NRS-based nutrition risk data screening optimization method and related equipment thereof

Abstract

The invention belongs to the technical field of data processing and screening, and particularly provides an NRS-based nutrition risk data screening optimization method and related equipment thereof, and the method mainly comprises the steps: integrating nutrition risk data and scene parameters of a patient, calculating a real-time dynamic heat demand, and generating a demand fluctuation ratio; and generating an emergency degree score in combination with the NRS total score and the abnormal frequency, and finally screening high-risk patients based on the emergency degree, the heat demand decline rate and the activity ability level, thereby automatically shortening the evaluation period. According to the method, the change of the nutritional condition of the patient can be more timely perceived, evaluation is carried out in a shorter period, the change can be captured in the first time, the nutritional support strategy is dynamically adjusted, nutritional intervention is ensured to always accord with the current state of the patient, the medical service quality is practically improved, and the patient is ensured to obtain the most appropriate care.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing and screening, and particularly relates to an optimization method for nutritional risk data screening based on NRS and related devices. Background Art

[0002] NRS, namely nutritional risk screening, is a tool for evaluating the nutritional status of patients. By comprehensively considering factors such as the patient's disease state, weight change, and dietary intake, it judges whether the patient has nutritional risk and the degree of risk, providing a basis for clinical nutritional support.

[0003] In clinical nutritional management, medical staff often customize the NRS assessment cycle based on experience and routine procedures, which is generally relatively fixed and difficult to cope with sudden changes in patients' nutritional needs. For example, in severely traumatized patients, the body metabolism is disordered in a short time after injury, and the nutritional needs increase sharply; under the stress state of major surgery, the body has a high catabolic metabolism, and the demand for nutrients far exceeds normal. When the nutritional needs of patients surge, it is difficult for medical staff to detect it in time. By the time of the next periodic assessment, the best nutritional intervention opportunity may have been missed, affecting the patient's recovery process and treatment effect. Summary of the Invention

[0004] The present application effectively solves the problem in the prior art that the NRS assessment cycle is generally relatively fixed. When the nutritional needs of patients surge, it is difficult for medical staff to detect it in time, and the best nutritional intervention opportunity may be missed, affecting the patient's recovery process and treatment effect. It can capture these changes in the first time, dynamically adjust the nutritional support strategy, ensure that the nutritional intervention always fits the patient's current state, effectively improve the quality of medical services, and ensure that patients receive the most appropriate care.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] In the first aspect, the present application provides an optimization method for nutritional risk data screening based on NRS, including:

[0007] Obtain the nutritional risk data and scenario parameters of the patient, where the nutritional risk data includes the NRS assessment cycle and the NRS total score, and the scenario parameters include the ward type coefficient, the season adjustment factor, and the patient's activity ability level.

[0008] Calculate the patient's dynamic calorie requirement according to the scenario parameters, and calculate the demand volatility according to the dynamic calorie requirement.

[0009] Set a first threshold and a first weight, compare the demand volatility with the first threshold, and record the number of anomalies when the demand volatility exceeds the first threshold.

[0010] Calculate the urgency score based on the first weight, the total score of the nutritional risk assessment, and the number of consecutive anomalies.

[0011] Based on the urgency score, the decline rate of the dynamic calorie requirement, and the patient's activity ability level, screen out high-risk nutritional risk data and shorten the NRS assessment cycle to a specified cycle.

[0012] Furthermore, the ward type coefficient is set as the general ward coefficient, the intensive care unit coefficient, or the rehabilitation ward coefficient according to the ward type.

[0013] Obtain the real-time temperature and real-time humidity, set the temperature threshold, humidity threshold, first season factor, and second season factor, where the first season factor is greater than the second season factor; when the real-time temperature is less than the temperature threshold and the real-time humidity is less than the second threshold, the season adjustment factor is the first season factor, otherwise the second season adjustment factor is the second season factor.

[0014] The patient's activity ability level is set as the first activity ability value, the second activity ability value, and the third activity ability value according to the patient's activity ability.

[0015] Furthermore, calculate the patient's dynamic calorie requirement according to the scenario parameters, including:

[0016] Obtain the patient's weight and set the first specified time.

