A method for predicting the status of patients in intensive care units

Abstract

The invention discloses a method for predicting the state of patients in an intensive care unit, and relates to the technical field of intensive care patient management. The method comprises the following steps: step one, obtaining electronic medical record data of patients in the intensive care unit through an HIS to form a patient data set; step two, obtaining real-time clinical data of patients in the intensive care unit through an intensive care information system to form a clinical data set; step three, obtaining diagnostic data of the condition of patients in the intensive care unit for each MDT through the HIS to form a diagnostic data set; step four, judging whether the patient enters the intensive care unit for treatment and monitoring for the first time, and analyzing and generating the critical illness duration; step five, establishing a time axis, analyzing the trend of the patient's condition change, and generating a fluctuation data group and an indicator line chart, so that the real-time analysis of the condition dynamic prediction has high accuracy; step six, analyzing and generating the diagnosis frequency, judging the rescue risk degree of patients in the intensive care unit, outputting the corresponding state prediction report, rationally allocating medical resources, and making the treatment more timely and effective.

Description

Technical Field

[0001] The present invention relates to the technical field of intensive care unit patient management, and in particular to a method for predicting the status of patients in an intensive care unit. Background Art

[0002] The ICU is a specialized area that provides advanced medical care and monitoring for patients who require emergency treatment and close monitoring. The ICU provides critically ill patients with the most advanced medical technology and equipment, as well as a professional nursing team, which can maximize the survival rate and quality of life of patients. The prediction of the status of patients in the ICU can help doctors and nurses better manage the patient's condition and take intervention measures in advance, thereby improving the patient's survival rate and quality of life. Commonly used methods for predicting the status of patients in the ICU include APACHE II (Acute Physiology and Chronic Health Evaluation II), SAPS II (Simplified Acute Physiology Scoring System II), and SOFA (Sequential Organ Failure Assessment). These scoring systems comprehensively evaluate the patient's condition by evaluating the patient's physiological indicators, age, underlying diseases and other factors, provide objective data and indicators, predict the patient's prognosis, and help doctors more accurately evaluate the patient's condition and treatment plan. For the prediction of the status of patients in the ICU, multidisciplinary team discussion (MDT) is also very important. MDT is composed of doctors from different specialties. By discussing the patient's condition, examination results and treatment plan together, they can have a more comprehensive understanding of the patient's condition and make more accurate predictions.

[0003] At present, traditional intensive care unit patient status prediction methods often rely on the medical staff's understanding of the patient to analyze and judge the patient's future condition changes. The longer the time span of the patient, the greater the treatment pressure on the medical staff. In addition, it is impossible to make dynamic predictions based on the patient's condition development trend, medical resources are unevenly allocated, and the multidisciplinary team does not discuss MDT treatment in a timely manner, which easily leads to missing the best treatment time for critically ill patients. Summary of the invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a method for predicting the status of patients in an intensive care unit, which has the advantages of high accuracy in real-time analysis of dynamic prediction of the disease, and more timely and effective treatment through reasonable allocation of medical resources. It solves the problem that the traditional method for predicting the status of patients in an intensive care unit cannot make dynamic predictions based on the development trend of the disease, and the multidisciplinary team cannot discuss MDT treatment in a timely manner.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for predicting the status of patients in an intensive care unit, comprising the following steps:

[0006] Step 1: Obtain the electronic medical record data of patients in the intensive care unit through the hospital information system HIS, and then form a patient data set with the acquired data;

[0007] Step 2: Obtain real-time clinical data of patients in the intensive care unit through the intensive care information system, and then form a clinical data set with the acquired data;

[0008] Step 3: Obtain the diagnostic data of each multidisciplinary team discussion on the condition of patients in the ICU through the hospital information system HIS, and then form a diagnostic data set with the acquired data;

[0009] Step 4: Based on the patient data set and clinical data set, determine whether the patient is entering the intensive care unit for treatment and monitoring for the first time, and analyze and generate the critical illness duration ;

[0010] Step 5: According to the duration of severe illness Create a timeline , combined with clinical data sets and diagnostic data sets, analyze the trend of patient condition changes and generate fluctuation data sets and indicator line chart ;

[0011] Step 6: According to the duration of severe illness and diagnostic datasets, analyzing the generated diagnostic frequencies , and judge the rescue risk level of patients in the intensive care unit, and output the corresponding status prediction report.

