Severe disease early warning detection method and computer equipment
By obtaining diagnostic and risk indicators from electronic medical records and conducting early warning detection in combination with the similarity of multiple dimensions, the hidden and sudden problems caused by the low similarity of severe diseases in the existing technology are solved, and the target patients are achieved. More accurate risk analysis and early warning improve patient safety.
Patent Information
- Application Number
- CN202410907238.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-08
- Publication Date
- 2024-11-01
AI Technical Summary
It is difficult for the prior art to effectively conduct comprehensive and accurate potential risk analysis of target patients from the risk dimension, especially when the diagnosis of severe diseases is not high, which leads to the occult and suddenness of severe diseases and threatens the safety of patients' lives.
By obtaining the first health indicators of the diagnostic dimension and the second health indicators of the risk dimension from the electronic medical records, combining the indicator similarity between multiple diagnostic dimensions and risk dimensions, early warning detection and warning prompts are carried out to detect potential risks in advance and prevent the disease from worsening.
It has achieved a more comprehensive and accurate analysis of the physical condition of the target patients from the risk dimension, discovered potential risks in advance, and improved the accuracy and timeliness of critical disease warnings, and prevented the disease from worsening.
Smart Images

Figure CN118888134A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical information processing technology, and in particular to a serious disease early warning detection method and computer equipment. Background Art
[0002] At present, many ordinary patients are prone to develop into critically ill patients due to their accompanying diseases, positive indicators, symptoms, signs, surgery, medication, nutrition, physique, age, adverse medical events, or the superposition of the above factors. Before these patients become critically ill patients, their health indicators are not very similar to those of critical diseases, and the relevant characteristics of critical diseases are not obvious. They are hidden and sudden, and once they occur, they will seriously threaten the life safety of patients. Summary of the invention
[0003] The purpose of the present invention is to provide a serious disease early warning detection method and computer equipment to address the deficiencies in the above-mentioned prior art, which can analyze the physical condition of the target patient from the risk dimension and determine the potential risks of the target patient's body more comprehensively and accurately.
[0004] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:
[0005] In a first aspect, an embodiment of the present application provides a method for early warning detection of serious diseases, including: if a change is detected in the electronic medical record of a target patient, obtaining a first health indicator of a diagnostic dimension and a second health indicator of a risk dimension of the target patient from the electronic medical record; determining the diagnostic similarity between the target patient and each preset serious disease based on the first health indicator and the diagnostic criteria of each preset serious disease; if the diagnostic similarity between the target patient and a first preset serious disease among the serious diseases does not meet the first preset similarity condition, performing early warning detection of the first preset serious disease on the target patient based on the second health indicator.
[0006] In one embodiment, the diagnostic similarity between the target patient and each preset serious disease is determined based on the first health indicator and the diagnostic criteria of each preset serious disease, including: according to the first health indicator in multiple diagnostic dimensions, and the diagnostic criteria of each preset serious disease in the multiple diagnostic dimensions, respectively determining the indicator similarity of the target patient in the multiple diagnostic dimensions; according to the indicator similarity of the target patient in the multiple diagnostic dimensions, determining the diagnostic similarity between the target patient and each preset serious disease.
[0007] In one embodiment, the multiple diagnostic dimensions include: at least two diagnostic dimensions of concomitant diseases, test indicators, signs, symptoms, physical examination, surgery, current medication, and intake and output.
[0008] In one embodiment, the early warning detection of the first preset serious disease on the target patient based on the second health indicator includes: determining the risk similarity between the target patient and the first preset serious disease based on the second health indicator and the serious risk factor of the first preset serious disease; if the risk similarity between the target patient and the first preset serious disease meets the second preset similarity condition, outputting the first early warning prompt information of the target patient for the first preset serious disease.
[0009] In one embodiment, the determining the risk similarity between the target patient and the first preset critical disease based on the second health indicator and the critical risk factor of the first preset critical disease includes: determining the indicator similarity between the second health indicator and the critical risk factor of the first preset critical disease under multiple risk dimensions based on the second health indicator and the critical risk factor of the first preset critical disease under multiple risk dimensions; determining the risk similarity between the target patient and the first preset critical disease based on the indicator similarity between the second health indicator and the critical risk factor of the first preset critical disease under multiple risk dimensions.
[0010] In one embodiment, the multiple risk dimensions include: at least two risk dimensions of physical condition, adult body mass index, weight, food intake, nutritional status, care level, age, occurrence of adverse medical events, and allergy history.
[0011] In one embodiment, the first health indicator of the diagnostic dimension includes: a positive indicator of the test and examination indicator; if the diagnostic similarity of the target patient for the first preset serious disease among the serious diseases does not meet the first preset similarity condition, the method also includes: determining the degree of harm persistence of the positive indicator according to the test result of the positive indicator; if the degree of harm persistence of the positive indicator exceeds the threshold value of the degree of harm persistence of the first preset serious disease, outputting the second warning prompt information of the target patient for the first preset serious disease.
[0012] In one embodiment, if the diagnostic similarity of the target patient for the first preset serious disease among the serious diseases does not meet the first preset similarity condition, the method further includes: determining the dangerous conversion rate of the positive indicator based on the test result of the positive indicator; if the dangerous conversion rate of the positive indicator exceeds the dangerous conversion rate threshold of the first preset serious disease, outputting the third warning prompt information of the target patient for the first preset serious disease.
[0013] In one embodiment, the method further includes: if the diagnostic similarity between the target patient and a first preset serious disease among the serious diseases meets the first preset similarity condition, outputting fourth warning prompt information of the target patient for the first preset serious disease.
[0014] In the second aspect, an embodiment of the present application also provides a serious disease early warning detection device, including: a data acquisition module, configured to obtain a first health indicator of the target patient's diagnosis dimension and a second health indicator of the risk dimension from the electronic medical record if a change is detected in the target patient's electronic medical record; a similarity determination module, configured to determine the diagnostic similarity between the target patient and each preset serious disease based on the first health indicator and the diagnostic criteria of each preset serious disease; and a warning detection module, configured to perform early warning detection of the first preset serious disease on the target patient based on the second health indicator if the diagnostic similarity between the target patient and a first preset serious disease among the serious diseases does not meet a first preset similarity condition.
[0015] In a third aspect, an embodiment of the present application further provides a computer device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of any one of the above methods.
[0016] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of any one of the above methods are executed.