[0017] Every first specified time, calculate the patient's dynamic calorie requirement according to the patient's weight, the ward type coefficient, the season adjustment factor, and the patient's activity ability level.

[0018] Furthermore, calculate the demand volatility according to the dynamic calorie requirement, including:

[0019] Set the first specified period and construct a demand sequence containing all the dynamic calorie requirements within the first specified period.

[0020] Extract the maximum value and minimum value in the demand sequence, and calculate the average value of all the dynamic calorie requirements in the demand sequence.

[0021] The quotient obtained by dividing the difference between the maximum value and the minimum value by the average value is marked as the demand volatility.

[0022] Furthermore, when the demand volatility exceeds the first threshold, perform a non-linear adjustment on the first weight using the hyperbolic tangent function. The specific rule is:

[0023] When the demand volatility is less than the first threshold, the first weight remains the initial value.

[0024] When the demand volatility is greater than or equal to the first threshold, the first weight is calculated as follows: the difference between the demand volatility and the set critical value is input into the hyperbolic tangent function, and after obtaining the mapping result, it is superimposed on the initial value.

[0025] The value range of the first weight is from one to two.

[0026] Furthermore, a first value, a second value, and a third value are set; the first value is less than the second value, and the second value is less than the third value.

[0027] When the ward type coefficient is the rehabilitation ward coefficient, the first threshold is the first value.

[0028] When the ward type coefficient is the general ward coefficient, the first threshold is the second value.

[0029] When the ward type coefficient is the intensive care unit coefficient, the first threshold is the third value.

[0030] Furthermore, based on the urgency score, the decline rate of the dynamic calorie demand, and the patient's activity ability level, the NRS assessment cycle is shortened to a specified cycle, including:

[0031] Set a second specified period, a second threshold, and a third threshold.

[0032] When the following conditions 1-3 are simultaneously satisfied, the NRS assessment cycle is shortened to the specified cycle:

[0033] Condition 1: The urgency score is greater than the second threshold.

[0034] Condition 2: The decline rate of the dynamic calorie demand within the second specified period is greater than or equal to the third threshold.

[0035] Condition 3: The patient's activity ability level is the second activity ability value or the third activity ability value.

[0036] In a second aspect, the present application provides an NRS-based nutritional risk data screening and optimization system, which includes: a data acquisition module, a dynamic calorie calculation module, a demand volatility comparison module, an urgency calculation module, and an assessment cycle adjustment module.

[0037] The data acquisition module is used to acquire the nutritional risk data and scenario parameters of the patient. The nutritional risk data includes the NRS assessment cycle and the NRS total score, and the scenario parameters include the ward type coefficient, the season adjustment factor, and the patient's activity ability level.

[0038] The dynamic calorie calculation module is used to calculate the dynamic calorie demand of the patient according to the scenario parameters, and calculate the demand volatility according to the dynamic calorie demand.

[0039] The demand volatility comparison module is used to set a first threshold and a first weight, compare the demand volatility with the first threshold, and record the number of anomalies when the demand volatility exceeds the first threshold.

[0040] The urgency calculation module is used to calculate the urgency score according to the first weight, the total score of the nutritional risk score, and the consecutive anomaly count.

[0041] The evaluation cycle adjustment module is used to screen out high-risk nutritional risk data based on the urgency score, the decline rate of the dynamic calorie requirement, and the patient's activity ability level, and shorten the NRS evaluation cycle to a specified cycle.

[0042] In a third aspect, the present application provides a device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the method for screening and optimizing nutritional risk data based on NRS described in the first aspect when executing the computer program.

[0043] In a fourth aspect, the present application provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and run by a processor, the steps of the method for screening and optimizing nutritional risk data based on NRS described in the first aspect are executed.

[0044] Advantages of the present invention:

[0045] By integrating the patient's nutritional risk data and scenario parameters, calculating the real-time dynamic calorie requirement and generating the demand volatility, combining the NRS total score and the anomaly frequency to generate the urgency score, and finally screening high-risk patients based on the urgency, the calorie requirement decline rate, and the activity ability level, and automatically shortening the evaluation cycle, the present application effectively solves the problem in the prior art that the NRS evaluation cycle is generally relatively fixed. When the patient's nutritional needs surge, it is difficult for medical staff to detect in time, which may miss the best nutritional intervention opportunity and affect the patient's recovery process and treatment effect. It can capture these changes in a timely manner, dynamically adjust the nutritional support strategy, ensure that the nutritional intervention always fits the patient's current state, effectively improve the quality of medical services, and ensure that the patient receives the most appropriate care.

