CN115810425B - Method and device for predicting mortality risk level of sepsis shock patient - Google Patents
Method and device for predicting mortality risk level of sepsis shock patient Download PDFInfo
- Publication number
- CN115810425B CN115810425B CN202211518222.3A CN202211518222A CN115810425B CN 115810425 B CN115810425 B CN 115810425B CN 202211518222 A CN202211518222 A CN 202211518222A CN 115810425 B CN115810425 B CN 115810425B
- Authority
- CN
- China
- Prior art keywords
- vis
- score value
- patient
- determining
- drug
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 206010040047 Sepsis Diseases 0.000 title claims abstract description 32
- 230000035939 shock Effects 0.000 title claims abstract description 19
- 239000003814 drug Substances 0.000 claims abstract description 144
- 229940079593 drug Drugs 0.000 claims abstract description 124
- 239000002550 vasoactive agent Substances 0.000 claims abstract description 100
- 238000004364 calculation method Methods 0.000 claims abstract description 70
- 230000009467 reduction Effects 0.000 claims abstract description 32
- 230000002227 vasoactive effect Effects 0.000 claims abstract description 29
- VYFYYTLLBUKUHU-UHFFFAOYSA-N dopamine Chemical compound NCCC1=CC=C(O)C(O)=C1 VYFYYTLLBUKUHU-UHFFFAOYSA-N 0.000 claims description 79
- 238000001802 infusion Methods 0.000 claims description 60
- 229960003638 dopamine Drugs 0.000 claims description 40
- SFLSHLFXELFNJZ-QMMMGPOBSA-N (-)-norepinephrine Chemical compound NC[C@H](O)C1=CC=C(O)C(O)=C1 SFLSHLFXELFNJZ-QMMMGPOBSA-N 0.000 claims description 38
- 229960003574 milrinone Drugs 0.000 claims description 38
- PZRHRDRVRGEVNW-UHFFFAOYSA-N milrinone Chemical compound N1C(=O)C(C#N)=CC(C=2C=CN=CC=2)=C1C PZRHRDRVRGEVNW-UHFFFAOYSA-N 0.000 claims description 38
- 229960002748 norepinephrine Drugs 0.000 claims description 38
- SFLSHLFXELFNJZ-UHFFFAOYSA-N norepinephrine Natural products NCC(O)C1=CC=C(O)C(O)=C1 SFLSHLFXELFNJZ-UHFFFAOYSA-N 0.000 claims description 38
- GXBMIBRIOWHPDT-UHFFFAOYSA-N Vasopressin Natural products N1C(=O)C(CC=2C=C(O)C=CC=2)NC(=O)C(N)CSSCC(C(=O)N2C(CCC2)C(=O)NC(CCCN=C(N)N)C(=O)NCC(N)=O)NC(=O)C(CC(N)=O)NC(=O)C(CCC(N)=O)NC(=O)C1CC1=CC=CC=C1 GXBMIBRIOWHPDT-UHFFFAOYSA-N 0.000 claims description 37
- 102000002852 Vasopressins Human genes 0.000 claims description 37
- 108010004977 Vasopressins Proteins 0.000 claims description 37
- KBZOIRJILGZLEJ-LGYYRGKSSA-N argipressin Chemical compound C([C@H]1C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CC(N)=O)C(=O)N[C@@H](CSSC[C@@H](C(N[C@@H](CC=2C=CC(O)=CC=2)C(=O)N1)=O)N)C(=O)N1[C@@H](CCC1)C(=O)N[C@@H](CCCN=C(N)N)C(=O)NCC(N)=O)C1=CC=CC=C1 KBZOIRJILGZLEJ-LGYYRGKSSA-N 0.000 claims description 37
- 229960003726 vasopressin Drugs 0.000 claims description 37
- JRWZLRBJNMZMFE-UHFFFAOYSA-N Dobutamine Chemical compound C=1C=C(O)C(O)=CC=1CCNC(C)CCC1=CC=C(O)C=C1 JRWZLRBJNMZMFE-UHFFFAOYSA-N 0.000 claims description 25
- 229960001089 dobutamine Drugs 0.000 claims description 25
- UCTWMZQNUQWSLP-VIFPVBQESA-N (R)-adrenaline Chemical compound CNC[C@H](O)C1=CC=C(O)C(O)=C1 UCTWMZQNUQWSLP-VIFPVBQESA-N 0.000 claims description 21
- 229930182837 (R)-adrenaline Natural products 0.000 claims description 21
- 229960005139 epinephrine Drugs 0.000 claims description 21
- 206010040070 Septic Shock Diseases 0.000 claims description 13
- 230000036303 septic shock Effects 0.000 claims description 13
- 229930013356 epothilone Natural products 0.000 claims description 12
- 150000003883 epothilone derivatives Chemical class 0.000 claims description 12
- 230000034994 death Effects 0.000 abstract description 18
- 231100000517 death Toxicity 0.000 abstract description 18
- 230000008859 change Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000474 nursing effect Effects 0.000 description 2
- 230000008506 pathogenesis Effects 0.000 description 2
- 238000004393 prognosis Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010051379 Systemic Inflammatory Response Syndrome Diseases 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Abstract
The invention discloses a method and a device for predicting mortality risk level of a sepsis shock patient, wherein the method comprises the following steps: determining a standard pump speed of each vasoactive drug according to drug configuration data and weight data of the vasoactive drug of the sepsis shock patient; determining a first maximum VIS score value of a patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of each vasoactive drug; determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula; and determining the mortality risk level of the patient according to a preset early warning grading strategy and a VIS score value reduction ratio. The method can solve the problem that the influence of dynamic change intensity of various vasoactive drugs on sepsis risk prediction is ignored in the existing model, improves the accuracy of death risk prediction, and simultaneously improves the information utilization rate through free noninvasive information such as vasoactive drugs.
Description
Technical Field
The invention relates to the technical field of medical data mining, in particular to a method and a device for predicting mortality risk level of a sepsis shock patient.
Background
Sepsis is a disease that poses a serious threat to life safety, is a systemic inflammatory response syndrome due to infection, and is one of the main causes of common high-risk complications and mortality in ICU patients. It is estimated that 3000 thousands of people suffer from sepsis each year worldwide, and sepsis has become a public medical problem of high concern worldwide because the number of sepsis deaths exceeds 600 thousands. Clinical diagnostic definitions of sepsis have evolved from 1.0 to 3.0, and are also continually updated. The current clinical latest definition of sepsis-3 was proposed by the European society of severe cases in 2016. Clinical research on the pathogenesis of sepsis has been advanced to a certain extent, but the pathogenesis of sepsis is complex, the factors of design variables are more, and the diagnosis accuracy is still to be improved.
