CN114121190A - Methods for establishing an early warning model for comorbid mood disorders in patients with chronic heart failure - Google Patents
Methods for establishing an early warning model for comorbid mood disorders in patients with chronic heart failure Download PDFInfo
- Publication number
- CN114121190A CN114121190A CN202010906399.5A CN202010906399A CN114121190A CN 114121190 A CN114121190 A CN 114121190A CN 202010906399 A CN202010906399 A CN 202010906399A CN 114121190 A CN114121190 A CN 114121190A
- Authority
- CN
- China
- Prior art keywords
- early warning
- data
- heart failure
- chronic heart
- warning model
- 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
- 206010007558 Cardiac failure chronic Diseases 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 27
- 208000019022 Mood disease Diseases 0.000 title claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 16
- 208000019901 Anxiety disease Diseases 0.000 claims abstract description 14
- 230000036506 anxiety Effects 0.000 claims abstract description 14
- 208000027534 Emotional disease Diseases 0.000 claims abstract description 11
- 238000010276 construction Methods 0.000 claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000010801 machine learning Methods 0.000 claims abstract description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 13
- 239000000523 sample Substances 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 10
- 201000010099 disease Diseases 0.000 claims description 9
- 208000024172 Cardiovascular disease Diseases 0.000 claims description 8
- 206010019280 Heart failures Diseases 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 7
- 101800000407 Brain natriuretic peptide 32 Proteins 0.000 claims description 6
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 claims description 6
- 230000002861 ventricular Effects 0.000 claims description 6
- 230000004970 emotional disturbance Effects 0.000 claims description 5
- 102400000667 Brain natriuretic peptide 32 Human genes 0.000 claims description 4
- 101800002247 Brain natriuretic peptide 45 Proteins 0.000 claims description 4
- 108010074051 C-Reactive Protein Proteins 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 108010008064 pro-brain natriuretic peptide (1-76) Proteins 0.000 claims description 4
- 102100032752 C-reactive protein Human genes 0.000 claims description 3
- 206010020751 Hypersensitivity Diseases 0.000 claims description 3
- 238000008050 Total Bilirubin Reagent Methods 0.000 claims description 3
- 230000001746 atrial effect Effects 0.000 claims description 3
- 235000012000 cholesterol Nutrition 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000013501 data transformation Methods 0.000 claims description 3
- 238000013524 data verification Methods 0.000 claims description 3
- 230000004217 heart function Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 108010023302 HDL Cholesterol Proteins 0.000 claims description 2
- 102000001554 Hemoglobins Human genes 0.000 claims description 2
- 108010054147 Hemoglobins Proteins 0.000 claims description 2
- 238000013145 classification model Methods 0.000 claims description 2
- 235000006694 eating habits Nutrition 0.000 claims description 2
- 230000000391 smoking effect Effects 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 4
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000013480 data collection Methods 0.000 abstract 1
- 238000011160 research Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 5
- 208000035475 disorder Diseases 0.000 description 4
- 230000008451 emotion Effects 0.000 description 3
- 208000017667 Chronic Disease Diseases 0.000 description 2
- 102000015225 Connective Tissue Growth Factor Human genes 0.000 description 2
- 108010039419 Connective Tissue Growth Factor Proteins 0.000 description 2
- 230000000994 depressogenic effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000474 nursing effect Effects 0.000 description 2
- 102400001263 NT-proBNP Human genes 0.000 description 1
- 108020001621 Natriuretic Peptide Proteins 0.000 description 1
- 102000004571 Natriuretic peptide Human genes 0.000 description 1
- 206010033372 Pain and discomfort Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012472 biological sample Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013278 delphi method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013209 evaluation strategy Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 108010022197 lipoprotein cholesterol Proteins 0.000 description 1
- 238000010197 meta-analysis Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003183 myoelectrical effect Effects 0.000 description 1
- 239000000692 natriuretic peptide Substances 0.000 description 1