[0017] The beneficial effect of the present application is that when the first health indicator of the target patient's diagnosis dimension is not highly similar to the first preset serious disease in each preset serious disease, early warning detection is performed according to the second health indicator of the target patient's risk dimension. In this way, the target patient's physical condition can be analyzed from the risk dimension, and the potential risks of the target patient's body can be determined more comprehensively and accurately. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0019] Figure 1A flowchart of a method for early warning detection of a serious disease provided in an embodiment of the present application;
[0020] Figure 2 A schematic diagram of a method for early warning detection of a serious disease provided in an embodiment of the present application;
[0021] Figure 3 A schematic diagram of a method for early warning detection of a serious disease provided in an embodiment of the present application;
[0022] Figure 4 A schematic diagram of a method for early warning detection of a serious disease provided in an embodiment of the present application;
[0023] Figure 5 A schematic diagram of a method for early warning detection of a serious disease provided in an embodiment of the present application;
[0024] Figure 6 A schematic diagram of a method for early warning detection of a serious disease provided in an embodiment of the present application;
[0025] Figure 7 A schematic diagram of the structure of a serious disease early warning detection device provided in an embodiment of the present application;
[0026] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments.
[0028] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0029] In the description of the present application, it should be noted that if the terms "upper", "lower", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or is the orientation or position relationship in which the product of the application is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.
[0030] In addition, the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0031] It should be noted that, in the absence of conflict, the features in the embodiments of the present application may be combined with each other.
[0032] Figure 1 A flowchart of a method for early warning detection of a serious disease provided in an embodiment of the present application; Figure 1 As shown, the method includes:
[0033] Step S110: If it is detected that the electronic medical record of the target patient has changed, a first health indicator of the diagnosis dimension and a second health indicator of the risk dimension of the target patient are obtained from the electronic medical record.
[0034] Among them, the first health indicator of the diagnosis dimension is used to determine the diagnostic similarity between the patient and each preset serious disease; the second health indicator of the risk dimension is used to analyze the patient's potential risk of the preset serious disease when the diagnostic similarity between the patient and the preset serious disease is not high.
[0035] Electronic medical records are obtained by recording and updating the entire process of patients from admission to discharge by medical staff. The critical disease early warning detection method provided in the embodiment of the present application collects electronic medical record information in the links of admission, physical examination, examination, diagnosis, surgery, anesthesia, blood transfusion, medication, general treatment, and nursing according to the daily diagnosis and treatment process. The collected electronic medical record information includes: medical record summary, test and examination records, general treatment records, nursing operation records, nursing assessment and plan, informed consent information, hospitalization medical record homepage, admission record, hospitalization course record, hospitalization doctor's order, adverse medical events, etc. The first health indicator of the above-mentioned diagnostic dimension and the second health indicator of the risk dimension can be specifically extracted from the above-mentioned electronic medical record information.
[0036] Step S120: Determine the diagnostic similarity between the target patient and each preset serious disease based on the first health indicator and the diagnostic criteria of each preset serious disease.
[0037] Among them, under normal circumstances, the diagnostic standards for different preset serious diseases are different, but the diagnostic dimensions can be the same; for example: the diagnostic dimensions of preset serious disease A and preset serious disease B both include: diagnostic dimension a and diagnostic dimension b; but the preset serious disease A focuses on health indicators 1 and health indicators 3 under diagnostic dimension a, and the preset serious disease B focuses on health indicators 2 and health indicators 4 under diagnostic dimension a; the preset serious disease A focuses on health indicators 1 to health indicators 3 under diagnostic dimension b, and the preset serious disease B focuses on health indicators 1 to health indicators 4 under diagnostic dimension b.
[0038] In this step, the diagnostic similarity between the target patient and each preset critical illness can be determined by comparing the first health indicator of the target patient with the diagnostic criteria of each preset critical illness; for example: according to the correlation between white blood cells and sepsis, when 12000 / u1<white blood cell index value≤12500 / u1 is defined, the diagnostic similarity between white blood cells and sepsis is 80%; when 12500 / u1<white blood cell index value≤13000 / u1, the diagnostic similarity between white blood cells and sepsis is 90%; when the white blood cell index value>13000 / u1, the diagnostic similarity between white blood cells and sepsis is 100%, then, the diagnostic similarity between the target patient and sepsis in the corresponding diagnostic dimension can be determined according to the index value of the white blood cells of the target patient.
[0039] Step S130: If the diagnostic similarity between the target patient and the first preset serious disease among the serious diseases does not meet the first preset similarity condition, perform early warning detection of the first preset serious disease on the target patient according to the second health indicator.
[0040] Among them, under normal circumstances, the risk dimensions of different preset serious diseases can be the same; for example: the diagnostic dimensions of preset serious disease C and preset serious disease D both include: risk dimension c and risk dimension d.
[0041] Among them, the first preset similarity condition can be that the diagnostic similarity between the preset patient's first health indicator and the first preset serious disease is greater than the diagnostic similarity threshold (for example: 85%, 90%, etc.); further, when the diagnostic similarity between the target patient and the first preset serious disease does not meet the first preset similarity condition (that is, the diagnostic similarity between the target patient's first health indicator and the first preset serious disease is less than the diagnostic similarity threshold), according to the second health indicator of the target patient's risk dimension, the target patient is subjected to early warning detection of the first preset serious disease.
[0042] Danger similarity is the similarity between the second health indicator of the target patient in multiple risk dimensions and the influencing factors of the first preset serious disease calculated according to certain rules.
[0043] The critical illness early warning detection method provided in the embodiment of the present application performs early warning detection based on the second health indicator of the target patient's risk dimension when the first health indicator of the target patient's diagnosis dimension is not highly similar to the first preset critical illness among the preset critical illnesses. In this way, the target patient's physical condition can be analyzed from the risk dimension, and the potential risks of the target patient's body can be determined more comprehensively and accurately.
[0044] The diagnostic similarity between the target patient and each preset critical illness can be determined by comparing the first health indicator of the target patient with the diagnostic criteria of each preset critical illness; specifically, Figure 2 As shown, the above step S120 may further include the following steps S210 and S220:
[0045] Step S210: According to the first health indicator in multiple diagnostic dimensions and the diagnostic criteria of each preset serious disease in multiple diagnostic dimensions, determine the indicator similarity of the target patient in multiple diagnostic dimensions respectively.
[0046] Among them, under normal circumstances, there are multiple diagnostic dimensions; for example: the diagnostic dimensions of pre-set critical illnesses such as sepsis, acute respiratory distress syndrome, and acute kidney injury all include: concomitant diseases, test indicators, signs, symptoms, physical examination, surgery, current medication, and intake and output.