[0046] Other features and advantages of the present invention will be described in the following specification, and, in part, will become apparent from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained through the structures pointed out in the specification and the drawings. Description of the Drawings

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1 Fig. shows the schematic flow chart of the method for optimizing the screening of nutritional risk data based on NRS of the present invention;

[0049] Figure 2 Fig. shows the schematic diagram of the system for optimizing the screening of nutritional risk data based on NRS of the present invention. Detailed implementation manners

[0050] To solve the problems raised in the background art, the present disclosure integrates the nutritional risk data and scenario parameters of patients, calculates the real-time dynamic calorie requirement and generates the demand volatility, combines the total NRS score and the abnormal frequency to generate the urgency score, and finally screens high-risk patients based on the urgency, the calorie requirement decline rate, and the activity ability level, automatically shortening the evaluation cycle, and can more timely detect changes in the nutritional status of patients.

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0052] NRS2002 (Nutritional Risk Screening 2002 for Adults) is a commonly used nutritional risk screening tool at present, and its main content is as follows:

[0053] Initial screening: Body Mass Index (BMI) < 18.5 kg / m 2 , score 3 points; if the patient has lost weight in the past 3 months, score 1 point (mild), 2 points (moderate), or 3 points (severe); if the patient has had a disease-caused reduction in food intake in the past week, score 1 point (mild), 2 points (moderate), or 3 points (severe); if the patient has a serious disease (such as ICU patients, tumors, hemodialysis, etc.), score 3 points.

[0054] Re-screening: Disease severity score: Corresponding scores are given according to the severity of the disease the patient has. For example, patients with chronic diseases who are hospitalized due to complications are counted as 1 point, major abdominal surgeries are counted as 2 points, craniocerebral injuries, bone marrow transplants, etc. are counted as 3 points; Age adjustment score: If the age is ≥70 years old, 1 point is added; Nutritional status score: It is related to weight, eating situation, etc. in the initial screening. For example, if the weight drops by 10% - 20% and the food intake decreases by 20% - 50%, it is counted as 2 points, etc.

[0055] Those with a total score ≥3 points are determined to have nutritional risk and need to formulate a nutritional support plan; those with a total score <3 points are rechecked once a week.

[0056] Screen out high-risk nutritional risk data from all nutritional risk data and shorten the assessment cycle, which can more timely detect changes in the patient's nutritional status. The development of the disease, the implementation of treatment means, etc. may all cause rapid changes in the patient's nutritional risk situation. Evaluating at a shorter cycle can capture these changes in the first time, dynamically adjust the nutritional support strategy, ensure that the nutritional intervention always fits the patient's current state, effectively improve the quality of medical services, and ensure that the patient receives the most appropriate care.

[0057] As Figure 1 shown, the present disclosure provides an optimization method for screening nutritional risk data based on NRS, including:

[0058] S100. Obtain the patient's nutritional risk data and scenario parameters. The nutritional risk data includes the NRS assessment cycle and the NRS total score, and the scenario parameters include the ward type coefficient, the season adjustment factor, and the patient's activity ability level.

[0059] S200. Calculate the patient's dynamic calorie requirement according to the scenario parameters, and calculate the demand volatility according to the dynamic calorie requirement.

[0060] S300. Set a first threshold and a first weight, compare the demand volatility with the first threshold, and record the number of abnormalities when the demand volatility exceeds the first threshold.

[0061] S400. Calculate the urgency score according to the first weight, the total score of the nutritional risk score, and the consecutive number of abnormalities.

[0062] S500. Based on the urgency score, the decline rate of the dynamic calorie requirement, and the patient's activity ability level, screen out high-risk nutritional risk data and shorten the NRS assessment cycle to the specified cycle.