- HPNRHPKXQZSDFX-OAQDCNSJSA-N nesiritide Chemical group C([C@H]1C(=O)NCC(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CC(O)=O)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@H](C(N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)NCC(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)N[C@@H](CSSC[C@@H](C(=O)N1)NC(=O)CNC(=O)[C@H](CO)NC(=O)CNC(=O)[C@H](CCC(N)=O)NC(=O)[C@@H](NC(=O)[C@H](CCSC)NC(=O)[C@H](CCCCN)NC(=O)[C@H]1N(CCC1)C(=O)[C@@H](N)CO)C(C)C)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CC=1N=CNC=1)C(O)=O)=O)[C@@H](C)CC)C1=CC=CC=C1 HPNRHPKXQZSDFX-OAQDCNSJSA-N 0.000 description 1
- 230000004007 neuromodulation Effects 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 108090000765 processed proteins & peptides Proteins 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- 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
- 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
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Primary Health Care (AREA)
- Psychiatry (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
本发明涉及智能机器学习和数据处理技术领域。本发明公开了一种建立慢性心力衰竭患者共病情绪障碍早期预警模型的方法，包括如下步骤：a、构建慢性心力衰竭患者抑郁和焦虑构建险指标体系；该步骤包括基本信息收集及量表评估；b、构建慢性心力衰竭患者共病情绪障碍的风险综合评估与预警模型；该步骤包括数据采集和预警模型构建。本发明针对危险因素，采用数据挖掘，筛选出主要的风险因子，并建立严谨的风险预警模型，能达到早期发现、有效预防，对慢性心力衰竭患者共病情绪障碍的防控具有指导性作用及实际意义。The invention relates to the technical field of intelligent machine learning and data processing. The invention discloses a method for establishing an early warning model for comorbid mood disorders in patients with chronic heart failure, comprising the following steps: a. constructing a risk index system for depression and anxiety in patients with chronic heart failure; the step includes basic information collection and scale evaluation b. Build a risk comprehensive assessment and early warning model for comorbid mood disorders in patients with chronic heart failure; this step includes data collection and early warning model construction. The invention aims at risk factors, adopts data mining to screen out main risk factors, and establishes a rigorous risk early warning model, which can achieve early detection and effective prevention, and has a guiding role in the prevention and control of comorbid emotional disorders in patients with chronic heart failure. practical meaning.
Description
Technical Field
The invention relates to the technical field of intelligent machine learning and data processing, in particular to relevant data processing and early warning model construction for chronic heart failure patients, and particularly relates to a method for establishing an early warning model for chronic heart failure patients with common-illness state disorder.
Background
Chronic heart failure presents a situation of high morbidity, high hospitalization rate, high fatality rate and heavy social and economic burden, so that the chronic heart failure is becoming a serious public health problem in China. Chronic heart failure not only causes physical pain and discomfort to the patient, but also causes great psychomental stress to the patient and the family, and even causes emotional disorder to the patient. Meta analysis of Chinese patients with depression showed an incidence of approximately 40.1%. Earlier researches find that the death risk of chronic heart failure patients with moderate and severe depression is 4.9 times higher than that of patients without combined depression, so that the mood disorder not only can influence the occurrence, development, treatment effect and life quality of diseases of the chronic heart failure patients, but also can increase the hospitalization rate and death rate, and influence the prognosis of the patients.
In recent years, medical data and artificial intelligence are continuously accumulated and developed to provide powerful resources and means for the management of patients with heart failure and emotional disorder. The chinese patent 111063453 collects daily physiological data of a patient through a cloud platform, and proposes an electrocardiographic data correlation analysis and a time series-based physiological index similarity evaluation strategy that uniformly describe characteristics of a large amount of medical data and satisfy complex semantics, thereby performing early detection and early warning of heart failure.
Chinese patent 109394203 is a device in which an electrocardiographic sensor is used to collect electrocardiographic signals of a patient, an electromyographic sensor is used to collect electromyographic signals of the patient, and a voice collecting assembly is used to collect voice signals around the patient; the controller transmits the collected electrocardiosignals and myoelectric signals to the intelligent terminal through the communication assembly, carries out pretreatment and corresponding characteristic value extraction to obtain emotion related characteristic values, and compares the emotion related characteristic values with a preset emotion recognition model to obtain a real-time emotion state monitoring method. Chinese patent 107922485 is a diagnostic method for determining whether an individual has or is at risk of developing an emotional disorder by detecting the expression level of Connective Tissue Growth Factor (CTGF) in a biological sample from the individual.
