CN114822838A - Method and system for constructing model for predicting falling risk of stroke patient - Google Patents

Method and system for constructing model for predicting falling risk of stroke patient Download PDF

Info

Publication number
CN114822838A
CN114822838A CN202210248534.0A CN202210248534A CN114822838A CN 114822838 A CN114822838 A CN 114822838A CN 202210248534 A CN202210248534 A CN 202210248534A CN 114822838 A CN114822838 A CN 114822838A
Authority
CN
China
Prior art keywords
patient
risk
falling
stroke
factors
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
Application number
CN202210248534.0A
Other languages
Chinese (zh)
Inventor
王涛
吴尧
王丹心
许玲
孙海
李玉敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hainan Medical College
Original Assignee
Hainan Medical College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hainan Medical College filed Critical Hainan Medical College
Priority to CN202210248534.0A priority Critical patent/CN114822838A/en
Publication of CN114822838A publication Critical patent/CN114822838A/en
Pending legal-status Critical Current

Links

Images

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
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medicinal Chemistry (AREA)
  • Pharmacology & Pharmacy (AREA)
  • Toxicology (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention provides a method for constructing a model for predicting the falling risk of a stroke patient, which comprises the following steps: determining falling risk factors of a stroke patient, and acquiring relevant data of each risk factor; all risk factors are brought into a Logistic regression equation to construct an initial prediction model of the falling risk of the stroke patient, and relevant data of each risk factor is imported into the initial prediction model to obtain the falling incidence rate of the stroke patient; based on the falling incidence rate of the stroke patients and in combination with the dynamic nomogram technology, a dynamic nomogram prediction model of the falling risk of the stroke patients is constructed, and the dynamic nomogram prediction model is further verified and calibrated to obtain a final falling risk prediction model of the stroke patients. By implementing the invention, various falling risk factors of the stroke patient can be taken into consideration and analyzed, the clinical decision can be guided, and the falling time and the risk of poor prognosis can be reduced.