At present, a disease critical degree scoring model such as APACHE II, SAPS II and the like is adopted to predict the death risk of sepsis under the general condition, however, the septic shock is often characterized by unstable blood flow dynamics, the prior scoring model ignores the characteristic, the evaluation of a septic shock patient is possibly insufficient, the accuracy of an evaluation result is poor, and meanwhile, medical data in the treatment process of the patient is not fully utilized.
Therefore, a new solution to the above-mentioned problems is needed for those skilled in the art.
Disclosure of Invention
In order to overcome the problems in the related art, the invention discloses a method and a device for predicting mortality risk level of a sepsis shock patient.
According to a first aspect of the disclosed embodiments of the invention, there is provided a method for predicting mortality risk level of a septic shock patient, the method comprising:
determining a standard pump rate for each vasoactive drug administered to a patient in sepsis shock based on drug profile data for the vasoactive drug administered to the patient and weight data for the patient;
determining a first maximum VIS score value of the patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of each vasoactive drug used by the patient;
determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula;
and determining the mortality risk level of the patient according to a preset early warning grading strategy and the VIS score value reduction ratio of the patient.
Optionally, the determining the standard pump rate of the patient using each vasoactive drug according to the drug configuration data of the patient using the vasoactive drug and the weight data of the patient for sepsis shock comprises:
Acquiring weight data of a patient;
obtaining medication configuration data for each vasoactive medication used by a patient, the medication configuration data comprising: drug name, drug infusion rate, and drug infusion volume;
determining a first medicine category or a second medicine category to which the vasoactive medicine belongs according to the name of the vasoactive medicine;
if the vasoactive drugs belong to the first drug category, determining a standard pump speed of each vasoactive drug according to the weight data and the drug configuration data of the patient by a preset first standard pump speed calculation formula, wherein the first standard pump speed calculation formula is as follows:
dose= (1000*infusion rate)/(60 x V x weight), where dose is the standard pump rate, infusion rate is the drug infusion rate, V is the drug infusion volume, weight is the patient's weight data;
if the vasoactive drug belongs to a second drug class, determining a standard pump speed of the vasoactive drug according to the weight data and the drug configuration data of the patient through a preset second standard pump speed calculation formula, wherein the second standard pump speed formula is as follows:
dose = infusion rate/(60 x V weight), dose is standard pump rate, infusion rate is drug infusion rate, V is drug infusion volume, weight is patient weight data.
Optionally, the first drug class includes: at least one of dopamine, dobutamine, norepinephrine, epinephrine, and milrinone;
the second drug class includes: vasopressin.
Optionally, the determining, according to the standard pump speed of the patient using each vasoactive drug, the first maximum VIS score value of the patient in the first preset time period and the second maximum VIS score value of the patient in the second preset time period respectively includes:
determining the real-time VIS score value of each vasoactive drug according to the standard pump speed and the VIS real-time score value calculation formula of each vasoactive drug;
determining the total VIS score value of all the vasoactive drugs used by the patient according to a preset total VIS score value calculation formula, wherein the total VIS score value calculation formula is as follows: total VIS = VIS dopamine + VIS epothilone + VIS milrinone + VIS norepinephrine + VIS vasopressin, wherein VIS dopamine is the real-time VIS score value for dopamine, VIS dopamine is the real-time VIS score value for dobutamine, VIS epothilone is the real-time VIS score value for epinephrine, VIS milrinone is the real-time VIS score value for milrinone, VIS norepinephrine is the real-time VIS score value for norepinephrine, and VIS vasopressin is the real-time VIS score value for vasopressin;
Determining a total VIS score value of the patient every 1 hour within a first preset time period, and determining a first maximum VIS score value in the total VIS score value of each hour, wherein the first time period is 1-24 hours when the patient enters an ICU ward;
and determining the total VIS score value of the patient every 1 hour in a second preset time period, and determining a second maximum VIS score value in the total VIS score value of each hour, wherein the second time period is 25-48 hours when the patient enters an ICU ward.
Optionally, the determining the real-time VIS score value of each vasoactive agent according to the standard pump speed and the VIS real-time score value calculation formula of each vasoactive agent includes:
determining a real-time VIS score value VIS dopamine=1 x dopamine dose according to a dopamine real-time VIS score value calculation formula;
determining a real-time VIS score value VIS dobutamine= 1*dobutamine dose of dobutamine by a real-time VIS score value calculation formula of dobutamine;
determining a real-time VIS score value VIS epiephrine= 100*epinephrine dose of epinephrine by an epinephrine real-time VIS score value calculation formula;
determining a real-time VIS score value VIS milrinone= 10*milrinone dose of milrinone through a milrinone real-time VIS score value calculation formula;
Determining a real-time VIS score value VIS norepinephrine = 100*norepinephrine dose of norepinephrine by a real-time VIS score value calculation formula of the norepinephrine;
the real-time VIS score value of vasopressin was determined by the calculation formula of the real-time VIS score value of vasopressin VIS vasopressin= 10000*vasopressin dose.
Optionally, the determining, according to the first maximum VIS score value and the second maximum VIS score value, the reduction ratio of the VIS score value of the patient according to a preset VRR calculation formula includes:
determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula,
wherein, the VRR calculation formula is: vrr= (VIS) max 1-24h -VIS max 25-48h )/VIS max 1-24h VRR is the ratio of the decrease in VIS score value, VIS max 1-24h For the first maximum VIS score value, VIS max25-48h The second largest VIS score value.
Optionally, the determining the mortality risk level of the patient according to a preset early warning grading policy and a reduction ratio of the VIS score value of the patient includes:
if the VIS score value reduction ratio is greater than or equal to 50%, determining that the mortality risk level of the patient is a four-level risk;
if the VIS score value reduction ratio is less than 50% and greater than or equal to 0, determining that the mortality risk level of the patient is a third-level risk;
If the VIS score value reduction ratio is smaller than 0 and larger than or equal to-50%, determining that the mortality risk level of the patient is secondary risk;
and if the VIS score value reduction ratio is less than-50%, determining that the mortality risk level of the patient is a primary risk.
According to a second aspect of the disclosed embodiments of the present invention, there is provided a device for predicting mortality risk level of a septic shock patient, the device comprising:
a standard pump speed determination module for determining a standard pump speed of each vasoactive drug used by a patient in sepsis shock according to drug configuration data of the vasoactive drug used by the patient and weight data of the patient;
the VIS determining module is connected with the standard pump speed determining module and is used for determining a first maximum VIS score value of the patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of each vasoactive drug used by the patient;
the VRR determining module is connected with the VIS determining module and used for determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula;
And the risk level determining module is connected with the VRR determining module and is used for determining the mortality risk level of the patient according to a preset early warning grading strategy and the VIS score value reduction ratio of the patient.