None of the above approaches address the problem of comorbidity in patients with chronic heart failure, and studies in this area have been omitted. The influence factors of the chronic heart failure patients suffering from the common condition disorder relate to population, biochemistry, immunity, neuromodulation, psychology and the like, and the early comprehensive analysis of risk factors and early warning intervention are very important. At present, no early, intelligent and scientific early warning system for the co-morbid state and emotional disorder of chronic heart failure patients exists in China.
Disclosure of Invention
The invention mainly aims to provide a method for establishing an early warning model of the co-morbid state and the emotional disturbance of the chronic heart failure patients, which establishes the early warning model of the co-morbid state and the emotional disturbance of the chronic heart failure patients by utilizing a machine learning technology and big data processing and provides a feasible basis for early intervention of the co-morbid state and the emotional disturbance of the chronic heart failure patients.
To achieve the above object, according to an aspect of embodiments of the present invention, there is provided a method for establishing an early warning model of a co-morbid state and a mood disorder of a patient with chronic heart failure, the method comprising the steps of:
a. constructing a depression and anxiety risk index system for chronic heart failure patients;
the method comprises the following steps of basic information collection and scale evaluation:
the basic information comprises social and demographic data, disease related information, biochemical indexes and physical examination results;
the scales include a depression self-rating scale, an anxiety self-rating scale, and a minnesota heart failure quality of life questionnaire;
b. constructing a risk comprehensive assessment and early warning model of the co-morbid state and emotional disorder of the chronic heart failure patient;
the method comprises the steps of data acquisition and early warning model construction;
the data acquisition comprises data source selection, data selection and data processing;
the construction of the early warning model comprises the steps of taking a certain percentage of total samples as a sample set, and establishing the early warning model through machine learning and big data processing.
Further, the social demographic data comprises the age, sex, cultural degree, marital status, smoking history, eating habits, exercise habits, income level, social support of the patient; the disease-related information comprises height, weight and body mass index of the patient; the disease course of heart failure, the history of major cardiovascular diseases and other non-cardiovascular diseases and the grading of heart functions; the biochemical indicators and physical examination results comprise BNP, hemoglobin, total bilirubin, total cholesterol, high-density lipoprotein cholesterol, heart rate variability, left ventricular inside diameter, left atrial inside diameter, left ventricular ejection fraction; b-type natriuretic peptide, amino-terminal pro-brain natriuretic peptide, hypersensitive C-reactive protein, and soluble ST 2.
Further, the data source comprises a medical record file and a historical data record; the data selection is to perform interactive query and data analysis mainly by using a Spark platform, and an Oracle database is used as an auxiliary probe and data verification; the data processing adopts functional operation programming of a kernel abstract data set Rdd of Spark and structured programming of a Date Frame object in a Spark SQL component, and realizes the data extraction task in Spark SQL language.
Further, the data processing further comprises data preprocessing, data cleaning, data integration, data transformation and data specification, and relevant data are screened out.
Further, the early warning model is specifically constructed by taking 70% of total samples as a sample set, based on chronic heart failure common illness state disorder events, utilizing Spark mlib library, respectively adopting Logistic regression and naive Bayes classification model algorithms, selecting an optimal model according to AUC value, and establishing a risk early warning model with the time length of 1 year.
Further, the construction of the early warning model comprises the steps of constructing a multi-factor Logistic regression model, solving the posterior maximum probability through Bayesian theorem, determining a risk early warning critical point and formulating an early warning mechanism.
According to the technical scheme of the invention and the technical scheme of further improvement in certain embodiments, the invention has the following beneficial effects:
aiming at the risk factors, the invention screens out main risk factors by adopting data mining and establishes a strict risk early warning system, can achieve early discovery and effective prevention, and has guiding function and practical significance for preventing and controlling emotional disorders of patients with chronic heart failure.
Detailed Description
It should be noted that the specific embodiments, examples and features thereof may be combined with each other in the present application without conflict.
In order to make the technical solution of the present invention better understood, the technical solution of the present invention will be clearly and completely described below with reference to the specific embodiments and examples of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments and examples obtained by a person skilled in the art without any inventive step should fall within the protection scope of the present invention.
The method for establishing the early warning model of the co-morbid state and mood disorder of the chronic heart failure patient can realize quick and early evaluation and warning of the mood disorder risk of the patient, thereby carrying out early prevention and intervention. The technical scheme comprises the following steps: constructing a depression and anxiety risk index system for patients with chronic heart failure; ② the risk comprehensive evaluation and early warning model construction of chronic heart failure patients with illness state and mood disorder.