Description

Method and system for constructing model for predicting falling risk of stroke patient
Technical Field
The invention relates to the technical field of medical statistical analysis and the technical field of computers, in particular to a method and a system for constructing a falling risk prediction model for a stroke patient.
Background
Compared with healthy people, stroke patients are lower in walking stability and more prone to fall due to the fact that trunk deviation and peak trunk speed cannot be controlled. It has been reported that in community-living stroke patients, the incidence of falls is 37% to 55%. Studies have also shown that up to 70% of stroke patients fall within 6 months after discharge from hospital or home after treatment by a rehabilitation facility. The fall can cause serious trauma, worsening of clinical symptoms, and even death of the patient. In addition to mortality, falls can increase hospital stay and treatment costs, increasing the economic burden on patients. In addition, the occurrence of a fall also seriously affects the mental health of a stroke patient, resulting in fear of falling (FOF), loss of confidence in walking, social isolation, anxiety, depression and the like, which all seriously affect the recovery and prognosis of the stroke patient. In addition, the occurrence of fall adverse events can also cause guilt and anxiety in medical staff and dissatisfaction of patients and family members with medical institutions, resulting in deterioration of medical environments.
In clinical work, the identification of falling-down high-risk patients can effectively improve the pertinence of safety management work, and is beneficial to obtaining greater health benefits under limited medical resources. The fall risk assessment scale is the most common form for clinically assessing the fall risk of patients, and for stroke patients, the clinically used "fall prevention risk assessment and prevention for adult inpatients" does not take into account and analyze the special risk factors of the stroke patients falling, so that it is necessary to develop a tool more suitable for the fall risk assessment of the stroke patients.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide a method and a system for constructing a model for predicting the falling risk of a stroke patient, which can take various falling risk factors of the stroke patient into consideration and analysis range, help to guide clinical decision, and reduce the falling time and the risk of poor prognosis.
In order to solve the technical problem, an embodiment of the present invention provides a method for constructing a model for predicting a fall risk of a stroke patient, where the method includes the following steps:
determining falling risk factors of a stroke patient, and acquiring relevant data of each risk factor; wherein the risk factors include common risk factors and special risk factors;
all risk factors are incorporated into a Logistic regression equation to construct an initial prediction model of the falling risk of the stroke patient, and acquired relevant data of each risk factor is imported into the initial prediction model to obtain the falling incidence rate of the stroke patient;
and establishing a dynamic nomogram prediction model of the falling risk of the stroke patient based on the falling incidence of the stroke patient and by combining a dynamic nomogram technology, and further verifying and calibrating the dynamic nomogram prediction model by adopting a preset verification mode and a preset calibration mode to obtain a final falling risk prediction model of the stroke patient.
Wherein the common risk factors include age of the patient, peak time when the patient falls, and primary location where the patient falls;
the special risk factors include adverse effect factors of drug treatment and factors that the patient himself is affected by the disease; the adverse effect factors of the drug therapy comprise the adverse effect of the hypoglycemic drug, the adverse effect of the antihypertensive drug, the adverse effect of the tranquilizer and the adverse effect of the anti-psychotic drug; factors that the patient is affected by the disease itself include patient muscle tension imbalance, patient lateral movement disorder, patient visual field disorder, and patient visual field abnormality.
And the preset verification mode is a Bootstrap verification mode.
The preset Calibration mode is a Hosmer-Lemeshow inspection mode or a Calibration mode of drawing a Calibration chart for Calibration.
The embodiment of the invention also provides a system for constructing a model for predicting the falling risk of a stroke patient, which comprises the following steps:
the risk factor determination unit is used for determining the falling risk factors of the stroke patient and acquiring the relevant data of each risk factor; wherein the risk factors include common risk factors and special risk factors;
the initial prediction model building unit is used for bringing all risk factors into a Logistic regression equation to build an initial prediction model of the falling risk of the stroke patient, and importing the acquired relevant data of each risk factor into the initial prediction model to obtain the falling incidence of the stroke patient;
and the final prediction model building unit is used for building a dynamic nomogram prediction model of the falling risk of the stroke patient based on the falling incidence of the stroke patient and by combining a dynamic nomogram technology, and further verifying and calibrating the dynamic nomogram prediction model by adopting a preset verification mode and a preset calibration mode to obtain the final falling risk prediction model of the stroke patient.
Wherein the common risk factors include age of the patient, peak time when the patient falls, and primary location where the patient falls;
the special risk factors include adverse effect factors of drug treatment and factors that the patient himself is affected by the disease; adverse effect factors of the drug therapy include adverse effects of hypoglycemic drugs, adverse effects of antihypertensive drugs, adverse effects of tranquilizers, and adverse effects of anti-psychotic drugs; factors that the patient is affected by the disease itself include patient muscle tension imbalance, patient lateral movement disorder, patient visual field disorder, and patient visual field abnormality.
And the preset verification mode is a Bootstrap verification mode.
The preset Calibration mode is a Hosmer-Lemeshow inspection mode or a Calibration mode of drawing a Calibration chart for Calibration.
The embodiment of the invention has the following beneficial effects:
according to the invention, various falling risk factors of the stroke patient are taken into consideration and analyzed within a range, so that a final dynamic nomogram prediction model of the falling risk of the stroke patient is obtained, visual analysis of the falling risk related scoring parameters of the stroke patient is realized, the values of various falling risk factor evaluations of the stroke patient are input, and the falling probability of the patient can be obtained through the dynamic nomogram, so that the clinical decision can be guided, and the falling time occurrence and the bad prognosis risk can be reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is within the scope of the present invention for those skilled in the art to obtain other drawings based on the drawings without inventive exercise.
Fig. 1 is a flowchart of a method for constructing a model for predicting the fall risk of a stroke patient according to an embodiment of the present invention;
fig. 2 is an application scene diagram of individual differentiation by an ROC curve in the method for constructing a model for predicting the fall risk of a stroke patient according to the embodiment of the present invention;
fig. 3 is an application scene diagram of Calibration of a Calibration plot in a method for constructing a model for predicting the fall risk of a stroke patient according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a system for building a model for predicting the risk of falling of a stroke patient according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, a method for constructing a model for predicting a fall risk of a stroke patient according to an embodiment of the present invention includes the following steps:
step S1, determining falling risk factors of the stroke patient, and collecting relevant data of each risk factor; wherein the risk factors include common risk factors and special risk factors;
step S2, incorporating all risk factors into a Logistic regression equation to construct an initial prediction model of the falling risk of the stroke patient, and importing the acquired relevant data of each risk factor into the initial prediction model to obtain the falling incidence rate of the stroke patient;
and S3, constructing a dynamic nomogram prediction model of the falling risk of the stroke patient based on the falling incidence of the stroke patient and by combining a dynamic nomogram technology, and further verifying and calibrating the dynamic nomogram prediction model by adopting a preset verification mode and a preset calibration mode to obtain a final falling risk prediction model of the stroke patient.
Specifically, in step S1, first, risk factors of falling of the stroke patient are determined, where the risk factors include common risk factors and special risk factors. Wherein, common risk factors include but are not limited to the age of the patient, the peak time when the patient falls, the main place where the patient falls, etc.; specific risk factors include adverse effects of drug treatment and factors that the patient himself is affected by the disease. In this case, the adverse side effects of drug therapy further include, but are not limited to, adverse side effects of hypoglycemic drugs, adverse side effects of hypotensive drugs, adverse side effects of tranquilizers, and adverse side effects of anti-psychotic drugs; factors that the patient himself is affected by the disease may further include, but are not limited to, patient muscle tension imbalance, patient lateral movement disorder, patient visual field disorder, and patient visual field disorder.
Secondly, in order to enable the factors for constructing the model to be better close to and suitable for clinic, an organization expert forms a discussion group, the content of the scale is revised by adopting a brain storm method, a questionnaire of the falling risk factors of the stroke patient is formulated, and survey data collected by the questionnaire is input into computer equipment, so that the computer equipment can automatically analyze the relevant data of each risk factor.
In step S2, first, statistical analysis is performed on the collected data, the subjects are classified into a fall group and a non-fall group according to the occurrence of the event, and further, single factor analysis is performed on all risk factors, and if P is less than 0.05, it is stated that the difference is statistically significant.
Second, variables with significant differences, and special risk factors that make sense through literature review and clinical discussion even if there are no significant differences, are incorporated into the multi-factor Logistic regression analysis. Considering Logistic multiple collinearity problem, before analysis, tolerance (tolerance) and Variance Inflectionfactor (VIF) are adopted to carry out multiple collinearity test between variables, and according to the tolerance<0.10, variance expansion factor>The "multiple collinearity" criterion is reached at 10.0. The variable screening adopts backward stepwise regression to establish a mathematical model of the falling risk of each variable and a patient, so that a preliminary prediction model of the falling risk of the stroke patient is established: log itP ═ ln [ p/(1-p)]＝β 0 +β 1 χ 1 +β 2 χ 2 +Λβ n x n 。
And finally, importing the acquired relevant data of each risk factor into the initial prediction model to obtain the falling incidence rate P of the stroke patient:
Figure BDA0003546023370000051
in step S3, a dynamic nomogram prediction model of the fall risk of the stroke patient is first constructed based on the fall incidence of the stroke patient and using a network risk calculator developed by a dynanom software package (version 3.0.2; a statistical calculation basis, vienna, austria) in the R software.
And secondly, internally verifying the developed dynamic nomogram prediction model of the falling risk of the stroke patient by adopting a Bootstrap verification mode.
Next, model discrimination, i.e., the ability of the model to distinguish individuals who experienced an endpoint event from individuals who did not experience an endpoint event, was assessed by the area under the ROC curve (receiver operating characteristic curve) (AUC). A good prediction model can correctly distinguish the population according to the future morbidity risk, as shown in figure 2.
And finally, calibrating the developed dynamic nomogram prediction model of the falling risk of the stroke patient through a Hosmer-Lemeshow test mode or drawing a Calibration chart, thereby obtaining the final falling risk prediction model of the stroke patient. The calibration degree is an important index of the evaluation model for predicting the probability of the occurrence of the ending event of a certain individual in the future, and reflects the consistency degree of the predicted risk and the actual occurrence risk. The Calibration plot of Calibration plot is drawn according to the actual observed value and the model predicted value, and a linear trend line is fitted to obtain a Calibration curve, as shown in fig. 3.
As shown in fig. 4, in an embodiment of the present invention, a system for constructing a model for predicting a fall risk of a stroke patient includes:
the risk factor determining unit 110 is configured to determine a risk factor of a stroke patient falling, and acquire relevant data of each risk factor; wherein the risk factors include common risk factors and special risk factors;
the initial prediction model building unit 120 is configured to incorporate all risk factors into a Logistic regression equation to build an initial prediction model of the falling risk of the stroke patient, and import the acquired relevant data of each risk factor into the initial prediction model to obtain the falling incidence of the stroke patient;
and a final prediction model constructing unit 130, configured to construct a dynamic nomogram prediction model of the stroke patient falling risk based on the stroke patient falling incidence and by combining a dynamic nomogram technology, and further verify and calibrate the dynamic nomogram prediction model by using a preset verification manner and a preset calibration manner, so as to obtain a final stroke patient falling risk prediction model.
Wherein the common risk factors include age of the patient, peak time when the patient falls, and primary location where the patient falls;
the special risk factors include adverse effect factors of drug treatment and factors that the patient himself is affected by the disease; adverse effect factors of the drug therapy include adverse effects of hypoglycemic drugs, adverse effects of antihypertensive drugs, adverse effects of tranquilizers, and adverse effects of anti-psychotic drugs; factors that the patient is affected by the disease itself include patient muscle tension imbalance, patient lateral movement disorder, patient visual field disorder, and patient visual field abnormality.
And the preset verification mode is a Bootstrap verification mode.
The preset Calibration mode is a Hosmer-Lemeshow inspection mode or a mode of drawing a Calibration chart of Calibration in Calibration.
The embodiment of the invention has the following beneficial effects:
according to the invention, various falling risk factors of the stroke patient are taken into consideration and analyzed within a range, so that a final dynamic nomogram prediction model of the falling risk of the stroke patient is obtained, the visual analysis of the falling risk related scoring parameters of the stroke patient is realized, the values of the falling risk factor evaluations of the stroke patient are input, and the falling probability of the patient can be obtained through the dynamic nomogram, so that the clinical decision can be guided, and the falling time occurrence and the bad prognosis risk can be reduced.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by relevant hardware instructed by a program, and the program may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims (8)

