CN112200213B - Method and device for realizing accurate blood transfusion of neonate - Google Patents
Method and device for realizing accurate blood transfusion of neonate Download PDFInfo
- Publication number
- CN112200213B CN112200213B CN202010841554.XA CN202010841554A CN112200213B CN 112200213 B CN112200213 B CN 112200213B CN 202010841554 A CN202010841554 A CN 202010841554A CN 112200213 B CN112200213 B CN 112200213B
- Authority
- CN
- China
- Prior art keywords
- data
- key index
- patient
- blood test
- test data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000004369 blood Anatomy 0.000 title claims abstract description 124
- 239000008280 blood Substances 0.000 title claims abstract description 124
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000009534 blood test Methods 0.000 claims abstract description 122
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000003672 processing method Methods 0.000 claims abstract description 24
- 102000001554 Hemoglobins Human genes 0.000 claims description 36
- 108010054147 Hemoglobins Proteins 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 17
- 230000023555 blood coagulation Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000001419 dependent effect Effects 0.000 claims description 6
- 238000007449 liver function test Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 9
- 238000012360 testing method Methods 0.000 description 9
- 230000003908 liver function Effects 0.000 description 8
- 208000007502 anemia Diseases 0.000 description 6
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 description 4
- 108010082126 Alanine transaminase Proteins 0.000 description 4
- 108010088751 Albumins Proteins 0.000 description 4
- 102000009027 Albumins Human genes 0.000 description 4
- 238000008789 Direct Bilirubin Methods 0.000 description 4
- 108010049003 Fibrinogen Proteins 0.000 description 4
- 102000008946 Fibrinogen Human genes 0.000 description 4
- 108090000190 Thrombin Proteins 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 210000003754 fetus Anatomy 0.000 description 4
- 229940012952 fibrinogen Drugs 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005534 hematocrit Methods 0.000 description 4
- 208000028867 ischemia Diseases 0.000 description 4
- 210000000265 leukocyte Anatomy 0.000 description 4
- 230000002028 premature Effects 0.000 description 4
- 102000004169 proteins and genes Human genes 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 4
- 229960004072 thrombin Drugs 0.000 description 4
- 210000003954 umbilical cord Anatomy 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000037396 body weight Effects 0.000 description 2
- 230000008774 maternal effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 206010019280 Heart failures Diseases 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 210000000777 hematopoietic system Anatomy 0.000 description 1
- 201000000977 neonatal anemia Diseases 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Epidemiology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Vascular Medicine (AREA)
- Anesthesiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Hematology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to a data processing method and a device, wherein the method comprises the following steps: receiving current blood test data of a patient; judging whether the key index data is lower than a preset threshold value, if yes, acquiring basic information of the patient and past blood test data from a database; calculating a key index difference value of the patient according to the current blood test data and the last blood test data; the basic information of the patient, the past blood test data, the key index difference value and the compensated key index data are taken as independent variables, the key index compensation value of the patient, which is recovered to the normal level, is taken as the independent variable, training is carried out by utilizing a XGBoost model, the key index compensation value is generated, and the data processing method establishes a blood replenishment amount prediction model by utilizing an artificial intelligence technology, and provides medical basis for accurately determining the blood replenishment amount for doctors in clinical medical treatment.
Description
Technical Field
The present invention relates to the field of electronic technologies, and in particular, to a data processing method and apparatus.
Background
The number of neonates per year in China is more than 1000 ten thousand, and the neonate is an important part of population in China. Newborns are in a special stage of growth and development, and their nervous, respiratory, immune and circulatory systems are still immature, and the hematopoietic systems also vary due to factors such as birth weight, gestational age and age of the day, which cause numerous uncertainties in the treatment of newborns.
Blood transfusion is the only treatment for most cases of neonatal anemia. At present, the blood transfusion opinions of newborns are not uniform internationally, and western countries such as the United kingdom and the Italy make new born blood transfusion guidelines suitable for own countries, and no clear guidance opinion is provided in the aspect of China, so that doctors can determine whether the newborns receive blood transfusion treatment and blood transfusion dosage according to own experience in the treatment process. However, blood transfusion by a doctor empirically may result in unstable hemoglobin, too high or too low. FIG. 1 shows the trend of hemoglobin of a newborn over time. In this period, the doctor performs two blood transfusions, the hemoglobin of the infant after the first blood transfusion is as high as 173g/L, which is obviously higher than the normal level, and then is sharply reduced to the normal level, and the doctor performs the secondary blood transfusion. Since the blood volume of the newborn is small, the transfusion amount needs to be accurate to 1ml, and if the transfusion amount is excessive, the circulation overload is caused, so that heart failure is caused; too little transfusion volume has no obvious treatment effect and needs multiple times of transfusion.