Optionally, the standard pump speed determining module includes:
a weight data acquisition unit that acquires weight data of a patient;
a configuration data acquisition unit connected to the weight data acquisition unit, for acquiring drug configuration data of each vasoactive drug used by the patient, the drug configuration data comprising: drug name, drug infusion rate, and drug infusion volume;
a drug class determining unit, connected to the configuration data acquiring unit, for determining a first drug class or a second drug class to which the vasoactive drug belongs according to the name of the vasoactive drug;
the first standard pump speed determining unit is connected with the medicine category determining unit, and if the vasoactive medicine belongs to the first medicine category, the standard pump speed of each vasoactive medicine is determined according to the weight data and the medicine configuration data of the patient through a preset first standard pump speed calculating formula, wherein the first standard pump speed calculating formula is as follows:
dose= (1000*infusion rate)/(60 x V x weight), where dose is the standard pump rate, infusion rate is the drug infusion rate, V is the drug infusion volume, weight is the patient's weight data;
the second standard pump speed determining unit is connected with the first standard pump speed determining unit, and if the vasoactive drug belongs to a second drug category, the standard pump speed of the vasoactive drug is determined according to the weight data and the drug configuration data of the patient through a preset second standard pump speed calculation formula, wherein the second standard pump speed formula is as follows:
dose = infusion rate/(60 x V weight), dose is standard pump rate, infusion rate is drug infusion rate, V is drug infusion volume, weight is patient weight data.
Optionally, the VIS determination module includes:
a real-time score determining unit for determining a real-time VIS score value of each vasoactive agent according to the standard pump speed and the VIS real-time score value calculation formula of each vasoactive agent;
the VIS total score value determining unit is connected with the real-time score determining unit and is used for determining the VIS total score value of all the vasoactive drugs used by the patient according to a preset VIS total score value calculating formula, wherein the VIS total score value calculating formula is as follows: total VIS = VIS dopamine + VIS epothilone + VIS milrinone + VIS norepinephrine + VIS vasopressin, wherein VIS dopamine is the real-time VIS score value for dopamine, VIS dopamine is the real-time VIS score value for dobutamine, VIS epothilone is the real-time VIS score value for epinephrine, VIS milrinone is the real-time VIS score value for milrinone, VIS norepinephrine is the real-time VIS score value for norepinephrine, and VIS vasopressin is the real-time VIS score value for vasopressin;
A first maximum VIS score value determining unit connected to the VIS total score value determining unit, for determining the VIS total score value of the patient every 1 hour in a first preset time period, and determining a first maximum VIS score value in the VIS total score value of each hour, wherein the first time period is 1-24 hours when the patient enters the ICU ward;
and the second maximum VIS score value determining unit is connected with the first maximum VIS score value determining unit, determines the total VIS score value of the patient every 1 hour in a second preset time period, and determines a second maximum VIS score value in the total VIS score value of each hour, wherein the second time period is 25-48 hours when the patient enters the ICU ward.
In summary, the present disclosure relates to a method and a device for predicting mortality risk level of a sepsis shock patient, where the method includes: determining a standard pump rate for each vasoactive drug based on the drug profile data and the weight data for the patient in sepsis shock using the vasoactive drug; determining a first maximum VIS score value of a patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of each vasoactive drug; determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula; and determining the mortality risk level of the patient according to a preset early warning grading strategy and a VIS score value reduction ratio. The method can solve the problem that the influence of dynamic change intensity of various vasoactive drugs on sepsis risk prediction is ignored in the existing model, improves the accuracy of death risk prediction, and simultaneously improves the information utilization rate through free noninvasive information such as vasoactive drugs.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification, illustrate the disclosure and together with the description serve to explain, but do not limit the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a method of mortality risk level prediction for a septic shock patient according to an exemplary embodiment;
FIG. 2 is a flow chart of a standard pump speed determination method according to the one shown in FIG. 1;
FIG. 3 is a flow chart of a method of determining a VIS score value according to the method shown in FIG. 1;
FIG. 4 is a block diagram illustrating a device for predicting mortality risk level of a septic shock patient according to an exemplary embodiment;
FIG. 5 is a block diagram of a standard pump speed determination module according to the one shown in FIG. 4;
fig. 6 is a block diagram of the structure of a VIS determination module shown in fig. 4.
Detailed Description
The following describes in detail the embodiments of the present disclosure with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the disclosure, are not intended to limit the disclosure.
FIG. 1 is a flow chart illustrating a method of mortality risk level prediction for a septic shock patient, according to an exemplary embodiment, as shown in FIG. 1, the method comprising:
in step 101, a standard pump rate for a patient in sepsis shock is determined for each vasoactive drug based on drug profile data for the patient using the vasoactive drug and weight data for the patient.
Illustratively, in the disclosed embodiment of the invention, a structural database at the rear end of a patient bedside nursing record sheet is queried through SQL language, and the configuration data and the weight data of the vasoactive drugs used in the treatment process of a patient with sepsis shock after entering an ICU ward are collected, so that the standard pump speed of the patient using each vasoactive drug is calculated. When the structural database at the back end of the patient bedside nursing sheet is inquired, the patient identification code can be presented to acquire the inquiring authority, so that the information safety of the patient can be ensured.
Specifically, fig. 2 is a flowchart of a standard pump speed determining method according to the method shown in fig. 1, and as shown in fig. 2, the step 101 includes:
in step 1011, weight data of the patient is acquired.
In step 1012, drug configuration data for each vasoactive drug used by the patient is acquired.
Wherein the medication configuration data comprises: drug name, drug infusion rate, and drug infusion volume.
In step 1013, a first drug class or a second drug class to which the vasoactive drug belongs is determined according to the name of the vasoactive drug.
Wherein the first drug class comprises: at least one of dopamine, dobutamine, norepinephrine, epinephrine, and milrinone; the second drug class includes: vasopressin.
Illustratively, the vasoactive drugs associated with sepsis generally include: the standard pump speed calculation formulas of the five vasoactive drugs including dopamine, dobutamine, norepinephrine, epinephrine, milrinone and vasopressin are the same, namely the first standard pump speed calculation formula in the disclosed embodiment of the invention, and the calculation of the standard pump speed of the vasopressin is required to be carried out through the second standard pump speed calculation formula in the disclosed embodiment of the invention. Therefore, it is also necessary to determine the class of the vasoactive drug before calculating the standard pump rate of the vasoactive drug.
In step 1014, if the vasoactive agent belongs to the first drug class, a standard pump rate for each vasoactive agent is determined from the patient's weight data and the drug profile data by a preset first standard pump rate calculation formula.
