Special sepsis data management system based on electronic medical record data

Abstract

The invention discloses the field of medical database systems, and particularly relates to a sepsis special disease data management system based on electronic medical record data. The sepsis special disease data management system comprises a total data acquisition module, a sepsis judgment module and an expert suggestion module, the sepsis judgment module comprises an infection judgment unit and an SOFA scoring unit; the infection judgment unit is used for collecting pathophysiological data to judge whether infection occurs or not; the SOFA scoring unit is used for acquiring SOFA scores (or predicting SOFA scores when some parameters are incomplete) change conditions to judge sepsis diagnosis conditions and specific sepsis occurrence time; and the expert suggestion module is used for giving system evaluation suggestions based on the diagnosis conditions given by the sepsis judgment module. Through the scheme, sepsis diagnosis can be more standardized, a reference basis is provided for sepsis occurrence time, the utilization rate of electronic cases is further improved, dependence on disease coding is reduced, and more possibilities are provided for sepsis diagnosis.

Description

Technical Field

[0001] This invention belongs to the field of medical database systems, specifically a sepsis-specific disease data management system based on electronic medical record data. Background Technology

[0002] With the development of medical informatization, the demand for building medical big data platforms and systematically managing various medical data is increasing. In existing related technologies, hospitals accumulate a large amount of patient medical data during the diagnosis and treatment process. However, this data exhibits various differences, resulting in a lack of data integration and making it difficult to effectively manage and utilize the data resources.

[0003] The lack of categorized management, particularly in the management of certain special cases such as sepsis, presents a significant challenge. When healthcare workers need to access relevant data, the process is complex and cumbersome, greatly increasing their workload. Furthermore, sepsis is a syndrome caused by infection, resulting in physiological, pathological, and biochemical abnormalities. The incidence of sepsis varies considerably across different studies, depending on data collection methods, study time periods, and study regions. Therefore, a standardized definition of sepsis and proper data screening are crucial. Currently, existing technologies typically use the discharge diagnosis of sepsis as the inclusion criterion for database entry. This approach carries a high risk of missed diagnoses, leading to a severe underestimation of the sepsis incidence rate. Summary of the Invention

[0004] To address the aforementioned problems, the purpose of this invention is to provide a sepsis-specific disease data management system based on electronic medical records, thereby standardizing specialized disease data, providing a standardized basis for sepsis diagnosis, improving the diagnostic rate of sepsis, and reducing the number of missed diagnoses of sepsis.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows:

[0006] The sepsis-specific disease data management system based on electronic medical records includes: a full data collection module, a sepsis diagnosis module, and an expert advice module.

[0007] The full data acquisition module includes a patient information unit, an interface unit, and a data conversion unit. The patient information unit is used to collect all in-hospital related information of patients from various hospital business systems. The interface unit is used to interface with patient medical record information from other hospitals. The data conversion unit is used to convert and unify data from different data sources and different data types.

[0008] The sepsis assessment module includes an infection assessment unit and an SOFA scoring unit; the infection assessment unit is used to collect pathophysiological data to determine whether an infection has occurred; the SOFA scoring unit is used to obtain changes in the SOFA score (or to predict the SOFA score when some parameters are incomplete) to determine the diagnosis of sepsis and the specific time of sepsis onset.

[0009] The expert advice module is used to provide system evaluation suggestions based on the diagnosis given by the sepsis judgment module.

[0010] The above solution achieved the following beneficial effects:

[0011] This solution collects all relevant patient information from within the hospital through a patient information unit, and aggregates and summarizes all medical records from other hospitals. A data conversion unit converts data from the information unit, the docking unit, and other formats, formatting all data according to a unified standard. Pathophysiological data is then extracted from the merged case information to determine if the patient is infected and whether further sepsis diagnosis is necessary.

[0012] If a patient is confirmed to have an infection, the SOFA unit is used to score changes in the patient's respiratory PaO2 / FiO2, platelet count, bilirubin levels in the liver, mean arterial pressure, dopamine, dobutamine, adrenaline, and norepinephrine levels in the kidneys, as well as changes in GCS, creatinine, and urine output in the kidneys. If the final score is greater than or equal to 2, sepsis is diagnosed, and the approximate onset time of sepsis can be determined based on the calculated SOFA scores for each time period; otherwise, it is not sepsis.