Construction of an index system for depression and anxiety risk of patients with chronic heart failure
The incidence and influence factor research of depression and anxiety of chronic heart failure patients. Patients meeting the study inclusion standard are subjected to basic information collection and scale evaluation after the stable state of the disease on days 1-2 after admission.
Social demographic data a, including: a1-patient age, A2-gender, A3-cultural degree, A4-marital status, A5-smoking history, A6-dietary habit, A7-exercise habit, A8-income level, A9-social support;
disease-related information B, including: b1-height, B2-weight, B3-body mass index; b4-course of heart failure, B5-history of major cardiovascular disease, B6-history of other non-cardiovascular disease, B7-grading of cardiac function;
biochemical indicators and physical examination results C, including: c1-type B natriuretic peptide (B-type natrietic peptide, BNP, C2-hemoglobin, C3-total bilirubin, C4-total cholesterol, C5-high density lipoprotein cholesterol, C6-heart rate variability, C7-left ventricular internal diameter, C8-left atrial internal diameter, C9-left ventricular ejection fraction, C10-E/E', C11-amino terminal brain natriuretic peptide precursor (N-terminal-proBNP, NT-proBNP), C12-hypersensitive C reactive protein (hs-CRP), C13-soluble ST2(soluble ST2, s ST 2);
depression self-rating scale D;
anxiety self-rating scale F;
minnesota quality of life heart failure questionnaire G.
And (4) statistically processing all data by adopting SPSS23.0 statistical software to obtain the risk factors of the emotional disorder of the chronic heart failure patient.
Secondly, constructing an index system of depression and anxiety risks of patients with chronic heart failure.
The method comprises the steps of firstly carrying out discretization classification on patient data, then constructing a decision table, and finally carrying out attribute reduction on the decision table based on an information entropy algorithm to screen out risk indexes.
(1) Discretizing classification, namely setting dis as (Fmax-Fmin)/3, wherein Fmax corresponds to the maximum value of the indexes, and Fmin corresponds to the minimum value of the indexes; indexes (including A2, A3, A4, A5, A6, A7, A8, A9, B5, B6 and B7) to be discretized are divided into 3 types, wherein 1 represents (Fmin +2 x dis, Fmax), 2 represents (Fmin + dis, Fmin +2 x dis) and 3 represents (Fmin, Fmin + dis).
(2) The method comprises the steps of constructing a decision table, wherein the decision table comprises an object set (research samples, U & ltX & gt 1, X & ltX & gt 2 & gt. & gt, Xn, wherein X1, X & ltX & gt 2 & gt. & gt, Xn represents each sample in the samples), an attribute set (condition attributes C & ltF & gt 1, F2 & gt. & gt, Fn, namely risk indexes, F1, F2 & ltF & gt. & gt, and Fn represent each index of the samples, namely an A-G index, and a decision attribute set D & ltD & gt 1, D2 & ltright. & gt, Dn, namely whether the research objects to be participated in are depressed and anxious or not, D1, D2 & ltD & gt, and Dn represents whether each research object is depressed or anxious or not, namely ending, and n is the number of the samples.
(3) Decision table attribute reduction: from the original variable set (including all data from a to G), variables with null rate (number of nulls/total number) > 80% were excluded and the remaining variables were reduced.
(4) And (3) inviting 15 experts with more than 10 years of working experience, academic records and higher titles in relevant working fields of chronic disease management, cardiovascular diseases, psychological consultation, nursing management and the like to participate in the study of the depression and anxiety risk indexes of the chronic heart failure patients in a field interview mode to finally establish the index content.
Examples
Establishment of chronic heart failure patient common state of illness obstacle early warning model
And (6) data acquisition and processing. a. The data source is as follows: the historical data of hospital case history files such as a third-level medical record in Sichuan province and the like relates to 5 ten thousand, and the total number of the medical data files exceeds 9000 ten thousand medical data records. b. Data selection: according to the characteristics of big data, interactive query and data analysis are carried out by taking a Spark platform as a main part, and an Oracle database is used as an auxiliary probe and data verification. In the research, the data processing mainly takes chronic heart failure and emotional disorder caused by the chronic heart failure as research targets, and medical knowledge as guidance, and field attributes irrelevant to mining targets are discarded. c. Data processing: and adopting functional operation programming of a kernel abstract data set Rdd of Spark and structured programming of a Date Frame object in a Spark SQL component, and realizing a data extraction task in Spark SQL language. And screening out data relevant to the research through data preprocessing, data cleaning, data integration, data transformation and data protocols.
