can accurately learn the laws of nursing data in the digestive department, provide reliable prediction support for the comparison and analysis of "First Nursing Data Information" and "Second Nursing Data Information", ensure the accuracy of the nursing warning marker set, and help the efficient operation of inpatient nursing supervision in the digestive department.

[0103] Collection and comparison module: Collect the standard nursing operation data set and the executed nursing operation data set according to the first nursing warning mark set, and compare the standard nursing operation data set and the executed nursing operation data set to obtain a section information set; wherein, the section information set includes the first nursing warning mark section information set, the second nursing warning mark section information set and the nursing safety misjudgment section result set; Warning module: Perform warning processing according to the patient's nursing status information, the first nursing warning mark section information set, the second nursing warning mark section information set and the nursing safety misjudgment section result set to obtain the nursing supervision warning information notification result.

[0104] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements a method for inpatient nursing supervision in the digestive department based on big data.

[0105] As Figure 3 shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640. Among them, the processor 610, the communications interface 620, and the memory 630 complete mutual communication through the communication bus 640. The processor 610 can call the logical instructions in the memory 630 to execute a method for inpatient nursing supervision in the digestive department based on big data.

[0106] In addition, when the logical instructions in the above-mentioned memory 630 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0107] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a method for inpatient nursing supervision in the digestive department based on big data.

[0108] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a method for supervising inpatient care in the department of gastroenterology based on big data.

[0109] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0110] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware. Based on this understanding, the above technical solution, 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., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0111] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0112] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for supervising inpatient nursing in the department of gastroenterology based on big data, characterized in that, Including: Collecting the nursing data information of digestive department patients during the inpatient care process, as well as collecting the condition change information of digestive department patients and the nursing data of the nursing section; Processing the nursing data information to obtain the patient's nursing status information; Extracting the nursing data of the nursing section according to the condition change information to obtain the first nursing data information; Predicting the nursing data according to the constructed nursing model to obtain the second nursing data information, and comparing and analyzing the first nursing data information and the second nursing data information to obtain the first nursing warning mark set; Collecting the standard nursing operation data set and the executed nursing operation data set according to the first nursing warning mark set, and comparing the standard nursing operation data set and the executed nursing operation data set to obtain the section information set; wherein, the section information set includes the first nursing warning mark section information set, the second nursing warning mark section information set, and the nursing safety misjudgment section result set; Performing warning processing according to the patient's nursing status information, the first nursing warning mark section information set, the second nursing warning mark section information set, and the nursing safety misjudgment section result set to obtain the nursing supervision warning information notification result.

2. The method for supervising inpatient care in the digestive department based on big data according to claim 1, wherein Comparing the standard nursing operation data set and the executed nursing operation data set to obtain the section information set; wherein, the section information set includes the first nursing warning mark section information set, the second nursing warning mark section information set, and the nursing safety misjudgment section result set, specifically: Comparing the standard nursing operation data set and the executed nursing operation data set; If there are the same situations in the standard nursing operation data set and the executed nursing operation data set, output the first nursing warning mark section information set; If there are different situations in the comparison results of the standard nursing operation data set and the executed nursing operation data set, perform processing and analysis and then output the second nursing warning mark section information set and the nursing safety misjudgment section result set.

3. The method for supervising inpatient care in the department of gastroenterology based on big data according to claim 2, characterized in that, Processing the nursing data information to obtain the patient's nursing status information, specifically including the following steps: Collecting the nursing data information of digestive department patients, and performing nursing status recognition on the nursing data information to obtain the nursing condition information; Presetting the matching nursing data according to the nursing condition information; Obtaining the first executed nursing data and the second executed nursing data according to the matching nursing data and the nursing condition information; wherein, the first executed nursing data and the second executed nursing data form the executed nursing data set; Comparing the nursing condition information with the preset standard nursing condition information to obtain the different information part and the same information part; Setting the first data collection point and the second data collection point according to the different information part; Counting the first feedback nursing data of the first data collection point according to the matching nursing data, and counting the second feedback nursing data of the second data collection point according to the matching nursing data; wherein, the first feedback nursing data and the second feedback nursing data form the feedback nursing data set; Performing processing and analysis on the nursing condition information, the executed nursing data set, and the feedback nursing data set to obtain the patient's nursing status information.