[0012] Preferably, in step 1, the expression of the patient data set is in, They are the 1st, 2nd, 3rd, and 4th patient data sets, respectively. Electronic medical record data of intensive care unit patients, superscript Electronic medical records include personal medical history, physical examination results, laboratory test results, imaging test results and treatment plans. Indicates that patients in intensive care units have name.

[0013] Preferably, in step 2, the expression of the clinical data set is ,in, They are the first, second, third, and Real-time clinical data of patients in the intensive care unit, including heart rate, blood pressure, oxygen saturation and body temperature. Indicates the time point of obtaining clinical data, Indicates that patients in intensive care units have name.

[0014] Preferably, in step 3, the expression of the diagnostic data set is ,in, The first, second, third, and When the multidisciplinary team discusses MDT, all departments will provide diagnostic data on the condition of patients in the ICU, including treatment decisions, drug recommendations, and prognostic results. Indicates the time point when the diagnostic data is obtained. Indicates the number of times the multidisciplinary team discussed MDT Second-rate.

[0015] Preferably, in step 4, the duration of severe illness The calculation process is as follows:

[0016] Extract the patient data set The electronic medical record data of intensive care unit patients were The personal medical history of the ICU patient is used to determine whether the patient is entering the ICU for treatment and monitoring for the first time. If the patient enters the ICU for treatment and monitoring multiple times, the number of times the patient appears in a critical state is marked as , If the patient is admitted to the intensive care unit for treatment and monitoring for the first time, ; In the formula, Indicates the duration of severe illness. Indicates the clinical data set Real-time clinical data of intensive care unit patients, Indicates the judgment When a patient first enters the intensive care unit for treatment and monitoring, the clinical data of the first intensive care period are counted, which is the duration of intensive care. Indicates the judgment When patients have been admitted to the intensive care unit multiple times, the comprehensive statistics The clinical data during the second intensive care period is the duration of critical illness.

[0017] Preferably, in step 5, the fluctuation data set The calculation process is as follows:

[0018] According to Duration of critical illness for each patient Create a timeline , and then extract the first Clinical data of all patients at all time points are inserted into the timeline in chronological order from early to late The data at each time point corresponds to a data node in the time axis. All data nodes in the ,in, Respectively represent Duration of critical illness 1st, 2nd, 3rd, The changes in clinical data are The condition change trends of the patients include changes in heart rate, blood pressure, oxygen saturation and body temperature. Indicates The number of times the condition of each patient changed was Second-rate; In the formula, represents a fluctuation data set, Indicates Duration of critical illness within, no. Clinical data at each change in condition, including heart rate ,blood pressure , oxygen saturation and body temperature , Indicates Duration of critical illness within, no. Clinical data at each change in condition, including heart rate ,blood pressure , oxygen saturation and body temperature , Indicates that the Patients When the condition changes, the sum of the differences in clinical data between two adjacent time points is the fluctuation data group, which includes heart rate fluctuations, blood pressure fluctuations, oxygen saturation fluctuations and body temperature fluctuations.

[0019] Preferably, in step 5, the fluctuation data set and timeline Substitute the data visualization tool for node processing and draw a line chart of the generated indicators , indicator line chart Including heart rate index line, blood pressure index line, oxygen saturation line and temperature index line. If the patient enters the intensive care unit for treatment and monitoring multiple times, the index line graph Presentation If the patient is admitted to the intensive care unit for treatment and monitoring for the first time, the indicator line graph Only the indicator line for a single time period is presented.

[0020] Preferably, in step six, the diagnosis frequency The calculation formula is as follows:

[0021] In the formula, represents the diagnosis frequency, Indicates Duration of critical illness In the diagnostic data set, The number of MDT discussions per patient, Indicates that for The number of multidisciplinary team discussions (MDT) and the duration of critical illness The ratio of is the diagnosis frequency.