Constructing an early warning model: taking 70% of the total sample as a sample set, based on chronic heart failure common-illness-condition-disorder events, selecting an optimal model by utilizing Spark Mllib library and respectively adopting Logistic regression, and establishing a 1-year-long risk early warning model.
And (3) constructing a multi-factor Logistic regression model, namely taking whether depression and anxiety occur as dependent variables, and taking the risk index of the co-morbid state and mood disorder of the chronic heart failure patient as an independent variable to be included in the Logistic regression model, so as to estimate the regression coefficient, the relative risk and a 95% confidence interval of each risk factor.
Classifying the risk factors and determining the value of each classification, namely cutting and grouping continuous variables, and taking a group median as a reference value; the classification variable sets a dummy variable, coded 0, 1.
And determining the basic risk reference values of all the risk factors, wherein if a certain risk factor of the patient takes the value as the value, the risk is scored as 0, and the higher the score is, the higher the risk is.
The distance D of each risk factor's classification from the underlying risk is calculated as measured in units of a regression coefficient multiplied by the group spacing.
A unit distance B of 1 minute is set.
The classification of each risk factor is scored as D/B.
Determining risk early warning critical point and making early warning mechanism
Determining the maximum johnson index through sensitivity and specificity to determine the critical points of occurrence of depression and anxiety, selecting 3 critical points (a, b and c) in the example, and finally determining the prediction probability of the occurrence of depression and anxiety through a Delphi method to achieve the score of a as low-risk early warning, b as medium-risk early warning, c as high-risk early warning and the intervention method of each early warning grade.
The expert screening standard comprises that the relevant working fields of chronic disease management, cardiovascular diseases, psychological consultation, nursing management and the like have more than 10 years of working experience, academic records and higher vocational titles and have higher enthusiasm for the project, and the expert screening standard can feed back the function inquiry result and answer the problem in time; the number of the experts is more than or equal to 15, and the early warning mechanism is formulated through 2-4 rounds of expert consultation.
Three indexes of sensitivity, specificity and john's index are indexes for evaluating the authenticity of the screening method.
The sensitivity is also called sensitivity, and refers to the proportion of patients which can be correctly judged by a screening method;
specificity is the proportion of people who are actually non-sick and can be correctly judged as non-sick by a screening method;
youden index (Youden index), also called the correct index, is a method for evaluating the authenticity of screening tests, and can be applied when the harmfulness of false negatives (missed diagnosis rate) and false positives (misdiagnosis rate) is assumed to be of equal significance. The jotan index is the sum of sensitivity and specificity minus 1. Indicating that the screening method finds true patient and non-patient total ability. The larger the index, the better the screening experiment and the greater the authenticity.
Claims (6)
1. The method for establishing the early warning model of the chronic heart failure patient with the common condition and the handicap is characterized by comprising the following steps of:
a. constructing a depression and anxiety risk index system for chronic heart failure patients;
the method comprises the steps of basic information collection and scale evaluation;
the basic information comprises social and demographic data, disease related information, biochemical indexes and physical examination results;
the scales include a depression self-rating scale, an anxiety self-rating scale, and a minnesota heart failure quality of life questionnaire;
b. constructing a risk comprehensive assessment and early warning model of the co-morbid state and emotional disorder of the chronic heart failure patient;
the method comprises the steps of data acquisition and early warning model construction;
the data acquisition comprises data source selection, data selection and data processing;
the construction of the early warning model comprises the steps of taking a certain percentage of total samples as a sample set, and establishing the early warning model through machine learning and big data processing.
2. The method for establishing an early warning model of chronic heart failure patient's comorbidity as in claim 1, wherein the socio-demographic data includes patient age, gender, cultural degree, marital status, smoking history, eating habits, exercise habits, income level, social support; the disease-related information comprises height, weight and body mass index of the patient; the disease course of heart failure, the history of major cardiovascular diseases and other non-cardiovascular diseases and the grading of heart functions; the biochemical indicators and physical examination results include BNP, hemoglobin, total bilirubin, total cholesterol, high density lipoprotein cholesterol, heart rate variability, left ventricular inside diameter, left atrial inside diameter, left ventricular ejection fraction, B-type natriuretic peptide, amino terminal pro-brain natriuretic peptide, hypersensitive C reactive protein, soluble ST 2.
