Automatic early warning and screening method and system based on sepsis

Through the connection with the hospital system through the clinical risk management software of sepsis, the intelligent evaluation and monitoring of sepsis is used to use the SOFA scoring mechanism, which solves the problem of early diagnosis and screening of sepsis, improves diagnostic efficiency and accuracy, and reduces medical staff burden.

CN119028570APending Publication Date: 2024-11-26RUIJIN HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411116103.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

It is difficult to effectively conduct early diagnosis and screening of sepsis in the prior art, resulting in missed diagnosis and high workload, affecting the evaluation efficiency and accuracy of medical staff.

Method used

Through the clinical risk management software for sepsis, the patient data is automatically captured and the SOFA scoring mechanism is used to conduct intelligent assessment and early warning, real-time monitoring and diagnosis or consultation prompts are provided, reducing the burden on medical staff and improving screening efficiency.

Benefits of technology

It has realized the automation and intelligence of early identification and diagnosis of sepsis, reduced the rate of missed diagnosis, reduced the work burden of medical staff, and improved the evaluation efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028570A_ABST
    Figure CN119028570A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of automatic early warning and screening, and provides an automatic early warning and screening method based on sepsis, which comprises the following steps: S1, docking sepsis clinical risk management software with an original hospital system, automatically capturing medical record data including patient basic information, examination results, medical advices and medical record documents in the original hospital system into the sepsis clinical risk management software; s2, the sepsis clinical risk management software analyzes the captured medical record data, and adopts an SOFA scoring mechanism to automatically perform intelligent assessment and early warning on the risk that the patient develops into sepsis; s3, the state of the patient is monitored in real time, when the risk of developing sepsis is monitored, definite diagnosis or consultation prompting is carried out, and critical treatment and illness state monitoring are carried out on the patient. From hospitalization screening, early recognition, early diagnosis and standard treatment of sepsis are gradually perfected and improved, health management is enhanced, and a prevention and treatment combined long-acting mechanism is constructed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of automatic early warning and screening, and in particular to an automatic early warning and screening method and system based on sepsis. Background Art

[0002] Sepsis is characterized by severe illness, high mortality, and rapid disease progression. Early diagnosis and treatment of sepsis is an important treatment measure to effectively avoid septic shock and death. Clinically, it is recommended to use a sofa score greater than or equal to two points plus clear signs of infection to diagnose sepsis. Therefore, the guidelines of the United States, Europe, and China strongly recommend early sofa evaluation of sepsis.

[0003] In the early warning and diagnosis of sepsis, how to conduct a full sample and dynamic risk assessment of in-hospital patients to screen out patients with high risk of confirmed sepsis is the most difficult and labor-intensive link. It is a very difficult task to accurately find high-risk patients. It is necessary to perform sofa scoring and determine whether the patient has infection indications, and the sofa scoring results of the patient need to be repeatedly evaluated every day. The traditional assessment is that medical staff check the corresponding items on the paper version of the assessment scale and then accumulate the scores. According to the score range recommended by the guidelines, the risk level is stratified according to the score. Some hospitals also embed the assessment scale into the hospital information system (HIS) to form an electronic form, but medical staff are still required to check the items in the electronic form like writing electronic medical records, and perform a "modified manual assessment". The above two assessment methods will form a certain burden on the daily work of medical staff, which is easy to cause medical staff to resist sepsis screening and evaluation, resulting in missed diagnosis of sepsis.

[0004] Early screening and intervention of sepsis play an important role in the treatment and alleviation of the patient's condition. The diagnosis of early sepsis in ICU patients plays an important role in the recovery of the disease. Early intervention can prevent the patient's condition from progressing to septic shock and improve the cure rate and mortality rate. Therefore, a simple, effective and timely early screening and intervention method for sepsis with a small workload for medical staff is needed. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide an automatic early warning and screening method and system based on sepsis, starting from hospitalization screening, gradually improving and enhancing the early identification, early diagnosis and standardized treatment of sepsis, strengthening health management, and building a long-term mechanism combining prevention and treatment. It helps hospitals explore new ways of sepsis and information-based intelligent diagnosis and treatment, and provides reference and support for the work of gradually reducing the high growth rate of sepsis.

[0006] The above-mentioned object of the present invention is achieved through the following technical solutions:

[0007] An automatic early warning and screening method based on sepsis comprises the following steps:

[0008] S1: The sepsis clinical risk management software is connected to the original hospital system, and the medical record data including basic patient information, examination and test results, doctor's orders and medical record documents in the original hospital system are automatically captured into the sepsis clinical risk management software;

[0009] S2: The sepsis clinical risk management software analyzes the captured medical record data and uses the SOFA scoring mechanism to automatically perform intelligent assessment and early warning on the risk of the patient developing sepsis;

[0010] S3: Monitor the patient's condition in real time. When the risk of developing sepsis is detected, confirm the diagnosis or provide a consultation prompt, and provide emergency treatment and condition monitoring for the patient.