1. A method for constructing a model for predicting the falling risk of a stroke patient is characterized by comprising the following steps:
determining falling risk factors of a stroke patient, and acquiring relevant data of each risk factor; wherein the risk factors include common risk factors and special risk factors;
all risk factors are incorporated into a Logistic regression equation to construct an initial prediction model of the falling risk of the stroke patient, and acquired relevant data of each risk factor is imported into the initial prediction model to obtain the falling incidence rate of the stroke patient;
and establishing a dynamic nomogram prediction model of the falling risk of the stroke patient based on the falling incidence of the stroke patient and by combining a dynamic nomogram technology, and further verifying and calibrating the dynamic nomogram prediction model by adopting a preset verification mode and a preset calibration mode to obtain a final falling risk prediction model of the stroke patient.
2. The method for constructing a model for predicting the fall risk of a stroke patient according to claim 1, wherein the common risk factors include the age of the patient, the peak time of the fall of the patient, and the main place of the fall of the patient;
the special risk factors include adverse effect factors of drug treatment and factors that the patient himself is affected by the disease; adverse effect factors of the drug therapy include adverse effects of hypoglycemic drugs, adverse effects of antihypertensive drugs, adverse effects of tranquilizers, and adverse effects of anti-psychotic drugs; factors that the patient is affected by the disease itself include patient muscle tension imbalance, patient lateral movement disorder, patient visual field disorder, and patient visual field abnormality.
3. The method for constructing a model for predicting the fall risk of a stroke patient according to claim 1, wherein the preset verification mode is a boottrap verification mode.
4. The method for constructing a model for predicting the fall risk of a stroke patient according to claim 1, wherein the preset Calibration mode is a mode of Calibration by means of a Hosmer-Lemeshow test or a mode of Calibration by drawing a Calibration plot.
5. A system for constructing a model for predicting the falling risk of a stroke patient is characterized by comprising the following steps:
the risk factor determining unit is used for determining falling risk factors of the stroke patient and acquiring relevant data of each risk factor; wherein the risk factors include common risk factors and special risk factors;
the initial prediction model building unit is used for bringing all risk factors into a Logistic regression equation to build an initial prediction model of the falling risk of the stroke patient, and importing the acquired relevant data of each risk factor into the initial prediction model to obtain the falling incidence of the stroke patient;
and the final prediction model building unit is used for building a dynamic nomogram prediction model of the falling risk of the stroke patient based on the falling incidence of the stroke patient and by combining a dynamic nomogram technology, and further verifying and calibrating the dynamic nomogram prediction model by adopting a preset verification mode and a preset calibration mode to obtain the final falling risk prediction model of the stroke patient.
6. The system for constructing a model for predicting the fall risk of a stroke patient according to claim 5, wherein the common risk factors include the age of the patient, the peak time of the fall of the patient, and the main location of the fall of the patient;
the special risk factors include adverse effect factors of drug treatment and factors that the patient himself is affected by the disease; adverse effect factors of the drug therapy include adverse effects of hypoglycemic drugs, adverse effects of antihypertensive drugs, adverse effects of tranquilizers, and adverse effects of anti-psychotic drugs; factors that the patient is affected by the disease itself include patient muscle tension imbalance, patient lateral movement disorder, patient visual field disorder, and patient visual field abnormality.
7. A system for constructing a model for predicting the fall risk of a stroke patient according to claim 5, wherein the preset verification mode is a Bootstrap verification mode.
8. The system for constructing a model for predicting the fall risk of a stroke patient according to claim 5, wherein the preset Calibration mode is a Hosmer-Lemeshow test mode or a Calibration mode of drawing a Calibration chart of Calibration.
CN202210248534.0A 2022-03-14 2022-03-14 Method and system for constructing model for predicting falling risk of stroke patient Pending CN114822838A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210248534.0A CN114822838A (en) 2022-03-14 2022-03-14 Method and system for constructing model for predicting falling risk of stroke patient