[0013] The expert advice module will then provide corresponding system assessment recommendations based on the different diagnostic conditions of the patient's sepsis.

[0014] This scheme standardizes the definition of sepsis through a sepsis assessment module, namely, a diagnosis of sepsis is made when the infection score plus a SOFA score greater than or equal to 2. Compared with traditional diagnostic methods, this scheme does not rely on disease codes (such as ICD-9 / ICD-10 codes), making better use of the patient's pathophysiological data in electronic medical records, expanding the diagnostic scope, reducing the chance of missing sepsis patients, and determining the specific time of sepsis onset as needed.

[0015] In summary, this scheme can make the diagnosis of sepsis more standardized, provide a reference for the timing of sepsis onset, further improve the utilization rate of electronic medical records, reduce the reliance on disease coding, and provide more possibilities for the diagnosis of sepsis.

[0016] Furthermore, the SOFA score includes: PaO2 / FiO2 changes in the respiratory system, whether ventilator support is required, platelet changes in the blood system, bilirubin changes in the liver, mean arterial pressure changes in the circulatory system, dopamine changes in the circulatory system, dobutamine changes in the circulatory system, adrenaline changes in the circulatory system, norepinephrine changes in the circulatory system, GCS score in the nervous system, creatinine changes in the kidneys, and urine output changes in the kidneys.

[0017] Furthermore, if the infection determination unit determines an infection and the SOFA scoring unit tests a SOFA score greater than or equal to 2, then the diagnosis is sepsis; otherwise, it is not sepsis.

[0018] Furthermore, when a patient's SOFA score parameters are missing, the sepsis assessment module will use artificial intelligence algorithms to compensate for the incomplete parameters based on the other remaining parameters and other indicators obtained, and then use the compensated parameters to make a comprehensive score.

[0019] Furthermore, it also includes a human suggestion module, which is used to provide manual assessment suggestions from sepsis medical experts based on the patient's condition when it is impossible to complete the scoring parameters.

[0020] Furthermore, when collecting patient pathophysiological data, the sepsis assessment module will perform completeness analysis and timeliness analysis on the patient's pathophysiological data. The completeness analysis determines whether the collected content is complete and verifies the completeness of the collected content; the timeliness analysis determines whether the time logic of the collected data is reasonable.

[0021] Furthermore, once the sepsis assessment module completes the missing parameters, it will use artificial intelligence big data algorithms combined with a medical knowledge base to verify and test the scoring parameters. Attached Figure Description

[0022] Figure 1 This is a system block diagram of Embodiment 1 of the sepsis-specific disease data management system based on electronic medical records of the present invention. Detailed Implementation

[0023] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0024] The following detailed description illustrates the specific implementation method:

[0025] Example 1

[0026] The basic implementation examples are as follows: Figure 1 As shown: The sepsis-specific disease data management system based on electronic medical records includes: a full data collection module, a sepsis diagnosis module, and an expert advice module;

[0027] The full data acquisition module includes a patient information unit, an interface unit, and a data conversion unit. The patient information unit is used to collect all in-hospital diagnosis and treatment information of patients from various hospital business systems. The interface unit is used to interface with patient medical record information from other hospitals. The data conversion unit is used to convert and unify data from different data sources and different data types.

[0028] The sepsis assessment module includes an infection assessment unit and an SOFA scoring unit; the infection assessment unit is used to collect pathophysiological data to determine whether an infection has occurred; the SOFA scoring unit is used to test changes in the SOFA score to determine the diagnosis of sepsis and the specific time of sepsis onset.

[0029] The expert advice module is used to provide system assessment suggestions based on the diagnosis given by the sepsis assessment module;

[0030] This solution collects all patient treatment information within the hospital through a patient information unit, and aggregates and summarizes all patient medical records from other hospitals through a data exchange unit. The data conversion unit converts data from the information unit, the data exchange unit, and other formats, unifying all data formats.

[0031] Then, pathophysiological data are collected from the merged case information to determine whether the patient is infected and whether further diagnosis of sepsis is needed. If the patient is confirmed to be infected, the SOFA unit is used to score the changes in PaO2 / FiO2 in the respiratory system, platelet count in the blood system, bilirubin in the liver, mean arterial pressure, dopamine, dobutamine, adrenaline, and norepinephrine in the blood system, GCS in the nervous system, creatinine in the kidneys, and urine output in the kidneys. If the final score is greater than or equal to 2, sepsis is diagnosed, and the approximate time of sepsis onset can be determined based on the calculated SOFA score for each time period; otherwise, it is not sepsis.