[0011] Furthermore, in step S1, the sepsis clinical risk management software is connected to the original hospital system, and the medical record data including basic patient information, examination and test results, doctor's orders and medical record documents in the original hospital system are automatically captured into the sepsis clinical risk management software, specifically:

[0012] The sepsis clinical risk management software automatically performs SOFA risk factor identification, scoring and early warning using the SOFA scoring mechanism based on the medical record data including the patient's basic information, the examination and test results, the doctor's orders and the medical record documents;

[0013] The sepsis clinical risk management software is connected to the original hospital system including the electronic medical record system EMR, the hospital information system HIS, the laboratory information system LIS, the radiology information system RIS, the hospital integration platform, the clinical data warehouse CDR, and the image archiving and communication system PACS, and automatically identifies the patient's risk factors including past medical history, surgery, and test results from the medical record data based on natural language processing (NLP) technology;

[0014] Among them, the risk factors include age, respiratory disease, chronic liver disease, diabetes, hypertension, chronic kidney disease, renal transplant status, portal hypertension, severe malnutrition, acute events, prerenal factors, renal factors, postrenal factors, and laboratory-related tests.

[0015] Furthermore, in step S2, the sepsis clinical risk management software analyzes the captured medical record data and uses the SOFA scoring mechanism to automatically perform intelligent assessment and early warning of the risk of the patient developing sepsis, specifically:

[0016] Based on the risk factors identified from the medical record data, performing a SOFA score;

[0017] For patients who have been diagnosed with sepsis, the data of the previous natural day are selected for early warning assessment every day. When the SOFA score is ≥ 2 points, a SOFA result confirmation prompt is pushed;

[0018] For patients with unconfirmed sepsis, the worst value of all data is selected daily for early warning assessment. When the SOFA score is ≥ 2 points, a SOFA result confirmation prompt and an infection confirmation prompt are pushed for diagnosis or consultation.

[0019] Furthermore, in step S2, it also includes: re-evaluating the SOFA score, specifically:

[0020] When the medical record data is modified, or the examination or test report is updated, or the nursing record is updated, the patient's risk change is recalculated in real time, and the patient's condition change is automatically monitored in real time. When the SOFA score is ≥2 points compared with the last time, and the minimum manual SOFA score time exceeds 24 hours, the system pushes a re-evaluation reminder;

[0021] The SOFA score is reviewed automatically or manually, and the comparison between human and machine scores is supported. When the human and machine scores are inconsistent, the automatic and manual scores are compared item by item on the same interface, and the original text basis content and location of the automatic score are given;

[0022] It also supports viewing historical scoring records, and supports modification, invalidation, and re-evaluation of scoring results. Multiple scoring results form an evaluation trend for doctors to view.

[0023] Furthermore, in step S3, the patient's condition is monitored in real time. When the risk of developing sepsis is detected, a diagnosis or consultation prompt is made, and the patient is given emergency treatment and condition monitoring, specifically:

[0024] Confirmation prompt: For patients without sepsis diagnosis, when the emergency ICU doctor confirms the patient's infection and the manually confirmed SOFA score is ≥ 2 points, the sepsis clinical risk management software will actively prompt the doctor to supplement the sepsis diagnosis and carry out corresponding treatment through timely early diagnosis to block the progression of the patient's condition;

[0025] Consultation reminder: If the patient is in a non-emergency ICU department or non-infectious disease department, the sepsis clinical risk management software intelligently analyzes the patient's test results and physical sign information. For infected patients with a SOFA score of ≥2 points, there is a possibility of sepsis, and the software intelligently pushes an ICU / infectious disease department consultation reminder;

[0026] For patients diagnosed with sepsis, routine critical care examinations and blood lactate monitoring reminders are automatically pushed to remind doctors to monitor patients' vital signs and lactic acidosis in a timely manner;

[0027] It automatically identifies the patient's condition and doctor's orders, and conducts routine monitoring of critically ill patients. It pushes routine tests such as primary examinations, blood routine, electrolytes, liver and kidney function to doctors, assisting doctors in conducting routine condition monitoring for patients.

[0028] Furthermore, the automatic early warning and screening method based on sepsis also includes: S4: the sepsis clinical risk management software provides conventional treatment strategies and personalized treatment strategies for patients, specifically:

[0029] Conduct quality control of routine treatment strategies, push targeted symptomatic treatment tips based on the patient's condition, and routinely push treatment strategies including antimicrobial drug treatment, anticoagulant therapy, nutritional support, and respiratory support to doctors for patients diagnosed with sepsis, reminding doctors to provide patients with timely and effective intervention measures;

[0030] Conduct quality control of personalized treatment strategies, monitor patients' blood sugar, hemoglobin, blood pH values ​​in real time, and push targeted symptomatic treatment strategies based on doctor's advice, including reminders for blood transfusion, sugar control, and acidosis correction. When the patient's hemoglobin is <70g / L, push a reminder for blood transfusion.

