CN119889672A - Method and system for predicting risk of concurrent constipation of first-onset cerebral hemorrhage patients of middle-aged and young people - Google Patents
Method and system for predicting risk of concurrent constipation of first-onset cerebral hemorrhage patients of middle-aged and young people Download PDFInfo
- Publication number
- CN119889672A CN119889672A CN202411649690.3A CN202411649690A CN119889672A CN 119889672 A CN119889672 A CN 119889672A CN 202411649690 A CN202411649690 A CN 202411649690A CN 119889672 A CN119889672 A CN 119889672A
- Authority
- CN
- China
- Prior art keywords
- constipation
- risk prediction
- young
- aged
- cerebral hemorrhage
- 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.)
- Pending
Links
Classifications
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a method and a system for predicting the risk of concurrent constipation of a middle-aged and young first-stage cerebral hemorrhage patient in the technical field of medical prediction, and belongs to the technical field of medical prediction. And drawing a nomogram of the constipation risk prediction result according to the constipation risk prediction result, wherein clinical data of the first-stage cerebral hemorrhage patients of the middle-aged and young are analyzed through a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, influence factors of the concurrent constipation of the first-stage cerebral hemorrhage patients of the middle-aged and young are determined, and the risk prediction model is constructed and used for the concurrent constipation risk of the first-stage cerebral hemorrhage patients of the middle-aged and young, so that the problem of the lack of the method for predicting the concurrent constipation risk of the first-stage cerebral hemorrhage patients of the middle-aged and young in the prior art is solved.
Description
Technical Field
The invention relates to a method and a system for predicting the risk of constipation of a young and middle-aged first-onset cerebral hemorrhage patient, and belongs to the technical field of medical prediction.
Background
Cerebral hemorrhage is an acute cerebrovascular accident, has the characteristics of sudden onset of disease, rapid disease progress and the like, and has extremely high risk of acute-phase death and long-term disability. According to statistics, hemorrhagic cerebral apoplexy accounts for 27.9% of global new stroke in 2019, the proportion of the first-onset disease group in the 15-49 years old age group exceeds 23%, and obvious younger trend is presented. While the physiology of young and middle-aged patients is still in a relatively healthy state, the occurrence of cerebral hemorrhage not only interrupts their occupation and life planning, but can also lead to various complications, causing long-term physical and psychological disorders. Therefore, prevention and care of complications after cerebral hemorrhage are of great significance to prognosis of young cerebral hemorrhage patients. Constipation is one of the most common complications of cerebral hemorrhage patients, and is generally referred to as a decrease in defecation frequency, difficulty in defecation or desiccation and induration of feces, with occurrence rates ranging from 40% to 91%. Research shows that the hard defecation is easy to induce cardiovascular and cerebrovascular diseases, increases the risk of secondary hemorrhage, interrupts the disease treatment process, even endangers life, prolongs the hospitalization time, increases the treatment cost, and seriously influences the rehabilitation and the life quality of patients.
The middle-aged and young people are in the core stage of society and families, and once cerebral hemorrhage occurs, the original life track of the middle-aged and young people can be interrupted, and various physical disabilities including dyskinesia, sensory disorders and cognitive and linguistic disorders can be experienced, so that the middle-aged and young people can not take responsibility of families and return to work continuously, and huge economic burden pressure and emotional trouble are born. Constipation not only causes physiological and psychological pain of patients, but also causes cardiovascular and cerebrovascular diseases and the like, seriously influences the life quality of the patients, and simultaneously brings great economic burden to families and the patients. Therefore, it is particularly important to screen young and middle-aged patients with first-line cerebral hemorrhage for risk of constipation and to administer preventive measures as early as possible. Currently, constipation reports of cerebral hemorrhage patients are particularly limited, and the existing study population is mainly patients with cerebral hemorrhage alone or in combination with ischemic stroke. In addition, the existing researches are mainly focused on the elderly patients, and the researches on the risk factors of constipation of the elderly and young first-stroke patients are relatively less. Middle-aged and young patients have significant differences from the elderly in physiological, psychological and social settings. Elderly patients are often associated with a variety of chronic diseases, the pathophysiological mechanisms of which are significantly different from those of young and middle-aged patients. In addition, lifestyle and mental state are different, and thus, young patients show different risk factors and rehabilitation challenges when they bleed their brains.
Disclosure of Invention
The invention aims to provide a method for predicting the concurrent constipation risk of a young and middle-aged first-stage cerebral hemorrhage patient, which is characterized in that clinical data of the young and middle-stage first-stage cerebral hemorrhage patient is analyzed by using a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, a risk prediction model is established by determining influence factors of the young and middle-stage first-stage cerebral hemorrhage patient concurrent constipation, and a constipation risk prediction result of the patient is accurately output by using the risk prediction model, and meanwhile, the constipation risk prediction result is displayed in an intuitive nomogram form, so that doctors and patients can know the condition of constipation risk more clearly.
In order to solve the technical problems, the invention is realized by adopting the following technical scheme.
In a first aspect, the invention provides a method for predicting the risk of constipation of a first-onset cerebral hemorrhage patient of young and middle-aged, comprising the following steps:
Acquiring clinical data of a first cerebral hemorrhage patient of the middle-aged and young;
Inputting clinical data of the first cerebral hemorrhage patient of the middle-aged and young people into a pre-trained risk prediction model, and outputting a constipation risk prediction result;
Drawing a constipation risk prediction result nomogram according to the constipation risk prediction result;
the clinical data of the first cerebral hemorrhage patients of the middle-aged and young are analyzed through a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young are determined, and the risk prediction model is constructed.