[0047] In one embodiment, the multiple diagnostic dimensions include: at least two diagnostic dimensions of concomitant diseases, test indicators, signs, symptoms, physical examination, surgery, current medication, and intake and output.
[0048] This step can be achieved through the following process: first, compare the first health indicators under multiple diagnostic dimensions with the diagnostic standards of each preset serious disease under multiple dimensions, and determine the similarity between the first health indicators of the target patient under multiple diagnostic dimensions and the diagnostic dimensions of each preset serious disease; then determine the indicator similarity of the target patient under multiple diagnostic dimensions based on the dimensional weights of multiple diagnostic dimensions, the weights of the first health indicators in their corresponding diagnostic dimensions, and the similarity between the first health indicators of the target patient under multiple diagnostic dimensions and the diagnostic dimensions of each preset serious disease.
[0049] For example, let the above-mentioned dimension weight be DP, the weight of the first health indicator in the corresponding diagnosis dimension be EDP, and the similarity between the first health indicator (single health indicator) and the diagnosis dimension of the preset serious disease be ES. Then, the indicator similarity DS of the target patient in multiple diagnosis dimensions is calculated by the following formula (1):
[0050] DS=(Σ(EDP×ES))×DP (1)
[0051] The indicator similarity can also be understood as the similarity between the diagnostic dimension to which the first health indicator belongs and the diagnostic dimension of the preset serious disease.
[0052] As shown in Table 1, according to the above formula (1), the similarity of indicators of the target patients in multiple diagnostic dimensions of sepsis is calculated as follows: the similarity of indicators of the target patients in the diagnostic dimension of concomitant diseases is 16%, the similarity of indicators in the diagnostic dimension of test indicators is 14.1%, the similarity of indicators in the diagnostic dimension of physical signs is 7.2%, the similarity of indicators in the diagnostic dimension of symptoms is 9%, the similarity of indicators in the diagnostic dimension of physical examination is 2.7%, the similarity of indicators in the diagnostic dimension of surgery is 4.5%, the similarity of indicators in the diagnostic dimension of current medication is 0%, and the similarity of indicators in the diagnostic dimension of input and output is 4%.
[0053]
[0054]
[0055]
[0056]
[0057]
[0058]
[0059]
[0060]
[0061] Table 1
[0062] It should be noted that:
[0063] Dimension weight (DP): It is the weight of the diagnostic dimensions such as concomitant diseases, test indicators, signs, symptoms, physical examination, surgery, current medication, intake and output in disease diagnosis, and the total is 100%.
[0064] Diagnostic criteria: It is a description of the characteristic values of the preset critical illness-related indicators in the diagnostic dimension. For example, in the diagnosis of sepsis, in the diagnostic dimension test indicators, the inflammatory response indicator is "leukocytosis: white blood cells (WBC)>12000 / u1", the organ dysfunction indicator is "blood creatinine>44.2umol / L (0.5mg / dl)", etc.; and in the diagnostic dimension physical signs, "body temperature>38.℃", "obvious edema", etc. are all descriptions of the diagnostic characteristic values of sepsis.
[0065] The weight of the first health indicator in the corresponding diagnostic dimension (EDP): refers to the weight of each indicator in a diagnostic dimension in the diagnostic dimension, and the sum of the weights of each indicator in a diagnostic dimension is 100%. For example: in the diagnostic dimension of concomitant diseases, there are indicators such as autoimmune diseases, diabetes, liver cirrhosis, malignant tumors, and organ transplantation, with weights of 60%, 10%, 10%, 10%, and 10% respectively, and the sum of the indicator weights is 100%.
[0066] First, the constraint relationship between health indicators (exclusive existence or non-exclusive existence): refers to the exclusive relationship between indicators in the same diagnostic dimension. For example: in the diagnostic dimension of test and examination indicators, there are three situations for inflammatory response indicators, namely 1. Leukocytosis: white blood cells (WBC)>12000 / u1; 2. Leukocytopenia: WBC<4000 / p; 3. Normal WBC but the total number of immature white blood cells exceeds 10%. Only one possibility can exist between 1, 2 and 3 at the same time, and they are mutually exclusive, that is, if 1 is true, then 2 and 3 are not true, and so on. In the diagnostic dimension of concomitant diseases, there are indicators such as autoimmune diseases, diabetes, cirrhosis, malignant tumors, and organ transplants. Multiple indicators can exist at the same time, and they are not exclusive.
[0067] First health indicator attribute (independent indicator or grouped indicator): From the perspective of clinical significance, whether a certain indicator has independent significance for determining disease similarity, if so, it is considered an independent indicator, and if several indicators need to be combined to be meaningful for determining disease similarity, then these indicators are considered grouped indicators. For example: In the diagnostic dimension of test results, the indicator "leukocytosis: white blood cells (WBC)>12000 / u1" is a determination of the inflammatory response, which is independent for determining the similarity of sepsis and is an independent indicator. In the diagnostic dimension of test indicators, the following three indicators "organ dysfunction indicator: abnormal coagulation function", "organ dysfunction indicator: thrombocytopenia: platelets (PLT) 510000 / p1", and "organ dysfunction indicator: hyperbilirubinemia" have a high correlation and are grouped indicators. The group number is set to 0002. This group of indicators has clinical reference significance for determining the similarity of sepsis. The four indicators in the physical sign diagnosis dimension are "body temperature > 38.℃", "heart rate > 90 times / min or "heart rate greater than two standard deviations of normal values for different ages", "respiration > 20 times / min or hyperventilation", and "obvious edema". The five indicators in the symptom diagnosis dimension are "chills", "fever", "palpitation", "shortness of breath", and "mental status changes (anxiety, slow reaction or confusion)"; and the one indicator in the physical examination diagnosis dimension is "continuous rapid pulse". These 10 indicators are grouped indicators with the group number set as 0001, which have clinical reference significance for determining the similarity of sepsis diseases. The three indicators in the physical sign diagnosis dimension are "body temperature <36℃", "heart rate >90 times / min" or "heart rate greater than two standard deviations of normal values for different ages", "respiration >20 times / min or hyperventilation", the four indicators in the symptom diagnosis dimension are "hypothermia", "palpitation", "shortness of breath", "mental status changes (anxiety, slow reaction or confusion)", and the two indicators in the physical examination diagnosis dimension are "continuous rapid pulse" and "cold limbs". These 9 indicators are grouped indicators with the group number set as 0003, which have clinical reference significance for determining the similarity of sepsis diseases. In particular, some indicators can belong to different groups at the same time because of their broader clinical significance. For example, "heart rate > 90 beats / min" or "heart rate greater than two standard deviations of normal values for different ages", "respiration > 20 times / min or hyperventilation" in the physical sign diagnosis dimension, and "palpitation", "shortness of breath", "mental state changes (anxiety, slow reaction or confusion)", and "continuous rapid pulse" in the symptom diagnosis dimension can belong to both group 0001 and group 0003.