Based on this, it is necessary to provide a data processing method, a data processing apparatus, and a computer-readable storage medium, which assist a doctor in a blood transfusion amount of a patient with an AI-precise transfusion system.
Disclosure of Invention
The embodiment of the application provides a data processing method and device, which are beneficial to improving the intelligence and accuracy of blood supplementation.
In a first aspect, an embodiment of the present application provides a data processing method, including the following steps:
receiving current blood test data of a patient, the current blood test data including at least key indicator data;
Judging whether the key index data is lower than a preset threshold value, if so, acquiring basic information of the patient and past blood test data from a database, wherein the past blood test data at least comprises the latest blood test data;
Calculating a key index difference value of the patient according to the current blood test data and the last blood test data;
And training the basic information of the patient, the past blood test data, the key index difference value and the compensated key index data serving as independent variables, and a key index compensation value of the patient, which is recovered to a normal level, serving as the independent variables by utilizing a XGBoost model to generate the key index compensation value, wherein the XGBoost model is obtained by training clinical data of a plurality of patients through machine learning, and the clinical data of the plurality of patients comprise the key index difference value and the key index compensation value.
In an alternative embodiment, the key indicator is hemoglobin data, the key indicator difference is blood loss, and the key indicator compensation value is transfusion.
In an alternative embodiment, the last blood test data includes key index data and routine data.
In an alternative embodiment, the routine data includes at least one of blood routine, blood clotting, blood gas, and liver function test data.
In an alternative embodiment, the basic information includes at least one of self-condition information and family factor information of the patient.
In a second aspect, an embodiment of the present application provides a data processing apparatus, including:
A receiving module for receiving current blood test data of a patient, the current blood test data including at least key indicator data;
the judging module is used for judging whether the key index data is lower than a preset threshold value or not;
The acquisition module is used for acquiring basic information of the patient and past blood test data from a database, wherein the past blood test data at least comprises the latest test data;
The calculating module can calculate the key index difference value of the patient according to the current blood test data and the last blood test data;
the training module is used for training basic information of the patient, the past blood test data, the key index difference value and the compensated key index data serving as independent variables, key index compensation values of the patient, which are recovered to normal levels, serving as dependent variables, by utilizing a XGBoost model to generate the key index compensation values, wherein the XGBoost model is obtained by machine learning training by using clinical data of a plurality of cases of patients, and the clinical data of the plurality of cases of patients comprise the key index difference value and the key index compensation values.
In an optional embodiment, the data processing apparatus further includes a triggering module, where the triggering module triggers the acquiring module to acquire the basic information of the patient and the past blood test data from a database when the judging module judges that the key index data in the current blood test data is lower than a preset threshold value.
In a third aspect, an embodiment of the present application provides a data processing apparatus, including: a processor, a memory, and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the first aspect of the embodiments of the present application.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program, where the computer program may cause a computer to perform the steps of the first aspect of the embodiments of the present application.
In an embodiment of the present application, first, current blood test data of a patient is received; secondly, judging whether key indexes in the current blood test data are lower than a preset threshold value, if yes, acquiring basic information of a patient and past blood test data from a database, wherein the past test data at least comprise the latest blood test data; thirdly, calculating a key index difference value of the patient according to the current blood test data and the last blood test data; and finally, taking the basic information of the patient, the past blood test data, the key index difference value and the compensated key index data as independent variables, taking a key index compensation value of the patient, which is recovered to a normal level, as the dependent variables, and training by using a XGBoost model to generate the key index compensation value.
It can be seen that, in this embodiment, the beneficial effects of the data processing method are as follows: on one hand, by using an artificial intelligence technology, a blood replenishment quantity prediction model is established, and in clinical medical treatment, a medical basis is provided for a doctor to accurately determine the replenishment quantity of blood; on the other hand, the data processing method can be used as an innovative method for the blood management of newborns in hospitals, overcomes the defect that the existing blood management method cannot accurately and quantitatively, and further promotes the cross fusion of information technology and medicine; secondly, the data processing method can effectively improve the blood management level of hospitals, realize more scientific and reasonable blood treatment, improve the return of patients and lighten the economic burden of the patients.
Drawings
In order to more clearly describe the embodiments of the present application or the technical solutions in the background art, the following description will describe the drawings that are required to be used in the embodiments of the present application or the background art.