[0063] S100. Obtain the patient's nutritional risk data and scenario parameters. The nutritional risk data includes the NRS assessment cycle and the NRS total score, and the scenario parameters include the ward type coefficient, the season adjustment factor, and the patient's activity ability level. In S100:

[0064] In some embodiments, the ward type coefficient is set as a general ward coefficient, an intensive care unit (ICU) coefficient, or a rehabilitation ward coefficient according to the ward type.

[0065] For example, according to the "Guidelines for Nutritional Support of Critically Ill Patients", the resting energy expenditure (REE) of ICU patients is 30% - 50% higher than that of ordinary patients. The ICU coefficient can be taken as 1.5 to cover high - metabolic scenarios such as ventilator support and sepsis. The general ward coefficient can be taken as 1. The rehabilitation ward coefficient can be obtained in real - time through the API of the hospital information system (HIS) for the ward type where the patient is located.

[0066] Obtain the real - time temperature and real - time humidity, and set a temperature threshold, a humidity threshold, a first season factor, and a second season factor, where the first season factor is greater than the second season factor. When the real - time temperature is less than the temperature threshold and the real - time humidity is less than the second threshold, the season adjustment factor is the first season factor; otherwise, the second season adjustment factor is the second season factor.

[0067] The temperature and humidity of the environment where the patient is located can be collected in real - time through temperature and humidity sensors deployed in the ward. A high - temperature and high - humidity environment will significantly increase the patient's basal metabolic rate, but may also suppress appetite and accelerate dehydration. The second season factor balances the risk of increased metabolic rate and insufficient nutritional intake by reducing the calculated value of calorie requirements; in a mild environment, a higher first season factor is used to reflect the calorie requirements of the patient in a normal metabolic state.

[0068] For example, the temperature threshold can be 30°C, the humidity threshold can be 80% RH, the first season factor can be 1.2, and the second season factor can be 1.0.

[0069] Exemplarily, when the real - time temperature is 28°C and the humidity is 75%, the season factor is 1.2; when the real - time temperature is 32°C or the humidity is 85%, the season factor is 1.0.

[0070] The patient's activity ability level is set as a first activity ability value, a second activity ability value, and a third activity ability value according to the patient's activity ability. The first activity ability value, the second activity ability value, and the third activity ability value correspond to patients in the states of bedridden, assisted activity, and independent activity respectively.

[0071] It can be automatically mapped to the patient's activity ability level through the "activities of daily living ability" field in the nursing record, such as "activities of daily living ability" like "eating independently" or "requiring wheelchair transfer".

[0072] For example, muscle atrophy will lead to an increase in protein catabolism rate. For bedridden patients, it can be taken as 2.0, for assisted activity patients, it can be taken as 1.5, and for independent activity patients, it can be taken as 1.0.

[0073] S200. Calculate the patient's dynamic calorie requirement based on the scenario parameters, and calculate the demand volatility based on the dynamic calorie requirement. In S200:

[0074] In some embodiments, calculating the patient's dynamic calorie requirement based on the scenario parameters includes:

[0075] S210. Obtain the patient's weight and set a first specified time.

[0076] S220. Every first specified time, calculate the patient's dynamic calorie requirement according to the patient's weight, the ward type coefficient, the season adjustment factor, and the patient's activity ability level.

[0077] For example, the human metabolic rate may change significantly within 4 hours due to drugs, infections, or treatments. The first specified time can be 4 hours. It can be synchronized with the hospital's electronic medical record system EMR to obtain the latest weight, medication record, and nutritional risk data every 4 hours.

[0078] The patient's dynamic calorie requirement Q t can be: Q t = (25 × weight) × λ × S + 10 × A, where Q t represents the patient's dynamic calorie requirement, weight represents the patient's weight, λ represents the ward type coefficient, S represents the season adjustment factor, A represents the patient's activity ability level. To simplify the calculation of the metabolic rate, the basic energy consumption corresponding to 25 kcal per kg of body weight, and 10 × A reflects the change in energy consumption caused by the difference in activity ability.

[0079] In some embodiments, calculating the demand volatility based on the dynamic calorie requirement includes:

[0080] S230. Set a first specified period and construct a demand sequence including all the dynamic calorie requirements within the first specified period.