[0068] The first health indicator and the similarity of the diagnostic dimension (ES): the value of the similarity between the patient's health indicator and the diagnostic dimension can be a value of a graded position based on the interval range of the patient's health indicator, such as 80% for slightly higher than the diagnostic standard, 90% for significantly higher than the diagnostic standard, and 100% for seriously higher than the diagnostic standard; it can also be a pre-set value when the patient's health indicator is consistent with the diagnostic standard, such as 80%, 90% or 100%, etc. Here, the patient's health indicator can be an independent indicator or a grouped indicator. When it is a grouped indicator, only when all indicators in the grouped indicator are consistent with the indicator value corresponding to the diagnostic standard, the similarity of all indicators in the grouped indicator and the diagnostic standard is uniformly set to the similarity when the group is consistent, such as 90%; otherwise, the similarity of those indicators in the grouped indicator that are consistent with the diagnostic standard is set to the similarity when the group is not consistent, such as reduced to 70%, because the significance of clinical judgment of individual indicators is reduced compared with the grouped indicators, and the similarity is also reduced. The above similarity values can be adjusted according to clinical significance. For example, for the diagnosis of sepsis, in the concomitant disease diagnosis dimension, "impaired immune system" is one of the diagnostic criteria. If the patient has an autoimmune disease, it is considered that the similarity between this health indicator of the patient and the diagnostic criterion of "impaired immune system" of sepsis is 100%; in the physical sign diagnosis dimension, if the patient's body temperature is greater than 38.℃, it is considered that the similarity between this health indicator of the patient and the diagnostic criterion of "body temperature greater than 38.℃" is 80%; for another example, in the test result diagnosis dimension, "leukocytosis: white blood cells (WBC)>12000 / u1" is one of the diagnostic criteria. The similarity value with the diagnostic criterion can be set according to the interval of the white blood cell indicator, such as 12000 / u1<white blood cells (WBC)≤12500 / u1, the similarity value is 80%; 12500 / u1<white blood cells (WBC)≤13000 / u1, the similarity value is 90%; white blood cells (WBC)>13000 / u1, the similarity value is 100%. If the patient's white blood cells (WBC) = 12800 / u1, then its similarity with the diagnostic standard of "leukocytosis: white blood cells (WBC)>12000 / u1" is 90%. In the grouped indicators with group number 0002, if its three indicators "organ dysfunction indicators: abnormal coagulation function", "organ dysfunction indicators: thrombocytopenia: platelets (PLT) <10000 / p1", and "organ dysfunction indicators: hyperbilirubinemia" are consistent with the corresponding indicator values of the sepsis diagnostic standard, then it is grouped and its similarity with the sepsis diagnostic dimension is 80%. If only one of the indicators is consistent with the corresponding indicator value of the sepsis diagnostic standard, then the indicator is not grouped and its similarity with the sepsis diagnostic dimension is reduced to 60%, and so on.
[0069] Step S220: Determine the diagnostic similarity between the target patient and each preset serious disease based on the similarity of the indicators of the target patient in multiple diagnostic dimensions.
[0070] Among them, the diagnostic similarity between the target patient and each preset serious disease can be obtained by adding the similarities of the indicators of the target patient in multiple diagnostic dimensions.
[0071] For example, let the diagnostic similarity between the target patient and the preset severe disease be S, then S is calculated by the following formula (2):
[0072] S=ΣDS (2)
[0073] Exemplarily, as shown in Table 1, the diagnostic similarity S between the target patient and sepsis calculated according to the above formula (2) is 16%+14.1%+7.2%+9%+2.7%+4.5%+4%=57.5%.
[0074] The critical illness early warning detection method provided in the embodiment of the present application determines the similarity between the target patient's first health indicator in multiple diagnostic dimensions and the diagnostic dimension of each preset critical illness by comparing the target patient with the diagnostic criteria of each preset critical illness, and then calculates (for example: according to formula (1)) the target patient's indicator similarity in multiple diagnostic dimensions, and then calculates (for example: according to formula (2)) the target patient's diagnostic similarity with each preset critical illness. In this way, the target patient's physical condition can be analyzed from multiple diagnostic dimensions, and the relationship between it and each preset critical illness can be determined more comprehensively and accurately.
[0075] Because many ordinary patients do not have a high similarity between their first health indicators and the preset critical illnesses before they develop critical illnesses, and the relevant characteristics of critical illnesses are not obvious, and they are hidden and sudden, which will seriously threaten the life safety of patients once they occur; therefore, when the patient's first health indicator is not similar to the preset critical illness, it is clinically significant to analyze the patient's potential risk; specifically, Figure 3 As shown, the above step S130 of "performing early warning detection of the first preset serious disease on the target patient according to the second health indicator" may further include the following steps S310 and S320:
[0076] Step S310: Determine the risk similarity between the target patient and the first preset serious disease based on the second health indicator and the serious disease risk factor of the first preset serious disease.
[0077] Among them, under normal circumstances, there are multiple risk dimensions; for example: the risk dimensions of pre-set critical illnesses such as sepsis, acute respiratory distress syndrome, acute kidney injury, etc. all include: physical condition, adult body mass index, weight, food intake, nutritional status, nursing level, age, occurrence of adverse medical events, and allergy history; among them, weight status can be recent weight status, such as: weight status in the past 1-3 months.
[0078] In one embodiment, the multiple risk dimensions include: at least two risk dimensions of physical condition, adult body mass index, weight condition, food intake, nutritional status, care level, age, occurrence of adverse medical events, and allergy history.
[0079] Severe disease risk factors are descriptions of the characteristic values of severe disease risk factors in the risk dimension. For example, in the risk dimension of adult body mass index (BMI), "underweight <18.5 kg / m2" and "overweight or obesity >23.9 kg / m2" are two risk factor indicators and their characteristic values; in the risk dimension of nutritional status, "moderate or above nutritional risk" is a risk factor indicator and its characteristic value, which are all descriptions of the characteristic values of severe disease risk factors.
[0080] This step can determine the risk similarity between the target patient and the first preset serious disease in multiple risk dimensions by comparing the second health indicators in multiple risk dimensions with the serious risk factors of the first preset serious disease.