FIG. 1 is a graph showing the trend of hemoglobin over time after blood transfusion in a newborn;
FIG. 2 is a schematic flow chart of a data processing method according to an embodiment of the present application;
FIG. 3 is a block diagram illustrating functional blocks of a data processing apparatus according to an embodiment of the present application;
FIG. 4 is a block diagram illustrating functional blocks of another data processing apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
The following will describe in detail.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims and drawings are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The sensing device according to the embodiment of the present application may include various handheld devices, vehicle-mounted devices, wireless headphones, computing devices or other processing devices connected to a wireless modem, and various forms of User Equipment (UE), mobile Station (MS), terminal devices (TERMINALDEVICE), etc., and the electronic device may be, for example, a smart phone, a tablet computer, a headset case, etc. For convenience of description, the above-mentioned devices are collectively referred to as electronic devices.
Embodiments of the present application are described in detail below.
Referring to fig. 2, fig. 2 is a flow chart of a data processing method according to an embodiment of the application, and as shown in the drawing, the data processing method includes:
Step S110: current blood test data of a patient is received.
Specifically, the current blood test data of the patient is derived by blood test, and the current blood test data includes, but is not limited to, at least one of white blood cells, platelets, thrombin time, total protein, albumin, fibrinogen, glutamic pyruvic transaminase, direct bilirubin, hematocrit, and hemoglobin, which can be used to indicate the current physical condition of the patient, wherein at least one of the at least one is key indicator data, which can be used to indicate the balance of blood in the patient.
The current blood test data is used for indicating the blood balance condition of the patient, the hemoglobin data is used as key index data of the blood test data, and the height of the hemoglobin data can be used for indicating whether the patient has the symptoms of anemia currently.
Step S120: and judging whether the key index data is lower than a preset threshold value.
Specifically, a key index threshold meeting medical standards is preset, key index data in the acquired current blood test data is compared with the key index threshold, whether the current key index data is lower than the key index threshold is judged, and if yes, basic information of a patient and previous blood test data are acquired from a database. The database stores basic information of a patient including at least one of self-condition information of the patient and family factor information of the patient, and past blood test data including a plurality of times of blood test data before the patient is sick and including the latest blood test data.
The past blood test data is obtained by blood test, and the past blood test data comprises, but is not limited to, at least one of white blood cells, platelets, thrombin time, total protein, albumin, fibrinogen, glutamic pyruvic transaminase, direct bilirubin, hematocrit and hemoglobin, and can be used for indicating the past physical condition of a patient, wherein at least one item is key index data, and the key index data can be used for indicating the balance condition of a certain substance in the patient. The latest blood test data comprises key index data and routine data, wherein the routine data comprises at least one of blood routine, blood coagulation, blood gas and liver function detection data, so that a basis is provided for the change of the physical condition of a patient.
The key index is hemoglobin data, which is used for indicating the ischemia condition of a patient, the threshold value of the key index is 120g/L which accords with the medical standard, if the hemoglobin data in the current detection data is smaller than the threshold value of 120g/L, the patient can be judged to be in an ischemia state and needs to be subjected to blood transfusion, otherwise, if the hemoglobin data in the current detection data is larger than the threshold value of 120g/L, the patient can be judged to be in a normal state and does not need to be subjected to blood transfusion.
In this embodiment, the routine data includes at least one of blood routine, blood coagulation, blood gas and liver function test data, and the number of items of the patient participating in the blood drawing test can be determined according to the routine data, so as to calculate the accumulated blood loss of the patient according to the number of items of the patient participating in the blood drawing test.
In this embodiment, the family factor information of the patient includes, but is not limited to, information of complications, birth times, delivery modes, whether multiple fetuses are present, and the like of the mother of the patient. The latest blood test data comprise key index hemoglobin data and routine data, wherein the routine data comprise at least one of blood routine, blood coagulation, blood gas and liver function detection data.
In this embodiment, the patient is an infant, and the patient's own condition information includes at least one of the patient's weight, length, age of day, umbilical cord clamp time after delivery, sex, WHO premature infant definition, admission diagnosis, concomitant diseases, anemia causes, blood loss, delivery room resuscitation mode, and blood loss information.
Step S130: and calculating the key index difference value of the patient according to the current blood test data and the latest blood test data.
Specifically, the key index is hemoglobin data, the key index difference value is blood loss, and the blood loss is the accumulated sum of the lost blood quantity of the patient.
Further, the blood loss is the sum of the blood collection amounts of various tests made by the patient in daily life, optionally, the conventional blood collection amount is 1ml, the liver function blood collection amount is 1.5ml, the blood qi blood collection amount is 1ml, the blood coagulation blood collection amount is 2ml, and the specific blood loss amount of the patient can be calculated through the sum of the data.
Step S140: training is carried out by utilizing XGBoost models, and key index compensation values are generated.
Specifically, basic information of a patient, past blood test data, a key index difference value and compensated key index data are taken as independent variables, a key index compensation value for recovering the key index data of the patient to a normal level is taken as the dependent variable, and the data are input into a XGBoost model for training, so that the key index compensation value is generated, wherein the XGBoost model is obtained by using clinical data of a plurality of cases of patients through machine learning training, and the clinical data of the plurality of cases of patients comprise the key index difference value and the key index compensation value.