[0032] The expert advice module provides systematic assessment recommendations based on the patient's sepsis diagnosis.

[0033] The specific implementation process is as follows:

[0034] This embodiment uses Zhang San's case as an example;

[0035] The patient information unit collects relevant information about Zhang San within this hospital, including:

[0036] Personal attribute data: such as patient name Zhang San, male, 82 years old, height 170cm, weight 58kg, etc.; hospitalization number, various examination and test related order numbers, etc.;

[0037] Health status data: chief complaint, present illness, past medical history, physical examination (signs), family history, symptoms, health check-up data, genetic counseling data, health-related information collected by wearable devices, lifestyle, etc.

[0038] Medical application data: outpatient (emergency) medical records, outpatient (emergency) prescriptions, inpatient medical orders, examination and test reports, medication information, medical records, surgical records, anesthesia records, blood transfusion records, nursing records, discharge summaries, referral (hospital) records, informed consent information, gene sequencing, transcriptome sequencing, protein analysis and determination, small molecule metabolic detection, human microbiome detection, etc.

[0039] Health resource data: basic hospital information, hospital health data, etc.;

[0040] Public health data: environmental health data, infectious disease outbreak data, disease detection data and prevention data, birth and death data, etc.

[0041] The docking unit will statistically summarize Zhang San's medical records from other hospitals and his records from this hospital;

[0042] The data conversion unit formats the data from the patient information unit and the interface unit according to a unified standard.

[0043] The infection assessment unit extracts Zhang San's pathophysiological information from his complete electronic medical record to determine whether Zhang San is infected (including bacterial, fungal, or viral infections). If the pathophysiological information confirms an infection, it further determines whether it is sepsis. The SOFA scoring unit tests changes in Zhang San's SOFA score. Zhang San's SOFA score is then assessed according to the Sequential Organ Failure Scale. If Zhang San's SOFA score is greater than or equal to 2, he is diagnosed with sepsis. Otherwise, he is diagnosed as not having sepsis (or having recovered from sepsis).

[0044] Sequential Organ Failure Table (SOFA)

[0045]

[0046] When Zhang San's pathophysiological data lacks parameters on bilirubin levels in the liver system, the following methods can be used to predict the future trend of Zhang San's condition based on the SOFA score parameters in Zhang San's past pathophysiological data and the changes in Zhang San's condition after suffering from sepsis. At the same time, the bilirubin level of Zhang San can be estimated based on the trend of the changes in the condition.

[0047] When it is impossible to estimate Zhang San's bilirubin level based on his past medical history, pathophysiological data, and changes in his condition, a SOFA training model is established. This model learns and practices based on a large amount of SOFA score parameter data from sepsis patients to obtain an algorithm for the relationship between SOFA score parameters. Other known SOFA score parameter information of Zhang San is then incorporated into the algorithm to deduce Zhang San's bilirubin level information.

[0048] Simultaneously, a complete parameter mapping table was established, which includes the SOFA score parameter table for patients with different diseases. Zhang San's current physical condition information and disease condition (such as abdominal infection) were compared with the parameter mapping tables of other patients with the same or similar disease conditions as Zhang San. Based on the parameter mapping tables of other patients with the same or similar experience, Zhang San's bilirubin content parameter was obtained.

[0049] If the above methods fail to obtain Zhang San's bilirubin levels, a sepsis medical expert can be contacted through the manual suggestion module. The medical expert will then provide a manual assessment suggestion based on Zhang San's condition.

[0050] Finally, the bilirubin parameters derived from the above methods are calculated using artificial intelligence big data algorithms, and the obtained bilirubin content is verified and tested in conjunction with a medical knowledge base to ensure the accuracy and consistency of the data.

[0051] Example 2

[0052] The only difference from the above embodiments is that when the sepsis judgment module collects the patient's pathophysiological data, it will perform a completeness analysis and a timeliness analysis on the patient's pathophysiological data. The completeness analysis is to determine whether the collected content is complete and to verify the completeness of the collected content; the timeliness analysis is to determine whether the time logic of the collected data is reasonable.