[0031] Furthermore, the sepsis clinical risk management software also provides data mining analysis of sepsis, specifically:

[0032] Supports distribution statistics of infection status of suspected sepsis patients, and supports downloading of patient lists corresponding to indicators; the patient details list includes data such as patient name, age, attending physician, admission time, discharge time, admission department, admission ward, discharge department, discharge ward, admission diagnosis, discharge diagnosis, AI diagnosis results, AI diagnosis basis, AI infection basis, confirmed sepsis days, ICU consultation, and SOFA assessment results;

[0033] Supports consultation statistics for suspected sepsis in non-I CU departments, and supports downloading of patient lists corresponding to indicators;

[0034] Supports monthly, weekly, and daily statistics on the number of sepsis patients, the number of patients diagnosed with sepsis, and the diagnosis rate of sepsis patients, and supports downloading of patient lists corresponding to the indicators;

[0035] Supports comparative analysis of SOFA assessments of sepsis in different departments, suspected sepsis patients, confirmed sepsis patients, and other information;

[0036] Statistical indicators are personalized for retrieval based on conditions including discharge time, admission time, department / ward, and attending physician.

[0037] An automatic early warning and screening system based on sepsis for executing the automatic early warning and screening method based on sepsis as described above, comprising:

[0038] A medical record data capture module is used to provide the sepsis clinical risk management software with the original hospital system for docking, and automatically capture the medical record data including basic patient information, examination and test results, doctor's orders and medical record documents in the original hospital system into the sepsis clinical risk management software;

[0039] A data analysis and evaluation module, used to provide the sepsis clinical risk management software with the captured medical record data for analysis, and to automatically conduct intelligent evaluation and early warning of the risk of the patient developing sepsis using the SOFA scoring mechanism;

[0040] The prompt processing monitoring module is used to monitor the patient's condition in real time. When the risk of developing sepsis is detected, a diagnosis or consultation prompt is issued, and the patient is given emergency treatment and the condition is monitored.

[0041] A computer device comprises a memory and one or more processors, wherein the memory stores computer codes, and when the computer codes are executed by the one or more processors, the one or more processors execute the above method.

[0042] A computer-readable storage medium stores computer codes. When the computer codes are executed, the above method is executed.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] By providing an automatic early warning and screening method based on sepsis, including: S1: the sepsis clinical risk management software is connected with the original hospital system, and the medical record data including the basic information of the patient, the test results, the doctor's order and the medical record documents in the original hospital system are automatically captured into the sepsis clinical risk management software; S2: the sepsis clinical risk management software analyzes the captured medical record data, and uses the SOFA scoring mechanism to automatically conduct intelligent assessment and early warning of the risk of the patient developing sepsis; S3: the patient's status is monitored in real time, and when the risk of developing sepsis is monitored, a diagnosis or consultation prompt is made, and the patient is critically treated and the condition is monitored. The above technical solution uses the existing medical record data in the original hospital system to intelligently and automatically screen and warn of sepsis, conduct full sample screening, effectively predict the risk level of the high-risk population of sepsis in the hospital medical records, and accurately screen out high-risk medical records. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The figure is an overall flow chart of the automatic early warning and screening method based on sepsis of the present invention;

[0046] Figure 2 This is a data processing diagram of the automatic early warning and screening method for sepsis according to the present invention;

[0047] Figure 3 This is a schematic diagram of the connection between the sepsis clinical risk management software of the present invention and the original hospital system;

[0048] Figure 4 The figure is an overall structural diagram of the automatic early warning and screening system based on sepsis of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0051] This application is a technical solution for a sepsis clinical risk early warning system for all patients in the hospital produced using information technology. Through real-time quality control reminders and scheduled quality control statistics, the hospital's sofa assessment rate and the early diagnosis rate of sepsis are improved. It aims to help hospitals achieve early detection and early warning of sepsis in patients, achieve early prevention and early intervention, and reduce the morbidity and mortality of sepsis.

[0052] This application is a method for disease prediction and intervention using artificial intelligence technology, using natural language processing (NLP), data mining and machine learning and other artificial intelligence technologies, applying text mining and semantic analysis technology, deeply analyzing the medical documents, diagnosis, surgery, inspection, doctor's orders and other related high-risk pathogenic information in the original medical system, and turning the medical record data in the form of unstructured text into structured data that can be used for statistics, query and analysis, with the characteristics of fast early warning, fast prompt and high intelligence. The system can use intelligent and automated sepsis screening early warning risk assessment technology to carry out full sample screening, effectively predict the risk level of high-risk sepsis population in hospital medical records, and accurately screen out high-risk medical records.