The key index is hemoglobin data, the key index difference value is blood loss, the key index compensation value is blood transfusion quantity, and the blood transfusion quantity is obtained through XGBoost model training.
In some embodiments, the XGBoost model is obtained through machine learning training using key index differences and key index compensation values of more than 5000 patients, and the XGBoost model is trained through a large amount of clinical data, so that the training result of the model is more scientific.
For a better understanding of the present invention, the following model prediction process is described with respect to a case of an infant patient:
First, medical staff inputs current blood test data of a patient into a system, the key index hemoglobin data of the system is 104g/L, and the system receives the current blood test data of the patient.
And secondly, comparing the key index hemoglobin data 104g/L of the current blood test data with a preset medical standard threshold value 120g/L by the system, and judging that the key index data is lower than the threshold value. The system automatically acquires basic information of the patient and past blood test data from a database, wherein the basic information comprises self-condition information of the patient and family factor information, and the self-condition information of the patient comprises: body weight, length, age of day, postpartum umbilical cord clamp time, sex, WHO premature infant definition, admission diagnosis, concomitant diseases, anemia causes, blood loss, delivery room resuscitation mode, blood loss. The family factor information of the patient includes: maternal complications, birth times, delivery mode, whether multiple fetuses are present. The previous blood test data comprise the latest blood test data, the latest blood test data comprise key index hemoglobin data and conventional data, and the conventional data comprise blood conventional, blood coagulation, blood gas and liver function detection data. The system screens and aggregates the above information to obtain patient basic information as shown in table 1:
table 1 patient basic information table
And thirdly, calculating the critical index difference blood loss of the patient to be 10ml according to the current blood test data and the latest blood test data by the system.
And fourthly, taking basic information of the patient, past blood test data, the critical index difference blood loss and the compensated critical index data as independent variables, taking critical index compensation value blood transfusion quantity of the patient for recovering the critical index data to a normal level as the independent variables, training by using a XGBoost model, and generating the critical index compensation value blood transfusion quantity, thereby predicting that the blood transfusion quantity required by the hemoglobin after blood transfusion reaches 120g/L is 19ml.
As can be seen from the above Table 1, by adopting the data processing method of the present invention, the system can rapidly and automatically obtain the basic information of the patient in the database and the previous blood test data, and also can rapidly calculate and obtain the result of the critical index difference blood loss through the preset formula, so that the calculation accuracy of the critical index difference is accurate to milliliter, and a foundation is laid for precisely obtaining the critical index compensation value blood transfusion quantity by utilizing XGBoost model training in the fourth step.
According to the data processing method, on one hand, the artificial intelligence technology is used for establishing a blood replenishment quantity prediction model, and in clinical medical treatment, medical basis is provided for doctors to accurately determine the blood replenishment quantity; on the other hand, the data processing method can be used as an innovative method for the blood management of newborns in hospitals, overcomes the defect that the existing blood management method cannot accurately and quantitatively, and further promotes the cross fusion of information technology and medicine; secondly, the data processing method can effectively improve the blood management level of hospitals, realize more scientific and reasonable blood treatment, improve the return of patients and lighten the economic burden of the patients.
The foregoing embodiments mainly describe the solution of the embodiment of the present application from the point of view of the method-side execution process. It is to be understood that, in order to achieve the above-described functions, they comprise corresponding hardware structures and/or software modules that perform the respective functions. Those skilled in the art will readily appreciate that the present application can be implemented in hardware or a combination of hardware and computer software in connection with the examples described in connection with the embodiments disclosed herein. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Referring to fig. 3, fig. 3 is a functional block diagram of a data processing apparatus according to an embodiment of the present application, and as shown in the drawing, the data processing apparatus 200 includes: the device comprises a receiving module 210, a judging module 220, an acquiring module 230, a calculating module 240 and a training module 250.
The receiving module 210 is configured to receive current blood test data of a patient, where the current blood test data includes at least key index data.
Specifically, the current blood test data of the patient is obtained by blood test, and the current blood test data includes, but is not limited to, at least one of white blood cells, platelets, thrombin time, total protein, albumin, fibrinogen, glutamic pyruvic transaminase, direct bilirubin, hematocrit and hemoglobin, which can be used to indicate the current physical condition of the patient, wherein at least one of the at least one is key indicator data, which can be used to indicate the balance of blood in the patient.
In this embodiment, the current blood test data is used to indicate the blood balance of the patient, the hemoglobin data is used as key index data of the blood test data, and the height of the hemoglobin data can be used to indicate whether the patient has symptoms of anemia currently.