Further, the analyzing the clinical data of the young and middle-aged first-onset cerebral hemorrhage patient through the single factor analysis method, the multiple linear analysis method and the Logistic regression analysis method, determining the influence factors of the constipation of the young and middle-aged first-onset cerebral hemorrhage patient, and constructing the risk prediction model comprises the following steps:
acquiring historical clinical data of the young and middle-aged first-onset cerebral hemorrhage patient by using a case control research method;
Analyzing variables in the historical clinical data of the first cerebral hemorrhage patient of the middle-aged and young people by a single factor analysis method to obtain the variables with statistical significance;
carrying out multiple collinearity analysis on the variables with statistical significance by a multiple linearity analysis method to obtain variables with statistical significance, wherein multiple collinearity does not exist among the variables;
Assigning the variables with statistical significance, wherein no multiple collinearity exists among the variables, so as to obtain the assigned variables;
Taking the assigned variable as an independent variable, and carrying out Logistic regression analysis by using a backward likelihood method to obtain an influence factor of the concurrent constipation of the first cerebral hemorrhage patient of the young and the middle-aged;
And constructing a risk prediction model based on the influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and the young.
Further, by a single factor analysis method, analyzing variables in the historical clinical data of the first cerebral hemorrhage patient of the middle-aged and young people to obtain the variables with statistical significance, wherein the probability of random errors generated by the variables with statistical significance is less than 5%.
Further, performing multiple co-linearity analysis on the variables with statistical significance by a multiple linear analysis method to obtain the variables with statistical significance, wherein when the tolerance of the variables with statistical significance is greater than 0.2 and the variance expansion factors are less than 5.0, the variables with statistical significance have no multiple co-linearity.
Further, the factors affecting constipation of the young and middle-aged first-onset cerebral hemorrhage patient include glasgow coma score GCS, whether there is surgical history, whether hemiplegia, whether mechanical ventilation is adopted, whether sedative is used, and whether a hypercalcium antagonist is used.
Further, after constructing the risk prediction model, the method further includes performing internal verification on the risk prediction model, including:
sampling historical clinical data of the young and middle-aged first-onset cerebral hemorrhage patient by using a Bootstrap autonomous sampling method to obtain an internal verification data set;
Inputting the internal verification data set into the risk prediction model, and outputting an internal verification constipation risk prediction result;
detecting a discrimination of the risk prediction model using an area under a subject operating characteristic curve based on the internal verification constipation risk prediction result;
based on the internally validated constipation risk prediction results, the predicted performance of the risk prediction model is evaluated using Hosmer-Lemeshow test and calibration graphs.
Further, based on the internal verification constipation risk prediction result, detecting the distinguishing degree of the risk prediction model by using the area under the operation characteristic curve of the subject, wherein the more the area under the curve value is close to 1, the better the distinguishing degree of the risk prediction model is.
Further, based on the internal verification constipation risk prediction result, the predicted performance of the risk prediction model is evaluated by using Hosmer-Lemeshow test and calibration chart, wherein when the predicted performance of the risk prediction model is tested by using Hosmer-Lemeshow, the fitting degree of the risk prediction model is evaluated by taking the significance level equal to 0.05 as a test level.
Further, after the internal verification of the risk prediction model, the method further includes the external verification of the risk prediction model:
using clinical data of the middle-aged and young first-onset cerebral hemorrhage patients in the later stage of the internal verification data set as an external verification data set;
inputting the external verification data set into the risk prediction model, and outputting an external verification constipation risk prediction result;
detecting a discrimination of the risk prediction model using an area under a subject operating characteristic curve based on the externally validated constipation risk prediction result;
And comparing the external verification constipation risk prediction result with the constipation risk actual result, and evaluating the fitting degree of the risk prediction model.
In a second aspect, the present invention provides a system for predicting risk of constipation associated with first cerebral hemorrhage of young and middle-aged patients, comprising:
the data acquisition module is used for acquiring clinical data of the first cerebral hemorrhage patient of the young and middle-aged;
The risk prediction module is used for inputting clinical data of the middle-aged and young first-onset cerebral hemorrhage patient into a pre-trained risk prediction model;
The predicted result output module is used for outputting a constipation risk predicted result;
The nomogram generation module is used for drawing a nomogram of the constipation risk prediction result according to the constipation risk prediction result;
And determining the influence factors of the concurrent constipation of the young and middle-aged first-onset cerebral hemorrhage patient by single factor analysis, multiple linear analysis and Logistic regression analysis methods, and constructing the risk prediction model.
Compared with the prior art, the invention has the beneficial effects that:
1. According to the invention, according to clinical data of the first cerebral hemorrhage patient of the middle-aged and young, the pre-trained risk prediction model is utilized to accurately output the constipation risk prediction result of the patient, the constipation risk prediction result is displayed in an intuitive nomographic form, and doctors and the patient can know the condition of constipation risk more clearly. Not only improves the evaluation accuracy of doctors on constipation risks of patients, but also provides scientific basis for making personalized preventive and intervention measures, thereby being beneficial to reducing the risk of constipation of the first cerebral hemorrhage patients of middle-aged and young, improving the life quality of the patients and relieving the economic and psychological burden caused by the risk. Solves the problem that the prior art lacks a method for predicting the risk of constipation of the first-onset cerebral hemorrhage patients of the young and the middle-aged.
2. Based on historical clinical data of the first cerebral hemorrhage patients of the middle-aged and young, the method determines the influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young through comprehensive application of a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, builds a risk prediction model according to the influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young, and remarkably improves the prediction precision of the concurrent constipation risk of the first cerebral hemorrhage patients of the middle-aged and young.