[0053] After the patient is admitted to the hospital, the medical staff of the corresponding professional department will use different methods (such as doctor's consultation, test and examination, etc.) to collect the patient's condition data and generate the patient's condition data set (such as medical record writing, doctor's advice, nursing records, etc.). The present invention is to dynamically evaluate the risk of sepsis on the basis of making full use of these condition data sets. The present invention extracts sepsis risk factor data from the patient data set (including structured and unstructured data). The principle of data collection is based on the SOFA (Sequential Organization Failure Assessment) table. The extracted data constitutes a database of high-risk populations for sepsis. The database of high-risk populations for sepsis automatically completes the SOFA score of all patients according to the scoring principle of the high-risk population scoring scale for sepsis. When the score is greater than or equal to two points, a score reminder appears on the doctor's side of the hospital intranet workstation, and the medical staff can revise the evaluation results. According to the score results, the system can propose auxiliary suggestions for preventive measures and diagnosis and treatment plans. During preventive diagnosis and treatment, according to the methods and means adopted (such as taking blood pressure reduction measures), refer to the corresponding procedure specifications, perform corresponding operations, and propose suggestions that can be used for patient treatment plans. Medical staff provide auxiliary suggestions for sepsis prevention and treatment, make manual intervention adjustments, and carry out diagnosis and treatment activities for high-risk groups of sepsis. Medical quality monitoring personnel implement full-loop monitoring, feedback and tracking of relevant departments in the hospital according to the hospital's standard specifications for sepsis prevention and treatment. The hospital's sepsis prevention and treatment data are summarized and counted, the current status and existing problems of sepsis prevention and treatment in the hospital are analyzed, and feedback information is tracked and monitored to evaluate the implementation of sepsis prevention and treatment by professional departments and medical staff.

[0054] The technical solution of the present invention is specifically described below through specific implementation:

[0055] First embodiment

[0056] like Figure 1 As shown, this embodiment provides an automatic early warning and screening method based on sepsis, comprising the following steps:

[0057] S1: The sepsis clinical risk management software is connected to the original hospital system to automatically capture the medical record data including basic patient information, examination and test results, medical advice and medical record documents in the original hospital system into the sepsis clinical risk management software.

[0058] Step S1 is specifically as follows:

[0059] The sepsis clinical risk management software automatically performs SOFA risk factor identification, scoring and early warning using the SOFA scoring mechanism based on the medical record data including the patient's basic information, the examination and test results, the doctor's orders and the medical record documents;

[0060] The sepsis clinical risk management software is connected to the original hospital system including the electronic medical record system EMR, the hospital information system HIS, the laboratory information system LIS, the radiology information system RIS, the hospital integration platform, the clinical data warehouse CDR, and the image archiving and communication system PACS, and automatically identifies the patient's risk factors including past medical history, surgery, and test results from the medical record data based on natural language processing NLP technology; the risk factors include age, respiratory disease, chronic liver disease, diabetes, hypertension, chronic kidney disease, renal transplant status, portal hypertension, severe malnutrition, acute events, prerenal factors, renal factors, postrenal factors, and laboratory-related examinations.

[0061] In this embodiment, the sepsis clinical risk management software and the original hospital system adopt an interface docking design. Through the docking of the sepsis clinical risk management software and the original hospital system, the intelligent prompt interface can be realized to obtain the data content in the original hospital system. After the original hospital system submits the patient's basic information, examination and test results, doctor's orders and medical records and other medical records data to the intelligent prompt interface, the software system analyzes the patient's condition, differential diagnosis and intelligent analysis and recommendation of related auxiliary diagnosis and treatment suggestions through powerful post-structuring capabilities and machine learning, combined with a powerful massive medical knowledge base. Analyze the patient's medical records and the doctor's diagnosis and treatment process, and remind the doctor of the diagnosis and treatment steps and disposal links that need to be performed during the diagnosis and treatment process.

[0062] like Figure 2 As shown in the figure, the medical records in the original hospital system are unstructured document data. The sepsis clinical risk management software supports receiving documents submitted by electronic medical records in various formats through an intelligent prompt interface, supports XML, plain text and key-value pairs, does not require electronic medical records to achieve structured entry, and can automatically extract structured information from unstructured electronic medical record content through machine learning, rule configuration and other methods, and supports flexible configuration. Through machine learning and doctor annotation and proofreading, a large number of medical maps are established, combined with natural language processing and NER and other intelligent algorithms, to achieve panoramic analysis of patient medical record data, differential diagnosis and intelligent recommendation.

[0063] The sepsis clinical risk management software is connected to the original hospital system and obtains the data content in the electronic medical record through an intelligent prompt interface. The original hospital system submits the patient's medical record data in XML format, plain text or key-value pairs, including but not limited to chief complaint, current medical history, past medical history and other information.