The judging module 220 is configured to judge whether the key indicator data is lower than a preset threshold.
In some embodiments, referring to fig. 4, an excitation module 225 is further provided after the determination module 220 and before the acquisition module 230.
When the judging module 220 judges that the key index data is lower than the preset threshold value, the activating module 225 activates the obtaining module 230.
The hemoglobin is used as a key index for indicating the ischemia condition of a patient, the threshold value of the hemoglobin is set to be 120g/L which accords with the medical standard, if the data of the hemoglobin in the current detection data is smaller than the threshold value of 120g/L, the patient can be judged to be in an ischemia state and needs to be subjected to blood transfusion, otherwise, if the data of the hemoglobin in the current detection data is larger than the threshold value of 120g/L, the patient can be judged to be in a normal state and does not need to be subjected to blood transfusion.
The obtaining module 230 is configured to obtain basic information of the patient and past blood test data from the database, where the past blood test data includes at least the last blood test data.
Specifically, a key index threshold meeting medical standards is preset, key index data in the acquired current blood test data is compared with the key index threshold, whether the current key index data is lower than the key index threshold is judged, and if yes, basic information of a patient and previous blood test data are acquired from a database. The database stores basic information of a patient including at least one of self-condition information of the patient and family factor information of the patient, and past blood test data including a plurality of times of blood test data before the patient is sick and including the latest blood test data.
The past blood test data is obtained by blood test, and the past blood test data comprises, but is not limited to, at least one of white blood cells, platelets, thrombin time, total protein, albumin, fibrinogen, glutamic pyruvic transaminase, direct bilirubin, hematocrit and hemoglobin, and can be used for indicating past physical conditions of a patient, wherein at least one of the at least one item is key index data, and the key index data can be used for indicating balance condition of blood in the patient. The latest blood test data comprise key index data and routine data, wherein the routine data comprise at least one of blood routine, blood coagulation, blood gas and liver function detection data, so that basis is provided for the change of physical conditions of patients.
In this embodiment, the routine data includes at least one of blood routine, blood coagulation, blood gas and liver function test data, and the number of items of the patient participating in the blood drawing test can be determined according to the routine data, so as to calculate the accumulated blood loss of the patient according to the number of items of the patient participating in the blood drawing test.
In this embodiment, the patient is an infant, and the patient's own status information includes, but is not limited to, patient's weight, length, age of day, umbilical cord clamp time after birth, sex, WHO premature infant definition, admission diagnosis, concomitant diseases, anemia causes, blood loss, delivery room resuscitation mode, blood loss, and the like.
In this embodiment, the family factor information of the patient includes, but is not limited to, information of complications, birth times, delivery modes, whether multiple fetuses are present, and the like of the mother of the patient. The latest blood test data comprise key index hemoglobin data and routine data, wherein the routine data comprise at least one of blood routine, blood coagulation, blood gas and liver function detection data.
The calculating module 240 can calculate the key index difference of the patient according to the current blood test data and the last blood test data.
And automatically acquiring the values of the current blood test data and the latest blood test data through a preset formula, and calculating a key index difference value.
Specifically, the key index is hemoglobin data, the key index difference is blood loss, and the blood loss is the accumulated sum of the lost blood quantity of the patient.
Further, the blood loss is the sum of the blood collection amounts of various tests made by the patient in daily life, optionally, the conventional blood collection amount is 1ml, the liver function blood collection amount is 1.5ml, the blood qi blood collection amount is 1ml, the blood coagulation blood collection amount is 2ml, and the specific blood loss amount of the patient can be calculated through the sum of the data.
The training module 250 performs training by using XGBoost models to generate key index compensation values.
Specifically, basic information of a patient, past blood test data, a key index difference value and compensated key index data are taken as independent variables, a key index compensation value for recovering the key index data of the patient to a normal level is taken as the dependent variable, and the data are input into a XGBoost model for training, so that the key index compensation value is generated, wherein the XGBoost model is obtained by using clinical data of a plurality of cases of patients through machine learning training, and the clinical data of the plurality of cases of patients comprise the key index difference value and the key index compensation value.
The key index is hemoglobin data, the key index difference value is blood loss, the key index compensation value is blood transfusion quantity, the blood transfusion quantity is obtained through XGBoost model training, and the XGBoost model is trained through a large amount of clinical data, so that the training result of the model is more scientific.
In this embodiment, XGBoost models are derived by machine learning training using key index differences and key index compensation values for more than 5000 patients.
For a better understanding of the present invention, the following model prediction process is described with respect to a case of an infant patient:
first, the receiving module receives current blood test data of a patient, wherein the key index hemoglobin data is 104g/L.