3. After the risk prediction model is constructed, strict internal verification including Bootstrap autonomous sampling method, area detection under the operation characteristic curve of the subject, hosmer-Lemeshow inspection and calibration chart evaluation and external verification is carried out, so that the stability and reliability of the risk prediction model are ensured, the accuracy of constipation risk prediction results is improved, and a firm scientific basis is provided for the wide application of the risk prediction model in clinical practice.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting risk of constipation of a first-onset cerebral hemorrhage patient of young and middle-aged people according to an embodiment of the present invention;
FIG. 2 is a chart showing the predicted risk of constipation;
FIG. 3 is a schematic diagram of a subject operation characteristic curve based on an internally validated constipation risk prediction result according to an embodiment of the present invention;
FIG. 4 is a graph comparing a risk prediction result of constipation with an actual risk result of constipation, which is shown in the risk prediction model provided by the embodiment of the present invention;
fig. 5 is a schematic diagram of a subject operation characteristic curve based on an external verification constipation risk prediction result according to an embodiment of the present invention.
Detailed Description
The following detailed description of the present invention is made with reference to the accompanying drawings and specific embodiments, and it is to be understood that the specific features of the embodiments and the embodiments of the present invention are detailed description of the technical solutions of the present invention, and not limited to the technical solutions of the present invention, and that the embodiments and the technical features of the embodiments of the present invention may be combined with each other without conflict.
The term "and/or" is merely an association relation describing the association object, and means that three kinds of relations may exist, for example, a and/or B, and that three kinds of cases where a exists alone, a and B exist together, and B exists alone. The character "/", generally indicates that the front and rear associated objects are an or relationship.
Example 1
As shown in fig. 1, this embodiment describes a method for predicting risk of constipation associated with first-born cerebral hemorrhage of young and middle-aged patients, which includes:
step one, acquiring clinical data of a first cerebral hemorrhage patient of the young and middle-aged.
Clinical data of the young and middle-aged first-onset cerebral hemorrhage patient is the basis for constructing a risk prediction model, and the clinical data of the young and middle-aged first-onset cerebral hemorrhage patient contains various information in the physiological, pathological, therapeutic and rehabilitation processes of the patient, so that the influence of the whole health condition and cerebral hemorrhage of the patient can be reflected.
Clinical data of the first cerebral hemorrhage patient of the middle-aged and young is used for analyzing potential influence factors of concurrent constipation, necessary input is provided for constructing a risk prediction model, comprehensive and accurate basic data of the construction of the prediction model can be ensured, and the accuracy and reliability of the risk prediction model can be improved.
And secondly, inputting clinical data of the young and middle-aged first-onset cerebral hemorrhage patient into a pre-trained risk prediction model, and outputting a constipation risk prediction result.
The risk prediction model provided by the invention is obtained based on the historical clinical data of a large number of young and middle-aged first-onset cerebral hemorrhage patients and a statistical analysis method, and can predict the newly input clinical data of the young and middle-aged first-onset cerebral hemorrhage patients through learning rules and modes in the historical data.
Clinical data of a new patient with the first cerebral hemorrhage of the young and the middle-aged is processed by using the risk prediction model, a constipation risk prediction result is output, and a doctor can timely take targeted preventive and intervention measures according to the prediction result, so that the incidence rate of constipation of the patient is reduced, and the rehabilitation effect is improved.
And thirdly, drawing a constipation risk prediction result alignment chart according to the constipation risk prediction result.
The nomogram is an intuitive graphic representation method, and can clearly display constipation risk prediction results and relations between the constipation risk prediction results and each influence factor.
According to the invention, the nomogram is drawn, and the constipation risk prediction result is presented in a graphical mode, so that a doctor can conveniently and quickly know the constipation risk condition of a patient, and a personalized treatment and rehabilitation plan is formulated according to the constipation risk prediction result. Meanwhile, the understanding and application capability of doctors to the prediction result are improved, doctor-patient communication is promoted, and the trust degree and the coordination degree of patients and families to the treatment scheme are enhanced.
The clinical data of the first cerebral hemorrhage patients of the middle-aged and young are analyzed through a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young are determined, and the risk prediction model is constructed.
According to the invention, the relationship between the influence factors of the concurrent constipation of the young and middle-aged first-onset cerebral hemorrhage patients and the constipation is analyzed one by utilizing a single factor analysis method, the variables with statistical significance are screened out, and the factors influencing the constipation are primarily determined.
According to the invention, a multiple linear analysis method is utilized to analyze the linear relation among a plurality of variables with statistical significance, and detect whether the multiple co-linearity problem exists, so that the variables in the risk prediction model are mutually independent, the prediction error caused by co-linearity is avoided, and the stability and the accuracy of the risk prediction model are improved.
The invention utilizes a Logistic regression analysis method to determine key factors influencing constipation based on the relation between two classification dependent variables and independent variable packages, and constructs a final prediction model.
Example 2
The same inventive concept as in example 1 is presented in this example to provide a method for predicting risk of constipation associated with primary cerebral hemorrhage in young and middle-aged patients. According to the historical clinical data of the first cerebral hemorrhage patients of the middle-aged and young, the embodiment deeply explores the influence factors of the constipation of the first cerebral hemorrhage patients of the middle-aged and young, further constructs a risk prediction model, and aims to provide a simple and convenient-to-use prediction tool for clinic, so that medical staff can be helped to identify high-risk patient groups early and accurately. The invention not only provides a solid theoretical support for preventing constipation of the young and middle-aged first-onset cerebral hemorrhage patients, but also promotes the realization of personalized management and prevention strategies for concurrent constipation of the young and middle-aged first-onset cerebral hemorrhage patients.
Step 1, acquiring clinical data of a first cerebral hemorrhage patient of the young and middle-aged.