[0022] Preferably, in step six, if the patient has been admitted to the intensive care unit for treatment and monitoring for many times, and the indicator line graph Middle The indicator line of the time period is lower than that of the When the indicator in a time period is broken, it means that the patient in the ICU has a high risk of rescue. The corresponding high-risk status prediction report is output, and the medical staff is reminded to conduct a multidisciplinary team discussion MDT for the patient. The high-risk status prediction report includes the duration of critical illness. , Fluctuation Data Group , indicator line chart , diagnostic data sets and high rescue risk judgment results.

[0023] Preferably, in step six, if the patient enters the intensive care unit for treatment monitoring for the first time, and the indicator line graph The indicator line trend fluctuates smoothly, indicating that the rescue risk of the patient in the ICU is low. The corresponding low-risk state prediction report is output. The low-risk state prediction report includes the duration of critical illness. , Fluctuation Data Group , indicator line chart , diagnostic data sets and low rescue risk judgment results.

[0024] Compared with the prior art, the present invention provides a method for predicting the status of patients in an intensive care unit, which has the following beneficial effects:

[0025] The present invention obtains the electronic medical record data of patients in the intensive care unit and the diagnostic data of the patients' conditions in each multidisciplinary team discussion MDT through the hospital information system HIS, and obtains the real-time clinical data of patients in the intensive care unit through the intensive care information system, and then classifies the acquired data into patient data sets, clinical data sets and diagnostic data sets. According to the patient data sets and clinical data sets, it is judged whether the patient enters the intensive care unit for treatment and monitoring for the first time, and the critical illness duration is generated by analysis. , which helps medical staff to better allocate medical resources and improve medical efficiency. Create a timeline , combined with clinical data sets and diagnostic data sets, comprehensively analyze the fluctuation of clinical data during intensive care and generate a fluctuation data set and indicator line chart , indicator line chart Including heart rate index line, blood pressure index line, oxygen saturation line and temperature index line, it directly reflects the fluctuation trend of the four major vital signs of patients in the intensive care unit. If the patient enters the intensive care unit for treatment and monitoring many times, the index line graph Presentation If the patient is admitted to the intensive care unit for treatment and monitoring for the first time, the indicator line graph Only the indicator line of a single time period is presented, and the disease dynamics are analyzed in real time with high prediction accuracy.

[0026] The present invention is through the duration of severe illness and diagnostic datasets, analyzing the generated diagnostic frequencies , and judge the degree of rescue risk of patients in the intensive care unit. If the patient has been admitted to the intensive care unit for treatment and monitoring many times, and the indicator line graph Middle The indicator line of the time period is lower than that of the When the indicator line graph in a time period is broken, it means that the rescue risk of the patient in the intensive care unit is high, and the corresponding high-risk status prediction report is output, and the medical staff is reminded to conduct a multidisciplinary team discussion MDT for the patient. If the patient enters the intensive care unit for treatment and monitoring for the first time, and the indicator line graph The indicator line trend fluctuates smoothly, indicating that the rescue risk of patients in the intensive care unit is low. The corresponding low-risk status prediction report is output to rationally allocate medical resources and make treatment more timely and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a step diagram of the method of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Since traditional ICU patient status prediction methods often rely on the medical staff's understanding of the patient to analyze and judge the patient's future condition changes, the longer the time span of the patient, the greater the treatment pressure on the medical staff. In addition, it is impossible to make dynamic predictions based on the patient's condition development trend, the uneven allocation of medical resources, and the untimely discussion of MDT treatment by the multidisciplinary team, which easily misses the best treatment opportunity for critically ill patients. Therefore, a ICU patient status prediction method is provided. Please refer to Figure 1 , the method comprises the following steps:

[0030] Step 1: Obtain the electronic medical record data of patients in the intensive care unit through the hospital information system HIS. The hospital information system HIS is the core system of hospital management. It integrates the medical information of various departments of the hospital, including patient information, doctor's order information, drug information, test information, etc., and provides comprehensive medical information support for medical staff, realizing information sharing, process optimization, data analysis and other functions, and improving medical quality and efficiency. The obtained electronic medical record data of patients in the intensive care unit are combined into a patient data set. The expression of the patient data set is ,in, to Corresponding to the electronic medical record data of each intensive care unit patient, They are the 1st, 2nd, 3rd, and 4th patient data sets, respectively. Electronic medical record data of intensive care unit patients, superscript Electronic medical records include personal medical history, physical examination results, laboratory test results, imaging test results and treatment plans. Indicates that patients in intensive care units have Name, that is, the patient who is receiving intensive care in the intensive care unit at the current time point patients, and these Patients were analyzed for status prediction and output one by one Status forecast report;

[0031] Step 2: Obtain real-time clinical data of patients in the intensive care unit through the intensive care information system, and then form a clinical data set with the acquired data. The expression of the clinical data set is: ,in, to Corresponding to the real-time clinical data of each patient in the intensive care unit, They are the first, second, third, and The real-time clinical data of patients in the ICU include heart rate, blood pressure, oxygen saturation and body temperature. The clinical data directly reflects the vital signs of patients. The ICU patients are monitored and analyzed 24 hours a day, providing real-time and accurate data support for subsequent status prediction. Indicates the time point of obtaining clinical data, Indicates that patients in intensive care units have name;

[0032] Step 3: Obtain the diagnostic data of each multidisciplinary team discussion on the condition of patients in the ICU through the hospital information system HIS, and then form a diagnostic data set with the acquired data. The expression of the diagnostic data set is: ,in, to Each time the multidisciplinary team discusses MDT, all departments will provide diagnostic data on the condition of patients in the intensive care unit. The first, second, third, and When the multidisciplinary team discusses MDT, all departments will provide diagnostic data on the condition of patients in the ICU, including treatment decisions, drug recommendations, and prognostic results. Indicates the time point when the diagnostic data is obtained. Indicates the number of times the multidisciplinary team discussed MDT Second, because the conditions of patients in the ICU are complex or involve multiple disciplines, doctors from other departments are needed to participate in discussions and provide professional opinions. The goal of MDT is to provide patients with the best diagnosis and treatment plans by integrating professional knowledge from different fields;

[0033] Step 4: Based on the patient data set and clinical data set, determine whether the patient is entering the intensive care unit for treatment and monitoring for the first time. For patients with a long time span, comprehensively consider the individual condition characteristics and previous medical history, effectively reduce the treatment pressure of medical staff, and analyze and generate the critical illness duration. , the calculation process is as follows:

[0034] Extract the patient data set The electronic medical record data of intensive care unit patients were The personal medical history of the ICU patient is used to determine whether the patient is entering the ICU for treatment and monitoring for the first time. If the patient enters the ICU for treatment and monitoring multiple times, the number of times the patient appears in a critical state is marked as , If the patient is admitted to the intensive care unit for treatment and monitoring for the first time, ; In the formula, Indicates the duration of severe illness. Indicates the clinical data set Real-time clinical data of intensive care unit patients, Indicates the judgment When a patient first enters the intensive care unit for treatment and monitoring, the clinical data of the first intensive care period are counted, which is the duration of intensive care. Indicates the judgment When patients have been admitted to the intensive care unit multiple times, the comprehensive statistics The clinical data of the second intensive care period is the duration of critical illness. The shorter the duration of critical illness and the more times the patient enters the intensive care unit, the more unstable the vital signs are and the higher the medical needs are. This helps medical staff to better allocate medical resources and improve medical efficiency.