[0064] After the original hospital system submits the patient's basic information, examination and test results, medical orders, medical records and other medical record data to the intelligent prompt interface, the software system uses powerful post-structuring capabilities and machine learning, combined with a powerful and massive medical knowledge base, to analyze the patient's condition, make differential diagnoses and intelligently analyze and recommend related auxiliary diagnosis and treatment suggestions.

[0065] Combined with the patient's medical record, the doctor's diagnosis and treatment process is analyzed at the same time, and the doctor is reminded of the diagnosis and treatment steps and disposal links that need to be carried out during the diagnosis and treatment process, standardizing the doctor's diagnosis and treatment path, conducting quality control during diagnosis, reducing medical risks, and alleviating the burden on doctors.

[0066] Through the data interaction interface with the original hospital system, auxiliary diagnosis and treatment information can be written back to the electronic medical record, including but not limited to differential diagnosis information, examination items, medication and surgical plan information, evaluation forms, etc.

[0067] like Figure 3 As shown in the figure, the sepsis clinical risk management software is connected with the original hospital systems such as HIS, EMR, data center and integration platform in the hospital to realize the structuring of the diagnosis and treatment data of all patients in the hospital and form a diagnosis and treatment data center. On the one hand, it provides standard data for clinical research, data upload and clinical data quality control; on the other hand, it provides auxiliary diagnosis tools for clinical doctors, nurses, medical technology departments and doctors in the medical department. It fully meets clinical and management needs.

[0068] S2: The sepsis clinical risk management software analyzes the captured medical record data and uses the SOFA scoring mechanism to automatically perform intelligent assessment and early warning of the patient's risk of developing sepsis.

[0069] Step S2 is specifically as follows:

[0070] Based on the risk factors identified from the medical record data, performing a SOFA score;

[0071] For patients who have been diagnosed with sepsis, the data of the previous natural day are selected for early warning assessment every day. When the SOFA score is ≥ 2 points, a SOFA result confirmation prompt is pushed;

[0072] For patients with unconfirmed sepsis, the worst value of all data is selected daily for early warning assessment. When the SOFA score is ≥ 2 points, a SOFA result confirmation prompt and an infection confirmation prompt are pushed for diagnosis or consultation.

[0073] Among them, based on the risk factors identified from the medical record data, the criteria for SOFA scoring are exemplified as follows:

[0074] (1) Respiratory system

[0075] Risk Factors: Respiratory Disease

[0076] SOFA scoring index: PaO2 / FiO2 (ratio of arterial oxygen partial pressure / inspired oxygen concentration)

[0077] Scoring criteria:

[0078] PaO2 / FiO2>400: 0 points

[0079] PaO2 / FiO2 300-400: 1 point

[0080] PaO2 / FiO2 200-300: 2 points

[0081] PaO2 / FiO2 100-200: 3 points

[0082] PaO2 / FiO2<100: 4 points

[0083] (2) Coagulation function

[0084] Risk factors: None directly, but platelet count is often used

[0085] SOFA score indicator: platelet count

[0086] Scoring criteria:

[0087] Platelet count > 150,000: 0 points

[0088] Platelet count 100,000-150,000: 1 point

[0089] Platelet count 50,000-100,000: 2 points

[0090] Platelet count 20,000-50,000: 3 points

[0091] Platelet count <20,000: 4 points

[0092] (3) Liver function

[0093] Risk factors: chronic liver disease, portal hypertension

[0094] SOFA score indicator: bilirubin

[0095] Scoring criteria:

[0096] Bilirubin < 1.2 mg / dL: 0 points

[0097] Bilirubin 1.2-1.9 mg / dL: 1 point

[0098] Bilirubin 2.0-5.9 mg / dL: 2 points

[0099] Bilirubin 6.0-11.9 mg / dL: 3 points

[0100] Bilirubin > 12.0 mg / dL: 4 points

[0101] (4) Cardiovascular function

[0102] Risk factors: hypertension, acute events

[0103] SOFA score indicator: hypotension

[0104] Scoring criteria:

[0105] No hypotension: 0 points

[0106] Mean arterial pressure < 70 mmHg: 1 point

[0107] Dopamine requirement ≤ 5 μg / kg / min or any dose of dobutamine: 2 points

[0108] Requires dopamine 5-15 μg / kg / min or epinephrine / norepinephrine ≤ 0.1 μg / kg / min: 3 points

[0109] Requires dopamine > 15 μg / kg / min or epinephrine / norepinephrine > 0.1 μg / kg / min: 4 points

[0110] (5) Central Nervous System

[0111] Risk factors: Acute events (eg, acute brain injury)

[0112] SOFA score index: Glasgow Coma Scale (GCS)

[0113] Scoring criteria:

[0114] GCS15: 0 points

[0115] GCS13-14: 1 point

[0116] GCS10-12: 2 points

[0117] GCS 6-9: 3 points

[0118] GCS<6: 4 points

[0119] (6) Renal function

[0120] Risk factors: chronic kidney disease, renal transplant status, prerenal factors, renal factors, postrenal factors

[0121] SOFA score indicators: serum creatinine or urine volume

[0122] Scoring criteria:

[0123] Serum creatinine <1.2 mg / dL or urine output >500 mL / day: 0 points

[0124] Serum creatinine 1.2-1.9 mg / dL or urine output <500 mL / day: 1 point

[0125] Serum creatinine 2.0-3.4 mg / dL or urine output <500 mL / day: 2 points

[0126] Serum creatinine 3.5-4.9 mg / dL or urine output <200 mL / day: 3 points

[0127] Serum creatinine ≥5.0 mg / dL: 4 points

[0128] The scores of the above functions are added together to obtain the SOFA score.

[0129] In addition, step S2 also includes: re-evaluating the SOFA score, specifically:

[0130] When the medical record data is modified, or the examination or test report is updated, or the nursing record is updated, the patient's risk change is recalculated in real time, and the patient's condition change is automatically monitored in real time. When the SOFA score is ≥2 points compared with the last time, and the minimum manual SOFA score time exceeds 24 hours, the system pushes a re-evaluation reminder;

[0131] The SOFA score is reviewed automatically or manually, and the comparison between human and machine scores is supported. When the human and machine scores are inconsistent, the automatic and manual scores are compared item by item on the same interface, and the original text basis content and location of the automatic score are given;

[0132] It also supports viewing historical scoring records, and supports modification, invalidation, and re-evaluation of scoring results. Multiple scoring results form an evaluation trend for doctors to view.

[0133] S3: Monitor the patient's condition in real time. When the risk of developing sepsis is detected, confirm the diagnosis or provide a consultation prompt, and provide emergency treatment and condition monitoring for the patient.

[0134] Step S3 is specifically as follows:

[0135] Confirmation prompt: For patients without sepsis diagnosis, when the emergency ICU doctor confirms the patient's infection and the manually confirmed SOFA score is ≥ 2 points, the sepsis clinical risk management software will actively prompt the doctor to supplement the sepsis diagnosis and carry out corresponding treatment through timely early diagnosis to block the progression of the patient's condition;

[0136] Consultation reminder: If the patient is in a non-emergency ICU department or non-infectious disease department, the sepsis clinical risk management software intelligently analyzes the patient's test results and physical sign information. For infected patients with a SOFA score of ≥2 points, there is a possibility of sepsis, and the software intelligently pushes an ICU / infectious disease department consultation reminder;

[0137] For patients diagnosed with sepsis, routine critical care examinations and blood lactate monitoring reminders are automatically pushed to remind doctors to monitor patients' vital signs and lactic acidosis in a timely manner;

[0138] It automatically identifies the patient's condition and doctor's orders, and conducts routine monitoring of critically ill patients. It pushes routine tests such as primary examinations, blood routine, electrolytes, liver and kidney function to doctors, assisting doctors in conducting routine condition monitoring for patients.

[0139] In addition, it also supports closed-loop management of test inspections and treatment strategies. When doctors complete the test inspections and treatment orders pushed by the software system, the corresponding reminder information of the system will automatically disappear. At the same time, according to the risk situation and the actual management needs of the hospital, corresponding card control management is set at different nodes, supporting the implementation of a three-level hierarchical card control mode configuration.

[0140] Furthermore, the automatic early warning and screening method based on sepsis also includes: S4: the sepsis clinical risk management software provides conventional treatment strategies and personalized treatment strategies for patients, specifically:

[0141] Conduct quality control of routine treatment strategies, push targeted symptomatic treatment tips based on the patient's condition, and routinely push treatment strategies including antimicrobial drug treatment, anticoagulant therapy, nutritional support, and respiratory support to doctors for patients diagnosed with sepsis, reminding doctors to provide patients with timely and effective intervention measures;

[0142] Conduct quality control of personalized treatment strategies, monitor patients' blood sugar, hemoglobin, blood pH values ​​in real time, and push targeted symptomatic treatment strategies based on doctor's advice, including reminders for blood transfusion, sugar control, and acidosis correction. When the patient's hemoglobin is <70g / L, push a reminder for blood transfusion.