And secondly, the judging module compares the key index hemoglobin data 104g/L of the current blood test data with a preset medical standard threshold value 120g/L and judges that the key index data is lower than the threshold value.
The third step, the acquisition module automatically acquires basic information of the patient and past blood test data from a database, wherein the basic information comprises self-condition information of the patient and family factor information, and the self-condition information of the patient comprises: body weight, length, age of day, postpartum umbilical cord clamp time, sex, WHO premature infant definition, admission diagnosis, concomitant diseases, anemia causes, blood loss, delivery room resuscitation mode, blood loss. The family factor information of the patient includes: maternal complications, birth times, delivery mode, whether multiple fetuses are present. The previous blood test data comprise the latest blood test data, the latest blood test data comprise key index hemoglobin data and conventional data, and the conventional data comprise blood conventional, blood coagulation, blood gas and liver function detection data. The system screens and aggregates the above information to obtain patient basic information as shown in table 2:
Table 2 patient basic information table
And step four, the calculation module calculates the critical index difference blood loss of the patient to be 10ml according to the current blood test data and the latest blood test data.
And fifthly, the training module takes basic information of the patient, past blood test data, key index difference blood loss and compensated key index data as independent variables, and key index compensation value blood transfusion quantity of the patient, which is recovered to a normal level, as the independent variables, and trains by utilizing a XGBoost model to generate the key index compensation value blood transfusion quantity, so that the blood transfusion quantity required by predicting that the hemoglobin after blood transfusion reaches 120g/L is 19ml.
As can be seen from the above Table 2, with the data processing apparatus of the present invention, the acquisition module can quickly and automatically acquire the basic information of the patient in the database and the previous blood test data, the calculation module can also quickly calculate the result of the critical index difference blood loss through the preset formula, and the calculation accuracy of the critical index difference is accurate to milliliter, so as to lay a foundation for accurately obtaining the critical index compensation value blood transfusion quantity in the fourth step XGBoost of model training.
It can be seen that in an embodiment of the present application, first, current blood test data of a patient is received; secondly, judging whether key indexes in the current blood test data are lower than a preset threshold value, if yes, acquiring basic information of a patient and past blood test data from a database, wherein the past test data at least comprise the latest blood test data; thirdly, calculating a key index difference value of the patient according to the current blood test data and the last blood test data; and finally, taking the basic information of the patient, the past blood test data, the key index difference value and the compensated key index data as independent variables, taking a key index compensation value of the patient, which is recovered to a normal level, as the dependent variables, and training by using a XGBoost model to generate the key index compensation value.
It can be seen that in this embodiment, the data processing apparatus has the following advantages: on one hand, by using an artificial intelligence technology, a blood replenishment quantity prediction model is established, and in clinical medical treatment, a medical basis is provided for a doctor to accurately determine the replenishment quantity of blood; on the other hand, the data processing method can be used as an innovative method for the blood management of newborns in hospitals, overcomes the defect that the existing blood management method cannot accurately and quantitatively, and further promotes the cross fusion of information technology and medicine; secondly, the data processing method can effectively improve the blood management level of hospitals, realize more scientific and reasonable blood treatment, improve the return of patients and lighten the economic burden of the patients.
In an embodiment of the present application, as shown in fig. 5, the data processing apparatus 300 includes a processor 310 and a memory 320, where the processor 310 is communicatively connected to the memory 320, and one or more computer programs are stored in the memory 320.
Wherein the processor 310 may include at least one of the following types: a general purpose central processing unit (CentralProcessing Unit, CPU), a digital signal Processor (DIGITAL SIGNAL Processor, DSP), a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a microcontroller (Microcontroller Unit, MCU), a field programmable gate array (Field Programmable GATE ARRAY, FPGA), or an integrated Circuit for implementing logic operations. For example, processor 310 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The multiple processors or units included within processor 310 may be integrated in one chip or located on multiple different chips.
The Memory 320 may be a non-powered-down volatile Memory such as EMMC (Embedded Multi MediaCard ), UFS (Universal Flash Storage, universal flash Memory) or Read-Only Memory (ROM), optionally the Memory 320 includes other types of static storage devices that can store static information and instructions, but may also be a powered-down volatile Memory (volatilememory), such as random access Memory (Random Access Memory, RAM) or other types of dynamic storage devices that can store information and instructions, but may also be an electrically erasable programmable Read-Only Memory (ELECTRICALLY ERASABLEPROGRAMMABLE READ-Only Memory, EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other computer readable storage media that can be used to carry or store program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.
The computer program comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform part or all of the steps of any one of the methods described in the method embodiments above. The computer program product may be a software installation package, said computer comprising an electronic device.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all of the steps of any one of the above method embodiments, and the computer includes an electronic device.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the modules described above, are merely a logical function division, and may be implemented in other manners, such as multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed.