[0081] S240. Extract the maximum value and the minimum value in the demand sequence, and calculate the average value of all the dynamic calorie requirements in the demand sequence.

[0082] S250. Denote the ratio obtained by dividing the difference between the maximum value and the minimum value by the average value as the demand volatility.

[0083] By default, 72 hours is used as the data analysis window to cover the periodic fluctuations of human metabolism (such as circadian rhythm, feeding cycle). The dynamic calorie requirement is collected every 4 hours within the window period, generating a total of 18 data points. Arrange the dynamic calorie requirements Q t , and construct a demand sequence Q xl , Q xl is: Q xl = {Qt , Q t-4 ,..., Q t-72}, Exemplarily, the 72-hour demand sequence of patient B is: {2100, 2150, 2080, 2300*, 2250,..., 2180}, where * indicates a sudden increase in demand due to infection.

[0084] The demand volatility ΔQ is: max(Q xl ) and min(Q xl ) represent the maximum and minimum values in Q xl respectively. By max(Q xl ) - min(Q xl ), the metabolic stability is quantified to capture abnormal signals of sudden events such as infection and trauma. mean(Q xl ) represents the average of all dynamic calorie demands Q xl in the demand sequence Q t , eliminating the differences in individual patient metabolic bases, such as different weights.

[0085] The 72-hour window covers 3 complete day-night cycles, effectively identifying patterns such as morning blood glucose fluctuations and reduced night-time metabolism. The 4-hour sampling matches clinical care nodes (such as drug administration and vital sign monitoring), avoiding data overload while ensuring sensitivity.

[0086] S300. Set the first threshold and the first weight, compare the demand volatility with the first threshold, and when the demand volatility exceeds the first threshold, record the number of anomalies. In S300:

[0087] In some embodiments, an outlier refers to an extreme fluctuation in a single dynamic calorie demand Q t or a continuous high level of demand volatility ΔQ. Exemplarily, when the difference between a calculated Q t and the previous value exceeds ±30%, such as when the patient's weight is stable, if the dynamic calorie demand Q t suddenly drops from 2000 kcal to 1400 kcal, it is regarded as an outlier, which may be caused by acute infection, drug side effects, or data collection errors, such as incorrect weight entry.

[0088] The first threshold can be 0.3. This threshold is obtained based on clinical data analysis and can effectively distinguish normal metabolic fluctuations from pathological fluctuations. A single demand volatility ΔQ ≥ 0.3 may be an occasional event, such as a temporary fever, and it is necessary to observe whether it persists. If the demand volatility ΔQ ≥ 0.3 continuously for multiple times, it indicates a deterioration of the condition, such as uncontrolled infection, multiple organ failure, etc.

[0089] When the demand volatility ΔQ is greater than the first threshold, it indicates that the fluctuation range of the nutritional demand within 72 hours exceeds 30% of the baseline mean, reflecting the instability of the patient's metabolic state.

[0090] In some embodiments, a first value, a second value, and a third value are set; the first value is less than the second value, and the second value is less than the third value.

[0091] When the ward type coefficient is the rehabilitation ward coefficient, the first threshold is the first value.

[0092] When the ward type coefficient is the general ward coefficient, the first threshold is the second value.

[0093] When the ward type coefficient is the intensive care unit coefficient, the first threshold is the third value.

[0094] The first threshold represents the upper limit of the allowable demand volatility ΔQ. The lower the first threshold, the smaller the allowable fluctuation range, and the more sensitive the system. For patients in the intensive care unit, due to mechanical ventilation, use of vasoactive drugs, etc., the demand volatility ΔQ is naturally high. If a low threshold is set, there will be frequent false alarms; for rehabilitation patients, the metabolism tends to be stable, and the demand volatility ΔQ should be maintained at a low level. Setting a lower first threshold can detect infections or complications at an early stage.

[0095] Exemplarily, the first value can be 0.2, the second value can be 0.25, and the third value can be 0.3.