3. The method of claim 1, wherein the data sources include medical records, historical data records; the data selection is to perform interactive query and data analysis mainly by using a Spark platform, and an Oracle database is used as an auxiliary probe and data verification; the data processing adopts functional operation programming of a kernel abstract data set Rdd of Spark and structured programming of a Date Frame object in a Spark SQL component, and realizes the data extraction task in Spark SQL language.
4. The method for establishing an early warning model of chronic heart failure patient co-morbid mood disorder according to claim 3, wherein the data processing further comprises data preprocessing, data cleaning, data integration, data transformation, data reduction, and screening out relevant data.
5. The method for establishing the early warning model for the comorbid condition and emotional disturbance of the chronic heart failure patients according to claim 1, wherein the early warning model is specifically established by taking 70% of total samples as a sample set, based on the comorbid condition and emotional disturbance events of the chronic heart failure, respectively adopting Logistic regression and naive Bayes classification model algorithms by using a Spark Mllib library, and selecting an optimal model according to an AUC value to establish a risk early warning model with the duration of 1 year.
6. The method for establishing the early warning model of the co-morbid state and emotional disorder of the chronic heart failure patients according to claim 5, wherein the early warning model establishment comprises establishing a multi-factor Logistic regression model, solving the posterior maximum probability through Bayesian theorem, determining the risk early warning critical point and establishing an early warning mechanism.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010906399.5A CN114121190A (en) | 2020-09-01 | 2020-09-01 | Methods for establishing an early warning model for comorbid mood disorders in patients with chronic heart failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010906399.5A CN114121190A (en) | 2020-09-01 | 2020-09-01 | Methods for establishing an early warning model for comorbid mood disorders in patients with chronic heart failure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114121190A true CN114121190A (en) | 2022-03-01 |
Family
ID=80360463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010906399.5A Pending CN114121190A (en) | 2020-09-01 | 2020-09-01 | Methods for establishing an early warning model for comorbid mood disorders in patients with chronic heart failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114121190A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116403718A (en) * | 2023-06-08 | 2023-07-07 | 中国医学科学院阜外医院 | Method, device, equipment and storage medium for constructing physiological index prediction model |
| CN119033348A (en) * | 2024-11-04 | 2024-11-29 | 吉林大学 | Nerve vessel postoperative patient safety monitoring method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106132286A (en) * | 2014-03-07 | 2016-11-16 | 心脏起搏器股份公司 | Multistage heart failure event detection |
| CN106897566A (en) * | 2017-02-28 | 2017-06-27 | 北京积水潭医院 | A kind of construction method and device of risk prediction model |
| CN107358047A (en) * | 2017-07-13 | 2017-11-17 | 刘峰 | Diabetic assesses and management system |
| CN109219854A (en) * | 2016-06-10 | 2019-01-15 | 心脏起搏器股份公司 | Patient risk's scoring and assessment system |
| CN110301899A (en) * | 2019-07-01 | 2019-10-08 | 湘南学院附属医院 | A kind of cardiovascular and cerebrovascular disease information detecting system and method |
| CN111081334A (en) * | 2019-12-18 | 2020-04-28 | 鲁东大学 | An early warning method for chronic diseases based on probabilistic combination analysis of risk factors |
| CN111081381A (en) * | 2019-11-08 | 2020-04-28 | 李静 | Intelligent screening method for critical indexes of prediction of nosocomial fatal gastrointestinal rebleeding |
-
2020
- 2020-09-01 CN CN202010906399.5A patent/CN114121190A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106132286A (en) * | 2014-03-07 | 2016-11-16 | 心脏起搏器股份公司 | Multistage heart failure event detection |
| CN109219854A (en) * | 2016-06-10 | 2019-01-15 | 心脏起搏器股份公司 | Patient risk's scoring and assessment system |
| CN106897566A (en) * | 2017-02-28 | 2017-06-27 | 北京积水潭医院 | A kind of construction method and device of risk prediction model |