According to a clinical data questionnaire of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young, the embodiment efficiently completes data collection work by means of the hospital electronic medical record data platform system. In order to ensure the accuracy and consistency of the research, the embodiment carries out comprehensive training on the members of the research team, and the training content covers the operation of the electronic medical record database and the effective collection and input method of data. In order to minimize data deviation or errors possibly caused by human factors, the embodiment adopts a strategy of double check, strictly examines the integrity and accuracy of the collected data of the young and middle-aged cerebral hemorrhage patients, and performs double input on the basis, thereby ensuring the reality and reliability of the data.
And 2, inputting clinical data of the young and middle-aged first-onset cerebral hemorrhage patient into a pre-trained risk prediction model, and outputting a constipation risk prediction result.
The method comprises the steps of analyzing clinical data of the first cerebral hemorrhage patient of the middle-aged and young people through a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, determining influence factors of concurrent constipation of the first cerebral hemorrhage patient of the middle-aged and young people, and constructing a risk prediction model, wherein the method comprises the following steps:
Step 2.1, acquiring historical clinical data of the young and middle-aged first-onset cerebral hemorrhage patient by using a case control research method.
Clinical data of young patients in first cerebral hemorrhage of neurosurgery visit in a third class of first class of hospitals in Suzhou, 2019, 1 month, 2023, are obtained by using a case control research method, and are divided into constipation groups and non-constipation groups according to whether constipation occurs.
In this example, inclusion criteria for historical clinical data for young and middle aged first-onset cerebral hemorrhage patients include:
Meets the diagnosis standard of the Chinese cerebral hemorrhage diagnosis and treatment guide (2019), and is diagnosed as cerebral hemorrhage through skull CT and nuclear magnetic resonance;
the age is 18-59 years old;
First onset;
The hospitalization time is more than or equal to 3 days.
In this example, the criteria for exclusion of historical clinical data for the young and middle aged first-onset cerebral hemorrhage patient were:
has serious gastrointestinal organic diseases, tumor or past gastrointestinal surgery;
combining heart and lung failure, serious liver and kidney diseases or malignant tumors;
incomplete case data;
In gestation or lactation.
And 2.2, analyzing variables in the historical clinical data of the first cerebral hemorrhage patient of the middle-aged and young people by a single factor analysis method to obtain the variables with statistical significance.
In this example, the statistically significant variables produced less than 5% random errors, wherein the results of the variables in the historical clinical data of the young first cerebral hemorrhage patient were analyzed using a single factor analysis method, as shown in table 1, wherein,Representing the total number of historical clinical data.
Results of variables in historical clinical data for young first-onset cerebral hemorrhage patients in table 1 (n=375)
| Project | Non-constipation group (n=123) | Constipation group (n=252) | Test statistics | P value |
| Sex (sex) | 0.5542) | 0.457 | ||
| Man's body | 90(73.2%) | 175(69.4%) | ||
| Female | 33(26.8%) | 77(30.6%) | ||
| Age (age) | -0.0701) | 0.944 | ||
| M(P25,P75) | 49(40,55) | 49(40.25,55) | ||
| Bleeding part | 7.0892) | 0.008 | ||
| Non-basal ganglia | 78(63.4%) | 123(48.8%) | ||
| Basal ganglia | 45(36.6%) | 129(51.2%) | ||
| Whether or not to operate | 11.2222) | 0.001 | ||
| Whether or not | 61(49.6%) | 80(31.7%) | ||
| Is that | 62(50.4%) | 172(68.3%) | ||
| Whether to use calcium antagonists | 20.2132) | <0.001 | ||
| 0 = No | 61(49.6%) | 66(26.2%) | ||
| 1 = Is | 62(50.4%) | 186(73.8%) | ||
| GCS | -2.5721) | 0.010 | ||
| M(P25,P75) | 14(8,15) | 12(7,15) | ||
| Highest body temperature (°c) | -2.9451) | 0.003 | ||
| 0=36.5~38.0 | 84(68.3%) | 127(50.4%) | ||
| 1=38.1~39.0 | 25(20.3%) | 90(35.7%) | ||
| ≥39.1 | 14(11.4%) | 35(13.9%) | ||
| Fever days (Tian) | -3.1751) | 0.001 | ||
| M(P25,P75) | 0(0,2) | 0.5(0,3) | ||
| Whether or not to mechanically ventilate | 13.0402) | <0.001 | ||
| 0 = No | 101(82.1%) | 161(63.9%) | ||
| 1 = Is | 22(17.9%) | 91(36.1%) | ||
| Whether or not to calm | 25.5232) | <0.001 | ||
| 0 = No | 99(80.5%) | 135(53.6%) | ||
| 1 = Is | 24(19.5%) | 117(46.4%) | ||
| Eating means | 18.1012) | <0.001 | ||
| 0 = Oral | 74(60.2%) | 93(36.9%) | ||
| 1 = Nasogastric tube | 49(39.8%) | 159(63.1%) | ||
| Whether or not vasopressin | 0.0062) | 0.939 | ||
| 0 = No | 114(92.7%) | 233(92.5%) | ||
| 1 = Is | 9(7.3%) | 19(7.5%) | ||
| Whether or not the limb is hemiplegia | 12.5662) | <0.001 | ||
| 0 = No | 82(66.7%) | 119(47.2%) | ||
| 1 = Is | 41(33.3%) | 133(52.8%) | ||
| Whether or not the ventricle bleeds | 4.5232) | 0.033 | ||
| 0 = No | 82(66.7%) | 139(55.2%) | ||
| 1 = Is | 41(33.3%) | 113(44.8%) | ||
| Diabetes mellitus | 0.0392) | 0.844 | ||