[0143] Furthermore, the sepsis clinical risk management software also provides data mining analysis of sepsis, specifically:

[0144] Supports distribution statistics of infection status of suspected sepsis patients, and supports downloading of patient lists corresponding to indicators; the patient details list includes data such as patient name, age, attending physician, admission time, discharge time, admission department, admission ward, discharge department, discharge ward, admission diagnosis, discharge diagnosis, AI diagnosis results, AI diagnosis basis, AI infection basis, confirmed sepsis days, ICU consultation, and SOFA assessment results;

[0145] Supports consultation statistics for suspected sepsis in non-I CU departments, and supports downloading of patient lists corresponding to indicators;

[0146] Supports monthly, weekly, and daily statistics on the number of sepsis patients, the number of patients diagnosed with sepsis, and the diagnosis rate of sepsis patients, and supports downloading of patient lists corresponding to the indicators;

[0147] Supports comparative analysis of SOFA assessments of sepsis in different departments, suspected sepsis patients, confirmed sepsis patients, and other information;

[0148] Statistical indicators are personalized for retrieval based on conditions including discharge time, admission time, department / ward, and attending physician.

[0149] Second embodiment

[0150] like Figure 4 As shown, this embodiment provides an automatic early warning and screening system based on sepsis for executing the automatic early warning and screening method based on sepsis in the first embodiment, comprising:

[0151] The medical record data capture module 1 is used to provide the sepsis clinical risk management software with the original hospital system for docking, and automatically capture the medical record data including the patient's basic information, examination and test results, doctor's orders and medical record documents in the original hospital system into the sepsis clinical risk management software.

[0152] The data analysis and evaluation module 2 is used to provide the sepsis clinical risk management software with the captured medical record data for analysis, and to automatically perform intelligent evaluation and early warning on the risk of the patient developing sepsis using the SOFA scoring mechanism.

[0153] The prompt processing monitoring module 3 is used to monitor the patient's condition in real time. When the risk of developing sepsis is detected, a diagnosis or consultation prompt is issued, and the patient is given emergency treatment and condition monitoring.

[0154] A computer-readable storage medium stores a computer code. When the computer code is executed, the above method is executed. A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0155] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

[0156] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0157] It should be noted that the above embodiments can be freely combined as needed. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention.

Claims

1. An automatic early warning and screening method based on sepsis, It is characterized in that The following steps are involved: S1: The sepsis clinical risk management software is connected to the original hospital system, and the medical record data including basic patient information, examination and test results, doctor's orders and medical record documents in the original hospital system are automatically captured into the sepsis clinical risk management software; S2: The sepsis clinical risk management software analyzes the captured medical record data and uses the SOFA scoring mechanism to automatically perform intelligent assessment and early warning of the risk of the patient developing sepsis; S3: Monitor the patient's condition in real time. When the risk of developing sepsis is detected, confirm the diagnosis or provide a consultation prompt, and provide emergency treatment and condition monitoring for the patient.

2. The automatic early warning and screening method based on sepsis according to claim 1, It is characterized in that In step S1, the sepsis clinical risk management software is connected to the original hospital system, and the medical record data including basic patient information, examination and test results, doctor's orders and medical record documents in the original hospital system are automatically captured into the sepsis clinical risk management software, specifically: The sepsis clinical risk management software automatically performs SOFA risk factor identification, scoring and early warning using the SOFA scoring mechanism based on the medical record data including the patient's basic information, the examination and test results, the doctor's orders and the medical record documents; The sepsis clinical risk management software is connected to the original hospital system including the electronic medical record system EMR, the hospital information system HIS, the laboratory information system LIS, the radiology information system RIS, the hospital integration platform, the clinical data warehouse CDR, and the image archiving and communication system PACS, and automatically identifies the patient's risk factors including past medical history, surgery, and test results from the medical record data based on natural language processing (NLP) technology; Among them, the risk factors include age, respiratory disease, chronic liver disease, diabetes, hypertension, chronic kidney disease, renal transplant status, portal hypertension, severe malnutrition, acute events, prerenal factors, renal factors, postrenal factors, and laboratory-related tests.

3. The automatic early warning and screening method based on sepsis according to claim 2, It is characterized in that In step S2, the sepsis clinical risk management software analyzes the captured medical record data and uses the SOFA scoring mechanism to automatically perform intelligent assessment and early warning of the patient's risk of developing sepsis, specifically: Performing a SOFA score based on the risk factors identified from the medical record data; For patients who have been diagnosed with sepsis, the data of the previous natural day are selected for early warning assessment every day. When the SOFA score is ≥ 2 points, a SOFA result confirmation prompt is pushed; For patients with unconfirmed sepsis, the worst value of all data is selected daily for early warning assessment. When the SOFA score is ≥ 2 points, a SOFA result confirmation prompt and an infection confirmation prompt are pushed for diagnosis or consultation.

4. The automatic early warning and screening method based on sepsis according to claim 3, It is characterized in that In step S2, it also includes: re-evaluating the SOFA score, specifically: When the medical record data is modified, or the examination or test report is updated, or the nursing record is updated, the patient's risk change is recalculated in real time, and the patient's condition change is automatically monitored in real time. When the SOFA score is ≥2 points compared with the last time, and the minimum manual SOFA score time exceeds 24 hours, the system pushes a re-evaluation reminder; The SOFA score is reviewed automatically or manually, and the comparison between human and machine scores is supported. When the human and machine scores are inconsistent, the automatic and manual scores are compared item by item on the same interface, and the original text basis content and location of the automatic score are given; It also supports viewing historical scoring records, and supports modification, invalidation, and re-evaluation of scoring results. Multiple scoring results form an evaluation trend for doctors to view.