[0035] Step 5: According to the duration of severe illness Create a timeline , combined with clinical data sets and diagnostic data sets, analyze the trend of patient condition changes and generate fluctuation data sets and indicator line chart ;

[0036] Fluctuation Data Group The calculation process is as follows:

[0037] According to Duration of critical illness for each patient Create a timeline , and then extract the first Clinical data of all patients at all time points are inserted into the timeline in chronological order from early to late , the data at each time point corresponds to a data node in the time axis, and the time axis All data nodes in the ,in, to Indicates Duration of critical illness Changes in clinical data, Respectively represent Duration of critical illness 1st, 2nd, 3rd, The changes in clinical data are The condition change trends of the patients include changes in heart rate, blood pressure, oxygen saturation and body temperature. Indicates The number of times the condition of each patient changed was Second-rate; In the formula, represents a fluctuation data set, Indicates Duration of critical illness within, no. Clinical data at each change in condition, including heart rate ,blood pressure , oxygen saturation and body temperature , Indicates Duration of critical illness within, no. Clinical data at each change in condition, including heart rate ,blood pressure , oxygen saturation and body temperature , Indicates that the Patients When the patient's condition changes, the sum of the differences in clinical data between two adjacent time points is the fluctuation data group, which includes heart rate fluctuations, blood pressure fluctuations, oxygen saturation fluctuations and body temperature fluctuations, and comprehensively analyzes the fluctuations of clinical data during the patient's intensive care period;

[0038] The fluctuation data set and timeline Substitute the data visualization tool for node processing and draw a line chart of the generated indicators , indicator line chart Including heart rate index line, blood pressure index line, oxygen saturation line and temperature index line, it directly reflects the fluctuation trend of the four major vital signs of patients in the intensive care unit. If the patient enters the intensive care unit for treatment and monitoring many times, the index line graph Presentation If the patient is admitted to the intensive care unit for treatment and monitoring for the first time, the indicator line graph Only the indicator line of a single time period is presented, and the disease dynamics are analyzed in real time, with high prediction accuracy;

[0039] Step 6: According to the duration of severe illness and diagnostic datasets, analyzing the generated diagnostic frequencies , and judge the rescue risk level of patients in the intensive care unit and output the corresponding status prediction report; In the formula, represents the diagnosis frequency, Indicates Duration of critical illness In the diagnostic data set, The number of MDT discussions per patient, Indicates that for The number of multidisciplinary team discussions (MDT) and the duration of critical illness The ratio of is the diagnosis frequency;

[0040] If the patient has been admitted to the intensive care unit for treatment and monitoring for many times, and the indicator line graph Middle The indicator line of the time period is lower than that of the When the indicator in a time period is broken, it means that the patient in the ICU has a high risk of rescue and is in a state of worsening condition. The corresponding high-risk status prediction report is output, and the medical staff is reminded to conduct a multidisciplinary team discussion MDT for the patient. The high-risk status prediction report includes the duration of critical illness , Fluctuation Data Group , indicator line chart , diagnostic data set and high rescue risk judgment results. On the contrary, if the patient has been admitted to the intensive care unit for treatment and monitoring many times, but the indicator line graph Middle The indicator line of the time period is higher than that of the When the indicator in a time period is broken, it means that the rescue risk of the patient in the intensive care unit is low and is gradually recovering, and the corresponding low-risk state prediction report is output;

[0041] If the patient enters the intensive care unit for treatment and monitoring for the first time, and the indicator line graph The indicator line trend fluctuates smoothly, indicating that the rescue risk of the patient in the ICU is low. The corresponding low-risk state prediction report is output. The low-risk state prediction report includes the duration of critical illness. , Fluctuation Data Group , indicator line chart , diagnostic data set and low rescue risk judgment results. On the contrary, if the patient enters the intensive care unit for treatment and monitoring for the first time, but the indicator line graph The indicator line trend fluctuates violently, indicating that the patient in the intensive care unit has a high risk of rescue and is in a state of worsening condition. The corresponding high-risk status prediction report is output, and medical staff are reminded to conduct a multidisciplinary team discussion MDT for the patient, rationally allocate medical resources, and provide more timely and effective treatment.