[0081] Step S320: If the risk similarity between the target patient and the first preset serious disease meets the second preset similarity condition, output the first warning prompt information of the target patient for the first preset serious disease.
[0082] Among them, the second preset similarity condition can be that the risk similarity between the preset patient's second health indicator and the first preset serious illness is greater than the risk similarity threshold (for example: the risk similarity threshold of sepsis is set to 85%, 90%, etc.); further, when the risk similarity between the target patient and the first preset serious illness meets the second preset similarity condition (that is, the risk similarity between the target patient's second health indicator and the first preset serious illness is greater than the risk similarity threshold), the first warning prompt information of the target patient for the first preset serious illness is output.
[0083] Exemplarily, if the risk similarity TPP between the target patient and sepsis is 95%, which is greater than a preset risk similarity threshold of 90% between the patient and sepsis, the first early warning prompt information of the target patient for the first preset severe disease is output.
[0084] The first warning prompt information can be output in the form of voice, text, or voice + text, and can also be accompanied by a buzzer sound, which is not limited here.
[0085] For the test and examination indicators in the first health indicator of the diagnosis dimension, the test results of some indicators may be positive. These positive indicators are of high value for analyzing the target patient's potential risk of the first preset serious disease.
[0086] The critical illness early warning detection method provided in the embodiment of the present application determines the risk similarity between the target patient and the first preset critical illness in multiple risk dimensions through the second health indicator in multiple risk dimensions and the critical illness risk factor of the first preset critical illness, and outputs early warning prompt information when the target patient has a high risk similarity with the first preset critical illness in multiple risk dimensions. In this way, the physical condition of the target patient can be analyzed from multiple risk dimensions, and when the target patient has a high risk similarity with the first preset critical illness, the early warning prompt information can be used to remind the target patient in time, thereby preventing the further deterioration of the physical condition of the target patient to a certain extent.
[0087] The risk similarity between the target patient and the first preset critical illness can be obtained by comparing the second health index under multiple risk dimensions with the critical illness risk factor of the first preset critical illness; specifically, Figure 4 As shown, the above step S310 may further include the following steps S410 and S420:
[0088] Step S410: Determine the indicator similarity between the second health indicator under multiple risk dimensions and the severe risk factor of the first preset severe disease based on the second health indicator under multiple risk dimensions.
[0089] This step can determine the similarity between the second health indicators under multiple risk dimensions and the severe risk factors of the first preset severe disease by comparing the second health indicators under multiple risk dimensions with the severe risk factors of the first preset severe disease.
[0090] For example, as shown in Table 2, by comparing the second health indicator "poor" under the risk dimension of physical condition and the severe risk factor of sepsis "poor", it is determined that the indicator similarity between the second health indicator under the risk dimension of physical condition and the severe risk factor of sepsis is 100%; by comparing the second health indicator "18" under the risk dimension of adult body mass index BMI and the severe risk factor of sepsis "<18.5 kg / m 2 "Underweight" determined that the second health indicator under the risk dimension of adult body mass index (BMI) had a 90% similarity with the indicator of severe risk factors for sepsis.
[0091]
[0092]
[0093] Table 2 needs to be explained:
[0094] Similarity between the patient's second health indicator and the severe illness risk factor indicator (RS): The value marking the similarity between the patient's second health indicator and the severe illness risk factor indicator can be a graded value based on the interval range of the patient's second health indicator to match the severe illness risk factor indicator, such as: slightly higher than the severe illness risk factor indicator is 80%, significantly higher than the severe illness risk factor indicator is 90%, and severely higher than the severe illness risk factor indicator is 100%, etc.; it can also be a pre-set value when the patient's second health indicator is consistent with the severe illness risk factor indicator, such as 80%, 90% or 100%, etc. The above similarity values can be adjusted according to clinical significance.
[0095] For example, in the risk dimension of adverse medical events, "adverse medical events have occurred" is its severe risk factor indicator. If a medical adverse event has occurred in a patient, it is considered that the patient's health indicator has a 100% similarity with the severe risk factor indicator. In the age risk dimension, "≤10 years old" and "≥75 years old" are its severe risk factor indicators. If the patient is 80 years old, it is considered that the patient's health indicator has a 100% similarity with the severe risk factor indicator. In the nursing level risk dimension, "secondary nursing or above" is its severe risk factor indicator. The similarity value corresponding to the severe risk factor indicator can be set according to the nursing level, such as 80% for secondary nursing, 90% for primary nursing, and 100% for special nursing. In the recent (1-3 months) weight situation risk dimension, "5.5% weight loss in one month" is its severe risk factor indicator. The similarity value with the severe risk factor indicator can be set according to the weight loss interval, such as 5%≤weight loss in one month <7%, the similarity value is 90%; weight loss in one month ≥7%, the similarity value is 100%.
[0096] Severe illness risk factor weight (RP): It is the weight of general physical condition, adult body mass index (BMI), recent (1-3 months) weight condition, etc. in calculating the similarity between the patient's second health indicator and severe illness risk factor, the total of which is 100%.
[0097] Step S420: Determine the risk similarity between the target patient and the first preset serious disease under multiple risk dimensions based on the similarity between the second health indicator under multiple risk dimensions and the indicator of the serious risk factor of the first preset serious disease.
[0098] This step can be achieved through the following process: first, weighting the indicator similarity and the weight of the severe risk factor between the second health indicator of the target patient in multiple risk dimensions and the severe risk factor of the first preset severe disease to obtain the weighted value of the severe risk factor of the second health indicator in multiple dimensions; secondly, adding the weighted values of the severe risk factor of the second health indicator in multiple dimensions to obtain the risk similarity between the second health indicator of the target patient and the first preset severe disease.
[0099] Exemplarily, the similarity between the second health indicator and the first preset critical illness risk factor is RS, the weight of the critical illness risk factor is RP, the weighted value of the critical illness risk factor of the second health indicator is PP, and the risk similarity between the target patient and the first preset critical illness is TPP. Then, TPP is calculated by the following formula (3) and formula (4):
[0100] PP=RS×RP (3)
[0101] TPP=ΣPP (4)
[0102] Exemplarily, as shown in Table 2, the risk similarity TPP between the target patient and sepsis calculated according to the above formula (3) and formula (4) is as follows:
[0103] TPP=5%+4.5%+18%+15%+13.5%+9%+5%+20%+5%=95%
[0104] The critical illness early warning detection method provided in the embodiment of the present application determines the index similarity between the second health index under multiple risk dimensions and the critical illness risk factor of the first preset critical illness by comparing the second health index under multiple risk dimensions with the critical illness risk factor of the first preset critical illness, and then calculates (for example: by formula (3)) the weighted value of the critical illness risk factor of the second health index under multiple dimensions, and then calculates (for example: by formula (4)) the risk similarity between the target patient and the first preset critical illness. In this way, the physical condition of the target patient can be analyzed from multiple risk dimensions, and when the target patient has a high risk similarity with respect to the first preset critical illness, the target patient can be reminded in time through early warning prompt information, thereby preventing the further deterioration of the physical condition of the target patient to a certain extent.