4. The method for supervising in-hospital care in the department of gastroenterology based on big data according to claim 3, wherein, Process and analyze the nursing status information, the executed nursing data set, and the feedback nursing data set to obtain the patient's nursing status information, which specifically includes 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 determine that the nursing status information is 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 qualified nursing data and the unqualified nursing data; Process and analyze the qualified nursing data, the unqualified nursing data, the first data collection point, the second data collection point, and the executed nursing data set to obtain the patient's nursing status information.

5. The method for supervising in-hospital care of the digestive department based on big data according to claim 4, characterized in that, Process and analyze the qualified nursing data, the unqualified nursing data, the first data collection point, the second data collection point, and the executed nursing data set to obtain the patient's nursing status information, which specifically includes the following steps: Select the data collection points that need to be correspondingly adjusted from the first data collection point and the second data collection point according to the unqualified nursing data, and obtain the third feedback nursing data according to the adjusted data collection points; Select the corresponding compared executed nursing data from the first executed nursing data and the second executed nursing data according to the unqualified nursing data. When the third feedback nursing data is the same as the compared executed nursing data, then identify the first comparison difference information according to the third feedback nursing data and the qualified nursing data; Integrate the first comparison difference information and the difference information part to obtain the first integrated difference information part, and obtain the patient's nursing status information according to the first integrated difference information part and the same information part.

6. The method for supervising inpatient care in the department of gastroenterology based on big data according to claim 5, wherein Compare and analyze the first nursing data information and the second nursing data information to obtain the first nursing warning mark set, specifically: Compare the first nursing data information and the second nursing data information to obtain the nursing data comparison result; Preset the nursing data difference amplitude determination value, extract the corresponding differential nursing data section greater than or equal to the nursing data difference amplitude determination value from the nursing data comparison result, output the differential nursing data section set according to the corresponding differential nursing data section, and mark the differential nursing data section set as the first nursing warning mark.

7. The method for supervising in-hospital nursing in the department of gastroenterology based on big data according to claim 6, characterized in that, If there are differences in the comparison results between the standard nursing operation data set and the executed nursing operation data set, then process and analyze them and output the second nursing warning mark section information set and the nursing safety misjudgment section result set, which specifically includes the following steps: Calculate the difference between the corresponding data in the standard nursing operation data set and the executed nursing operation data set to obtain the operation data difference amplitude set; Preset the nursing operation data difference amplitude interval value, and extract the nursing warning mark section corresponding to the operation data difference amplitude set located in the preset nursing operation data difference amplitude interval value to obtain the second nursing warning mark section information set; Extract the nursing warning mark section corresponding to the operation data difference amplitude set not located in the preset nursing operation data difference amplitude interval value to obtain the nursing safety misjudgment section result set.

8. A digestive department inpatient nursing supervision system based on big data, which is applied to a digestive department inpatient nursing supervision method according to any one of claims 1-7, and is characterized in that, Including: Collection module: Collect the nursing data information of patients in the department of gastroenterology during the hospitalization care process, as well as the information on the changes in the condition of patients in the department of gastroenterology and the nursing data of the nursing section; Processing module: Process the nursing data information to obtain the patient's nursing status information; Extraction and analysis module: Extract the first nursing data information from the nursing data of the nursing section according to the information on the changes in the condition; Predict the nursing data according to the constructed nursing model to obtain the second nursing data information, and compare and analyze the first nursing data information with the second nursing data information to obtain the first nursing warning marker set; Collection and comparison module: Collect the standard nursing operation data set and the executed nursing operation data set according to the first nursing warning marker set, and compare the standard nursing operation data set and the executed nursing operation data set to obtain the section information set; wherein, the section information set includes the first nursing warning marker section information set, the second nursing warning marker section information set and the nursing safety misjudgment section result set; Warning module: Perform warning processing according to the patient's nursing status information, the first nursing warning marker section information set, the second nursing warning marker section information set and the nursing safety misjudgment section result set to obtain the nursing supervision warning information notification result.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements a method for supervising the hospitalization care of the department of gastroenterology based on big data as described in any one of claims 1 to 7.

Images