[0042] Example 1: In this experiment, two patients were set up in the intensive care unit. The first patient had been admitted to the intensive care unit for treatment and monitoring for 3 times, and the treatment and monitoring lasted for 5 days each time. The second patient was admitted to the intensive care unit for the first time for treatment and monitoring for 2 days. The duration of the critical illness of the two patients was The calculation process is as follows: ;In the formula, Indicates the duration of severe illness. Indicates the judgment When a patient first enters the intensive care unit for treatment and monitoring, the clinical data of the first intensive care period are counted, and 2 days is the duration of the second patient's intensive care. Indicates the judgment When a patient has been admitted to the intensive care unit three times, the clinical data of the three intensive care periods are comprehensively counted, and 15 days is the duration of the first patient's intensive care unit.

[0043] Example 2: In this experiment, a patient in the intensive care unit is set up, and the duration of critical illness The clinical data on the first day included a heart rate of 60 beats per minute, a blood pressure of 90, an oxygen saturation of 0.8, and a body temperature of 36.0°C. The clinical data on the second day included a heart rate of 50 beats per minute, a blood pressure of 60, an oxygen saturation of 0.9, and a body temperature of 39.0°C. The clinical data on the third day included a heart rate of 100 beats per minute, a blood pressure of 50, an oxygen saturation of 0.7, and a body temperature of 37.0°C. The patient's fluctuating data set The calculation process is as follows:

[0044] According to the duration of the patient's critical illness Create a timeline , extract the clinical data of this patient at all time points in the clinical data set, and insert them into the timeline in chronological order from early to late , the data at each time point corresponds to a data node in the time axis, and the time axis All data nodes in the , to It indicates the changes of clinical data of this patient in the intensive care unit within 3 days, including changes in heart rate, blood pressure, oxygen saturation and body temperature. Subscripts 1 to 3 indicate that the patient's condition has changed 3 times; ;In the formula, represents a fluctuation data set, It indicates the clinical data of the patient's condition change on the second day within 3 days. It indicates the clinical data of the patient's condition change on the first day within 3 days. It means that when calculating the patient's condition change for 3 days at the same time, the sum of the clinical data differences between two adjacent time points is the fluctuation data group, which includes heart rate fluctuation of 40, blood pressure fluctuation of -40, oxygen saturation fluctuation of -0.1 and body temperature fluctuation of 1.