[0096] S400. Calculate the urgency score according to the first weight, the total nutritional risk score, and the number of consecutive anomalies. In S400:

[0097] In some embodiments, the urgency value is calculated by the following formula:

[0098] EC = NRS total score × F e ×(1 + 0.1×C a )

[0099] where EC represents the urgency value, NRS total score represents the nutritional risk screening score, with a range of 3 - 7 points, C a represents the number of consecutive anomalies, with an upper limit of 3 times, which can prevent the urgency value EC from getting out of control due to long-term fluctuations, and F e represents the first weight, and the value of the first weight can be 1.

[0100] In some embodiments, when the demand volatility exceeds the first threshold, a hyperbolic tangent function is used to non-linearly adjust the first weight. The specific rule is:

[0101] 1. When the demand volatility is less than the first threshold, the first weight remains at the initial value.

[0102] 2. When the demand volatility is greater than or equal to the first threshold, the first weight is calculated as follows: The difference between the demand volatility and the set critical value is input into the hyperbolic tangent function, and after obtaining the mapping result, it is superimposed on the initial value.

[0103] 3. The value range of the first weight is from one to two.

[0104] The hyperbolic tangent function is introduced to dynamically adjust the first weight Fe to balance the sensitivity and anti-interference ability of metabolic fluctuation detection.

[0105] The first weight F e can be: F e = 1 + tanh(ΔQ - 0.3), and the tanh function maps ΔQ - 0.3 to (-1, 1), making F e continuously increase from 1.0 when ΔQ = 0.3, avoiding misjudgment caused by step jumps.

[0106] F e ∈[1.0, 2.0], which can prevent extreme fluctuations from overly amplifying the EC value, such as ΔQ = 10 caused by instrument failure.

[0107] Exemplarily, the demand volatility ΔQ is 0.5, representing a mild anomaly, and the first weight F e is approximately 1.197, which can increase the EC value; the demand volatility ΔQ is 1, representing a significant anomaly, and the first weight F e is approximately 1.602, with a medium weight increase; the demand volatility ΔQ is 10, representing an extreme anomaly, such as instrument failure, and the first weight F e is automatically capped at 2.0 to prevent the emergency level value EC from being overly amplified by incorrect data.

[0108] When the total NRS score ≥ 5, it indicates a high-risk population, and the EC value can directly amplify the emergency level of such patients; when the demand volatility ΔQ is 0.6, the first weight value F e ≈ 1.29, increasing the emergency level value EC of patients with a total NRS score = 5 to 6.45; in extreme scenarios, such as severe infection, the first weight value F e ≈ 1.76, and the emergency level value EC = 12.32, requiring immediate intervention.

[0109] S500. Based on the emergency level score, the decline rate of the dynamic calorie demand, and the patient's activity ability level, high-risk nutritional risk data is screened, and the NRS assessment cycle is shortened to the specified cycle. In S500:

[0110] In some embodiments, S500 includes:

[0111] Set the second specified period, the second threshold, and the third threshold; when the following conditions 1-3 are simultaneously met, shorten the NRS assessment period to the specified period:

[0112] Condition 1: The urgency score is greater than the second threshold.

[0113] Condition 2: The decline rate of dynamic heat demand within the second specified period is greater than or equal to the third threshold.

[0114] Condition 3: The patient's activity ability level is the second activity ability value or the third activity ability value.

[0115] The urgency value being greater than the second threshold indicates that the patient's urgency exceeds the baseline risk level that the current medical resources can bear.

[0116] The second specified period can be set to 24 hours, covering the golden window period for the development of acute diseases.

[0117] The second threshold T c Can be: Among them, c N Represents the current number of critically ill patients in the hospital, and b t Represents the total number of beds. When the proportion of critically ill patients increases, the threshold automatically decreases to ensure that the most critical patients are given priority treatment when resources are scarce. For example, when Increases from 20% to 80%, the second threshold T c Decreases from 6.65 to 6.72, and more patients can be included in the cohort with the NRS assessment period shortened to the specified period.

[0118] The coefficient 0.05 can be adjusted according to the hospital scale. For example, it can be changed to 0.03 for Class III Grade A hospitals; the CN data is connected to the hospital HIS system in real time and synchronized every 15 minutes.

[0119] The third threshold can be 15%. A ≥15% decrease in nutritional requirements within 24 hours may be strongly correlated with acute diseases such as septic shock and gastrointestinal bleeding.