The modules described above as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, that is, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.
The integrated modules described above, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the above-mentioned method according to the embodiments of the present application.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and that the program may be stored in a computer readable memory.
The foregoing has outlined rather broadly the more detailed description of embodiments of the application, wherein the principles and embodiments of the application are explained in detail using specific examples, the above examples being provided solely to facilitate the understanding of the method and core concepts of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (9)
1. A data processing method, comprising the steps of:
receiving current blood test data of a patient, wherein the current blood test data at least comprises key index data, and the key index is hemoglobin data;
Judging whether the key index data is lower than a preset threshold value, if so, acquiring basic information of the patient and past blood test data from a database, wherein the past blood test data at least comprises the latest blood test data;
Calculating a key index difference value of the patient according to the current blood test data and the last blood test data;
And training the basic information of the patient, the past blood test data, the key index difference value and the compensated key index data serving as independent variables, and a key index compensation value of the patient, which is recovered to a normal level, serving as the independent variables by utilizing a XGBoost model to generate the key index compensation value, wherein the XGBoost model is obtained by training clinical data of a plurality of patients through machine learning, and the clinical data of the plurality of patients comprise the key index difference value and the key index compensation value.
2. The data processing method according to claim 1, wherein the key index difference is blood loss and the key index compensation value is transfusion quantity.
3. The data processing method of claim 2, wherein the most recent blood test data includes key index data and regular data.
4. A data processing method according to claim 3, wherein the routine data comprises at least one of blood routine, blood clotting, blood gas and liver function test data.
5. The data processing method according to claim 2, wherein the basic information includes at least one of self-condition information and family factor information of the patient.
6. The data processing method of claim 1, wherein the number of clinical data for the plurality of patients exceeds 5000.
7. A data processing apparatus, comprising:
The receiving module is used for receiving current blood test data of a patient, wherein the current blood test data at least comprises key index data, and the key index is hemoglobin data;
the judging module is used for judging whether the key index data is lower than a preset threshold value or not;
the acquisition module is used for acquiring basic information of the patient and past blood test data from a database, wherein the past blood test data at least comprises the latest blood test data;
The calculating module can calculate the key index difference value of the patient according to the current blood test data and the last blood test data;
A training module, taking the basic information of the patient, the past blood test data, the key index difference value and the compensated key index data as independent variables, taking the key index compensation value of the patient, which is recovered to the normal level, as the dependent variable, and training by using a XGBoost model to generate the key index compensation value, wherein the XGBoost model is obtained by using clinical data of a plurality of cases of patients through machine learning training, the clinical data of the plurality of cases of patients comprises the key index difference value and the key index compensation value,
The blood test system further comprises a triggering module, and when the judging module judges that the key index data in the current blood test data is lower than a preset threshold value, the triggering module triggers the acquisition module to acquire the basic information of the patient and the past blood test data from a database.
8. A data processing apparatus, comprising: a processor, a memory and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising steps for performing the method of any of claims 1-6.
9. A computer readable storage medium for storing a computer program, wherein the computer program is operative to cause a computer to perform the steps of the method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010841554.XA CN112200213B (en) | 2020-08-20 | 2020-08-20 | Method and device for realizing accurate blood transfusion of neonate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010841554.XA CN112200213B (en) | 2020-08-20 | 2020-08-20 | Method and device for realizing accurate blood transfusion of neonate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200213A CN112200213A (en) | 2021-01-08 |
| CN112200213B true CN112200213B (en) | 2024-05-14 |
Family
ID=74006504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010841554.XA Active CN112200213B (en) | 2020-08-20 | 2020-08-20 | Method and device for realizing accurate blood transfusion of neonate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200213B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113384244B (en) * | 2021-07-30 | 2022-05-24 | 中国人民解放军陆军军医大学第一附属医院 | Negative pressure suction system |