The first standard pump speed calculation formula is as follows:
dose= (1000*infusion rate)/(60 x V x weight), where dose is the standard pump rate, infusion rate is the drug infusion rate, V is the drug infusion volume, weight is the patient weight data.
In step 1015, if the vasoactive drug belongs to the second drug class, the standard pump speed of the vasoactive drug is determined according to the weight data and the drug configuration data of the patient according to a preset second standard pump speed calculation formula.
The second standard pump speed formula is as follows:
dose = infusion rate/(60 x V weight), dose is standard pump rate, infusion rate is drug infusion rate, V is drug infusion volume, weight is patient weight data.
In step 102, a first maximum VIS score value for the patient over a first preset time period and a second maximum VIS score value for the patient over a second preset time period, respectively, are determined based on the patient's standard pump speed for each vasoactive drug.
Illustratively, after the standard pump rate for each vasoactive agent is obtained, it is also necessary to convert the standard pump rate to the patient's VIS score (including real-time VIS score, maximum VIS score, total VIS score, etc.) for the vasoactive agent, and then find the maximum value of the VIS score for each vasoactive agent at different time nodes, thereby determining the dynamic rate of change of the patient's use of the vasoactive agent.
Specifically, fig. 3 is a flowchart of a method for determining a VIS score value according to the method shown in fig. 1, and as shown in fig. 3, the step 102 includes:
in step 1021, a real-time VIS score value for each vasoactive agent is determined based on the standard pump speed and the VIS real-time score calculation formula for each vasoactive agent.
Illustratively, the real-time VIS score value of each vasoactive agent is obtained by multiplying the standard pump speed value of each vasoactive agent by a preset coefficient, that is, the process of determining the real-time VIS score value of each vasoactive agent by a VIS real-time score value calculation formula.
It will be understood that the standard pump speed value of each vasoactive drug of the patient calculated in the embodiment disclosed in the present invention refers to the standard pump speed value of the vasoactive drug used by the patient at each moment, and reflects the dynamic change condition of the medication of the patient, so that the VIS score calculated according to the standard pump speed value at each moment is also the real-time VIS score value of each vasoactive drug used by the patient.
In addition, if the patient simultaneously performs overlapped injection on the same vasoactive medicine at a certain moment, the pump speeds of the overlapped vasoactive medicines are required to be added to obtain the standard pump speed value of the same vasoactive medicine at the moment.
The specific process of determining the real-time VIS score from the real-time VIS score calculation formula for each vasoactive agent and the standard pump speed value for that vasoactive agent comprises:
and determining the real-time VIS score value VIS dopamine=1 x dopamine dose according to the real-time VIS score value calculation formula of the dopamine.
The real-time VIS score value of dobutamine, VIS dobutamine= 1*dobutamine dose, is determined by the real-time VIS score value calculation formula of dobutamine.
The real-time VIS score value VIS epiephrine= 100*epinephrine dose of epinephrine is determined by an epinephrine real-time VIS score calculation formula.
The real-time VIS score value VIS milrinone= 10*milrinone dose of milrinone is determined by a milrinone real-time VIS score value calculation formula.
The real-time VIS score value VIS norepinephrine = 100*norepinephrine dose of norepinephrine is determined by the formula of calculation of the real-time VIS score value of norepinephrine.
The real-time VIS score value of vasopressin was determined by the calculation formula of the real-time VIS score value of vasopressin VIS vasopressin= 10000*vasopressin dose.
In step 1022, the total VIS score for all vasoactive agents administered to the patient is determined according to a predetermined total VIS score calculation formula.
The calculation formula of the VIS total score value is as follows: total VIS = VIS dopamine + VIS epothilone + VIS milrinone + VIS norepinephrine + VIS vasopressin, wherein VIS dopamine is the real time VIS score value of dopamine, VIS dopamine is the real time VIS score value of dobutamine, VIS epothilone is the real time VIS score value of epinephrine, VIS milrinone is the real time VIS score value of milrinone, VIS norepinephrine is the real time VIS score value of norepinephrine, and VIS vasopressin is the real time VIS score value of vasopressin.
Illustratively, from the real-time VIS score values for each vasoactive agent, a total VIS score value for the 6 vasoactive agents used by the patient may be obtained. It will be appreciated that the total VIS score reflects the value of the total VIS score for the 6 vasoactive agents at each moment. In the disclosed embodiment of the invention, the time period of 1-24 hours and 25-48 hours when the patient enters the ICU ward is taken as the key time period for monitoring the dynamic change condition of the medication of the patient, and the total VIS score value of the patient can be obtained every other hour, so that the maximum value is selected to execute the following steps 1023 and 1024.
In step 1023, the patient's total VIS score value is determined every 1 hour for a first preset period of time, and a first maximum VIS score value is determined among the total VIS score values per hour.
Wherein the first time period is a 1-24 hour period during which the patient enters the ICU ward.
In step 1024, the patient's total VIS score value is determined every 1 hour for a second preset period of time, and a second maximum VIS score value is determined among the total VIS score values per hour.
Wherein the second time period is a 25-48 hour period during which the patient enters the ICU ward.
In step 103, according to the first maximum VIS score value and the second maximum VIS score value, the reduction ratio of the VIS score value of the patient is determined by a preset VRR calculation formula.
Specifically, according to the first maximum VIS score value and the second maximum VIS score value, determining a reduction ratio of the VIS score value of the patient through a preset VRR calculation formula, wherein the VRR calculation formula is as follows: vrr= (VIS) max 1-24h -VIS max 25-48h )/VIS max 1-24h VRR is the ratio of the decrease in VIS score value, VIS max 1-24h For the first maximum VIS score value, VIS max 25-48h The second largest VIS score value.
Illustratively, in the disclosed embodiment of the present invention, the first maximum VIS score value and the second maximum VIS score value within the period of 1-24h and 25-48h after the start of the treatment of the vasoactive drug may be used as the inputs of the XGBoost model trained in advance, and the VIS score value decrease ratio may be determined according to the output of the model, that is, the process of calculating the VIS score value decrease ratio by the above-mentioned preset VRR calculation formula.
In addition, the trained XGBoost model may further use a line graph to perform visual output on VIS max dopamine (maximum value of real-time VIS score values of VIS dopamin), VIS max dobutamine (maximum value of real-time VIS score values of VIS dobutamine), VIS max epinephrine (maximum value of real-time VIS score values of VIS epiephrine and epinephrine), VIS max milrinone (maximum value of real-time VIS score values of VIS milrinone and milrinone), VIS max norepinephrine (maximum value of real-time VIS score values of VIS norepinephrine and norepinephrine), VIS max vasopressin (maximum value of real-time VIS score values of VIS vasopressin) and VIS max (first maximum VIS score value and second maximum VIS score value) at the front end, so that ICU medical staff can intuitively observe changes of the VIS-related data, count ICU death and intra-hospital death probability of the patient, and output and display by using a bar graph.