[0045] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting the status of patients in an intensive care unit, characterized in that: The following steps are involved: Step 1: Obtain the electronic medical record data of patients in the intensive care unit through the hospital information system HIS, and then form a patient data set with the acquired data; The expression for the patient dataset is ,in, They are the 1st, 2nd, 3rd, and 4th patient data sets, respectively. Electronic medical record data of intensive care unit patients, superscript Electronic medical records include personal medical history, physical examination results, laboratory test results, imaging test results and treatment plans. Indicates that patients in intensive care units have name; Step 2: Obtain real-time clinical data of patients in the intensive care unit through the intensive care information system, and then form a clinical data set with the acquired data; The expression of the clinical data set is ,in, They are the first, second, third, and Real-time clinical data of patients in the intensive care unit, including heart rate, blood pressure, oxygen saturation and body temperature. Indicates the time point of obtaining clinical data, Indicates that patients in intensive care units have name; Step 3: Obtain the diagnostic data of each multidisciplinary team discussion on the condition of patients in the ICU through the hospital information system HIS, and then form a diagnostic data set with the acquired data; The expression of the diagnostic data set is ,in, The first, second, third, and When the multidisciplinary team discusses MDT, all departments will provide diagnostic data on the condition of patients in the ICU, including treatment decisions, drug recommendations, and prognostic results. Indicates the time point when the diagnostic data is obtained. Indicates the number of times the multidisciplinary team discussed MDT Second-rate; Step 4: Based on the patient data set and clinical data set, determine whether the patient is entering the intensive care unit for treatment and monitoring for the first time, and analyze and generate the critical illness duration ; Duration of severe illness The calculation process is as follows: Extract the patient data set The electronic medical record data of intensive care unit patients were The personal medical history of the ICU patient is used to determine whether the patient is entering the ICU for treatment and monitoring for the first time. If the patient enters the ICU for treatment and monitoring multiple times, the number of times the patient appears in a critical state is marked as , If the patient is admitted to the intensive care unit for treatment and monitoring for the first time, ; ； In the formula, Indicates the duration of severe illness. Indicates the clinical data set Real-time clinical data of intensive care unit patients, Indicates the judgment When a patient first enters the intensive care unit for treatment and monitoring, the clinical data of the first intensive care period are counted, which is the duration of intensive care. Indicates the judgment When patients have been admitted to the intensive care unit multiple times, the comprehensive statistics Clinical data during the secondary intensive care period, i.e., the duration of critical illness; Step 5: According to the duration of severe illness Create a timeline , combined with clinical data sets and diagnostic data sets, analyze the trend of patient condition changes and generate fluctuation data sets and indicator line chart ; Fluctuation Data Group The calculation process is as follows: According to Duration of critical illness for each patient Create a timeline , and then extract the first Clinical data of all patients at all time points are inserted into the timeline in chronological order from early to late , the data at each time point corresponds to a data node in the time axis, and the time axis All data nodes in the ,in, Respectively represent Duration of critical illness 1st, 2nd, 3rd, The changes in clinical data are The condition change trends of the patients include changes in heart rate, blood pressure, oxygen saturation and body temperature. Indicates The number of times the condition of each patient changed was Second-rate; ； In the formula, represents a fluctuation data set, Indicates Duration of critical illness within, no. Clinical data at each change in condition, including heart rate ,blood pressure , oxygen saturation and body temperature , Indicates Duration of critical illness within, no. Clinical data at each change in condition, including heart rate ,blood pressure , oxygen saturation and body temperature , Indicates that the Patients When the condition changes, the sum of the differences in clinical data between two adjacent time points is the fluctuation data group, which includes heart rate fluctuation, blood pressure fluctuation, oxygen saturation fluctuation and body temperature fluctuation; Step 6: According to the duration of severe illness and diagnostic datasets, analyzing the generated diagnostic frequencies , and judge the rescue risk level of patients in the intensive care unit and output the corresponding status prediction report; Frequency of diagnosis The calculation formula is as follows: ； In the formula, represents the diagnosis frequency, Indicates Duration of critical illness In the diagnostic data set, The number of MDT discussions per patient, Indicates that for The number of multidisciplinary team discussions (MDT) and the duration of critical illness The ratio of is the diagnosis frequency.

2. A method for predicting the status of patients in an intensive care unit according to claim 1, characterized in that: In step 5, the fluctuation data set and timeline Substitute the data visualization tool for node processing and draw a line chart of the generated indicators , indicator line chart Including heart rate index line, blood pressure index line, oxygen saturation line and temperature index line. If the patient enters the intensive care unit for treatment and monitoring multiple times, the index line graph Presentation If the patient is admitted to the intensive care unit for treatment and monitoring for the first time, the indicator line graph Only the indicator line for a single time period is presented.

3. A method for predicting the status of patients in an intensive care unit according to claim 2, characterized in that: In step 6, if the patient has been admitted to the intensive care unit for treatment and monitoring for many times, and the indicator line graph Middle The indicator line of the time period is lower than that of the When the indicator in a time period is broken, it means that the rescue risk of the patient in the ICU is high, and the corresponding high-risk status prediction report is output, and the medical staff is reminded to conduct a multidisciplinary team discussion MDT for the patient. The high-risk status prediction report includes the duration of critical illness , Fluctuation Data Group , indicator line chart , diagnostic data sets and high rescue risk judgment results.

4. A method for predicting the status of patients in an intensive care unit according to claim 3, characterized in that: In step 6, if the patient enters the intensive care unit for treatment and monitoring for the first time, and the indicator line graph The indicator line trend fluctuates smoothly, indicating that the rescue risk of the patient in the ICU is low. The corresponding low-risk state prediction report is output. The low-risk state prediction report includes the duration of critical illness. , Fluctuation Data Group , indicator line chart , diagnostic data sets and low rescue risk judgment results.

Images