[0105] The potential risk of the target patient for the first preset serious disease can also be further analyzed by calculating the degree of hazard persistence; specifically, Figure 5 As shown, if the diagnostic similarity of the target patient to the first preset serious disease among the preset serious diseases does not meet the first preset similarity condition, the method may further include the following steps S510 and S520:
[0106] Step S510: Determine the duration of the harm of the positive indicator according to the test result of the positive indicator.
[0107] The test result can be understood as the index value of the positive index; for example, the index value of the patient's white blood cell is 66.5×10 9 / L, while the normal range of white blood cells is 4.0~10.0×10 9 / L, then the patient's white blood cells are positive, and the corresponding index value is 66.5×10 9 / L; the patient's blood creatinine index value is 208umol / L, and the normal range of blood creatinine is 57-111umol / L (male), then the patient's blood creatinine is a positive indicator, and the corresponding index value is 208umol / L.
[0108] This step can be determined by the positive indicator hazard coefficient and duration; in one embodiment, the positive indicator hazard coefficient can be first determined by the indicator value of the positive indicator and the upper limit or lower limit of the normal range of the indicator; and then the duration of the hazard of the positive indicator can be determined by the positive indicator hazard coefficient and duration.
[0109] The hazard coefficient of a positive indicator can be the quotient of the positive indicator value and the upper limit of the normal range of the indicator, or it can be the quotient of the lower limit of the normal range of the indicator and the positive indicator value, which is not limited here.
[0110] The duration can be the time difference between the current time and the sample extraction time; or the time difference between the current time and the sample inspection time.
[0111] For example, as shown in Table 3, the white blood cell index value "66.5×10 9 / L" and the upper limit of the normal range of white blood cells is "10.0×10 9 / L”, and the hazard coefficient of white blood cells was determined to be 66.5×10 9 / 10.0×10 9 =6.65, the duration is 53.5 hours, then the duration of leukocyte harm is 6.65×53.5=355.8; through the index value of blood creatinine "208umol / L" and the upper limit of the normal range of blood creatinine "111umol / L (male)", the hazard coefficient of blood creatinine is determined to be 208umol / 111umol=1.87, the duration is 53.5 hours, then the duration of blood creatinine harm is 1.8753.5×53.5=100.
[0112]
[0113] Table 3
[0114] Step S520: If the degree of harm persistence of the positive indicator exceeds the threshold value of the degree of harm persistence of the first preset serious disease, output the second early warning prompt information of the target patient for the first preset serious disease.
[0115] The threshold of the duration of harm can be set based on experience or by consulting literature, and is not limited here; for example, the threshold of the duration of harm for white blood cells is 300, 320, etc., and the threshold of the duration of harm for blood creatinine is 90, 95, etc.
[0116] Exemplarily, if the above-mentioned white blood cell damage persistence level 355.8 is greater than the white blood cell damage persistence level threshold value 320, the second early warning prompt information for the target patient for the first preset serious disease is output; if the above-mentioned blood creatinine damage persistence level 100 is greater than the blood creatinine damage persistence level threshold value 95, the second early warning prompt information for the target patient for the first preset serious disease is output.
[0117] The second warning prompt information can be output in the form of voice, text, or voice + text, and can also be accompanied by a buzzer sound, which is not limited here.
[0118] The critical illness early warning detection method provided in the embodiment of the present application determines the positive indicator hazard coefficient by the indicator value of the positive indicator and the upper limit or lower limit of the normal range of the indicator, and then determines the hazard duration of the positive indicator by the positive indicator hazard coefficient and duration, and outputs a second early warning prompt message when the hazard duration of the positive indicator exceeds the hazard duration threshold of the first preset critical illness. In this way, the physical condition of the target patient can be analyzed from multiple risk dimensions, and when the target patient has a high hazard duration for the first preset critical illness, the early warning prompt message can be used to promptly remind the target patient, thereby preventing the further deterioration of the physical condition of the target patient to a certain extent.
[0119] The potential risk of the target patient for the first preset severe disease can also be further analyzed by calculating the risk conversion rate; specifically, Figure 6 As shown, if the target patient's diagnostic similarity to the first preset severe disease among the severe diseases does not meet the first preset similarity condition, the method may further include the following steps S610 and S620:
[0120] Step S610: Determine the dangerous conversion speed of the positive indicator according to the test result of the positive indicator.
[0121] The test result can be understood as the index value of the positive index; for example, the index value of the patient's white blood cell is 66.5×10 9 / L, while the normal range of white blood cells is 4.0~10.0×10 9 / L, then the patient's white blood cells are positive, and the corresponding index value is 66.5×10 9 / L; the patient's blood creatinine index value is 208umol / L, and the normal range of blood creatinine is 57-111umol / L (male), then the patient's blood creatinine is a positive indicator, and the corresponding index value is 208umol / L.
[0122] This step can be determined by the deviation rate of the indicator value of the positive indicator and the dangerous conversion time; in one embodiment, this step can be achieved by the following process:
[0123] Case 1: When the test index changes from a normal index value to a positive index value, the dangerous conversion rate is calculated as follows:
[0124] (1) If the index value of the positive index is greater than the upper limit of the normal range, then the risk conversion rate = {(the index value of the positive index - the upper limit of the normal range) / the upper limit of the normal range} / the risk conversion time;
[0125] (2) If the index value of the positive index is less than the lower limit of the normal range, then the risk conversion rate = {|the index value of the positive index - the lower limit of the normal range| / the lower limit of the normal range} / risk conversion time.
[0126] Case 2: When the inspection index changes from a low positive index value to a high positive index value, the danger conversion speed is calculated as follows:
[0127] (1) For the same right-biased position, the danger conversion speed = {(high positive index value - low positive index value) / upper limit of normal range index value} / danger conversion time;
[0128] (2) For the same left-biased position, the speed of danger conversion = {|high positive index value - low positive index value| / lower limit of normal range index value} / danger conversion time.