In step 104, the mortality risk level of the patient is determined according to a preset pre-alarm classification strategy and the patient's VIS score value decrease ratio.
Specifically, if the reduction ratio of the VIS score value is greater than or equal to 50%, determining that the mortality risk level of the patient is a four-level risk; if the VIS score value reduction ratio is less than 50% and greater than or equal to 0, determining that the mortality risk level of the patient is a third-level risk; if the VIS score value reduction ratio is smaller than 0 and larger than or equal to-50%, determining that the mortality risk level of the patient is secondary risk; if the VIS score decrease rate is less than-50%, the mortality risk level of the patient is determined to be a primary risk.
It will be appreciated that a high rate of decrease in the VIS score indicates that the patient is using a vasoactive drug that exhibits a significant decrease in the tendency of the patient to see that the patient's condition is improving, and therefore, the higher the rate of decrease in the VIS score, the lower the risk of mortality for the patient. In the embodiment of the invention, the death risk of a patient is divided into 4 grades, namely a first grade risk, a second grade risk, a third grade risk and a fourth grade risk, wherein the first grade risk represents the highest death risk, the second grade risk represents the death risk lower than the first grade risk, the third grade risk represents the death rate lower than the second grade risk, and the fourth grade risk represents the death rate lower than the third grade risk, namely the fourth grade risk represents the lowest death rate.
In addition, in the disclosed embodiment of the invention, SHAP can be used for explaining ICU death risk and nosocomial death risk results predicted by the constructed XGBoost model, namely, calculating average marginal contributions (Shapley values) of features in VIS variables of all feature sequences of septic shock patients in 1-24h and 25-48h to measure importance degree of each feature and whether the features benefit or are hazard factors to ICU death risk and nosocomial death risk of the patients, and explaining the relation between each VIS variable and the predicted death risk in early stage. The goal of SHAP (SHapley AdditiveexPlanation) is to interpret predictions for x-tags by calculating the contribution of each feature to the prediction x. In particular, in interpreting the predicted risk of mortality in septic shock patients, the marginal contribution of a feature when added to the model is calculated, and then the average is taken taking into account the different marginal contributions of that feature in the case of all feature sequences, i.e. SHAP baseline value of that feature. SHAP is represented using a linear model using an additive feature attribution method. The concrete expression form is as follows:
SHAP interprets the predicted value of the model as the sum of the eigenvalues of each input feature:
yi＝ybase+f(xi，1)+f(xi，2)+…+f(xi，k)
for each predicted sample, the model generates a predicted value, SHAP value, which is the value assigned to each feature in the sample. Assuming that the ith sample is xi, the jth feature of the ith sample is xi, j, the predicted value of the model for the ith sample is yi, and the baseline of the entire model (typically the average of the target variables for all samples) is ybase. Where f (xi, j) is the SHAP value of xi, j. f (xi, 1) is the contribution value of the 1 st feature in the i-th sample to the final predicted value yi, and when f (xi, 1) >0, the feature promotes the predicted value and also acts positively; conversely, this feature is described as having a negative effect on the predicted value being reduced.
Specifically, the structural database isBased on Postgresql, patient basic information (icu_id, subject_id, age, weight); VIS-related data (VIS max dopamine, VIS max dobutamine, VIS max epinephrine, VIS max milrinone, VIS max norepinephrine, VIS max vasopressin, VIS max) over a period of 1-24h, 25-48 h; the XGBOOST model is stored in the relevant fields and is available for querying past records at the front end. The variable screening algorithm, which iterates the updating of the VIS data of ICU septic shock patients in the record database to be continuously optimized, was LASSO (Least absolute shrinkageand selection operator) regression (optional part). The LASSO regression method was used to screen for prognostic VIS-related variables that are significantly related to patient survival. LASSO regression used for screening the VIS related dynamic characteristics enables regression coefficients of independent variables which are relatively unimportant to be 0 by constructing penalty functions on all variable coefficients, so that important variable selection is realized except modeling, and the stability of modeling is greatly improved. The loss function is as follows: Wherein the ith training set is assumed to have p predicted variables: yi is the ith prediction result; xij is the jth predicted variable in the ith training set; beta j is the partial regression coefficient of the j variable xij in the multiple linear regression model in the i training set; lambda is the penalty strength for adjusting parameters to control L1 regularization. And (5) performing visual output construction of a prognosis model by using the XGBoost model and the SHAP algorithm again according to the determined prognosis variables. And if the prediction performance of the new model exceeds that of the original model, updating the model.
Fig. 4 is a block diagram illustrating a device for predicting mortality risk level of a septic shock patient according to an exemplary embodiment, as shown in fig. 4, the device 400 includes:
a standard pump speed determination module 410 that determines a standard pump speed for a patient in sepsis shock for each vasoactive drug based on drug profile data for the patient using the vasoactive drug and weight data for the patient;
the VIS determination module 420 is connected to the standard pump speed determination module 410, and determines a first maximum VIS score value of the patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of the patient using each vasoactive drug;
The VRR determining module 430, connected to the VIS determining module 420, determines a reduction ratio of the VIS score value of the patient according to the first maximum VIS score value and the second maximum VIS score value by a preset VRR calculation formula;
the risk level determining module 440, connected to the VRR determining module 430, determines the mortality risk level of the patient according to a preset pre-alarm classification strategy and the patient's VIS score value decrease ratio.
Fig. 5 is a block diagram of the structure of a standard pump speed determination module according to the one shown in fig. 4, and as shown in fig. 5, the standard pump speed determination module 410 includes:
a weight data acquisition unit 411 that acquires weight data of a patient;
a configuration data acquisition unit 412 connected to the weight data acquisition unit 411, for acquiring drug configuration data of each vasoactive drug used by the patient, the drug configuration data including: drug name, drug infusion rate, and drug infusion volume;
a drug class determination unit 413 connected to the configuration data acquisition unit 412, for determining a first drug class or a second drug class to which the vasoactive drug belongs, based on the name of the vasoactive drug;
a first standard pump speed determining unit 414, connected to the drug class determining unit 413, for determining a standard pump speed of each vasoactive drug according to the weight data and the drug configuration data of the patient by a preset first standard pump speed calculation formula, if the vasoactive drug belongs to the first drug class, wherein the first standard pump speed calculation formula is:
dose= (1000*infusion rate)/(60 x V x weight), where dose is the standard pump rate, infusion rate is the drug infusion rate, V is the drug infusion volume, weight is the patient's weight data;
a second standard pump speed determining unit 415, connected to the first standard pump speed determining unit 414, for determining a standard pump speed of the vasoactive drug according to a preset second standard pump speed calculation formula according to the weight data and the drug configuration data of the patient if the vasoactive drug belongs to a second drug class, wherein the second standard pump speed formula is:
dose = infusion rate/(60 x V weight), dose is standard pump rate, infusion rate is drug infusion rate, V is drug infusion volume, weight is patient weight data.