| 0 = No | 111(90.2%) | 229(90.9%) | ||
| 1 = Is | 12(9.8%) | 23(9.1%) | ||
| Coronary heart disease | 0.4183) | 0.518 | ||
| 0 = No | 122(99.2%) | 246(97.6%) | ||
| 1 = Is | 1(0.8%) | 6(2.4%) | ||
| Hypertension of the type | 0.7602) | 0.383 | ||
| 0 = No | 63(51.2%) | 117(46.4%) | ||
| 1 = Is | 60(48.8%) | 135(53.6%) | ||
| Cerebral infarction | 0.1672) | 0.682 | ||
| 0 = No | 117(95.1%) | 242(96.0%) | ||
| 1 = Is | 6(4.9%) | 10(4.0%) | ||
| Anticoagulant drug | 0.0033) | 0.957 | ||
| 0 = No | 119(96.7%) | 242(96.0%) | ||
| 1 = Is | 4(3.3%) | 10(4.0%) | ||
| Speech disorders | 0.2212) | 0.638 | ||
| 0 = No | 109(88.6%) | 219(86.9%) | ||
| 1 = Is | 14(11.4%) | 33(13.1%) | ||
| Pulmonary infection | 0.8732) | 0.350 | ||
| 0 = No | 111(90.2%) | 219(86.9%) | ||
| 1 = Is | 12(9.8%) | 33(13.1%) | ||
| Whether to live the ICU | 2.2092) | 0.137 | ||
| 0 = No | 89(72.4%) | 163(64.7%) | ||
| 1 = Is | 34(27.6%) | 89(35.3%) | ||
| Dehydrating agent | -2.1101) | 0.035 | ||
| 0 = No | 12(9.8%) | 10(4.0%) | ||
| 1=1~ | 102(82.9%) | 215(85.3%) | ||
| 2=4~ | 9(7.3%) | 27(10.7%) | ||
| BI | -2.8481) | 0.004 | ||
| M(P25,P75) | 20(0,50) | 10(0,30) |
And 2.3, performing multiple collinearity analysis on the variables with statistical significance by a multiple linearity analysis method to obtain the variables with statistical significance, wherein multiple collinearity does not exist among the variables.
In this example, when the tolerance of the statistically significant variables is greater than 0.2 and the variance expansion factor is less than 5.0, there is no multiple collinearity between the statistically significant variables.
And 2.4, assigning values to the variables with statistical significance, wherein no multiple collinearity exists among the variables, as shown in the table 2. And obtaining the assigned variable.
Table 2 assignment of statistically significant variables with no multiple collinearity between the variables
| Project | Assignment mode |
| Bleeding part | Non-basal lamina=0, basal lamina=1 |
| Surgical treatment | No=0, yes=1 |
| Use of calcium antagonists | No=0, yes=1 |
| GCS score (score) | Original value input |
| Highest body temperature (°c) during hospitalization | 36.5~38.0=0 |
| 38.1~39.0=1 | |
| ≥39.1=2 | |
| Fever days (Tian) | Original value input |
| Mechanical ventilation | No=0, yes=1 |
| Sedative agent | No=0, yes=1 |
| Eating means | Oral = 0, nasal feeding = 1 |
| Hemiplegia of limbs | No=0, yes=1 |
| Ventricular hemorrhage | No=0, yes=1 |
| Quantity of drug (seed) using dehydrating agent | No=0, 1-3=1, 4=2 |
| BI | Original value input |
And 2.5, taking the assigned variable as an independent variable, and carrying out Logistic regression analysis by using a backward likelihood method to obtain the influence factors of the concurrent constipation of the young and middle-aged first cerebral hemorrhage patients.
In this example, factors that determine the concomitant constipation of young and middle-aged first-onset cerebral hemorrhage patients include glasgow coma score GCS, whether surgery has been performed, whether hemiplegia has occurred, whether mechanical ventilation has been used, whether sedatives have been used, and whether hypercalcium antagonists have been used.
The results of Logistic regression analysis of constipation of the first cerebral hemorrhage patients of the middle-aged and young are shown in table 3.
Logistic regression analysis results of the young first cerebral hemorrhage patients with concurrent constipation in Table 3 (n=375)
| Project | Beta value | Standard error | Wald χ2 value | P value | OR value | 95%CI |
| Constant value | -1.850 | 0.633 | 8.539 | 0.003 | 0.157 | |
| Surgical treatment | 0.629 | 0.259 | 5.883 | 0.015 | 1.875 | 1.129~3.117 |
| Use of calcium antagonists | 0.758 | 0.248 | 9.344 | 0.002 | 2.134 | 1.312~3.469 |
| GCS scoring | 0.084 | 0.040 | 4.426 | 0.035 | 1.088 | 1.006~1.176 |
| Mechanical ventilation | 0.818 | 0.362 | 5.120 | 0.024 | 2.267 | 1.116~4.606 |
| Sedative agent | 0.894 | 0.277 | 10.397 | 0.001 | 2.445 | 1.420~4.209 |
| Hemiplegia of limbs | 0.650 | 0.249 | 6.798 | 0.009 | 1.915 | 1.175~3.120 |
And 2.6, constructing a risk prediction model based on the influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young people.
And 3, carrying out internal verification on the risk prediction model.
After constructing the risk prediction model, further comprising, performing internal verification on the risk prediction model, including:
Step 3.1, sampling historical clinical data of the young and middle-aged first-onset cerebral hemorrhage patient by using a Bootstrap autonomous sampling method to obtain an internal verification data set;
step 3.2, inputting the internal verification data set into the risk prediction model, and outputting an internal verification constipation risk prediction result;
Step 3.3, detecting the distinguishing degree of the risk prediction model by using the area under the operation characteristic curve of the subject based on the internal verification constipation risk prediction result;
In this embodiment, the area under the curve value is closer to1, the discrimination of the risk prediction model is better, wherein the subject operation characteristic curve diagram based on the internal verification constipation risk prediction result is shown in fig. 3.