[0129] Among them, the danger conversion time can be the time taken for the test indicator to change from a normal indicator value to a positive indicator value, or it can be the time taken for the test indicator to change from a low positive indicator value to a high positive indicator value, and there is no limitation here.
[0130] Usually, the normal range of each test indicator will have two positions. The value higher than the upper limit of the normal range is called the right deviation zone, and the value lower than the lower limit of the normal range is called the left deviation zone.
[0131] Exemplarily, as shown in Table 4, the above calculation process determines that the deviation rate of the white blood cell index value is (66.5-32) / 10.0=3.45, and the corresponding dangerous conversion rate is 3.45 / 73=0.047. The deviation rate of the blood creatinine index value is (208-111) / 111=0.87, and the corresponding dangerous conversion rate is 0.87 / 73=0.012.
[0132]
[0133] Table 4
[0134] Step S620: If the risk conversion rate of the positive indicator exceeds the risk conversion rate threshold of the first preset serious disease, output the third early warning prompt information of the target patient for the first preset serious disease.
[0135] The dangerous conversion rate threshold can be set based on experience or by consulting literature, and is not limited here; for example, the dangerous conversion rate threshold of white blood cells is 0.040, and the dangerous conversion rate threshold of blood creatinine is 0.010.
[0136] Exemplarily, if the dangerous conversion rate of white blood cells of 0.047 is greater than the dangerous conversion rate threshold of white blood cells of 0.040, the third early warning prompt information of the target patient for the first preset serious disease is output; if the dangerous conversion rate of blood creatinine of 0.87 is greater than the dangerous conversion rate threshold of blood creatinine of 0.010, the third early warning prompt information of the target patient for the first preset serious disease is output.
[0137] The third warning prompt information can be output in the form of voice, text, or voice + text, and can also be accompanied by a buzzer sound, which is not limited here.
[0138] The critical illness early warning detection method provided in the embodiment of the present application determines the dangerous conversion speed of the positive indicator of the target patient according to the test results of the positive indicator, and outputs the third early warning prompt information when the dangerous conversion speed of the positive indicator is high. In this way, the physical condition of the target patient can be analyzed from multiple risk dimensions, and when the target patient has a high degree of dangerous conversion speed of the first preset critical illness, the early warning prompt information can be used to remind the target patient in time, thereby preventing the further deterioration of the physical condition of the target patient to a certain extent.
[0139] Above Figures 1 to 6 The method mainly explains the situation where the diagnostic similarity between the target patient and the first preset serious disease among various serious diseases does not satisfy the first preset similarity condition. The following explains the situation where the diagnostic similarity between the target patient and the first preset serious disease among various serious diseases satisfies the first preset similarity condition.
[0140] The critical disease early warning detection method provided in the application embodiment also includes the following steps:
[0141] If the diagnostic similarity between the target patient and a first preset serious disease among the serious diseases meets a first preset similarity condition, fourth warning prompt information of the target patient for the first serious disease is output.
[0142] Among them, the first preset similarity condition can be that the diagnostic similarity between the preset patient's first health indicator and the first preset serious disease is greater than the diagnostic similarity threshold (for example: 85%, 90%, etc.); further, when the diagnostic similarity between the target patient and the first preset serious disease meets the first preset similarity condition (that is, the diagnostic similarity between the target patient's first health indicator and the first preset serious disease is greater than the diagnostic similarity threshold), the fourth warning prompt information of the target patient for the first preset serious disease is output.
[0143] In summary, the embodiment of the present application provides a method for early warning detection of serious diseases. If a change is detected in the electronic medical record of a target patient, a first health indicator of the target patient's diagnosis dimension and a second health indicator of the risk dimension are obtained from the electronic medical record; the diagnostic similarity between the target patient and each preset serious disease is determined based on the first health indicator and the diagnostic criteria of each preset serious disease; if the diagnostic similarity between the target patient and the first preset serious disease among the serious diseases does not meet the first preset similarity condition, early warning detection of the first preset serious disease is performed on the target patient based on the second health indicator. When the first health indicator of the target patient's diagnosis dimension is not highly similar to the first preset serious disease among the preset serious diseases, early warning detection is performed using the second health indicator of the target patient's risk dimension to analyze the target patient's potential risk regarding the first preset serious disease, to detect and prevent the occurrence of serious diseases in multiple ways.
[0144] In actual production life, the calculated values of the diagnostic similarity between the target patient and each preset serious disease, the risk similarity between the target patient and the first preset serious disease, the duration of harm of the positive indicator, and the risk conversion speed of the positive indicator can be pushed to the doctor's workstation and the nurse's workstation in real time, and prompts for the similarity of each preset serious disease will be given, abnormal values will be highlighted, and compared with the pre-set thresholds, to remind medical staff to intervene in time for patients at risk of developing serious illness.
[0145] After introducing the critical disease early warning detection method according to the exemplary embodiment of the present disclosure, next, refer to Figure 7 A critical disease early warning detection device 700 according to an exemplary embodiment of the present disclosure will be described.
[0146] refer to Figure 7As shown, the serious disease early warning detection device 700 includes: a data acquisition module 710, the data acquisition module 710 is configured to obtain the first health indicator of the diagnosis dimension and the second health indicator of the risk dimension of the target patient from the electronic medical record if a change is detected in the electronic medical record of the target patient; a similarity determination module 720, the similarity determination module 720 is configured to determine the diagnostic similarity between the target patient and each preset serious disease based on the first health indicator and the diagnostic criteria of each preset serious disease; an early warning detection module 730, the early warning detection module 730 is configured to perform early warning detection of the first preset serious disease on the target patient based on the second health indicator if the diagnostic similarity between the target patient and the first preset serious disease among the serious diseases does not meet the first preset similarity condition.
[0147] In one embodiment, the similarity determination module 720 is configured to: determine the indicator similarity of the target patient in multiple diagnostic dimensions based on the first health indicator in multiple diagnostic dimensions, and the diagnostic criteria of each preset serious disease in multiple diagnostic dimensions; determine the diagnostic similarity between the target patient and each preset serious disease based on the indicator similarity of the target patient in multiple diagnostic dimensions.
[0148] In one embodiment, the multiple diagnostic dimensions include: at least two diagnostic dimensions of concomitant diseases, test indicators, signs, symptoms, physical examination, surgery, current medication, and intake and output.
[0149] In one embodiment, the early warning detection module 730 is configured to: determine the risk similarity between the target patient and the first preset serious disease based on the second health indicator and the serious risk factor of the first preset serious disease; if the risk similarity between the target patient and the first preset serious disease meets the second preset similarity condition, output the first early warning prompt information of the target patient for the first preset serious disease.