[0120] For patients with limited mobility and bedridden patients, muscle breakdown accelerates, nutritional requirements increase steeply, and the risk of complications is higher, such as septic shock and postoperative hypercatabolism. The nutritional requirements of patients may change drastically within a few hours. For example, the nutritional requirements of patients with multiple organ failure may increase step by step. The conventional cycle cannot capture the step jumps. Bedridden patients may experience a sharp increase in protein requirements due to muscle atrophy within 24 hours. Timely adjustment of the nutritional intervention plan can significantly reduce the mortality rate.

[0121] The specified period can be 12 hours. Shortening the assessment period to 12 hours allows medical staff to intervene in a timely manner during the compensatory period of metabolic imbalance. For example, when the lactate level increases slightly but does not reach the shock standard, the intervention window is 50% earlier than the traditional 24-hour cycle, significantly reducing the risk of multiple organ failure.

[0122] As Figure 2 shown, in some embodiments, the present disclosure provides an optimized system for screening nutritional risk data based on NRS, which includes: a data acquisition module, a dynamic calorie calculation module, a demand volatility comparison module, an urgency calculation module, and an evaluation cycle adjustment module.

[0123] The data acquisition module is used to obtain the nutritional risk data and scenario parameters of the patient. The nutritional risk data includes the NRS evaluation cycle and the total NRS score. The scenario parameters include the ward type coefficient, the season adjustment factor, and the patient's activity ability level. The dynamic calorie calculation module is used to calculate the patient's dynamic calorie demand according to the scenario parameters, and calculate the demand volatility according to the dynamic calorie demand. The demand volatility comparison module is used to set a first threshold and a first weight, compare the demand volatility with the first threshold, and record the number of anomalies when the demand volatility exceeds the first threshold. The urgency calculation module is used to calculate the urgency score according to the first weight, the total nutritional risk score, and the consecutive number of anomalies. The evaluation cycle adjustment module is used to screen out high-risk nutritional risk data based on the urgency score, the decline rate of the dynamic calorie demand, and the patient's activity ability level, and shorten the NRS evaluation cycle to a specified cycle.

[0124] The optimized system for screening nutritional risk data based on NRS has the advantages of the optimized method for screening nutritional risk data based on NRS, and can automatically implement all steps of the optimized method for screening nutritional risk data based on NRS.

[0125] In some embodiments, the present disclosure provides a device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the optimized method for screening nutritional risk data based on NRS when executing the computer program.

[0126] In some embodiments, the present disclosure provides a readable storage medium, characterized in that the readable storage medium stores computer program instructions, and when the computer program instructions are read and run by a processor, the steps of the optimized method for screening nutritional risk data based on NRS are executed.

[0127] Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention may include non-volatile and / or volatile memories. The non-volatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM) or an external cache memory.

[0128] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0129] Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements 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. An optimized method for screening nutritional risk data based on NRS, characterized in that, Including: Obtain the nutritional risk data and scenario parameters of the patient. The nutritional risk data includes the NRS assessment period and the total NRS score. The scenario parameters include the ward type coefficient, the seasonal adjustment factor, and the patient's activity ability level; Calculate the patient's dynamic calorie requirement according to the scenario parameters, and calculate the demand volatility according to the dynamic calorie requirement; Set a first threshold and a first weight, compare the demand volatility with the first threshold, and record the number of anomalies when the demand volatility exceeds the first threshold; Calculate the emergency score according to the first weight, the total nutritional risk score, and the consecutive number of anomalies; Based on the emergency score, the decline rate of the dynamic calorie requirement, and the patient's activity ability level, screen out the high-risk nutritional risk data and shorten the NRS assessment period to the specified period.

2. The optimized method for screening nutritional risk data based on NRS according to claim 1, wherein The ward type coefficient is set as the general ward coefficient, the intensive care unit coefficient, or the rehabilitation ward coefficient according to the ward type; Obtain the real-time temperature and real-time humidity, set the temperature threshold, the humidity threshold, the first seasonal factor, and the second seasonal factor, where the first seasonal factor is greater than the second seasonal factor; When the real-time temperature is less than the temperature threshold and the real-time humidity is less than the second threshold, the seasonal adjustment factor is the first seasonal factor; otherwise, the second seasonal adjustment factor is the second seasonal factor; The patient's activity ability level is set as the first activity ability value, the second activity ability value, and the third activity ability value according to the patient's activity ability.