Based on the internal verification risk prediction result, the area value under the operation characteristic curve of the subject is 0.733, the sensitivity is 51.2%, the specificity is 87.0%, and the maximum approximate sign index is 1.382, so that the risk prediction model has a good fitting effect and a high prediction value.
And 3.4, based on the internal verification constipation risk prediction result, evaluating the prediction performance of the risk prediction model by using Hosmer-Lemeshow test and calibration chart.
In this embodiment, based on the result of the internal verification constipation risk prediction, the predicted performance of the risk prediction model is evaluated by using Hosmer-Lemeshow test and calibration chart, wherein when the predicted performance of the risk prediction model is checked by using Hosmer-Lemeshow, the fitting degree of the risk prediction model is evaluated with the significance level equal to 0.05 as a test level.
In the embodiment, a graph of the internal verification constipation risk prediction result and the actual constipation risk result is compared, as shown in FIG. 4, and based on the internal verification risk prediction result, hosmer-Lemeshow test shows that the continuous correction test result= 8.956, Probability of random error=0.346, Indicating that the predicted curve and ideal curve of the risk prediction model in the calibration map overlap higher. In addition, the area value under the operation characteristic curve of the subject of the risk prediction model is 0.716, which indicates that the prediction model has better identification capability.
And 4, carrying out external verification on the risk prediction model.
And 4.1, utilizing clinical data of the middle-aged and young first-onset cerebral hemorrhage patients in the later stage of the internal verification data set as an external verification data set.
In this example, the data of the first cerebral hemorrhage patients in the young in 146 cases of neurosurgery treatment in the same hospital obtained from 2023, 2 months, 2024, 9 months by using the case control study method were externally verified on the risk prediction model, and the risk prediction model was divided into constipation groups and non-constipation groups according to whether constipation occurred.
In this embodiment, the inclusion criteria for the external validation dataset are:
Meets the diagnosis standard of the Chinese cerebral hemorrhage diagnosis and treatment guide (2019), and is diagnosed as cerebral hemorrhage through skull CT and nuclear magnetic resonance;
the age is 18-59 years old;
First onset;
The hospitalization time is more than or equal to 3 days.
In this embodiment, the exclusion criteria for the external validation dataset are:
has serious gastrointestinal organic diseases, tumor or past gastrointestinal surgery;
combining heart and lung failure, serious liver and kidney diseases or malignant tumors;
incomplete case data;
In gestation or lactation.
And 4.2, inputting the external verification data set into the risk prediction model, and outputting an external verification constipation risk prediction result.
In this example, in 146 cases, in 101 men and 45 women of the young first-born cerebral hemorrhage patients, the risk prediction model predicts 123 cases of constipation occurrence and actually 94 cases of constipation occurrence.
And 4.3, detecting the distinguishing degree of the risk prediction model by using the area under the operation characteristic curve of the subject based on the result of the external verification constipation risk prediction.
In this example, a schematic diagram of the subject operation characteristic based on the result of the external verification constipation risk prediction is shown in fig. 5. Based on the constipation risk prediction result of external verification, the area under the operation characteristic curve of the subject is 0.751, which indicates that the risk prediction model has better differentiation.
And 4.4, comparing the external verification constipation risk prediction result with the constipation risk actual result, and evaluating the fitting degree of the risk prediction model.
Hosmer-Lemeshow test shows that the test results are continuously corrected= 7.536, Probability of random error=0.480, Indicating that the risk prediction model fits well.
When the optimal critical value of the risk prediction model provided in this embodiment is calculated to be 0.643 based on the about log index, the sensitivity is 73.4%, and the specificity is 69.2%. The risk prediction model has good fitting effect and high prediction value.
And 5, drawing a constipation risk prediction result alignment chart according to the constipation risk prediction result.
The secret risk prediction result alignment chart obtained in this embodiment is shown in fig. 2.
In conclusion, the incidence rate of constipation of the first cerebral hemorrhage patients of the young and the middle-aged is high, and constipation is more likely to occur for the patients who perform operation treatment, adopt mechanical ventilation, hemiplegia and use sedatives and calcium antagonists. The risk prediction model constructed by the embodiment has stronger prediction capability, can be used as a screening tool for constipation high-risk patients, and provides a reference for formulating personalized prevention strategies in time.
Example 3
Based on the same inventive concept as in example 1, this example describes a system for predicting risk of constipation associated with first-born cerebral hemorrhage of young and middle-aged patients, comprising:
the data acquisition module is used for acquiring clinical data of the first cerebral hemorrhage patient of the young and middle-aged;
The risk prediction module is used for inputting clinical data of the middle-aged and young first-onset cerebral hemorrhage patient into a pre-trained risk prediction model;
The predicted result output module is used for outputting a constipation risk predicted result;
The nomogram generation module is used for drawing a nomogram of the constipation risk prediction result according to the constipation risk prediction result;
And determining the influence factors of the concurrent constipation of the young and middle-aged first-onset cerebral hemorrhage patient by single factor analysis, multiple linear analysis and Logistic regression analysis methods, and constructing the risk prediction model.
Specific functional implementation of each module described above refers to the relevant content in the method of embodiment 1 or 2, and will not be repeated.
Example 4
The present invention provides a computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method of embodiment 1 or 2 described above.
Example 5
The present invention also provides a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the method of embodiments 1 or 2 described above, as well as the inventive concepts of the other embodiments.