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210248534.0A CN114822838A (en) 2022-03-14 2022-03-14 Method and system for constructing model for predicting falling risk of stroke patient

Publications (1)

Publication Number Publication Date
CN114822838A true CN114822838A (en) 2022-07-29

Family

ID=82528562

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210248534.0A Pending CN114822838A (en) 2022-03-14 2022-03-14 Method and system for constructing model for predicting falling risk of stroke patient

Country Status (1)

Country Link
CN (1) CN114822838A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115813372A (en) * 2022-09-30 2023-03-21 天津大学 Stroke coordination stability motion function assessment device based on kinematic characteristics
CN117612713A (en) * 2023-10-08 2024-02-27 郑州大学 Intelligent analysis system and method for cerebral apoplexy behavior based on cloud computing

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115813372A (en) * 2022-09-30 2023-03-21 天津大学 Stroke coordination stability motion function assessment device based on kinematic characteristics
CN117612713A (en) * 2023-10-08 2024-02-27 郑州大学 Intelligent analysis system and method for cerebral apoplexy behavior based on cloud computing
CN117612713B (en) * 2023-10-08 2024-06-11 郑州大学 Intelligent analysis system and method for cerebral apoplexy behavior based on cloud computing

Similar Documents

Publication Publication Date Title
CN114822838A (en) Method and system for constructing model for predicting falling risk of stroke patient
Bagust et al. Modelling EuroQol health‐related utility values for diabetic complications from CODE‐2 data
Garcia-Aymerich et al. Identification and prospective validation of clinically relevant chronic obstructive pulmonary disease (COPD) subtypes
Siminoff et al. The cancer communication assessment tool for patients and families (CCAT‐PF): a new measure
Bode et al. Issues in the development of an item bank
CN110875087B (en) Chronic pulmonary disease management system
Chung et al. Development of the Korean developmental screening test for infants and children (K-DST)
Van Deventer et al. The diagnostic and prognostic utility of the dual-task tandem gait test for pediatric concussion
CN112908481B (en) Automatic personal health assessment and management method and system
Garrison et al. Emergency Medical Services Outcomes Project III (EMSOP III): the role of risk adjustment in out-of-hospital outcomes research
Stefan et al. How well do patients and providers agree on the severity of dyspnea?
Preston et al. The Brief Symptom Inventory and the Positive and Negative Syndrome Scale: Discriminate validity between a self-reported and observational measure of psychopathology
CN117476217B (en) Chronic heart disease state of illness trend prediction system
CN117316452A (en) Method and device for health assessment of hypertension and diabetes mellitus in closed-loop management scene
Spatz et al. Phenotypes of hypertensive ambulatory blood pressure patterns: Design and rationale of the ECHORN Hypertension Study
Chen et al. PREDICTIVE MODELING OF POSTOPERATIVE OUTCOMES
CN116861252A (en) Method for constructing fall evaluation model based on balance function abnormality
Fowler et al. Quality of object representations related to service utilization in a long-term residential treatment center.
KR101274431B1 (en) Apparatus and method for determining health using survey information, apparatus and method for generating health sort function
CN114550896A (en) Dizziness patient emergency pre-examination triage decision-making method, device and model based on artificial neural network
CN114093481A (en) System and method for opening and supervising resident health records
Madkour et al. Lifetime alcohol use trajectories and health status among persons living with HIV (PLWH)
Wilson et al. Preoperative 5-meter walk test as a predictor of length of stay after open heart surgery
Canal-Rivero et al. Insight trajectories and their impact on psychosocial functioning: A 10-year follow-up study in first episode psychosis patients.
Limpens et al. Physical activity and sedentary behaviour changes during and after cardiac rehabilitation: Can patients be clustered?

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