Fig. 6 is a block diagram of the structure of a VIS determination module according to fig. 4, and as shown in fig. 6, the VIS determination module 420 includes:
a real-time score determining unit 421 for determining a real-time VIS score value of each vasoactive agent according to a standard pump speed and a VIS real-time score value calculation formula of each vasoactive agent;
the VIS total score determining unit 422 is connected to the real-time score determining unit 421, and determines the VIS total score of all the vasoactive drugs used by the patient according to a preset VIS total score calculating formula, where the VIS total score calculating formula is: total VIS = VIS dopamine + VIS epothilone + VIS milrinone + VIS norepinephrine + VIS vasopressin, wherein VIS dopamine is the real-time VIS score value for dopamine, VIS dopamine is the real-time VIS score value for dobutamine, VIS epothilone is the real-time VIS score value for epinephrine, VIS milrinone is the real-time VIS score value for milrinone, VIS norepinephrine is the real-time VIS score value for norepinephrine, and VIS vasopressin is the real-time VIS score value for vasopressin;
A first maximum VIS score value determining unit 423 connected to the VIS total score value determining unit 422, for determining the VIS total score value of the patient every 1 hour within a first preset period of time, and determining a first maximum VIS score value among the VIS total score values per hour, wherein the first period of time is a period of 1-24 hours when the patient enters the ICU ward;
a second maximum VIS score value determining unit 424 connected to the first maximum VIS score value determining unit 423, determines a total VIS score value of the patient every 1 hour in a second preset period of time, and determines a second maximum VIS score value among the total VIS score values of each hour, wherein the second period of time is a period of 25-48 hours when the patient enters the ICU ward.
In summary, the present disclosure relates to a method and a device for predicting mortality risk level of a sepsis shock patient, where the method includes: determining a standard pump rate for each vasoactive drug based on the drug profile data and the weight data for the patient in sepsis shock using the vasoactive drug; determining a first maximum VIS score value of a patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of each vasoactive drug; determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula; and determining the mortality risk level of the patient according to a preset early warning grading strategy and a VIS score value reduction ratio. The method can solve the problem that the influence of dynamic change intensity of various vasoactive drugs on sepsis risk prediction is ignored in the existing model, improves the accuracy of death risk prediction, and simultaneously improves the information utilization rate through free noninvasive information such as vasoactive drugs.
The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure, and all the simple modifications belong to the protection scope of the present disclosure.
In addition, the specific features described in the foregoing embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, the present disclosure does not further describe various possible combinations.
Moreover, any combination between the various embodiments of the present disclosure is possible as long as it does not depart from the spirit of the present disclosure, which should also be construed as the disclosure of the present disclosure.
Claims (6)
1. A method of predicting mortality risk level for a septic shock patient, the method comprising:
determining a standard pump rate for each vasoactive drug administered to a patient in sepsis shock based on drug profile data for the vasoactive drug administered to the patient and weight data for the patient;
determining a first maximum VIS score value of the patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of each vasoactive drug used by the patient;
Determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula;
determining the mortality risk level of the patient according to a preset early warning grading strategy and the VIS score value reduction ratio of the patient;
the determining a standard pump rate for a patient in sepsis shock using each vasoactive drug based on drug profile data for the patient using the vasoactive drug and weight data for the patient, comprising: acquiring weight data of a patient; obtaining medication configuration data for each vasoactive medication used by a patient, the medication configuration data comprising: drug name, drug infusion rate, and drug infusion volume; determining a first medicine category or a second medicine category to which the vasoactive medicine belongs according to the name of the vasoactive medicine; if the vasoactive drugs belong to the first drug category, determining a standard pump speed of each vasoactive drug according to the weight data and the drug configuration data of the patient by a preset first standard pump speed calculation formula, wherein the first standard pump speed calculation formula is as follows: dose= (1000 x infusion rate)/(60 x V weight), where dose is the standard pump rate, infusion rate is the drug infusion rate, V is the drug infusion volume, weight is the patient weight data; if the vasoactive drug belongs to a second drug class, determining a standard pump speed of the vasoactive drug according to the weight data and the drug configuration data of the patient by a preset second standard pump speed calculation formula, wherein the second standard pump speed calculation formula is as follows: dose = infusion rate/(60 x V x weight), dose is standard pump rate, infusion rate is drug infusion rate, V is drug infusion volume, weight is patient weight data;
The determining, according to the standard pump speed of the patient using each vasoactive drug, a first maximum VIS score value of the patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period respectively includes: determining the real-time VIS score value of each vasoactive drug according to the standard pump speed and the VIS real-time score value calculation formula of each vasoactive drug; determining the total VIS score value of all the vasoactive drugs used by the patient according to a preset total VIS score value calculation formula, wherein the total VIS score value calculation formula is as follows: total VIS = VIS dopamine + VIS epothilone + VIS milrinone + VIS norepinephrine + VIS vasopressin, wherein VIS dopamine is the real-time VIS score value for dopamine, VIS dopamine is the real-time VIS score value for dobutamine, VIS epothilone is the real-time VIS score value for epinephrine, VIS milrinone is the real-time VIS score value for milrinone, VIS norepinephrine is the real-time VIS score value for norepinephrine, and VIS vasopressin is the real-time VIS score value for vasopressin; determining a total VIS score value of the patient every 1 hour within a first preset time period, and determining a first maximum VIS score value in the total VIS score value of each hour, wherein the first preset time period is a 1-24 hour time period when the patient enters an ICU ward; and determining the total VIS score value of the patient every 1 hour within a second preset time period, and determining a second maximum VIS score value in the total VIS score value of each hour, wherein the second preset time period is 25-48 hours when the patient enters an ICU ward.
2. The method of claim 1, wherein the first drug class comprises: at least one of dopamine, dobutamine, norepinephrine, epinephrine, and milrinone;
the second drug class includes: vasopressin.