In summary, according to the embodiment of the invention, according to the clinical data of the first cerebral hemorrhage patient of the middle-aged and young, the constipation risk prediction result of the patient can be accurately output by using the pre-trained risk prediction model, and the constipation risk prediction result is displayed in an intuitive alignment form, so that doctors and patients can know the condition of constipation risk more clearly. Not only improves the evaluation accuracy of doctors on constipation risks of patients, but also provides scientific basis for making personalized preventive and intervention measures, thereby being beneficial to reducing the risk of constipation of the first cerebral hemorrhage patients of middle-aged and young, improving the life quality of the patients and relieving the economic and psychological burden caused by the risk. Solves the problem that the prior art lacks a method for predicting the risk of constipation of the first-onset cerebral hemorrhage patients of the young and the middle-aged.
Based on historical clinical data of the first cerebral hemorrhage patients of the middle-aged and young, the method determines the influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young through comprehensive application of a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, builds a risk prediction model according to the influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young, and remarkably improves the prediction precision of the concurrent constipation risk of the first cerebral hemorrhage patients of the middle-aged and young.
After the risk prediction model is constructed, strict internal verification including Bootstrap autonomous sampling method, area detection under the operation characteristic curve of the subject, hosmer-Lemeshow inspection and calibration chart evaluation and external verification is carried out, so that the stability and reliability of the risk prediction model are ensured, the accuracy of constipation risk prediction results is improved, and a firm scientific basis is provided for the wide application of the risk prediction model in clinical practice. It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are all within the protection of the present invention.
Claims (10)
1. A method for predicting risk of concurrent constipation for a young and middle-aged first-onset cerebral hemorrhage patient, comprising:
Acquiring clinical data of a first cerebral hemorrhage patient of the middle-aged and young;
Inputting clinical data of the first cerebral hemorrhage patient of the middle-aged and young people into a pre-trained risk prediction model, and outputting a constipation risk prediction result;
Drawing a constipation risk prediction result nomogram according to the constipation risk prediction result;
the clinical data of the first cerebral hemorrhage patients of the middle-aged and young are analyzed through a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and young are determined, and the risk prediction model is constructed.
2. The method for constructing a risk prediction model for concurrent constipation of a young and middle-aged first-stage cerebral hemorrhage patient according to claim 1, wherein analyzing clinical data of the young and middle-stage first-stage cerebral hemorrhage patient by a single factor analysis method, a multiple linear analysis method and a Logistic regression analysis method, determining influence factors of concurrent constipation of the young and middle-stage first-stage cerebral hemorrhage patient, and constructing the risk prediction model comprises:
acquiring historical clinical data of the young and middle-aged first-onset cerebral hemorrhage patient by using a case control research method;
Analyzing variables in the historical clinical data of the first cerebral hemorrhage patient of the middle-aged and young people by a single factor analysis method to obtain the variables with statistical significance;
carrying out multiple collinearity analysis on the variables with statistical significance by a multiple linearity analysis method to obtain variables with statistical significance, wherein multiple collinearity does not exist among the variables;
Assigning the variables with statistical significance, wherein no multiple collinearity exists among the variables, so as to obtain the assigned variables;
Taking the assigned variable as an independent variable, and carrying out Logistic regression analysis by using a backward likelihood method to obtain an influence factor of the concurrent constipation of the first cerebral hemorrhage patient of the young and the middle-aged;
And constructing a risk prediction model based on the influence factors of the concurrent constipation of the first cerebral hemorrhage patients of the middle-aged and the young.
3. The method for constructing the model for predicting the risk of concurrent constipation of the young and middle-aged first-stage cerebral hemorrhage patient according to claim 2, wherein the variables in the historical clinical data of the young and middle-aged first-stage cerebral hemorrhage patient are analyzed by a single factor analysis method to obtain the variables with statistical significance, wherein the probability of random errors generated by the variables with statistical significance is less than 5%.
4. The method for constructing the model for predicting the risk of concurrent constipation of the young and middle-aged first-line cerebral hemorrhage patient according to claim 2, wherein multiple collinearity analysis is performed on the variables with statistical significance through a multiple linear analysis method to obtain the variables with statistical significance, wherein when the tolerance of the variables with statistical significance is greater than 0.2 and the variance expansion factor is less than 5.0, the variables with statistical significance have no multiple collinearity.
5. The method for constructing a model for predicting risk of concurrent constipation for a young and middle-aged first-line cerebral hemorrhage patient according to claim 1, wherein the factors affecting the concurrent constipation for the young and middle-aged first-line cerebral hemorrhage patient include glasgow coma score GCS, whether there is surgical experience, whether hemiplegia, whether mechanical ventilation is adopted, whether sedative is used, and whether a calcium antagonist is used.
6. The method for constructing a risk prediction model for concurrent constipation in a young and middle-aged first-line cerebral hemorrhage patient according to claim 2, further comprising, after constructing the risk prediction model, performing internal verification on the risk prediction model, comprising:
sampling historical clinical data of the young and middle-aged first-onset cerebral hemorrhage patient by using a Bootstrap autonomous sampling method to obtain an internal verification data set;
Inputting the internal verification data set into the risk prediction model, and outputting an internal verification constipation risk prediction result;
detecting a discrimination of the risk prediction model using an area under a subject operating characteristic curve based on the internal verification constipation risk prediction result;
based on the internally validated constipation risk prediction results, the predicted performance of the risk prediction model is evaluated using Hosmer-Lemeshow test and calibration graphs.
7. The method for constructing a concurrent constipation risk prediction model for a young and middle-aged first-onset cerebral hemorrhage patient according to claim 6, wherein the discrimination of the risk prediction model is detected by using the area under the subject operation characteristic curve based on the internal verification constipation risk prediction result, wherein the discrimination of the risk prediction model is better as the area under the curve value is closer to 1.