[0053] When collecting Zhang San's pathophysiological data in the sepsis assessment module, the system will scan to identify whether the scoring parameters required for SOFA are complete. If bilirubin content information is not collected or identified, a reminder will be issued indicating that the collected data is incomplete. At the same time, the system will also check whether the scoring parameters required for SOFA are collected in a reasonable time sequence. If the timeline of the collected scoring parameters is not reasonable (e.g., the collected bilirubin content is data from the previous case, i.e., the collected data is not on a continuous and unified timeline), a reminder will be issued indicating that the collected data is abnormal.

[0054] The above descriptions are merely embodiments of the present invention, and common knowledge such as specific structures and / or characteristics in the solutions are not described in detail here. It should be noted that those skilled in the art can make various modifications and improvements without departing from the structure of the present invention, and these should also be considered within the scope of protection of the present invention. These modifications and improvements will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A sepsis-specific disease data management system based on electronic medical record data, characterized in that, include: The module includes a full data collection module, a sepsis diagnosis module, and an expert advice module. The full data acquisition module includes a patient information unit, an interface unit, and a data conversion unit. The patient information unit is used to collect all in-hospital diagnosis and treatment information of patients from various hospital business systems. The interface unit is used to interface with patient medical record information from other hospitals. The data conversion unit is used to convert and unify data from different data sources and different data types. The sepsis assessment module includes an infection assessment unit and an SOFA scoring unit. The infection assessment unit is used to collect pathophysiological data to determine whether an infection has occurred. The SOFA scoring unit is used to obtain changes in the SOFA score (or to predict the SOFA score when some SOFA score parameters are incomplete) to determine the diagnosis of sepsis and the specific time of sepsis onset. The expert advice module is used to provide system evaluation suggestions based on the diagnosis given by the sepsis judgment module.

2. The sepsis-specific disease data management system based on electronic medical record data according to claim 1, characterized in that: The SOFA score includes: changes in PaO2 / FiO2 in the respiratory system, whether ventilator support is required, changes in platelet count in the blood system, changes in bilirubin in the liver, changes in mean arterial pressure in the circulatory system, changes in dopamine in the circulatory system, changes in dobutamine in the circulatory system, changes in adrenaline in the circulatory system, changes in norepinephrine in the circulatory system, GCS score in the nervous system, changes in creatinine in the kidneys, and changes in urine output in the kidneys. Furthermore, when some SOFA score parameters are incomplete, the algorithm can predict the SOFA score for diagnostic purposes.

3. The sepsis-specific disease data management system based on electronic medical record data according to claim 1, characterized in that: If the infection determination unit determines an infection and the SOFA scoring unit tests a SOFA score greater than or equal to 2, then the diagnosis is sepsis; otherwise, it is not sepsis.

4. The sepsis-specific disease data management system based on electronic medical record data according to claim 1, characterized in that: When a patient's SOFA score parameters are missing, the sepsis assessment module will compensate for the missing parameters based on the other remaining parameters obtained, and then use the compensated parameters to make a comprehensive score.

5. The sepsis-specific disease data management system based on electronic medical record data according to claim 1, characterized in that: The compensation method when parameters are incomplete is as follows: Through big data-driven artificial intelligence algorithms, when some parameters are missing, the remaining parameters or other indicators can be used to predict the score of the missing parameters, and finally predict the patient's possible SOFA score and information on the trend of disease changes.

6. The sepsis-specific disease data management system based on electronic medical record data according to claim 1, characterized in that: It also includes a human suggestion module, which is used to provide human assessment suggestions by sepsis medical experts based on the patient's condition when it is impossible to complete the scoring parameters.

7. The sepsis-specific disease data management system based on electronic medical record data according to claim 1, characterized in that: When collecting patient pathophysiological data, the sepsis assessment module will perform completeness analysis and timeliness analysis on the patient's pathophysiological data. The completeness analysis is to determine whether the collected content is complete and to verify the completeness of the collected content; the timeliness analysis is to determine whether the time logic of the collected data is reasonable.

8. The sepsis-specific disease data management system based on electronic medical record data according to claim 1, characterized in that: Once the sepsis assessment module completes the missing parameters, it will use artificial intelligence big data algorithms combined with a medical knowledge base to verify and test the scoring parameters.

Images