5. The automatic early warning and screening method based on sepsis according to claim 4, It is characterized in that In step S3, the patient's condition is monitored in real time. When the risk of developing sepsis is detected, a diagnosis or consultation prompt is made, and the patient is given emergency treatment and condition monitoring, specifically: Confirmation prompt: For patients without sepsis diagnosis, when the emergency ICU doctor confirms the patient's infection and the manually confirmed SOFA score is ≥ 2 points, the sepsis clinical risk management software will actively prompt the doctor to supplement the sepsis diagnosis and carry out corresponding treatment through timely early diagnosis to block the progression of the patient's condition; Consultation reminder: If the patient is not in the emergency ICU department or the infectious department, the sepsis clinical risk management software intelligently analyzes the patient's test results and physical sign information. For infected patients with a SOFA score of ≥2 points, there is a possibility of sepsis, and the software intelligently pushes ICU / infectious department consultation reminders; For patients diagnosed with sepsis, routine critical care examinations and blood lactate monitoring reminders are automatically pushed to remind doctors to monitor patients' vital signs and lactic acidosis in a timely manner; It automatically identifies the patient's condition and doctor's orders, and conducts routine monitoring of critically ill patients. It pushes routine tests such as primary examinations, blood routine, electrolytes, liver and kidney function to doctors, assisting doctors in conducting routine condition monitoring for patients.

6. The automatic early warning and screening method based on sepsis according to claim 1, It is characterized in that Also includes: S4: The sepsis clinical risk management software provides patients with conventional treatment strategies and personalized treatment strategies, specifically: Conduct quality control of routine treatment strategies, push targeted symptomatic treatment tips based on the patient's condition, and routinely push treatment strategies including antimicrobial drug treatment, anticoagulant therapy, nutritional support, and respiratory support to doctors for patients diagnosed with sepsis, reminding doctors to provide patients with timely and effective intervention measures; Conduct quality control of personalized treatment strategies, monitor patients' blood sugar, hemoglobin, blood pH values ​​in real time, and push targeted symptomatic treatment strategies based on doctor's advice, including reminders for blood transfusion, sugar control, and acidosis correction. When the patient's hemoglobin is <70g / L, push a reminder for blood transfusion.

7. The automatic early warning and screening method based on sepsis according to claim 1, It is characterized in that The sepsis clinical risk management software also provides data mining analysis of sepsis, specifically: Supports distribution statistics of infection status of suspected sepsis patients, and supports downloading of patient lists corresponding to indicators; the patient details list includes data such as patient name, age, attending physician, admission time, discharge time, admission department, admission ward, discharge department, discharge ward, admission diagnosis, discharge diagnosis, AI diagnosis results, AI diagnosis basis, AI infection basis, confirmed sepsis days, ICU consultation, and SOFA assessment results; Supports statistics on consultations for suspected sepsis in non-ICU departments, and supports downloading of patient lists corresponding to indicators; Supports monthly, weekly, and daily statistics on the number of sepsis patients, the number of patients diagnosed with sepsis, and the diagnosis rate of sepsis patients, and supports downloading of patient lists corresponding to the indicators; Supports comparative analysis of SOFA assessments of sepsis in different departments, suspected sepsis patients, confirmed sepsis patients, and other information; Statistical indicators are personalized for retrieval based on conditions including discharge time, admission time, department / ward, and attending physician.

8. An automatic early warning and screening system based on sepsis for executing the automatic early warning and screening method based on sepsis according to any one of claims 1 to 7, It is characterized in that include: A medical record data capture module is used to provide the sepsis clinical risk management software with the original hospital system for docking, and automatically capture the medical record data including basic patient information, examination and test results, doctor's orders and medical record documents in the original hospital system into the sepsis clinical risk management software; A data analysis and evaluation module, used to provide the sepsis clinical risk management software with the captured medical record data for analysis, and to automatically conduct intelligent evaluation and early warning of the risk of the patient developing sepsis using the SOFA scoring mechanism; The prompt processing monitoring module is used to monitor the patient's condition in real time. When the risk of developing sepsis is detected, a diagnosis or consultation prompt is issued, and the patient is given emergency treatment and the condition is monitored.

9. A computer device comprising a memory and one or more processors, wherein the memory stores computer codes, and when the computer codes are executed by the one or more processors, the one or more processors execute the method according to any one of claims 1 to 7. 10 . A computer-readable storage medium storing a computer code. When the computer code is executed, the method according to claim 1 is executed.