8. The method for constructing a concurrent constipation risk prediction model for a young and middle-aged first-onset cerebral hemorrhage patient according to claim 6, wherein the prediction performance of the risk prediction model is evaluated by using Hosmer-Lemeshow test and calibration chart based on the internal verification constipation risk prediction result, wherein the fitness of the risk prediction model is evaluated by using a significance level equal to 0.05 as a test level when the prediction performance of the risk prediction model is checked by using Hosmer-Lemeshow.
9. The method for constructing a risk prediction model for concurrent constipation in a young and middle-aged first-line cerebral hemorrhage patient according to claim 6, wherein after the internal verification of the risk prediction model, further comprising the external verification of the risk prediction model:
using clinical data of the middle-aged and young first-onset cerebral hemorrhage patients in the later stage of the internal verification data set as an external verification data set;
inputting the external verification data set into the risk prediction model, and outputting an external verification constipation risk prediction result;
detecting a discrimination of the risk prediction model using an area under a subject operating characteristic curve based on the externally validated constipation risk prediction result;
And comparing the external verification constipation risk prediction result with the constipation risk actual result, and evaluating the fitting degree of the risk prediction model.
10. A system for predicting risk of concurrent constipation for a first-born cerebral hemorrhage patient of young and middle-aged people, comprising:
the data acquisition module is used for acquiring clinical data of the first cerebral hemorrhage patient of the young and middle-aged;
The risk prediction module is used for inputting clinical data of the middle-aged and young first-onset cerebral hemorrhage patient into a pre-trained risk prediction model;
The predicted result output module is used for outputting a constipation risk predicted result;
The nomogram generation module is used for drawing a nomogram of the constipation risk prediction result according to the constipation risk prediction result;
And determining the influence factors of the concurrent constipation of the young and middle-aged first-onset cerebral hemorrhage patient by single factor analysis, multiple linear analysis and Logistic regression analysis methods, and constructing the risk prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411649690.3A CN119889672A (en) | 2024-11-19 | 2024-11-19 | Method and system for predicting risk of concurrent constipation of first-onset cerebral hemorrhage patients of middle-aged and young people |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411649690.3A CN119889672A (en) | 2024-11-19 | 2024-11-19 | Method and system for predicting risk of concurrent constipation of first-onset cerebral hemorrhage patients of middle-aged and young people |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119889672A true CN119889672A (en) | 2025-04-25 |
Family
ID=95423242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411649690.3A Pending CN119889672A (en) | 2024-11-19 | 2024-11-19 | Method and system for predicting risk of concurrent constipation of first-onset cerebral hemorrhage patients of middle-aged and young people |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119889672A (en) |
-
2024
- 2024-11-19 CN CN202411649690.3A patent/CN119889672A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | The development an artificial intelligence algorithm for early sepsis diagnosis in the intensive care unit | |
| Sun et al. | Correlation of leukocytosis with early neurological deterioration following supratentorial intracerebral hemorrhage | |
| JP2022514162A (en) | Systems and methods for designing clinical trials | |
| US20230187067A1 (en) | Use of clinical parameters for the prediction of sirs | |
| EP2435940B1 (en) | A method and device for side-effect prognosis and monitoring | |
| Magid et al. | Health-related quality of life predicts emergency department utilization for patients with asthma | |
| Singh et al. | Evaluation of disease activity in rheumatoid arthritis by Routine Assessment of Patient Index Data 3 (RAPID3) and its correlation to Disease Activity Score 28 (DAS28) and Clinical Disease Activity Index (CDAI): an Indian experience | |
| Fortis et al. | An automated computerized critical illness severity scoring system derived from APACHE III: modified APACHE | |
| CN111210890A (en) | Anticoagulation pharmacy monitoring management method based on clinical data | |
| Wang et al. | A time-series feature-based recursive classification model to optimize treatment strategies for improving outcomes and resource allocations of COVID-19 patients | |
| Al-Sakran et al. | Impact of comorbidity on hospitalizations in individuals newly diagnosed with multiple sclerosis: a longitudinal population-based study | |
| Huang et al. | A longitudinal study of healthcare utilisation and expenditure in people with type 2 diabetes mellitus with and without major depressive disorder | |
| He et al. | Evaluation of maternal infection during pregnancy and childhood leukemia among offspring in Denmark | |
| Luchristt et al. | Risk of obstetric anal sphincter injuries at the time of admission for delivery: a clinical prediction model | |
| Schiman et al. | Cardiovascular health in young and middle adulthood and medical care utilization and costs at older age–The Chicago Heart Association Detection Project Industry (CHA) | |
| CN116543867A (en) | Method and device for guiding MTM mode of T2DM patient based on predictive model | |
| Ladapo et al. | Clinical utility of a precision medicine test evaluating outpatients with suspected obstructive coronary artery disease | |
| Islahudin et al. | Continuous medication monitoring: A clinical model to predict adherence to medications among chronic kidney disease patients | |
| Dummitt et al. | Using survival analysis to predict septic shock onset in ICU patients | |
| Duncan et al. | Care fragmentation, social determinants of health, and postoperative mortality in older veterans | |
| CN116030965A (en) | A processing method covering the whole course of diagnosis and treatment data of special diseases inside and outside the hospital | |
| Huang et al. | Prediction models for amputation after diabetic foot: systematic review and critical appraisal | |
| CN119889672A (en) | Method and system for predicting risk of concurrent constipation of first-onset cerebral hemorrhage patients of middle-aged and young people | |
| Rockwell et al. | Screening for unhealthy alcohol use among patients with multiple chronic conditions in primary care | |
| CN114649098A (en) | Modeling method of coronary heart disease PCI operation based on SYNTAX-II integral |
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 |