3. The method of claim 1, wherein determining the real-time VIS score for each vasoactive agent based on a standard pump speed and a VIS real-time score calculation formula for each vasoactive agent comprises:
determining a real-time VIS score value VIS dopamine=1 x dopamine dose according to a dopamine real-time VIS score value calculation formula;
determining a real-time VIS score value VIS dobutamine=1 x dobutamine dose of dobutamine according to a real-time VIS score value calculation formula of dobutamine;
determining an epinephrine real-time VIS score value VIS epiephrine=100 x epiephrine dose by an epinephrine real-time VIS score value calculation formula;
determining a real-time VIS score value VIS milrinone=10, which is a milrinone dose, of milrinone according to a milrinone real-time VIS score value calculation formula;
Determining a real-time VIS score value VIS norepinephrine =100× norepinephrine dose of norepinephrine by a real-time VIS score value calculation formula of the norepinephrine;
the real-time VIS score value of vasopressin is determined by the calculation formula of the real-time VIS score value of vasopressin, VIS vasopressin=10000.
4. The method of claim 1, wherein determining the patient's rate of decrease in the VIS score value from the first and second maximum VIS score values by a predetermined VRR calculation formula comprises:
determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula,
wherein, the VRR calculation formula is: vrr= (VIS) max 1-24h - VIS max 25-48h ) / VIS max 1-24h VRR is the ratio of the decrease in VIS score value, VIS max 1-24h For the first maximum VIS score value, VIS max 25-48h The second largest VIS score value.
5. The method of claim 4, wherein determining the mortality risk level of the patient based on a pre-set pre-alarm classification strategy and a rate of decrease in the patient's VIS score value comprises:
If the VIS score value reduction ratio is greater than or equal to 50%, determining that the mortality risk level of the patient is a four-level risk;
if the VIS score value reduction ratio is less than 50% and greater than or equal to 0, determining that the mortality risk level of the patient is a third-level risk;
if the VIS score value reduction ratio is smaller than 0 and larger than or equal to-50%, determining that the mortality risk level of the patient is secondary risk;
and if the VIS score value reduction ratio is less than-50%, determining that the mortality risk level of the patient is a primary risk.
6. A device for predicting mortality risk level in a septic shock patient, the device comprising:
a standard pump speed determination module for determining a standard pump speed of each vasoactive drug used by a patient in sepsis shock according to drug configuration data of the vasoactive drug used by the patient and weight data of the patient;
the VIS determining module is connected with the standard pump speed determining module and is used for determining a first maximum VIS score value of the patient in a first preset time period and a second maximum VIS score value of the patient in a second preset time period according to the standard pump speed of each vasoactive drug used by the patient;
the VRR determining module is connected with the VIS determining module and used for determining the VIS score value reduction ratio of the patient according to the first maximum VIS score value and the second maximum VIS score value through a preset VRR calculation formula;
The risk level determining module is connected with the VRR determining module and used for determining the mortality risk level of the patient according to a preset early warning grading strategy and the VIS score value reduction ratio of the patient;
the standard pump speed determination module includes: a weight data acquisition unit that acquires weight data of a patient; a configuration data acquisition unit connected to the weight data acquisition unit, for acquiring drug configuration data of each vasoactive drug used by the patient, the drug configuration data comprising: drug name, drug infusion rate, and drug infusion volume; a drug class determining unit, connected to the configuration data acquiring unit, for determining a first drug class or a second drug class to which the vasoactive drug belongs according to the name of the vasoactive drug; the first standard pump speed determining unit is connected with the medicine category determining unit, and if the vasoactive medicine belongs to the first medicine category, the standard pump speed of each vasoactive medicine is determined according to the weight data and the medicine configuration data of the patient through a preset first standard pump speed calculating formula, wherein the first standard pump speed calculating formula is as follows: dose= (1000 x infusion rate)/(60 x V weight), where dose is the standard pump rate, infusion rate is the drug infusion rate, V is the drug infusion volume, weight is the patient weight data; the second standard pump speed determining unit is connected with the first standard pump speed determining unit, and if the vasoactive drug belongs to a second drug category, the standard pump speed of the vasoactive drug is determined according to the weight data and the drug configuration data of the patient through a preset second standard pump speed calculating formula, wherein the second standard pump speed calculating formula is as follows: dose = infusion rate/(60 x V x weight), dose is standard pump rate, infusion rate is drug infusion rate, V is drug infusion volume, weight is patient weight data;
The VIS determination module includes: a real-time score determining unit for determining a real-time VIS score value of each vasoactive agent according to the standard pump speed and the VIS real-time score value calculation formula of each vasoactive agent; the VIS total score value determining unit is connected with the real-time score determining unit and is used for determining the VIS total score value of all the vasoactive drugs used by the patient according to a preset VIS total score value calculating formula, wherein the VIS total score value calculating formula is as follows: total VIS = VIS dopamine + VIS epothilone + VIS milrinone + VIS norepinephrine + VIS vasopressin, wherein VIS dopamine is the real-time VIS score value for dopamine, VIS dopamine is the real-time VIS score value for dobutamine, VIS epothilone is the real-time VIS score value for epinephrine, VIS milrinone is the real-time VIS score value for milrinone, VIS norepinephrine is the real-time VIS score value for norepinephrine, and VIS vasopressin is the real-time VIS score value for vasopressin; the first maximum VIS score value determining unit is connected with the VIS total score value determining unit, and is used for determining the VIS total score value of the patient every 1 hour in a first preset time period, and determining the first maximum VIS score value in the VIS total score value of each hour, wherein the first preset time period is 1-24 hours when the patient enters an ICU ward; and the second maximum VIS score value determining unit is connected with the first maximum VIS score value determining unit, determines the total VIS score value of the patient every 1 hour in a second preset time period, and determines the second maximum VIS score value in the total VIS score value of each hour, wherein the second preset time period is 25-48 hours when the patient enters an ICU ward.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211518222.3A CN115810425B (en) | 2022-11-30 | 2022-11-30 | Method and device for predicting mortality risk level of sepsis shock patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211518222.3A CN115810425B (en) | 2022-11-30 | 2022-11-30 | Method and device for predicting mortality risk level of sepsis shock patient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115810425A CN115810425A (en) | 2023-03-17 |