3. The optimized method for screening nutritional risk data based on NRS according to claim 2, characterized in that, Calculate the patient's dynamic calorie requirement according to the scenario parameters, including: Obtain the patient's weight and set the first specified time; Every first specified time, calculate the patient's dynamic calorie requirement according to the patient's weight, the ward type coefficient, the seasonal adjustment factor, and the patient's activity ability level.

4. The optimized method for screening nutrition risk data based on NRS according to claim 3, wherein, Calculate the demand volatility according to the dynamic calorie requirement, including: Set the first specified period, and construct a demand sequence containing all the dynamic calorie requirements within the first specified period; Extract the maximum value and the minimum value in the demand sequence, and calculate the average value of all the dynamic calorie requirements in the demand sequence; The quotient obtained by dividing the difference between the maximum value and the minimum value by the average value is marked as the demand volatility.

5. The optimized method for screening nutritional risk data based on NRS according to claim 4, characterized in that, When the demand volatility exceeds the first threshold, perform a non-linear adjustment on the first weight using the hyperbolic tangent function. The specific rule is: When the demand volatility is less than the first threshold, the first weight remains the initial value; When the demand volatility is greater than or equal to the first threshold, the first weight is calculated as follows: Input the difference between the demand volatility and the set critical value into the hyperbolic tangent function, and then add the mapped result to the initial value; The value range of the first weight is from one to two.

6. The optimized method for screening nutrition risk data based on NRS according to claim 5, wherein Set the first value, the second value, and the third value; the first value is less than the second value, and the second value is less than the third value; When the ward type coefficient is the rehabilitation ward coefficient, the first threshold is the first value; When the ward type coefficient is the general ward coefficient, the first threshold is the second value; When the ward type coefficient is the intensive care unit coefficient, the first threshold is the third value.

7. The optimized method for screening nutritional risk data based on NRS according to claim 3, characterized in that Shorten the NRS assessment cycle to a specified cycle based on the emergency degree score, the decline rate of the dynamic calorie requirement, and the patient's activity ability level, including: Set a second specified period, a second threshold, and a third threshold; When the following conditions 1-3 are simultaneously satisfied, shorten the NRS assessment cycle to a specified cycle: Condition 1: The emergency degree score is greater than the second threshold; Condition 2: The decline rate of the dynamic calorie requirement within the second specified period is greater than or equal to the third threshold; Condition 3: The patient's activity ability level is the second activity ability value or the third activity ability value.

8. A nutrition risk data screening optimization system based on NRS, which includes: A data acquisition module, which is used to acquire the nutrition risk data and scenario parameters of the patient. The nutrition risk data includes the NRS assessment cycle and the NRS total score, and the scenario parameters include the ward type coefficient, the season adjustment factor, and the patient's activity ability level; A dynamic calorie calculation module, which is used to calculate the patient's dynamic calorie requirement according to the scenario parameters and calculate the demand volatility according to the dynamic calorie requirement; A demand volatility comparison module, which is used to set a first threshold and a first weight, compare the demand volatility with the first threshold, and record the number of abnormal times when the demand volatility exceeds the first threshold; An emergency degree calculation module, which is used to calculate the emergency degree score according to the first weight, the total nutrition risk score, and the consecutive abnormal times; An assessment cycle adjustment module, which is used to screen out high-risk nutrition risk data based on the emergency degree score, the decline rate of the dynamic calorie requirement, and the patient's activity ability level, and shorten the NRS assessment cycle to a specified cycle.

9. A device, characterized in that, It includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the nutrition risk data screening optimization method based on NRS according to any one of claims 1-7 when executing the computer program.

10. A readable storage medium, characterized in that, Computer program instructions are stored in a readable storage medium. When the computer program instructions are read and run by a processor, the steps of the nutrition risk data screening optimization method based on NRS according to any one of claims 1-7 are executed.

Images