[0150] In one embodiment, the early warning detection module 730 is configured to: determine the indicator similarity between the second health indicators under multiple risk dimensions and the severe risk factors of the first preset severe disease based on the second health indicators under multiple risk dimensions and the severe risk factors of the first preset severe disease; determine the risk similarity between the target patient and the first preset severe disease based on the indicator similarity between the second health indicators under multiple risk dimensions and the severe risk factors of the first preset severe disease.
[0151] In one embodiment, the multiple risk dimensions include: at least two risk dimensions of physical condition, adult body mass index, weight condition, food intake, nutritional status, care level, age, occurrence of adverse medical events, and allergy history.
[0152] In one embodiment, the first health indicator of the diagnostic dimension includes: a positive indicator of the test and examination indicator; if the diagnostic similarity of the target patient for the first preset serious disease among the serious diseases does not meet the first preset similarity condition, the early warning detection module 730 is configured to: determine the degree of harm persistence of the positive indicator based on the test result of the positive indicator; if the degree of harm persistence of the positive indicator exceeds the threshold value of the degree of harm persistence of the first preset serious disease, output the second early warning prompt information of the target patient for the first preset serious disease.
[0153] In one embodiment, if the diagnostic similarity of the target patient for the first preset serious disease among various serious diseases does not meet the first preset similarity condition, the early warning detection module 730 is configured to: determine the dangerous conversion rate of the positive indicator according to the test result of the positive indicator; if the dangerous conversion rate of the positive indicator exceeds the dangerous conversion rate threshold of the first preset serious disease, output the third early warning prompt information of the target patient for the first preset serious disease.
[0154] In one embodiment, the serious disease warning detection device 700 also includes a warning prompt module 740, which is configured to output fourth warning prompt information of the target patient for the first preset serious disease if the diagnostic similarity between the target patient and the first preset serious disease among various serious diseases meets the first preset similarity condition.
[0155] The above-mentioned device is used to execute the method provided by the aforementioned embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.
[0156] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more microprocessors, or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
[0157] Figure 8 A schematic diagram of a computer device 800 provided in an embodiment of the present application. The device may be integrated into a terminal device or a chip of a terminal device. The terminal may be a computing device with data processing capabilities.
[0158] The device includes: a processor 801 , a storage medium 802 and a bus 803 .
[0159] The storage medium 802 stores program instructions executable by the processor 801. When the computer device 800 is running, the processor 801 communicates with the storage medium 802 via the bus 803. The processor 801 executes the program instructions to perform the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.
[0160] Optionally, the present invention also provides a program product, such as a computer-readable storage medium, comprising a program, which is used to execute the above method embodiment when executed by a processor.
[0161] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0163] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0164] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.
[0165] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A method for early warning detection of severe diseases, characterized in that: include: If a change is detected in the electronic medical record of the target patient, a first health indicator of the diagnosis dimension and a second health indicator of the risk dimension of the target patient are obtained from the electronic medical record; Determining the diagnostic similarity between the target patient and each preset serious disease according to the first health indicator and the diagnostic criteria of each preset serious disease; If the diagnostic similarity between the target patient and a first preset serious disease among the serious diseases does not satisfy a first preset similarity condition, an early warning detection of the first preset serious disease is performed on the target patient based on the second health indicator.
2. The method according to claim 1, characterized in that Determining the diagnostic similarity between the target patient and each preset serious disease according to the first health indicator and the diagnostic criteria of each preset serious disease includes: According to the first health indicator under the multiple diagnostic dimensions and the diagnostic criteria of each preset serious disease under the multiple diagnostic dimensions, respectively determine the indicator similarity of the target patient under the multiple diagnostic dimensions; According to the similarity of the indicators of the target patient in the multiple diagnostic dimensions, the diagnostic similarity between the target patient and each preset serious disease is determined.
3. The method according to claim 2, characterized in that The multiple diagnostic dimensions include: at least two diagnostic dimensions of concomitant diseases, test indicators, signs, symptoms, physical examination, surgery, current medication, and intake and output.
4. The method according to claim 1, characterized in that The performing early warning detection of the first preset severe disease on the target patient according to the second health indicator includes: Determining the risk similarity between the target patient and the first preset critical disease according to the second health indicator and the critical risk factor of the first preset critical disease; If the risk similarity between the target patient and the first preset serious disease meets a second preset similarity condition, the first early warning prompt information of the target patient for the first preset serious disease is output.
5. The method according to claim 4, characterized in that The determining, based on the second health indicator and the critical illness risk factor of the first predetermined critical illness, the risk similarity between the target patient and the first predetermined critical illness comprises: Determining the index similarity between the second health index under multiple risk dimensions and the critical illness risk factor of the first preset critical illness according to the second health index under multiple risk dimensions and the critical illness risk factor of the first preset critical illness; Based on the similarity between the second health indicator and the severe risk factor of the first preset severe disease under multiple risk dimensions, the risk similarity between the target patient and the first preset severe disease is determined.
6. The method according to claim 5, characterized in that The multiple risk dimensions include: at least two risk dimensions of physical condition, adult body mass index, weight, food intake, nutritional status, nursing level, age, occurrence of adverse medical events, and allergy history.
7. The method according to claim 1, characterized in that The first health indicator of the diagnostic dimension includes: a positive indicator of the inspection and examination indicator; If the target patient's diagnosis similarity to the first preset severe disease among the severe diseases does not satisfy the first preset similarity condition, the method further includes: Determining the degree of persistence of harm caused by the positive indicator according to the test result of the positive indicator; If the duration of harm of the positive indicator exceeds the threshold of the duration of harm of the first preset serious disease, the second early warning prompt information of the target patient for the first preset serious disease is output.
8. The method according to claim 7, characterized in that If the target patient's diagnosis similarity to the first preset severe disease among the severe diseases does not satisfy the first preset similarity condition, the method further includes: Determining the dangerous conversion speed of the positive indicator according to the test result of the positive indicator; If the dangerous conversion rate of the positive indicator exceeds the dangerous conversion rate threshold of the first preset serious disease, the third early warning prompt information of the target patient for the first preset serious disease is output.
9. The method according to claim 1, characterized in that: The method further comprises: If the diagnostic similarity between the target patient and a first preset serious disease among the serious diseases meets the first preset similarity condition, the fourth early warning prompt information of the target patient for the first preset serious disease is output.
10. A computer device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the data processing method as described in any one of claims 1 to 9.
Citation Information
Cited By
Internal medicine critical nursing early warning system based on multi-parameter monitoring
CN121003421A