| CN115810425B true CN115810425B (en) | 2023-12-08 |
Family
ID=85484478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211518222.3A Active CN115810425B (en) | 2022-11-30 | 2022-11-30 | Method and device for predicting mortality risk level of sepsis shock patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115810425B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2131200A1 (en) * | 2008-06-04 | 2009-12-09 | BRAHMS Aktiengesellschaft | A marker for graft failure and mortality |
| CN102845406A (en) * | 2012-04-20 | 2013-01-02 | 陈田来 | Efficient biological active matter distribution method and device |
| CN104615884A (en) * | 2015-02-04 | 2015-05-13 | 中国科学院地理科学与资源研究所 | Severe infectious disease and mortality risk early warning system and method based on virus detection rate |
| CN104992058A (en) * | 2015-06-25 | 2015-10-21 | 成都厚立信息技术有限公司 | Disease risk regulation model establishment method |
| CN105491519A (en) * | 2015-11-24 | 2016-04-13 | 西安电子科技大学 | Privacy protection method based on continuous real time inquiry scene in position service |
| CN105675609A (en) * | 2016-01-19 | 2016-06-15 | 北京阳明智道光电科技有限公司 | Measuring device and quantitative assessment method of retinal photic injury |
| CN110073220A (en) * | 2016-09-29 | 2019-07-30 | 米密德诊断学有限公司 | The method of risk assessment and classification of diseases |
| CN110489860A (en) * | 2019-08-16 | 2019-11-22 | 兰州交通大学 | A kind of novel landslide risk evaluating method |
| CN110827993A (en) * | 2019-11-21 | 2020-02-21 | 北京航空航天大学 | Early death risk assessment model establishing method and device based on ensemble learning |
| CN112912072A (en) * | 2018-04-09 | 2021-06-04 | 通用医疗公司 | Combination therapy for treating amyotrophic lateral sclerosis and related diseases |
| RU2756025C1 (en) * | 2021-02-12 | 2021-09-24 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Рязанский государственный медицинский университет имени академика И.П. Павлова" Министерства здравоохранения Российской Федерации | Method for predicting survival in chronic obstructive pulmonary disease |
| CN113506628A (en) * | 2021-03-25 | 2021-10-15 | 首都医科大学宣武医院 | Device and method for determining risk of great vessel occlusion |
| CN113782125A (en) * | 2021-09-17 | 2021-12-10 | 平安国际智慧城市科技股份有限公司 | Clinic scoring method and device based on artificial intelligence, electronic equipment and medium |
| CN114038570A (en) * | 2021-11-25 | 2022-02-11 | 中南大学湘雅医院 | Sepsis related acute kidney injury patient death prediction method, system, apparatus and medium |
| CN114585923A (en) * | 2019-10-28 | 2022-06-03 | 豪夫迈·罗氏有限公司 | Management of sepsis |
-
2022
- 2022-11-30 CN CN202211518222.3A patent/CN115810425B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2131200A1 (en) * | 2008-06-04 | 2009-12-09 | BRAHMS Aktiengesellschaft | A marker for graft failure and mortality |
| CN102845406A (en) * | 2012-04-20 | 2013-01-02 | 陈田来 | Efficient biological active matter distribution method and device |
| CN104615884A (en) * | 2015-02-04 | 2015-05-13 | 中国科学院地理科学与资源研究所 | Severe infectious disease and mortality risk early warning system and method based on virus detection rate |
| CN104992058A (en) * | 2015-06-25 | 2015-10-21 | 成都厚立信息技术有限公司 | Disease risk regulation model establishment method |
| CN105491519A (en) * | 2015-11-24 | 2016-04-13 | 西安电子科技大学 | Privacy protection method based on continuous real time inquiry scene in position service |
| CN105675609A (en) * | 2016-01-19 | 2016-06-15 | 北京阳明智道光电科技有限公司 | Measuring device and quantitative assessment method of retinal photic injury |
| CN110073220A (en) * | 2016-09-29 | 2019-07-30 | 米密德诊断学有限公司 | The method of risk assessment and classification of diseases |
| CN112912072A (en) * | 2018-04-09 | 2021-06-04 | 通用医疗公司 | Combination therapy for treating amyotrophic lateral sclerosis and related diseases |
| CN110489860A (en) * | 2019-08-16 | 2019-11-22 | 兰州交通大学 | A kind of novel landslide risk evaluating method |
| CN114585923A (en) * | 2019-10-28 | 2022-06-03 | 豪夫迈·罗氏有限公司 | Management of sepsis |
| CN110827993A (en) * | 2019-11-21 | 2020-02-21 | 北京航空航天大学 | Early death risk assessment model establishing method and device based on ensemble learning |
| RU2756025C1 (en) * | 2021-02-12 | 2021-09-24 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Рязанский государственный медицинский университет имени академика И.П. Павлова" Министерства здравоохранения Российской Федерации | Method for predicting survival in chronic obstructive pulmonary disease |
| CN113506628A (en) * | 2021-03-25 | 2021-10-15 | 首都医科大学宣武医院 | Device and method for determining risk of great vessel occlusion |
| CN113782125A (en) * | 2021-09-17 | 2021-12-10 | 平安国际智慧城市科技股份有限公司 | Clinic scoring method and device based on artificial intelligence, electronic equipment and medium |
| CN114038570A (en) * | 2021-11-25 | 2022-02-11 | 中南大学湘雅医院 | Sepsis related acute kidney injury patient death prediction method, system, apparatus and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115810425A (en) | 2023-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8054178B2 (en) | System and method for correlating biometric trends with a related temporal event | |
| US8510126B2 (en) | Patient monitoring | |
| CN112365978B (en) | Method and device for establishing early risk assessment model of tachycardia event | |
| CN101911078B (en) | Coupling similar patient case | |
| CN109920547A (en) | A kind of diabetes prediction model construction method based on electronic health record data mining | |
| US9613187B2 (en) | Clinical information processing apparatus, method and program | |
| US20190311809A1 (en) | Patient status monitor and method of monitoring patient status | |
| CN104487975A (en) | Method of rendering hemodynamic instability index indicator information | |
| JP2013513846A (en) | Automatic annotation of medical data | |
| CN110289061B (en) | Time sequence prediction method for traumatic hemorrhagic shock injury | |
| US20200058408A1 (en) | Systems, methods, and apparatus for linking family electronic medical records and prediction of medical conditions and health management | |
| EP2766886A1 (en) | System and methods for generating predictive combinations of hospital monitor alarms | |
| JP2006163465A (en) | Medical treatment information analysis apparatus, method, and program | |
| JP2023527001A (en) | Method and system for personalized risk score analysis | |
| CN115810425B (en) | Method and device for predicting mortality risk level of sepsis shock patient | |
| CN111317458A (en) | Blood pressure detection system based on deep learning | |
| CN113520319A (en) | Epileptic event risk management method and system based on logistic regression | |
| CN109994211B (en) | Modeling method for chronic kidney disease worsening risk based on EHR data | |
| US8145664B2 (en) | Disease oriented user interfaces | |
| Chang et al. | A structural design of clinical decision support system for chronic diseases risk management | |
| Shickel et al. | DeepSOFA: a real-time continuous acuity score framework using deep learning | |
| CN114121190A (en) | Method for establishing early warning model of chronic heart failure patient with co-morbid state and mood disorder | |
| Wu et al. | A machine learning approach to predict length of stay for opioid overdose admitted patients | |
| CN116741346B (en) | Medical intelligent cloud image management system and method based on cloud computing | |
| US20230068453A1 (en) | Methods and systems for determining and displaying dynamic patient readmission risk and intervention recommendation |
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 |