A method and system for assessing the quality of gastroenterology nursing services using big data processing

Abstract

This invention discloses a method and system for assessing the quality of gastroenterology nursing services using big data processing, relating to the field of nursing service technology. The key technical solutions include the following steps: collecting real-time interactive data from nursing operation interactions, doctor-patient communication interactions, and equipment usage interactions within a gastroenterology nursing scenario; collecting training records of nursing staff, patient medical history data, and performance tracking data within the same scenario to form traceability-related data; performing multi-dimensional verification on the real-time interactive data and traceability-related data to obtain verification result values; when the verification result value triggers a quality warning threshold, locating the source of quality deviation through data tracing; the effect is that by comparing curves and tracing data, the source of deviation is accurately located, moving the identification of potential quality issues from post-event review to real-time warning, effectively solving the problems of delayed quality deviation detection and untimely intervention.

Description

Technical Field

[0001] This invention relates to the field of nursing service technology, and more specifically, to a method and system for assessing the quality of gastroenterology nursing services using big data processing. Background Technology

[0002] In the modern healthcare system, the gastroenterology department, as a clinical department with a large number of patients and a complex range of diseases, directly impacts patients' treatment safety and overall healthcare experience through the quality of its nursing services. With the aging population and rising incidence of digestive diseases, gastroenterology nursing faces multiple challenges, including a surge in workload, dispersed risk points, and significant pressure on resource allocation.

[0003] However, most existing gastroenterology nursing service quality assessments in medical institutions rely primarily on manual inspections, post-event reviews, and managerial experience, failing to effectively integrate big data technology for comprehensive and refined management. Furthermore, the data collection methods in current assessment models are fragmented, focusing mainly on end-point indicators such as patient satisfaction and adverse event rates, making it difficult to collect dynamic data on bedside nursing procedures, doctor-patient communication details, and equipment operation status in real time. They also lack integration of traceability data such as nursing staff training records, patient medical histories, and departmental quality assessments, resulting in incomplete and inconsistent assessment data. Simultaneously, existing assessment models lack scientific quantitative analysis and multi-dimensional verification mechanisms. Identification of quality deviations relies on manual screening, which is not only inefficient but also prone to missed or incorrect judgments, failing to pinpoint the source of deviations in a timely manner, leading to delayed quality warnings and hindering early risk intervention. Regarding resource allocation, existing assessment models rely heavily on subjective experience to allocate human and material resources, failing to dynamically schedule resources based on the degree of quality deviation and task priority. This easily leads to an imbalance where core nursing tasks have insufficient resources while auxiliary tasks have redundant resources, resulting in resource waste and hindering the improvement of nursing quality. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a method and system for evaluating the quality of gastroenterology nursing services using big data processing.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A method for assessing the quality of gastroenterology nursing services using big data processing, comprising the following steps: Collect real-time interactive data and traceable related data in the gastroenterology nursing scenario; Multi-dimensional verification of real-time interactive data and traceable related data is performed to obtain verification result values. When the verification result value triggers the quality warning threshold, the source of quality deviation is located by data tracing. The quality abnormality category is determined based on the scope and severity of the impact of the quality deviation source. The quality deviation quantitative index of nursing service is calculated based on the quality abnormality category. Based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, the amount of resources required to achieve quality standards within the target optimization cycle is calculated, and the cost-effectiveness of the resource input is judged to obtain the first quality improvement coefficient. A nursing task priority ranking system was constructed to classify and categorize the gastroenterology nursing tasks, resulting in core essential tasks, optimization and improvement tasks, and auxiliary support tasks. A second quality improvement coefficient was obtained by combining the quality contribution weight of each task with resource requirements. Based on the first and second quality improvement coefficients, a nursing quality improvement plan is formulated and dynamic resource allocation is implemented.

[0006] Preferably, the collection of real-time interactive data and traceability data in the gastroenterology nursing scenario includes the following steps: Real-time interactive data is generated by collecting nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data in the gastroenterology nursing scenario. Collect training records of nursing staff, patient medical history data, and assessment data in the gastroenterology nursing setting to form traceability data; The real-time interactive data and traceable related data are verified from multiple dimensions to obtain the verification result value. When the verification result value triggers the quality warning threshold, the source of the quality deviation is located by tracing the data source. The specific steps include: Real-time streaming data analysis is performed on nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data to generate real-time nursing interaction quality monitoring curves; The association mining and judgment of nursing staff training record data, patient past medical history data, and assessment traceability data are used to generate traceability dimension quality impact factor curves. The real-time nursing interaction quality monitoring curves are broken down into operation interaction quality curves, communication interaction quality curves, and equipment interaction quality curves according to interaction type. The traceability dimension quality impact factor curve is broken down into personnel qualification impact curve, individual patient impact curve, and department management impact curve according to the impact attribute. Each segmented curve is compared with its corresponding standard curve to identify abnormal curve segments that exceed the allowable deviation range. The source of quality deviation is located by tracing the data of the abnormal curve segments.

[0007] Preferably, the quality abnormality category is determined based on the scope and severity of the impact of the deviation source, and the quality deviation quantification index of the nursing service is calculated based on the quality abnormality category, specifically including the following steps: At least three quality anomaly categories are preset, each category corresponds to a unique range of impact and severity level, and each quality anomaly category is configured with a corresponding basic deviation coefficient and impact amplification coefficient; The impact range and severity values ​​of the source of the quantification deviation are matched with the corresponding intervals and levels of each quality abnormality category to determine the quality abnormality category of nursing services. The quality deviation quantification index of the nursing service is obtained by calculating the basic deviation coefficient, the influence amplification coefficient, and the cumulative duration of the deviation corresponding to the quality abnormality category.

[0008] Preferably, based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, the resource input required to achieve quality standards within the target optimization period is calculated, specifically including the following steps: Using the quality deviation quantification index as the core parameter, the basic resource input requirements are obtained by calculating the preset resource allocation efficiency coefficient. Taking into account the projected growth of nursing services and the resource depletion coefficient during the target optimization period, the basic resource input requirements are revised and calculated to obtain the resource input amount.

[0009] Preferably, the first quality improvement coefficient is obtained by assessing the cost-effectiveness of resource input, specifically including the following steps: The total input cost is obtained by calculating the human resource input cost, material consumption cost, technical support cost, and management coordination cost corresponding to the resource input amount; Based on the expected improvement ratio of the quality deviation quantification index, combined with the positive impact of improved nursing service quality on patient treatment outcomes and medical satisfaction, the comprehensive effectiveness value after quality improvement is calculated. The first quality improvement coefficient is obtained by calculating the ratio of total investment cost to comprehensive efficiency value and combining it with the preset efficiency conversion coefficient.

[0010] Preferably, a nursing task priority ranking system is constructed to classify and categorize gastroenterology nursing tasks, resulting in core essential tasks, optimization and improvement tasks, and auxiliary support tasks. This includes the following steps: We selected patient safety priority, quality impact weight, resource consumption efficiency, and urgency requirements as ranking indicators to construct a nursing task priority ranking system. Collect the specific values ​​of each nursing task under each ranking indicator, and calculate the comprehensive priority score based on the priority ranking system; Based on the overall priority score, core tasks that must be guaranteed, optimization and improvement tasks, and auxiliary support tasks are defined.

[0011] Preferably, the second quality improvement coefficient is obtained by combining the quality contribution weight of each task and the resource requirements, specifically including the following steps: Calculate the quality contribution weight coefficient and resource requirement coefficient for core essential tasks, optimization and improvement tasks, and auxiliary support tasks respectively; Based on the hierarchical weight ratio of each task, the quality contribution weight coefficient and resource demand coefficient are calculated to obtain the comprehensive contribution coefficient and comprehensive demand coefficient. The second quality improvement coefficient is obtained by calculating the ratio of the comprehensive contribution coefficient to the comprehensive demand coefficient, combined with a preset balance adjustment factor.

[0012] Preferably, based on the first quality improvement coefficient and the second quality improvement coefficient, a nursing quality improvement plan is formulated and dynamic resource allocation is implemented, specifically including the following steps: If the first quality improvement coefficient is greater than the second quality improvement coefficient, a comprehensive rectification plan will be formulated with the goal of maximizing the effectiveness of quality improvement. All nursing tasks will be allocated in a balanced manner according to the optimal allocation ratio of resource input. If the first quality improvement coefficient is less than or equal to the second quality improvement coefficient, a priority-oriented rectification plan is formulated with the core quality assurance as the goal. Resources are prioritized for allocation to core essential tasks, and the remaining resources are allocated to optimization and improvement tasks and auxiliary support tasks in order of priority.

[0013] Preferably, it further includes: Set the basic cycle standard for optimizing nursing quality and record the warning time point when the verification result first triggers the quality warning threshold; By combining the current nursing resource load status of the gastroenterology department with historical quality optimization cycle data, the basic cycle standard is intelligently adjusted to obtain the final target optimization cycle.

[0014] A big data processing-based gastroenterology nursing service quality assessment system, characterized in that it includes: Data acquisition module: Collects nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data in the gastroenterology nursing scenario to form real-time interactive data; collects nursing staff training record data, patient past medical history related data, and assessment traceability data in the gastroenterology nursing scenario to form traceability related data; Data verification module: Performs multi-dimensional verification on real-time interactive data and traceable related data to obtain verification result values. When the verification result value triggers the quality warning threshold, it locates the source of quality deviation through data tracing, determines the quality abnormality category based on the impact range and severity of the quality deviation source, and calculates the quality deviation quantitative index of nursing services based on the quality abnormality category. First calculation module: Based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, calculate the amount of resource input required to achieve quality standards within the target optimization cycle, and obtain the first quality improvement coefficient by judging the cost-effectiveness of the resource input. The second calculation module: Constructs a nursing task priority ranking system, classifies and categorizes gastroenterology nursing tasks, obtains core essential tasks, optimization and improvement tasks, and auxiliary support tasks, and obtains the second quality improvement coefficient by combining the quality contribution weight of each task and resource requirements. The rectification implementation module: Based on the first quality improvement coefficient and the second quality improvement coefficient, formulate nursing quality rectification plans and implement dynamic resource scheduling.

[0015] Compared with existing technologies, this invention has the following beneficial effects: Through real-time collection and multi-dimensional verification of multi-source data, it integrates and judges nursing operation interaction data, doctor-patient communication interaction data, equipment usage interaction data, and traceability-related data of personnel qualifications and patient medical history across the entire chain; when data triggers a quality warning threshold, the system can accurately locate the source of deviation through curve splitting comparison and data tracing, advancing the identification of quality risks from post-event review to real-time warning, effectively solving the problems of delayed quality deviation detection and untimely intervention, and significantly reducing the incidence of risk events in core nursing tasks in the gastroenterology department; by calculating a first quality improvement coefficient and a second quality improvement coefficient, a dual evaluation system based on resource efficiency and task priority is constructed; when the first quality improvement coefficient... When the improvement coefficient is higher, the system implements a comprehensive rectification plan, allocating resources evenly to maximize overall efficiency. When the second quality improvement coefficient is higher, the system switches to a priority-oriented plan, prioritizing the resource needs of core tasks. The dynamic scheduling mechanism effectively solves the problems of resource allocation relying on subjective judgment and insufficient resources for core tasks, improving resource utilization efficiency and avoiding redundant investment. Through big data multi-dimensional verification, curve splitting and comparison, and data traceability technology, the system accurately identifies the source of quality deviations, facilitating the definition of the severity of deviations. It transforms manual experience judgment into big data-driven quantitative assessment, avoiding problems such as missed judgments, misjudgments, and delayed warnings. This enables real-time early warning and precise intervention for potential nursing quality risks, improving the accuracy and timeliness of assessments. Attached Figure Description

[0016] Figure 1 This invention provides a schematic diagram illustrating the steps of a method for assessing the quality of gastroenterology nursing services using big data processing, as described in an embodiment of the invention. Figure 2 This is a schematic diagram illustrating the steps of determining and locating the source of quality deviation in a method for assessing the quality of gastroenterology nursing services using big data processing, as provided in this embodiment of the invention. Figure 3 This is a schematic diagram of a big data processing-based gastroenterology nursing service quality assessment system provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0020] Reference Figures 1-3 As shown.

[0021] This embodiment further illustrates the gastroenterology nursing service quality assessment method and system based on big data processing proposed in this invention.

[0022] A method for assessing the quality of gastroenterology nursing services using big data processing, comprising the following steps: Collect real-time interactive data and traceable related data in the gastroenterology nursing scenario; Multi-dimensional verification of real-time interactive data and traceable related data is performed to obtain verification result values. When the verification result value triggers the quality warning threshold, the source of quality deviation is located by data tracing. The quality abnormality category is determined based on the scope and severity of the impact of the quality deviation source. The quality deviation quantitative index of nursing service is calculated based on the quality abnormality category. Based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, the amount of resources required to achieve quality standards within the target optimization cycle is calculated, and the cost-effectiveness of the resource input is judged to obtain the first quality improvement coefficient. A nursing task priority ranking system was constructed to classify and categorize the gastroenterology nursing tasks, resulting in core essential tasks, optimization and improvement tasks, and auxiliary support tasks. A second quality improvement coefficient was obtained by combining the quality contribution weight of each task with resource requirements. Based on the first and second quality improvement coefficients, a nursing quality improvement plan is formulated and dynamic resource allocation is implemented.

[0023] Collecting real-time interactive data and traceable data in a gastroenterology nursing setting includes the following steps: Real-time interactive data is generated by collecting nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data in the gastroenterology nursing scenario. Collect training records of nursing staff, patient medical history data, and assessment data in the gastroenterology nursing setting to form traceability data; The real-time interactive data and traceable related data are verified from multiple dimensions to obtain the verification result value. When the verification result value triggers the quality warning threshold, the source of the quality deviation is located by tracing the data source. The specific steps include: Real-time streaming data analysis is performed on nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data to generate real-time nursing interaction quality monitoring curves; The association mining and judgment of nursing staff training record data, patient past medical history data, and assessment traceability data are used to generate traceability dimension quality impact factor curves. The real-time nursing interaction quality monitoring curves are broken down into operation interaction quality curves, communication interaction quality curves, and equipment interaction quality curves according to interaction type. The traceability dimension quality impact factor curve is broken down into personnel qualification impact curve, individual patient impact curve, and department management impact curve according to the impact attribute. Each segmented curve is compared with its corresponding standard curve to identify abnormal curve segments that exceed the allowable deviation range. The source of quality deviation is located by tracing the data of the abnormal curve segments.

[0024] First, the system performs real-time data analysis on bedside nursing procedures, the use of medical staff communication devices, and real-time interaction data in dynamic medical staff communication scenarios. This transforms fragmented dynamic behaviors into real-time nursing interaction quality monitoring curves, visually presenting the quality fluctuations of various nursing interactions. For example, the system collects real-time data on the duration and standardization of nurses' actions during post-endoscopy care, generating corresponding operation interaction quality curves. It also collects data on the completeness of response time information in medical staff communication, generating communication interaction quality curves; and it collects data on the frequency and matching degree of device usage parameters, generating device interaction quality curves.

[0025] Simultaneously, the system will perform correlation mining and judgment on static traceability data of nursing staff training records, patient past medical history, and departmental quality assessments to extract factors that may have a potential impact on nursing quality and generate traceability-dimensional quality impact factor curves. For example, data such as training duration and assessment scores can be extracted from nursing staff training records to generate a personnel qualification impact curve; data such as disease complexity and allergy history can be extracted from patient past medical history to generate an individual patient impact curve; and data such as assessment frequency and percentage of unqualified items can be extracted from departmental quality assessment data to generate a departmental management impact curve.

[0026] Next, the system will break down and refine the real-time nursing interaction quality monitoring curve and the traceability dimension quality influencing factor curve, ensuring a one-to-one correspondence between quality performance and influencing factors in different dimensions. The real-time nursing interaction quality monitoring curve is divided into three sub-curves based on interaction type: operation, communication, and equipment. Simultaneously, the traceability dimension quality influencing factor curve is divided into three sub-curves based on influencing attributes: personnel qualifications, individual patients, and departmental management. After this breakdown, the system will compare each refined curve with its corresponding clinically calibrated standard curve. When the fluctuation of a curve segment exceeds the preset allowable deviation range, the system will mark the abnormal curve segment. For example, in the monitoring of a certain shift, the system will find that the value of the operation interaction quality curve is consistently below the allowable deviation range of the standard curve, triggering anomaly identification. The system will further link the corresponding traceability sub-curve, comparing it with the personnel qualification influencing curve, and find that the endoscopy nursing special retraining records of two junior nurses in that shift did not meet the standards, and the individual patient influencing curve shows that the two patients received in that shift were both high-risk postoperative bleeding patients. Through this intermediate reasoning step, the system can clearly pinpoint that the root cause of the abnormal operation interaction quality is the non-standard operation by low-qualified nursing staff when dealing with high-risk patients, rather than simply equipment failure or communication problems.

[0027] When tracing and locating the source of quality deviations through data source analysis, the system initiates bidirectional reasoning based on objective clinical data. When an anomaly occurs in a certain interaction quality sub-curve, the system first traces back along the real-time data generation path of that curve to pinpoint the specific nursing behavior, time point, and personnel involved. For example, if the operation interaction quality curve shows abnormal fluctuations over a certain period, the system will first identify an operational deviation by Nurse A during post-endoscopy care for Patient B. Next, the system will correlate this abnormal event with the three influencing factor sub-curves of the tracing dimension, and the parameters of these sub-curves are already associated with objective clinical data. For instance, if the personnel qualification influence curve shows that Nurse A's endoscopy nursing assessment score is lower than the clinical pass rate standard, it can be inferred that the deviation stems from insufficient personnel skills; if the patient individual influence curve shows that Patient B has severe coagulation dysfunction, and this indicator exceeds the clinical risk warning threshold, it can be inferred that the deviation stems from individual patient risk; if the department management influence curve shows that the endoscopy equipment disinfection record is incomplete on that day, and the frequency of this problem exceeds the department's historical average, it can be inferred that the deviation stems from departmental management oversight. Through a dual reasoning mechanism that combines real-time behavioral retrospection with clinical data correlation, the system is able to accurately pinpoint the source of quality deviations, providing clear clinical evidence for subsequent precise rectification.

[0028] The quality deviation category is determined based on the scope and severity of the deviation source, and the quality deviation quantitative index of the nursing service is calculated based on the quality deviation category. The specific steps include: At least three quality anomaly categories are preset, each category corresponds to a unique range of impact and severity level, and each quality anomaly category is configured with a corresponding basic deviation coefficient and impact amplification coefficient; The impact range and severity values ​​of the source of the quantification deviation are matched with the corresponding intervals and levels of each quality abnormality category to determine the quality abnormality category of nursing services. The quality deviation quantification index of the nursing service is obtained by calculating the basic deviation coefficient, the influence amplification coefficient, and the cumulative duration of the deviation corresponding to the quality abnormality category.

[0029] First, the system pre-defines at least three quality abnormality categories, each corresponding to a unique impact range and severity level. It also configures a corresponding baseline deviation coefficient and impact amplification coefficient for each quality abnormality category. For example, it sets three categories: mild, moderate, and severe abnormalities. A mild abnormality affects only a single patient or a single operation, with a low severity level, a baseline deviation coefficient of 0.2, and an impact amplification coefficient of 1.0. A moderate abnormality affects 2 to 5 patients or multiple operations within the same shift, with a moderate severity level, a baseline deviation coefficient of 0.5, and an impact amplification coefficient of 1.5. A severe abnormality affects more than 5 patients or batch operations across shifts, with a high severity level, a baseline deviation coefficient of 0.8, and an impact amplification coefficient of 2.0.

[0030] Next, the system quantifies the scope and severity of the deviation's impact. For example, if a deviation occurs during post-endoscopy nursing care, the system might find that the deviation only affects one patient (impact range value of 1) and only prolongs recovery time without causing harm (severity value of 1). These two values ​​are then matched with preset category intervals and levels to determine that the deviation falls under the mild abnormality category.

[0031] Finally, the system combines the parameters corresponding to the identified quality anomaly categories with the cumulative duration of the deviation to calculate the quality deviation quantification index. The calculation formula is as follows: In this index, G represents the quality deviation quantification index, J is the basic deviation coefficient, E is the impact amplification coefficient, and S is the duration of deviation accumulation. Taking a minor anomaly as an example, if the duration of deviation accumulation is 2 hours, substituting the basic deviation coefficient of 0.2 and the impact amplification coefficient of 1.0 for a minor anomaly, the quality deviation quantification index can be calculated as 0.2 × 1.0 × 2 = 0.4. For a moderate anomaly, with a basic deviation coefficient of 0.5, an impact amplification coefficient of 1.5, and a duration of deviation accumulation of 4 hours, the quality deviation quantification index is 0.5 × 1.5 × 4 = 3.0. For a severe anomaly, with a basic deviation coefficient of 0.8, an impact amplification coefficient of 2.0, and a duration of deviation accumulation of 8 hours, the quality deviation quantification index is 0.8 × 2.0 × 8 = 12.8. This index can intuitively reflect the severity and impact of different deviations, providing a clear quantitative basis for subsequent resource allocation and quality rectification.

[0032] Based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, the resource input required to achieve quality standards within the target optimization period is calculated, specifically including the following steps: Using the quality deviation quantification index as the core parameter, the basic resource input requirements are obtained by calculating the preset resource allocation efficiency coefficient. Taking into account the projected growth of nursing services and the resource depletion coefficient during the target optimization period, the basic resource input requirements are revised and calculated to obtain the resource input amount.

[0033] Preferably, the first quality improvement coefficient is obtained by assessing the cost-effectiveness of resource input, specifically including the following steps: The total input cost is obtained by calculating the human resource input cost, material consumption cost, technical support cost, and management coordination cost corresponding to the resource input amount; Based on the expected improvement ratio of the quality deviation quantification index, combined with the positive impact of improved nursing service quality on patient treatment outcomes and medical satisfaction, the comprehensive effectiveness value after quality improvement is calculated. The first quality improvement coefficient is obtained by calculating the ratio of total investment cost to comprehensive efficiency value and combining it with the preset efficiency conversion coefficient.

[0034] First, the system uses the quality deviation quantification index as the core parameter, combined with a preset resource allocation efficiency coefficient, to calculate the basic resource input requirements. For example, when the quality deviation quantification index is 3.0 and the preset resource allocation efficiency coefficient is 0.6, the formula for calculating the basic resource input requirements is: Where JT is the basic resource input requirement, ZP is the quality deviation quantification index, and ZY is the resource allocation efficiency coefficient. Substituting the values, we can get the basic resource input requirement JT = 3.0 × 0.6 = 1.8. This value represents the initial resource scale required only for the current quality deviation.

[0035] Considering the projected growth of nursing services and the resource depletion coefficient within the target optimization period, the basic resource input requirements are revised and calculated to arrive at the final resource input amount. Assuming the projected growth of nursing services within the target optimization period is 0.3 and the resource depletion coefficient is 0.1, the revised resource input amount is calculated using the following formula: Where ZR is the amount of resource input, JT is the basic resource input demand, HC is the predicted value of nursing service growth, and ZS is the resource depletion coefficient. Substituting the values, the amount of resource input is: 1.8×(1+0.3)×(1+0.1)=2.574. This value takes into account the increase in resource demand brought about by service growth and the natural depletion of resources, ensuring that the resource input can cover the actual demand.

[0036] After obtaining the resource input amount, its cost-effectiveness is further assessed to generate a first quality improvement coefficient. First, the total input cost is calculated. The system statistically analyzes the corresponding human resource input cost, material consumption cost, technical support cost, and management coordination cost. For example, if the human resource input cost is 1200 yuan, the material consumption cost is 800 yuan, the technical support cost is 500 yuan, and the management coordination cost is 300 yuan, the formula for calculating the total input cost is: Where ZT is the total input cost, RT is the human resource input cost, WX is the material consumption cost, JZ is the technical support cost, and GX is the management and coordination cost. Substituting the values, we can get the total input cost ZT = 1200 + 800 + 500 + 300 = 2800 yuan.

[0037] Next, the overall effectiveness value after quality improvement is calculated. The system will calculate the overall effectiveness value based on the expected improvement ratio of the quality deviation quantification index, combined with the positive impact of improved nursing service quality on patient treatment outcomes and medical satisfaction. The formula for calculating the overall effectiveness value is as follows: Where ZX represents the overall efficacy value, ZC represents the quality deviation quantification index, YG represents the expected improvement ratio, ZL represents the treatment efficacy value, and MD represents the satisfaction efficacy value. Assuming the expected improvement ratio of the quality deviation quantification index is 0.7, the efficacy value from improved patient treatment effect is 1500 yuan, and the efficacy value from improved patient satisfaction is 1200 yuan, substituting these values, the overall efficacy value is (3.0 × 0.7) × (1500 + 1200) = 5670 yuan.

[0038] Finally, based on the ratio of total input cost to comprehensive efficiency value, and combined with the preset efficiency conversion coefficient, the first quality improvement coefficient is derived. The formula for calculating the first quality improvement coefficient is as follows: Where DY is the first quality improvement coefficient, ZX is the comprehensive efficiency value, ZT is the total input cost, and XZ is the efficiency conversion coefficient. Assuming a preset efficiency conversion coefficient of 1.2, substituting into the formula, we get the first quality improvement coefficient as (5670 / 2800)×1.2≈2.43. This value reflects the cost-efficiency ratio of the current resource input plan; the higher the coefficient, the more significant the quality improvement benefits brought about by the resource input.

[0039] A nursing task priority ranking system was constructed to classify and categorize gastroenterology nursing tasks, resulting in core essential tasks, optimization and improvement tasks, and auxiliary support tasks. This process includes the following steps: We selected patient safety priority, quality impact weight, resource consumption efficiency, and urgency requirements as ranking indicators to construct a nursing task priority ranking system. Collect the specific values ​​of each nursing task under each ranking indicator, and calculate the comprehensive priority score based on the priority ranking system; Based on the overall priority score, core tasks that must be guaranteed, optimization and improvement tasks, and auxiliary support tasks are defined.

[0040] First, the system selects patient safety priority, quality impact weight, resource consumption efficiency, and urgency requirement as core ranking indicators to jointly constitute a nursing task priority ranking system. These core ranking indicators comprehensively measure the importance of each nursing task from four dimensions: patient safety baseline, impact on overall nursing quality, cost-effectiveness of resource investment, and time urgency. For example, in a gastroenterology setting, the emergency management of post-endoscopy bleeding has a high priority in terms of patient safety and urgency; while routine patient health education tasks have a relatively stable quality impact weight and a high resource consumption efficiency.

[0041] Next, the system will collect specific values ​​for each nursing task under the core ranking indicators and calculate a comprehensive priority score based on the priority ranking system. To more accurately reflect the weight differences of each indicator, a weighted calculation formula can be introduced: .

[0042] Among them, w1, w2, w3, and w4 are preset weight coefficients for patient safety priority, quality impact weight, resource consumption efficiency, and urgency requirements, respectively, and satisfy w1+w2+w3+w4=1.

[0043] S is a quantitative value representing the priority of patient safety, ranging from 1 to 10. A higher value indicates a greater impact on patient safety.

[0044] Q is the quantitative value of the quality impact weight, ranging from 1 to 10. The higher the value, the more significant the impact on the overall quality of care.

[0045] R is a quantitative value of resource consumption efficiency, ranging from 1 to 10. The higher the value, the more resources are required to complete the task. Therefore, the formula takes its reciprocal to reflect efficiency.

[0046] U is a quantitative value representing the urgency of the task, ranging from 1 to 10. A higher value indicates a greater time urgency for the task.

[0047] Taking three typical tasks in gastroenterology as examples for calculation. Assume the preset weighting coefficients are w1=0.3, w2=0.2, w3=0.2, w4=0.3. For the task of emergency management of post-endoscopic bleeding, the values ​​of each indicator are S=9, Q=8, R=7, U=10. Substituting into the formula, we get: Overall priority score = (0.3×9)+(0.2×8)+(0.2×1 / 7)+(0.3×10)≈7.33. For the task of optimizing bowel preparation before colonoscopy, the values ​​of each indicator are S=6, Q=7, R=5, U=6. Substituting into the formula, we get: Overall priority score = (0.3×6)+(0.2×7)+(0.2×1 / 5)+(0.3×6)≈5.04. For the task of guiding follow-up of discharged patients, the values ​​of each indicator are S=4, Q=5, R=3, U=3. Substituting into the formula, we get: Overall priority score = (0.3×4) + (0.2×5) + (0.2×1 / 3) + (0.3×3) ≈ 3.17.

[0048] Finally, the system categorizes all nursing tasks into three levels based on their overall priority scores. Typically, the highest-scoring tasks are designated as core, mandatory tasks, such as the emergency management of post-endoscopy bleeding mentioned above. These tasks directly impact patient safety and require priority resource allocation. Tasks with scores in the middle range are designated as optimization and improvement tasks, such as optimizing bowel preparation before colonoscopy. These tasks significantly impact nursing quality and require continuous improvement. The lowest-scoring tasks are designated as auxiliary support tasks, such as guidance for discharged patient follow-up. These tasks can be advanced using remaining resources after the core tasks are completed. Through this hierarchical classification, nursing managers can clearly identify the urgency and importance of tasks, achieving optimal resource allocation and thus improving the overall efficiency and quality of nursing services.

[0049] The second quality improvement coefficient is obtained by combining the quality contribution weight of each task and the resource requirements, specifically including the following steps: Calculate the quality contribution weight coefficient and resource requirement coefficient for core essential tasks, optimization and improvement tasks, and auxiliary support tasks respectively; Based on the hierarchical weight ratio of each task, the quality contribution weight coefficient and resource demand coefficient are calculated to obtain the comprehensive contribution coefficient and comprehensive demand coefficient. The second quality improvement coefficient is obtained by calculating the ratio of the comprehensive contribution coefficient to the comprehensive demand coefficient, combined with a preset balance adjustment factor.

[0050] First, the system calculates the quality contribution weight coefficient and resource requirement coefficient for each of the three task categories: core essential tasks, optimization and improvement tasks, and auxiliary support tasks. The quality contribution weight coefficient represents the proportion of the task's contribution to improving overall nursing quality, while the resource requirement coefficient represents the proportion of resources required to complete the task. Taking the gastroenterology scenario as an example, core essential tasks such as emergency hemostasis care are directly related to patient safety, and their quality contribution weight coefficient is usually the highest, set at 0.6; optimization and improvement tasks such as preoperative bowel preparation optimization play an important role in reducing complications and improving treatment efficiency, with a quality contribution weight coefficient set at 0.3; and auxiliary support tasks such as health education mainly play a supporting role, with a quality contribution weight coefficient set at 0.1. Regarding resource requirements, core essential tasks often require more manpower and material support, with a resource requirement coefficient set at 0.5; optimization and improvement tasks require continuous improvement investment, with a resource requirement coefficient set at 0.3; and auxiliary support tasks have relatively lower resource consumption, with a resource requirement coefficient set at 0.2.

[0051] Next, the system will integrate the quality contribution weight coefficients and resource demand coefficients of the three task categories based on their respective hierarchical weight proportions to obtain a comprehensive contribution coefficient and a comprehensive demand coefficient. The hierarchical weight proportions here are the preset proportions of each task's workload in the overall nursing work. The formula for calculating the comprehensive contribution coefficient is: Where ZG is the comprehensive contribution coefficient, z i The weighting coefficient for quality contribution, f i The weighting is based on the tiered weighting; for example, core tasks account for 0.4, optimization and improvement tasks account for 0.4, and auxiliary support tasks account for 0.2. Substituting the values, we get: Comprehensive Contribution Coefficient = (0.6 × 0.4) + (0.3 × 0.4) + (0.1 × 0.2) = 0.38. The formula for calculating the comprehensive demand coefficient is: Where ZX is the comprehensive demand coefficient, and y i Let j be the resource demand coefficient. i Substituting the numerical values ​​into the weighting percentages for each level, we can obtain the comprehensive demand coefficient as (0.5×0.4)+(0.3×0.4)+(0.2×0.2)=0.36.

[0052] Finally, the system calculates the second quality improvement coefficient by combining the ratio of the comprehensive contribution coefficient to the comprehensive demand coefficient with a preset balancing adjustment factor. The balancing adjustment factor, set to 1.0, is used to correct for differences in resource allocation across different departments or stages. The formula for calculating the second quality improvement coefficient is as follows: Where DX is the second quality improvement coefficient, ZX is the comprehensive demand coefficient, ZG is the comprehensive contribution coefficient, and PJ is the balance adjustment factor; substituting the values, we get: Second quality improvement coefficient DX = (0.38 / 0.36) × 1.0 ≈ 1.06. This coefficient reflects the quality improvement brought about by unit resource input under the current task classification model. A coefficient greater than 1 indicates that the resource input efficiency of this task classification system is relatively high, and the quality improvement benefit is better than the resource input cost; a coefficient less than 1 suggests that task weights or resource allocation strategies need to be adjusted to optimize overall efficiency.

[0053] Based on the first and second quality improvement coefficients, a nursing quality improvement plan is formulated and dynamic resource allocation is implemented, specifically including the following steps: If the first quality improvement coefficient is greater than the second quality improvement coefficient, a comprehensive rectification plan will be formulated with the goal of maximizing the effectiveness of quality improvement. All nursing tasks will be allocated in a balanced manner according to the optimal allocation ratio of resource input. If the first quality improvement coefficient is less than or equal to the second quality improvement coefficient, a priority-oriented rectification plan is formulated with the core quality assurance as the goal. Resources are prioritized for allocation to core essential tasks, and the remaining resources are allocated to optimization and improvement tasks and auxiliary support tasks in order of priority.

[0054] By comparing the relationship between the first and second quality improvement coefficients, the most suitable rectification strategy and resource allocation logic are dynamically selected to address the problem of blind resource allocation. The first quality improvement coefficient reflects the effectiveness of improving nursing quality through increased resource input, and it is directly related to the cost-benefit of resource input; a higher coefficient indicates a greater improvement in quality per unit of resource input. The second quality improvement coefficient reflects the effectiveness of improving quality by optimizing the priority structure of nursing tasks; a higher coefficient indicates that adjusting the task execution order and ensuring core tasks can more efficiently improve overall nursing quality.

[0055] First, the system will calculate the specific values ​​of these two coefficients, and then trigger different rectification paths based on the relationship between them.

[0056] When the first quality improvement coefficient is greater than the second quality improvement coefficient, it indicates that increasing resource investment is more efficient at improving quality than simply adjusting the task structure. In this case, the system will formulate a comprehensive rectification plan with the goal of maximizing quality improvement efficiency. For example, in the assessment of a gastroenterology ward, the calculated first quality improvement coefficient was 0.85, and the second quality improvement coefficient was 0.72, indicating that the return on investment of additional resources was higher. The system will calculate the optimal resource investment required to achieve quality standards, including increasing the number of highly qualified nurses, increasing the number of specialized endoscopic nursing training sessions, and replenishing gastrointestinal decompression consumables. Then, according to the optimal allocation ratio, these resources will be evenly distributed among core essential tasks, optimization and improvement tasks, and auxiliary support tasks. For example, it is necessary to ensure manpower investment for high-risk patient rounds, increase material support for nursing education, and increase the frequency of environmental cleaning, so that the quality of all nursing tasks can be improved simultaneously.

[0057] When the first quality improvement coefficient is less than or equal to the second quality improvement coefficient, it indicates that optimizing the task priority structure is more effective than blindly increasing resource investment. In this case, the system will formulate a priority-oriented rectification plan with core quality assurance as the goal. For example, in another scenario, if the first quality improvement coefficient is 0.70 and the second quality improvement coefficient is 0.83, the system will prioritize allocating resources to core, essential tasks, such as adding experienced nurses to be responsible for perioperative care of endoscopic procedures and the monitoring of tubing for high-risk bleeding patients, ensuring that the core aspects of patient safety are handled flawlessly. After ensuring the resource needs of core tasks are met, the remaining resources are allocated according to priority. For example, dietary guidance and psychological support in optimization tasks are arranged first, and resources are finally allocated to auxiliary support tasks, such as material organization and environmental cleaning.

[0058] Through a dynamic decision-making mechanism, different nursing scenarios and resource conditions can be flexibly adapted to avoid ineffective resource investment. When resources are sufficient and there is significant room for improvement in overall efficiency, a comprehensive solution can achieve an overall leap in quality; when resources are scarce or core risks are high, a priority-oriented solution can focus on key tasks and ensure the core objective of nursing safety, so that the rectification plan is always precisely matched with the quality improvement needs of the current nursing scenario, and that every resource can play its maximum value in improving quality.

[0059] Also includes: Set the basic cycle standard for optimizing nursing quality and record the warning time point when the verification result first triggers the quality warning threshold; By combining the current nursing resource load status of the gastroenterology department with historical quality optimization cycle data, the basic cycle standard is intelligently adjusted to obtain the final target optimization cycle.

[0060] First, the system pre-sets a basic cycle standard for nursing quality optimization, such as an initial setting of 7 days, and records the warning time when the verification result first triggers the quality warning threshold. This time point serves as a key anchor point for subsequent cycle adjustments. For example, if the warning is triggered on Monday due to a deviation in post-endoscopy nursing procedures, this time point will be marked by the system and associated with all data related to this quality event.

[0061] By combining the current nursing resource load status of the gastroenterology department with historical quality optimization cycle data, the basic cycle standard is intelligently adjusted to derive the final target optimization cycle. The resource load status includes real-time data on the current number of nurses on duty, bed occupancy rate, and equipment turnover efficiency, while the historical quality optimization cycle data covers historical information on the rectification time and resource input efficiency of multiple past quality incidents.

[0062] To achieve precise adjustments, a dynamic correction formula is used, namely: Where MZ is the final target optimization cycle, JZ is the basic cycle standard, PF is the historical average resource load rate, DF is the current resource load rate, JZ is the basic cycle standard, JT is the number of days in advance of the current warning time, α is the resource load adjustment coefficient, ranging from 0.2 to 0.5, used to reflect the impact of resource scarcity on the cycle; β is the warning time adjustment coefficient, ranging from 0.1 to 0.3, used to reflect the impact of the advance warning time on the cycle. The current resource load rate is the comprehensive proportion of indicators such as the current number of on-duty personnel and bed occupancy rate; the number of days in advance of the current warning time is the difference between the current warning time and the historical average warning time.

[0063] Taking a real-world scenario as an example, assuming a base cycle of 7 days, a historical average resource load rate of 0.7, a current resource load rate of 0.9, and an alert time 2 days earlier than the historical average, and setting α=0.3 and β=0.2, substituting into the formula yields the final target optimization cycle. This result indicates that when the current resource load is high and the warning time is earlier, the system will appropriately shorten the optimization cycle in order to respond to quality risks more quickly.

[0064] Through a dynamic adjustment mechanism, the system can avoid insufficient rectification caused by using a fixed cycle when resources are scarce, and can also reasonably extend the cycle to reduce costs when resources are abundant. For example, when the gastroenterology department is experiencing peak patient admissions and the resource load rate reaches 0.9, the system will shorten the optimization cycle to allow quality rectification to be implemented more quickly; while when the resource load rate drops to 0.5, the system will appropriately extend the cycle to avoid excessive resource investment. Simultaneously, if the warning time point is significantly earlier, indicating an early occurrence of quality risks, the system will compress the cycle through coefficient adjustments to ensure that risks are controlled in a timely manner. A big data processing-based gastroenterology nursing service quality assessment system, characterized in that it includes: Data acquisition module: Collects nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data in the gastroenterology nursing scenario to form real-time interactive data; collects nursing staff training record data, patient past medical history related data, and assessment traceability data in the gastroenterology nursing scenario to form traceability related data.

[0065] By collecting records of execution nodes, durations, and compliance for gastrointestinal decompression, stoma care, and postoperative observation after endoscopy through nursing PDAs and mobile nursing workstations, interactive nursing operation data is generated, such as the execution time of postoperative patient positioning care and pressure ulcer risk assessment records.

[0066] By using ward voice collection terminals and patient mobile feedback tools, complete audio-visual transcripts of communication regarding medical conditions, dietary guidance, and psychological intervention are collected, along with real-time patient satisfaction scores, forming data on doctor-patient communication interaction.

[0067] Through the device IoT data acquisition card, data on the power-on time, parameter settings, usage compliance, and fault alarms of monitors, endoscopes, and nutrition pumps are obtained, forming device usage interaction data, such as flow rate setting deviations of infusion pumps and disinfection cycle records of endoscopes.

[0068] Nursing scenarios are constructed through timed synchronization via interfaces of the Hospital Information System (HIS), Nursing Management System, and Electronic Medical Record System.

[0069] Nursing staff training records include specialist training hours, operational qualification certifications such as endoscopic nursing qualifications, continuing education records, and past error events.

[0070] Patient's past medical history data includes: underlying digestive system diseases, history of drug allergies, surgical history, and fall / bleeding risk score.

[0071] Assessment traceability data includes monthly nursing quality control inspection results, operational assessment scores, and historical quality problem rectification records.

[0072] All collected data is transmitted to the system data platform via the hospital's intranet and stored in a standardized manner according to two categories: real-time streaming data and batch traceability data, providing a complete data source for subsequent verification and calculation.

[0073] The data verification module performs multi-dimensional verification on real-time interactive data and traceable related data to obtain verification result values. When the verification result value triggers the quality warning threshold, the source of quality deviation is located through data tracing. The quality abnormality category is determined based on the scope and severity of the impact of the quality deviation source, and the quality deviation quantitative index of nursing service is calculated based on the quality abnormality category.

[0074] The system verifies the completeness, logical consistency, timeliness, and compliance of real-time interactive data and traceable related data. After verification, the system outputs the verification result value, which quantifies the compliance level of the data on a percentage basis.

[0075] Warning Triggering and Deviation Tracing: When the verification result value is lower than the preset quality warning threshold, such as operation compliance rate < 95% or communication integrity rate < 90%, the system automatically initiates the data tracing process. By associating data tags such as the operator's ID, equipment number, and patient's medical record number, the source of quality deviations can be quickly located. For example, nurse A may not have completed the skin assessment for stoma care, equipment B may have incorrect pressure parameter settings leading to insufficient gastrointestinal decompression, or patient C may not have had their allergy history verified before medication administration.

[0076] At the same time, by combining the traceability data, we can further investigate the underlying causes, such as whether nursing staff A has not completed the special training for ostomy care, or whether equipment B has been neglected in its regular maintenance.

[0077] The first calculation module calculates the amount of resources required to achieve quality standards within the target optimization period based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, and obtains the first quality improvement coefficient by judging the cost-effectiveness of the resource input.

[0078] The system uses the quality deviation quantification index as its core, combined with preset resource allocation efficiency coefficients of 0.4 for manpower, 0.3 for equipment, 0.2 for training, and 0.1 for materials, to calculate the amount of resources required to achieve quality standards within the target optimization cycle, such as 7 days.

[0079] If the quality deviation quantification index is 40 points, the system will calculate the number of nursing staff to be added, the number of specialized equipment to be allocated, the number of new training hours, and the amount of nursing supplies to be supplemented.

[0080] For example, in response to deviations in ostomy care procedures, it is calculated that 16 additional hours of specialized ostomy care training and 2 additional nurses with ostomy care qualifications are needed.

[0081] The cost-efficiency judgment and coefficient output system compares the cost and efficiency of resource input, evaluates the quality improvement corresponding to unit resource input, eliminates high-cost and low-efficiency solutions, and finally outputs the first quality improvement coefficient.

[0082] The second calculation module constructs a nursing task priority ranking system, classifies and categorizes gastroenterology nursing tasks to obtain core essential tasks, optimization and improvement tasks, and auxiliary support tasks, and obtains the second quality improvement coefficient by combining the quality contribution weight of each task and resource requirements.

[0083] The system, taking into account the characteristics of gastroenterology diagnosis and treatment, divides nursing tasks into core essential tasks, optimization and improvement tasks, and auxiliary support tasks.

[0084] Core essential tasks: Tasks directly related to patient safety, such as monitoring critically ill pancreatitis patients, controlling post-endoscopic bleeding risks, and verifying medication administration.

[0085] Optimize and enhance tasks: Tasks that improve patient experience and prognosis, such as dietary education for patients with cirrhosis and psychological care for patients with inflammatory bowel disease.

[0086] Support tasks: Basic tasks that ensure the smooth operation of processes, such as ward environment organization and nursing document entry.

[0087] The weighting and coefficient output system assigns quality contribution weights to tasks of different levels: 0.6 for core tasks, 0.3 for optimization and improvement, and 0.1 for auxiliary support. It also performs weighted calculations based on the resource requirements of each task, such as manpower, time, and materials, and outputs a second quality improvement coefficient.

[0088] For example, the core mandatory task of observing post-endoscopic bleeding has a high quality contribution weight and clear resource requirements, and its corresponding second quality improvement coefficient is higher, which means that prioritizing the execution of this task can achieve a more significant quality improvement.

[0089] The rectification implementation module: Based on the first quality improvement coefficient and the second quality improvement coefficient, formulate nursing quality rectification plans and implement dynamic resource scheduling.

[0090] The system calculates a comprehensive score by weighting the first quality improvement coefficient and the second quality improvement coefficient at a 5:5 ratio, and determines the key areas for rectification, the execution sequence, and the resource allocation ratio based on the score.

[0091] For example, if the item with the highest overall score is the core essential task of increasing manpower and providing specialized training, the system will prioritize allocating qualified nurses for post-endoscopic care and arrange specialized training.

[0092] The dynamic resource scheduling system achieves real-time resource scheduling through interfaces with the nursing scheduling system, equipment management system, and material requisition system. When new quality deviations occur, such as nursing interruptions caused by equipment failure, the system automatically adjusts the shift schedule, allocates spare equipment, and updates the rectification plan to ensure timely response.

[0093] Data from the iterative rectification process, such as training completion rate, task compliance rate, and patient satisfaction, will be fed back to the data collection module and re-enter the verification and calculation process. This process involves collection, verification, calculation, rectification, and re-collection, continuously optimizing the evaluation model and scheduling strategy to achieve a spiral improvement in nursing quality.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for assessing the quality of gastroenterology nursing services using big data processing, characterized in that, The method includes the following steps: Collect real-time interactive data and traceable related data in the gastroenterology nursing scenario; Multi-dimensional verification of real-time interactive data and traceable related data is performed to obtain verification result values. When the verification result value triggers the quality warning threshold, the source of quality deviation is located by data tracing. The quality abnormality category is determined based on the scope and severity of the impact of the quality deviation source. The quality deviation quantitative index of nursing service is calculated based on the quality abnormality category. Based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, the amount of resources required to achieve quality standards within the target optimization cycle is calculated, and the cost-effectiveness of the resource input is judged to obtain the first quality improvement coefficient. A nursing task priority ranking system was constructed to classify and categorize the gastroenterology nursing tasks, resulting in core essential tasks, optimization and improvement tasks, and auxiliary support tasks. A second quality improvement coefficient was obtained by combining the quality contribution weight of each task with resource requirements. Based on the first and second quality improvement coefficients, a nursing quality improvement plan is formulated and dynamic resource allocation is implemented.

2. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 1, characterized in that, Collecting real-time interactive data and traceable data in a gastroenterology nursing setting includes the following steps: Real-time interactive data is generated by collecting nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data in the gastroenterology nursing scenario. Collect training records of nursing staff, patient medical history data, and assessment data in the gastroenterology nursing setting to form traceability data; The real-time interactive data and traceable related data are verified from multiple dimensions to obtain the verification result value. When the verification result value triggers the quality warning threshold, the source of the quality deviation is located by tracing the data source. The specific steps include: Real-time streaming data analysis is performed on nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data to generate real-time nursing interaction quality monitoring curves; The association mining and judgment of nursing staff training record data, patient past medical history data, and assessment traceability data are used to generate traceability dimension quality impact factor curves. The real-time nursing interaction quality monitoring curves are broken down into operation interaction quality curves, communication interaction quality curves, and equipment interaction quality curves according to interaction type. The traceability dimension quality impact factor curve is broken down into personnel qualification impact curve, individual patient impact curve, and department management impact curve according to the impact attribute. Each segmented curve is compared with its corresponding standard curve to identify abnormal curve segments that exceed the allowable deviation range. The source of quality deviation is located by tracing the data of the abnormal curve segments.

3. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 2, characterized in that, The quality deviation category is determined based on the scope and severity of the deviation source, and the quality deviation quantitative index of the nursing service is calculated based on the quality deviation category. The specific steps include: At least three quality anomaly categories are preset, each category corresponds to a unique range of impact and severity level, and each quality anomaly category is configured with a corresponding basic deviation coefficient and impact amplification coefficient; The impact range and severity values ​​of the source of the quantification deviation are matched with the corresponding intervals and levels of each quality abnormality category to determine the quality abnormality category of nursing services. The quality deviation quantification index of the nursing service is obtained by calculating the basic deviation coefficient, the influence amplification coefficient, and the cumulative duration of the deviation corresponding to the quality abnormality category.

4. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 3, characterized in that, Based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, the resource input required to achieve quality standards within the target optimization period is calculated, specifically including the following steps: Using the quality deviation quantification index as the core parameter, the basic resource input requirements are obtained by calculating the preset resource allocation efficiency coefficient. Taking into account the projected growth of nursing services and the resource depletion coefficient during the target optimization period, the basic resource input requirements are revised and calculated to obtain the resource input amount.

5. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 4, characterized in that, The first quality improvement coefficient is obtained by assessing the cost-effectiveness of resource input, which includes the following steps: The total input cost is obtained by calculating the human resource input cost, material consumption cost, technical support cost, and management coordination cost corresponding to the resource input amount; Based on the expected improvement ratio of the quality deviation quantification index, combined with the positive impact of improved nursing service quality on patient treatment outcomes and medical satisfaction, the comprehensive effectiveness value after quality improvement is calculated. The first quality improvement coefficient is obtained by calculating the ratio of total investment cost to comprehensive efficiency value and combining it with the preset efficiency conversion coefficient.

6. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 5, characterized in that, A nursing task priority ranking system was constructed to classify and categorize gastroenterology nursing tasks, resulting in core essential tasks, optimization and improvement tasks, and auxiliary support tasks. This process includes the following steps: We selected patient safety priority, quality impact weight, resource consumption efficiency, and urgency requirements as ranking indicators to construct a nursing task priority ranking system. Collect the specific values ​​of each nursing task under each ranking indicator, and calculate the comprehensive priority score based on the priority ranking system; Based on the overall priority score, core tasks that must be guaranteed, optimization and improvement tasks, and auxiliary support tasks are defined.

7. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 6, characterized in that, The second quality improvement coefficient is obtained by combining the quality contribution weight of each task and the resource requirements, specifically including the following steps: Calculate the quality contribution weight coefficient and resource requirement coefficient for core essential tasks, optimization and improvement tasks, and auxiliary support tasks respectively; Based on the hierarchical weight ratio of each task, the quality contribution weight coefficient and resource demand coefficient are calculated to obtain the comprehensive contribution coefficient and comprehensive demand coefficient. The second quality improvement coefficient is obtained by calculating the ratio of the comprehensive contribution coefficient to the comprehensive demand coefficient, combined with a preset balance adjustment factor.

8. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 7, characterized in that, Based on the first and second quality improvement coefficients, a nursing quality improvement plan is formulated and dynamic resource allocation is implemented, specifically including the following steps: If the first quality improvement coefficient is greater than the second quality improvement coefficient, a comprehensive rectification plan will be formulated with the goal of maximizing the effectiveness of quality improvement. All nursing tasks will be allocated in a balanced manner according to the optimal allocation ratio of resource input. If the first quality improvement coefficient is less than or equal to the second quality improvement coefficient, a priority-oriented rectification plan is formulated with the core quality assurance as the goal. Resources are prioritized for allocation to core essential tasks, and the remaining resources are allocated to optimization and improvement tasks and auxiliary support tasks in order of priority.

9. The method for evaluating the quality of gastroenterology nursing services using big data processing according to claim 8, characterized in that, Also includes: Set the basic cycle standard for optimizing nursing quality and record the warning time point when the verification result first triggers the quality warning threshold; By combining the current nursing resource load status of the gastroenterology department with historical quality optimization cycle data, the basic cycle standard is intelligently adjusted to obtain the final target optimization cycle.

10. A gastroenterology nursing service quality assessment system based on big data processing, applied to the gastroenterology nursing service quality assessment method based on big data processing as described in claims 1-9, characterized in that, include: Data acquisition module: Collects nursing operation interaction data, doctor-patient communication interaction data, and equipment usage interaction data in the gastroenterology nursing scenario to form real-time interactive data; collects nursing staff training record data, patient past medical history related data, and assessment traceability data in the gastroenterology nursing scenario to form traceability related data; Data verification module: Performs multi-dimensional verification on real-time interactive data and traceable related data to obtain verification result values. When the verification result value triggers the quality warning threshold, it locates the source of quality deviation through data tracing, determines the quality abnormality category based on the impact range and severity of the quality deviation source, and calculates the quality deviation quantitative index of nursing services based on the quality abnormality category. First calculation module: Based on the quality deviation quantification index and the preset resource allocation efficiency coefficient, calculate the amount of resource input required to achieve quality standards within the target optimization cycle, and obtain the first quality improvement coefficient by judging the cost-effectiveness of the resource input. The second calculation module: Constructs a nursing task priority ranking system, classifies and categorizes gastroenterology nursing tasks, obtains core essential tasks, optimization and improvement tasks, and auxiliary support tasks, and obtains the second quality improvement coefficient by combining the quality contribution weight of each task and resource requirements. The rectification implementation module: Based on the first quality improvement coefficient and the second quality improvement coefficient, formulate nursing quality rectification plans and implement dynamic resource scheduling.

Images