| CN107358047A (en) * | 2017-07-13 | 2017-11-17 | 刘峰 | Diabetic assesses and management system |
| CN110301899A (en) * | 2019-07-01 | 2019-10-08 | 湘南学院附属医院 | A kind of cardiovascular and cerebrovascular disease information detecting system and method |
| CN111081381A (en) * | 2019-11-08 | 2020-04-28 | 李静 | Intelligent screening method for critical indexes of prediction of nosocomial fatal gastrointestinal rebleeding |
| CN111081334A (en) * | 2019-12-18 | 2020-04-28 | 鲁东大学 | An early warning method for chronic diseases based on probabilistic combination analysis of risk factors |
Non-Patent Citations (3)
| Title |
|---|
| 谷鸿秋: "危险因素评分预测模型是怎么倒腾出来的？", vol. 2, pages 246 - 144, Retrieved from the Internet <URL:http://paper.dxy.cn/article/503262> * |
| 马丽娜: "慢性心力衰竭患者情绪障碍的相关研究" * |
| 马丽娜: "慢性心力衰竭患者情绪障碍的相关研究", 中国优秀硕士学位论文全文数据库医药卫生科技辑, no. 08, pages 7 - 10 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116403718A (en) * | 2023-06-08 | 2023-07-07 | 中国医学科学院阜外医院 | Method, device, equipment and storage medium for constructing physiological index prediction model |
| CN116403718B (en) * | 2023-06-08 | 2023-09-01 | 中国医学科学院阜外医院 | Method, device, equipment and storage medium for constructing physiological index prediction model |
| CN119033348A (en) * | 2024-11-04 | 2024-11-29 | 吉林大学 | Nerve vessel postoperative patient safety monitoring method and system |
| CN119033348B (en) * | 2024-11-04 | 2025-01-21 | 吉林大学 | Nerve vessel postoperative patient safety monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tutuko et al. | AFibNet: an implementation of atrial fibrillation detection with convolutional neural network | |
| CN111430029A (en) | Multi-dimensional stroke prevention screening method based on artificial intelligence | |
| CN109920547A (en) | A method for constructing diabetes prediction model based on data mining of electronic medical records | |
| CN113744869B (en) | Method for establishing early screening light chain type amyloidosis based on machine learning and application thereof | |
| Exarchos et al. | Supervised and unsupervised machine learning for automated scoring of sleep–wake and cataplexy in a mouse model of narcolepsy | |
| Kanwade et al. | Combined weighted feature extraction and deep learning approach for chronic obstructive pulmonary disease classification using electromyography | |
| CN114121190A (en) | Methods for establishing an early warning model for comorbid mood disorders in patients with chronic heart failure | |
| CN116584893A (en) | Epileptic signal detection method based on channel selection time convolution network | |
| Selvakumar et al. | Decision support system for type II diabetes and its risk factor prediction using bee-based harmony search and decision tree algorithm | |
| Veena et al. | An automated pre-term prediction system using EHG signal with the aid of deep learning technique | |
| Sharma et al. | Mortality Prediction of ICU patients using Machine Leaning: A survey | |
| CN119385526B (en) | Intelligent diagnosis wearable device for acute myocardial infarction based on structural causal model | |
| CN115019958B (en) | A method and device for detecting abnormal cases | |
| Arslan | Sleep disorder and apnea events detection framework with high performance using two-tier learning model design | |
| CN119541840A (en) | Intelligent remote follow-up method and system for tumor patients | |
| Blessie et al. | Novel approach for psychiatric patient detection and prediction using data mining techniques | |
| CN117153422B (en) | Early sepsis detection device based on deep learning and ChatGPT | |
| Li et al. | Classification of resting state EEG data in patients with depression | |
| Patil et al. | Logistic regression based model for pain intensity level detection from biomedical signal | |
| Rahman et al. | Application of artificial neural network and binary logistic regression in detection of diabetes status | |
| Byeon | Predicting the anxiety of patients with alzheimer’s dementia using boosting algorithm and data-level approach | |
| CN116844720A (en) | Intelligent monitoring and management system for elderly frailty health | |
| Muthulakshmi et al. | Big Data Analytics for Heart Disease Prediction using Regularized Principal and Quadratic Entropy Boosting | |
| Anusha et al. | Heart disease prediction using ML and DL approaches | |
| Zhao et al. | A CNN-based method for depression detecting form audio |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220301 |
|
| RJ01 | Rejection of invention patent application after publication |