| CN113611391A (en) * | 2021-08-25 | 2021-11-05 | 中南大学湘雅三医院 | Liver transplantation process blood transfusion prediction method, system, equipment and medium |
| CN114662623B (en) * | 2022-05-25 | 2022-08-16 | 山东师范大学 | XGboost-based blood sample classification method and system in blood coagulation detection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104661582A (en) * | 2012-05-14 | 2015-05-27 | 高斯外科公司 | System and methods for managing blood loss of a patient |
| CN106250689A (en) * | 2016-07-28 | 2016-12-21 | 汪德清 | The assessment of a kind of red blood cell transfusion demand and the system and method for therapeutic evaluation |
| CN108511057A (en) * | 2018-02-28 | 2018-09-07 | 北京和兴创联健康科技有限公司 | Transfusion volume model foundation and prediction technique, device, equipment and its storage medium |
| CN110767316A (en) * | 2019-09-06 | 2020-02-07 | 中国人民解放军总医院 | Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume |
| CN110841152A (en) * | 2019-11-21 | 2020-02-28 | 青岛市中心血站 | Heatable pressure device for blood transfusion of hematology department |
| CN111161865A (en) * | 2019-09-06 | 2020-05-15 | 中国人民解放军总医院 | Blood demand prediction method and blood dynamic inventory early warning system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9646375B2 (en) * | 2011-07-09 | 2017-05-09 | Gauss Surgical, Inc. | Method for setting a blood transfusion parameter |
| EP3033001B1 (en) * | 2013-08-12 | 2021-01-06 | University of Maryland, Baltimore | Apparatus for predicting a need for a blood transfusion |
| WO2016187070A1 (en) * | 2015-05-15 | 2016-11-24 | Gauss Surgical, Inc. | Method for projecting blood loss of a patient during a surgery |
-
2020
- 2020-08-20 CN CN202010841554.XA patent/CN112200213B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104661582A (en) * | 2012-05-14 | 2015-05-27 | 高斯外科公司 | System and methods for managing blood loss of a patient |
| CN106250689A (en) * | 2016-07-28 | 2016-12-21 | 汪德清 | The assessment of a kind of red blood cell transfusion demand and the system and method for therapeutic evaluation |
| CN108511057A (en) * | 2018-02-28 | 2018-09-07 | 北京和兴创联健康科技有限公司 | Transfusion volume model foundation and prediction technique, device, equipment and its storage medium |
| CN110767316A (en) * | 2019-09-06 | 2020-02-07 | 中国人民解放军总医院 | Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume |
| CN111161865A (en) * | 2019-09-06 | 2020-05-15 | 中国人民解放军总医院 | Blood demand prediction method and blood dynamic inventory early warning system |
| CN110841152A (en) * | 2019-11-21 | 2020-02-28 | 青岛市中心血站 | Heatable pressure device for blood transfusion of hematology department |
Non-Patent Citations (2)
| Title |
|---|
| Prediction of blood transfusion donation;Darwiche, M. 等;《2010 Fourth International Conference on Research Challenges in Information Science (RCIS 2010)》;20100521;1-6 * |
| 再次剖宫产术中出血危险因素分析及机器学习对术中输血预测研究;李杰;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20200315;E068-162 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112200213A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200213B (en) | Method and device for realizing accurate blood transfusion of neonate | |
| TWI768216B (en) | Dehydration amount prediction method for hemodialysis and electronic device using the same | |
| Cournoyer et al. | Near‐infrared spectroscopy monitoring during cardiac arrest: a systematic review and meta‐analysis | |
| US20130324861A1 (en) | Health condition determination method and health condition determination system | |
| WO2018028222A1 (en) | Tertiary prevention health management system and method | |
| CN111053540B (en) | CRRT computer-patient body temperature correction system based on machine learning | |
| CN110874409A (en) | Disease grading prediction system, method, electronic device and readable storage medium | |
| CN112509669A (en) | AI technology-based renal disease hemodialysis scheme customization method and system | |
| US20140172459A1 (en) | Clinical support system and method | |
| CN111588384A (en) | Method, device and equipment for obtaining blood sugar detection result | |
| CN112183572A (en) | Method and device for generating prediction model for predicting pneumonia severity | |
| CN111956193A (en) | Health state detection method, device, medium and equipment applied to intelligent earphone | |
| CN110755047B (en) | Cardiovascular and cerebrovascular disease prevention method, device, terminal and storage medium | |
| CN113066574A (en) | Neural network-based aneurysm rupture prediction method, device and storage medium | |
| WO2022205601A1 (en) | Dynamic intervention method and apparatus for treatment strategy, electronic device and storage medium | |
| JP2018527133A5 (en) | ||
| CN113974578A (en) | Device for estimating physiological heart measurement according to qi and blood analysis | |
| CN113223713A (en) | Dynamic monitoring method, system and storage medium based on risk assessment | |
| CN117393147A (en) | Method and system for recommending intracranial rupture aneurysm clinical treatment scheme | |
| CN111223536A (en) | Method and device for predicting heparin dosage | |
| CN116580836A (en) | Device, system and medium for evaluating bad ending risk in hospital of advanced patient | |
| CN114300073A (en) | Clinical patient monitoring method, system and computer storage medium | |
| CN113057586B (en) | Disease early warning method, device, equipment and medium | |
| CN115359908A (en) | Intelligent diagnosis system and method for chest X-ray image beside ICU bed of newborn | |
| CN113057588A (en) | Disease early warning method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |