D-type personality prediction method and system based on millimeter wave radar

Abstract

The invention relates to a D-type personality prediction method and system based on millimeter wave radar, and the method comprises the steps: collecting the human body heart rate variability HRV data of a target patient through the millimeter wave radar when the target patient is diagnosed with the coronary heart disease, and carrying out the short-time frequency domain analysis of the HRV data, and obtaining the frequency domain index parameters of the target patient; predicting whether the target patient is D-type personality according to a preset D-type personality prediction algorithm and the frequency domain index parameters; and if the target patient has the D-type personality, performing coronary heart disease prognosis on the target patient according to the D-type personality. According to the method, non-contact HRV data acquisition of a coronary heart disease patient is realized by using a millimeter wave radar, and after short-time frequency domain analysis is performed on the HRV data, frequency domain index parameters for D-type personality prediction are obtained, so that D-type personality prediction is realized. Compared with the existing scale evaluation, the accuracy is higher, and the disease prognosis of the coronary heart disease patient with the D-type personality can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of medical technology, and in particular relates to a method and system for predicting type D personality based on millimeter wave radar. Background Art

[0002] Millimeter wave radar is a device that uses electromagnetic wave frequencies in the millimeter wave band. It can emit electromagnetic waves to the target and receive electromagnetic waves reflected by the target. In the field of medical health monitoring, millimeter wave radar has attracted widespread attention because of its non-contact detection method. Type D personality (Distressed Personality Type), also known as "distressed personality", is a psychological trait whose core characteristics include persistent negative emotions and social inhibition. Type D personality is of great significance in the medical field, especially in the research and treatment of coronary heart disease. "Disease prognosis" refers to the prediction of the future course and outcome of the disease after the disease occurs, such as recovery, recurrence, deterioration, disability, complications and death. Studies have shown that individuals with type D personality traits are more likely to suffer from coronary heart disease, and their mortality rate is significantly higher than that of other types of personality. Early identification and intervention of type D personality is crucial to improving the prognosis of patients with coronary heart disease and improving the overall treatment effect.

[0003] In the existing technology, clinicians pay more and more attention to the assessment of type D personality in patients with coronary heart disease, so as to identify high-risk patients early and reduce the mortality rate and the incidence of complications. However, in the existing medical and psychological fields, the DS16 scale (Distress Scale 16) is usually used to assess type D personality, which relies on manual operation of coronary heart disease patients and doctors. That is, the prediction of type D personality in the existing technology has the technical problems of high manpower and time costs and insufficient estimation accuracy. Summary of the invention

[0004] In order to make up for the defects of the prior art, the present invention provides a method and system for predicting type D personality based on millimeter wave radar. Compared with the prior art, the application of technical means such as millimeter wave radar can greatly improve the accuracy of type D personality prediction and save manpower and time costs.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] In a first aspect, a method for predicting type D personality based on millimeter wave radar is provided, comprising:

[0007] When the target patient is diagnosed with coronary heart disease, the millimeter wave radar is used to collect the target patient's human heart rate variability HRV data, and the HRV data is analyzed in the short-term frequency domain to obtain the target patient's frequency domain index parameters;

[0008] Predict whether the target patient has type D personality based on the preset type D personality prediction algorithm and frequency domain index parameters;

[0009] If the target patient has type D personality, the prognosis of coronary heart disease will be conducted for the target patient according to type D personality.

[0010] Furthermore, the human heart rate variability HRV data of the target patient is collected by using a millimeter wave radar, and the HRV data is subjected to a short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient, including the following steps:

[0011] Adjust the target patient to a resting state, and use the millimeter wave radar to detect and record the HRV data of the target patient in the resting state. x1 , x1 Indicates resting state;

[0012] HRV is analyzed by regression or fast Fourier transform. x1 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the resting state. The frequency domain index parameters include the total power TP in the resting state. x1 , Very Low Frequency Band Power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x1 and normalized high frequency band power HFnorm x1 , normalized low-frequency band power , normalized high-frequency band power

[0013] Further, predicting whether the target patient has a type D personality based on a preset type D personality prediction algorithm and frequency domain index parameters includes:

[0014] The calculation formula for obtaining the preset D-type personality prediction algorithm in the resting state is:

[0015] Type D personality prediction value S x1 =(TP x1 -TP1)+(VLF x1 -VLF1)+(LF x1 -LF1);

[0016] TP1 represents the average total power of a large number of non-type D personality patients in the resting state;

[0017] VLF1 represents the average very low frequency band power of a large number of non-type D personality patients in the resting state;

[0018] LF1 represents the average low-frequency band power of a large number of non-type D personality patients in the resting state;

[0019] When S x1 When ≥0, the target patient in the resting state is judged to be a non-type D personality;

[0020] When S x1 <0 and (TP x1 -TP1)<0、(VLF x1 -VLF1)<0 and (LF x1 -LF1)<0, the target patient is judged to be type D personality in the resting state.

[0021] Furthermore, after determining that the target patient in the resting state is a non-type D personality, the method further includes the following steps:

[0022] Adjust the target patient to enter the abdominal breathing state, and use the millimeter wave radar to detect and record the HRV data of the target patient in the abdominal breathing state x2 , x2 Indicates abdominal breathing state;

[0023] HRV is analyzed by regression or fast Fourier transform. x2 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient under abdominal breathing state. The frequency domain index parameters include the total power TP under abdominal breathing state. x2 , Very Low Frequency Band Power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x2 and normalized high frequency band power HFnorm x2 , normalized low-frequency band power Normalized high-band power

[0024] The calculation formula for obtaining the preset D-type personality prediction algorithm under abdominal breathing state is:

[0025] Type D personality prediction value S x2 =(TP x2 -TP2)+(HF x2 -HF2);

[0026] TP2 represents the average total power of a large number of non-type D personality patients under abdominal breathing, and HF2 represents the average high-frequency band power of a large number of non-type D personality patients under abdominal breathing;

[0027] When S x2 When ≥0, the target patient in the abdominal breathing state is judged to be a non-type D personality;

[0028] When Sx2 <0 and (TP x2 -TP2)<0 and (HF x2 -HF2)<0, the target patient is judged to be type D personality in the abdominal breathing state.

[0029] Furthermore, after determining that the target patient in the resting state is a non-type D personality, the method further includes the following steps:

[0030] Adjust the target patient to enter the passive stress state after rest, and use millimeter wave radar to detect and record the HRV data of the target patient in the passive stress state after rest x3 , x3 It indicates the passive stress state after rest;

[0031] HRV is analyzed by regression or fast Fourier transform. x3 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the passive stress state after rest. The frequency domain index parameters include the total power TP in the passive stress state after rest. x3 , Very Low Frequency Band Power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x3 and normalized high frequency band power HFnorm x3 , normalized low-frequency band power Normalized high-band power

[0032] The calculation formula for obtaining the preset D-type personality prediction algorithm under the passive stress state after rest is:

[0033]

[0034] S x3_2 =(HFnorm3-HFmorm x3 );

[0035] represents the average low-frequency / high-frequency ratio of a large number of non-type D personality patients in the passive stress state after rest; LFnorm3 represents the average normalized low-frequency band power of a large number of non-type D personality patients in the passive stress state after rest; HFnorm3 represents the average normalized high-frequency band power of a large number of non-type D personality patients in the passive stress state after rest;

[0036] When S x3_1 <0、 and (LFnorm3-LFnorm x3 )<0, and S x3_2>0, the target patient in the passive stress state after rest is judged to be type D personality;

[0037] When S x3_1 ≥0 or S x3_2 When ≤0, the target patient in the passive stress state after rest is judged as non-type D personality.

[0038] Further, after determining that the target patient in the abdominal breathing state is a non-type D personality, the method further includes the following steps:

[0039] Adjust the target patient to enter the passive stress state after abdominal breathing, and use millimeter wave radar to detect and record the HRV data before entering the passive stress state after abdominal breathing. 前 , and the HRV data after entering the passive stress state after abdominal breathing 后 ;

[0040] The calculation formula for the change of HRV data before and after is:

[0041] ΔHRV=HRV 后 -HRV 前 ;

[0042] When |ΔHRV|>H, the target patient is judged to be type D personality, and H is the preset threshold;

[0043] When |ΔHRV|≤H, the target patient is judged to be a non-type D personality.

[0044] Furthermore, the method also includes:

[0045] After determining that the target patient has type D personality, obtain the type D personality test scale information of the target patient;

[0046] If the target patient is inferred to have a Type D personality based on the Type D personality test scale information, then the prediction result is accurate;

[0047] If the target patient is inferred to have a non-Type D personality based on the Type D personality test scale information, the prediction result will be inaccurate.

[0048] In the second aspect, a type D personality prediction system based on millimeter wave radar is provided, comprising:

[0049] The data acquisition module is used to collect the human heart rate variability HRV data of the target patient using the millimeter wave radar when the target patient is diagnosed with coronary heart disease, perform short-term frequency domain analysis on the HRV data, and obtain the frequency domain index parameters of the target patient;

[0050] A type D personality prediction module, used to predict whether the target patient has a type D personality based on a preset type D personality prediction algorithm and frequency domain index parameters;

[0051] The coronary heart disease prognosis module is used to perform coronary heart disease prognosis on the target patient according to the type D personality if the target patient has the type D personality.

[0052] Furthermore,

[0053] The data acquisition module is specifically used to adjust the target patient to a resting state, and use the millimeter wave radar to detect and record the HRV data of the target patient in the resting state. x1 , x1 Indicates resting state; HRV is analyzed by regression method or fast Fourier transform method. x1 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the resting state. The frequency domain index parameters include the total power TP in the resting state. x1 , Very Low Frequency Band Power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x1 and normalized high frequency band power HFnorm x1 , normalized low-frequency band power Normalized high-band power

[0054] The calculation formula of the D-type personality prediction module for obtaining the preset D-type personality prediction algorithm in the resting state is:

[0055] Type D personality prediction value S x1 =(TP x1 -TP1)+(VLF x1 -VLF1)+(LF x1 -LF1);

[0056] TP1 represents the average total power of a large number of non-type D personality patients in the resting state;

[0057] VLF1 represents the average very low frequency band power of a large number of non-type D personality patients in the resting state;

[0058] LF1 represents the average low-frequency band power of a large number of non-type D personality patients in the resting state;

[0059] When S x1 When ≥0, the target patient in the resting state is judged to be a non-type D personality;

[0060] When S x1 <0 and (TP x1 -TP1)<0、(VLF x1 -VLF1)<0 and (LF x1-LF1)<0, the target patient is judged to be type D personality in the resting state.

[0061] Furthermore,

[0062] After determining that the target patient is not a Type D personality at rest,

[0063] The data acquisition module is also used to adjust the target patient to enter the abdominal breathing state, and use the millimeter wave radar to detect and record the HRV data of the target patient in the abdominal breathing state. x2 , x2 Indicates abdominal breathing state; HRV is analyzed by regression method or fast Fourier transform method. x2 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient under abdominal breathing state. The frequency domain index parameters include the total power TP under abdominal breathing state. x2 , Very Low Frequency Band Power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x2 and normalized high frequency band power HFnorm x2 , normalized low-frequency band power , normalized high-frequency band power

[0064] The D-type personality prediction module is also used to obtain the calculation formula of the preset D-type personality prediction algorithm under the abdominal breathing state:

[0065] Type D personality prediction value S x2 =(TP x2 -TP2)+(HF x2 -HF2);

[0066] TP2 represents the average total power of a large number of non-type D personality patients under abdominal breathing, and HF2 represents the average high-frequency band power of a large number of non-type D personality patients under abdominal breathing;

[0067] When S x2 When ≥0, the target patient in the abdominal breathing state is judged to be a non-type D personality;

[0068] When S x2 <0 and (TP x2 -TP2)<0 and (HF x2 -HF2)<0, the target patient in the abdominal breathing state is judged to be type D personality;

[0069] After determining that the target patient is not a Type D personality at rest,

[0070] The data acquisition module is also used to adjust the target patient to enter a passive stress state after rest, and use millimeter wave radar to detect and record the HRV data of the target patient in the passive stress state after rest. x3 , x3 Represents the passive stress state after rest; HRV is analyzed by regression method or fast Fourier transform method. x3 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the passive stress state after rest. The frequency domain index parameters include the total power TP in the passive stress state after rest. x3 , Very Low Frequency Band Power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x3 and normalized high frequency band power HFnorm x3 , normalized low-frequency band power Normalized high-band power

[0071] The D-type personality prediction module is also used to obtain the calculation formula of the preset D-type personality prediction algorithm under the passive stress state after rest:

[0072]

[0073] S x3_2 =(HFnorm3-HFnorm x3 );

[0074] represents the average low-frequency / high-frequency ratio of a large number of non-type D personality patients in the passive stress state after rest; LFnorm3 represents the average normalized low-frequency band power of a large number of non-type D personality patients in the passive stress state after rest; HFnorm3 represents the average normalized high-frequency band power of a large number of non-type D personality patients in the passive stress state after rest;

[0075] When S x31 <0、 and (LFnorm3-LFnorm x3 )<0, and S x3_2 >0, the target patient in the passive stress state after rest is judged to be type D personality;

[0076] When S x3_1 ≥0 or S x3_2 When ≤0, the target patient in the passive stress state after rest is judged as non-type D personality.

[0077] The beneficial effects achieved by the present invention are:

[0078] When the target patient is diagnosed with coronary heart disease, the millimeter wave radar is used to collect the human heart rate variability HRV data of the target patient, and the HRV data is analyzed in the short-term frequency domain to obtain the frequency domain index parameters of the target patient; the preset D-type personality prediction algorithm and frequency domain index parameters are used to predict whether the target patient has a D-type personality; if the target patient has a D-type personality, the target patient is given a coronary heart disease prognosis according to the D-type personality. The millimeter wave radar is used to realize non-contact HRV data collection of patients with coronary heart disease, and the HRV data is analyzed in the short-term frequency domain to obtain the frequency domain index parameters for predicting the D-type personality, thereby realizing the prediction of the D-type personality. Compared with the existing scale assessment, the accuracy is higher, and the technical problem of the high labor cost and time cost of medical staff required for the D-type personality prediction in the existing technology is overcome. Compared with the existing technology, the application of technical means such as millimeter wave radar can greatly improve the accuracy of the D-type personality prediction and save labor cost and time cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 The flowchart of the method for predicting type D personality based on millimeter wave radar of the present invention;

[0080] Figure 2 This is the HRV data detection process in the resting state;

[0081] Figure 3 This is the HRV data detection process under abdominal breathing state;

[0082] Figure 4 This is the HRV data detection process under passive stress state after rest;

[0083] Figure 5 This is the HRV data detection process under passive stress state after abdominal breathing;

[0084] Figure 6 This is a structural diagram of the D-type personality prediction system based on millimeter-wave radar of the present invention. DETAILED DESCRIPTION

[0085] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0086] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting type D personality based on millimeter wave radar, comprising:

[0087] 101. When the target patient is diagnosed with coronary heart disease, the HRV data of the target patient is collected by using a millimeter wave radar, and the HRV data is analyzed in the short-term frequency domain to obtain the frequency domain index parameters of the target patient;

[0088] Among them, millimeter wave radar is a device that uses electromagnetic wave frequencies in the millimeter wave band. It can emit electromagnetic waves to the target and receive electromagnetic waves reflected by the target. When electromagnetic waves encounter moving objects, the frequency will change due to the Doppler effect. By carefully analyzing this frequency change, namely the Doppler shift, millimeter wave radar can detect and measure the speed and direction of movement of the target object. The human heartbeat is accompanied by micro-movements of the chest cavity. The radar uses the time-varying Doppler effect of frequency-modulated continuous waves under micro-movements of the chest cavity to complete the extraction and analysis of the frequency domain signal of human heart rate variability.

[0089] When performing HRV data detection, it is usually divided into four situations: the first is in a resting state, the second is in an abdominal breathing state, the third is in a passive stress state after rest, and the fourth is in a passive stress state after abdominal breathing;

[0090] like Figure 2 The following is the test process in a resting state. Please ask the target patient to lean on a high-back chair with armrests and close his eyes to rest for ten minutes, then use the millimeter-wave radar to detect and record HRV data, rest for five minutes, and record the second HRV data.

[0091] like Figure 3 The figure shows the detection process under abdominal breathing state; ask the target patient to lean on a high-back chair with armrests and close his eyes to rest for ten minutes, guide the target patient to practice abdominal breathing, seven times per minute, and after practicing for one minute, ask the target patient to take deep abdominal breaths for five minutes, use millimeter wave radar to detect and record HRV data, after resting for five minutes, repeat the above steps to record the second HRV data.

[0092] like Figure 4 The following is the test process under passive stress after rest. The target patient is asked to lean on a high-back chair with armrests and close his eyes to rest for ten minutes. The target patient is asked to watch the sad emotion inducing video material for five minutes, and the HRV data is detected and recorded using the millimeter wave radar. After resting for five minutes, the above steps are repeated, the sad emotion inducing video material is replaced, and the HRV data is recorded for the second time.

[0093] like Figure 5 The following is the test process under passive stress after abdominal breathing. The target patient is asked to lean on a high-back chair with armrests and close his eyes to rest for ten minutes. The target patient is instructed to practice abdominal breathing seven times per minute. After practicing for one minute, the target patient is asked to take deep abdominal breaths for five minutes. The target patient is asked to watch the sad emotion inducing video material for five minutes. The HRV data is detected and recorded using the millimeter wave radar. After resting for five minutes, the above steps are repeated, the sad emotion inducing video material is replaced, and the HRV data for the second time is recorded.

[0094] Through the above Figure 2-Figure 5 From the gradual changes of the four situations, we can know that abdominal breathing state is a further deepening of the rest state, the passive stress state after rest is a further deepening of the rest state, and the passive stress state after abdominal breathing is a further deepening of the abdominal breathing state. So when predicting type D personality, we can also proceed step by step according to the gradual changes of the four states.

[0095] Using the above characteristics of millimeter-wave radar, adjust the target patient to a resting state, and use the millimeter-wave radar to detect and record the HRV data of the target patient in the resting state. x1 , x1 Indicates resting state;

[0096] The HRV data is analyzed in the short-term frequency domain by using regression method or fast Fourier transform method, that is, the HRV data is divided into multiple frequency bands; high frequency band (HF): 0.15~0.4Hz, reflecting the tension of parasympathetic nerves; low frequency band (LF): 0.04~0.15Hz, reflecting the joint action of sympathetic and parasympathetic nerves, with sympathetic nerves as the main factor; very low frequency band (VLF): 0.0033~0.04Hz; total power (TP): ≤0.4Hz.

[0097] The power spectrum with frequency as the horizontal axis and power spectrum density PSD as the vertical axis, the vertical axis unit is ms 2 / Hz;

[0098] The normal range of power spectrum recorded during 5 minutes of lying still is:

[0099] TP: 3466±1018ms 2 / Hz;

[0100] LF: 1170±416ms 2 / Hz;

[0101] LFnorm: 54±4nu;

[0102] HF: 975±203ms 2 / Hz;

[0103] HFnorm: 29±3nu;

[0104] LF / HF:1.5~2.0.

[0105] The frequency domain index parameters of the target patient at rest include the total power TP at rest x1 , Very Low Frequency Band Power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio ,

[0106] Normalized low frequency band power LFnorm x1 and normalized high frequency band power HFnorm x1 , normalized low-frequency band power Normalized high-band power

[0107] 102, predicting whether the target patient has a type D personality according to a preset type D personality prediction algorithm and frequency domain index parameters;

[0108] (I) The calculation formula for obtaining the preset D-type personality prediction algorithm in the resting state is:

[0109] Type D personality prediction value S x1 =(TP x1 -TP1)+(VLF x1 -VLF1)+(LF x1 -LF1);

[0110] TP1 represents the average total power of a large number of non-type D personality patients in the resting state;

[0111] VLF1 represents the average very low frequency band power of a large number of non-type D personality patients in the resting state;

[0112] LF1 represents the average low-frequency band power of a large number of non-type D personality patients in the resting state;

[0113] According to the existing known test parameters, Type D personality is lower than non-Type D personality in TP, VLF, and LF. In the resting state, Type D personality has lower sympathetic nerve excitability and HRV than non-Type D personality.

[0114] When S x1 When ≥0, it indicates the TP of the target patient x1 、VLF x1 , LF x1 If one or more of the above is higher than that of non-type D personality, then the target patient can be judged as non-type D personality in the resting state;

[0115] When S x1 <0 and (TP x1 -TP1)<0、(VLF x1 -VLF1)<0 and (LF x1 -LF1)<0, the target patient meets the requirement of type D personality in resting state.

[0116] (II) After determining in (I) above that the target patient is a non-type D personality at rest, it may be due to TP x1 、VLF x1, LF x1 There is data loss and confusion in the prediction of type D personality, so it is necessary to further add abdominal breathing state for prediction:

[0117] Adjust the target patient to enter the abdominal breathing state, and use the millimeter wave radar to detect and record the HRV data of the target patient in the abdominal breathing state x2 , x2 Indicates abdominal breathing state;

[0118] HRV is analyzed by regression or fast Fourier transform. x2 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient under abdominal breathing state. The frequency domain index parameters include the total power TP under abdominal breathing state. x2 , Very Low Frequency Band Power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x2 and normalized high frequency band power HFnorm x2 , normalized low-frequency band power , normalized high-frequency band power

[0119] The calculation formula for obtaining the preset D-type personality prediction algorithm under abdominal breathing state is:

[0120] Type D personality prediction value S x2 =(TP x2 -TP2)+(HF x2 -HF2);

[0121] TP2 represents the average total power of a large number of non-type D personality patients under abdominal breathing, and HF2 represents the average high-frequency band power of a large number of non-type D personality patients under abdominal breathing;

[0122] According to the currently known test parameters, under the abdominal breathing state, the TP and HF of type D personality are lower than those of non-type D personality;

[0123] When S x2 When ≥0, it indicates the TP of the target patient x2 HF x2 If one or two of the above are higher than non-type D personality, then the target patient is judged as non-type D personality in the abdominal breathing state;

[0124] When S x2 <0 and (TP x2 -TP2)<0 and (HF x2-HF2)<0, the target patient in the abdominal breathing state meets the characteristics of type D personality and is judged as type D personality.

[0125] (III) After determining in (II) above that the target patient in the abdominal breathing state is a non-type D personality, it may be due to TP x2 HF x2 There are data loss and confusion in the prediction, which leads to inaccurate prediction of type D personality. Therefore, it is necessary to add passive stress state after abdominal breathing for prediction.

[0126] Adjust the target patient to enter the passive stress state after abdominal breathing, and use millimeter wave radar to detect and record the HRV data before entering the passive stress state after abdominal breathing. 前 , and the HRV data after entering the passive stress state after abdominal breathing 后 ;

[0127] The calculation formula for the change of HRV data before and after is:

[0128] ΔHRV=HRV 后 -HRV 前 ;

[0129] According to the known test parameters, the heart rate of the subjects with type D personality in the state of abdominal breathing and passive stress state before and after watching the video changes significantly; so the preset threshold value H of the change before and after is set in advance;

[0130] When |ΔHRV|>H, the target patient is judged to be type D personality;

[0131] When |ΔHRV|≤H, the target patient is judged to be a non-type D personality.

[0132] (IV) After determining in (I) above that the target patient is a non-type D personality at rest, it may be due to TP x1 、VLF x1 , LF x1 There are data loss and confusion in the prediction of type D personality, so it is necessary to further add passive stress state for prediction;

[0133] Adjust the target patient to enter the passive stress state after rest, and use millimeter wave radar to detect and record the HRV data of the target patient in the passive stress state after rest x3 , x3 It indicates the passive stress state after rest;

[0134] HRV is analyzed by regression or fast Fourier transform. x3Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the passive stress state after rest. The frequency domain index parameters include the total power TP in the passive stress state after rest. x3 , Very Low Frequency Band Power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x3 and normalized high frequency band power HFnorm x3 , normalized low-frequency band power , normalized high-frequency band power

[0135] The calculation formula for obtaining the preset D-type personality prediction algorithm under the passive stress state after rest is:

[0136]

[0137] S x3_2 =(HFnorm3-HFnorm x3 );

[0138] represents the average low-frequency / high-frequency ratio of a large number of non-type D personality patients in the passive stress state after rest; LFnorm3 represents the average normalized low-frequency band power of a large number of non-type D personality patients in the passive stress state after rest; HFnorm3 represents the average normalized high-frequency band power of a large number of non-type D personality patients in the passive stress state after rest;

[0139] According to the known test parameters, after watching the sad emotion induction video in the resting state, the passive stress state test of the type D personality testers is higher in LF / HF and LFnorm than the non-type D personality testers, while the HFnorm of the type D personality testers is lower than that of the non-type D personality testers;

[0140] When S x3_1 <0、 and (LFnorm3-LFnorm x3 )<0, and S x3_2 >0, the target patient in the passive stress state after rest is judged to be type D personality;

[0141] When S x3_1 ≥0 or S x3_2 When ≤0, the target patient in the passive stress state after rest is judged as non-type D personality.

[0142] 103. Prognosis of coronary heart disease is evaluated for target patients based on their type D personality.

[0143] After determining that the target patient has type D personality, obtain the type D personality test scale information of the target patient;

[0144] If the target patient is inferred to have a non-Type D personality based on the Type D personality test scale information, the prediction result is inaccurate;

[0145] If the target patient is inferred to have a Type D personality based on the Type D personality test scale information, then the prediction result is accurate;

[0146] After determining that the target patient has type D personality, the prognosis of coronary heart disease is conducted according to type D personality.

[0147] The implementation principle of the embodiment of the present invention is:

[0148] When the target patient is diagnosed with coronary heart disease, the millimeter-wave radar is used to collect the target patient's human heart rate variability HRV data, and the HRV data is analyzed in the short-term frequency domain to obtain the frequency domain index parameters of the target patient; the preset D-type personality prediction algorithm and frequency domain index parameters are used to predict whether the target patient has a D-type personality; if the target patient has a D-type personality, the target patient is given a coronary heart disease prognosis according to the D-type personality. The millimeter-wave radar is used to realize non-contact HRV data collection of patients with coronary heart disease, and after a short-term frequency domain analysis of the HRV data, the frequency domain index parameters for predicting the D-type personality are obtained, thereby realizing the prediction of the D-type personality. Compared with the existing scale assessment, the accuracy is higher, and it can effectively improve the prognosis of coronary heart disease patients with type D personality.

[0149] In combination with the method for predicting type D personality based on millimeter wave radar described in the above embodiments, a system for predicting type D personality based on millimeter wave radar is described below through an embodiment.

[0150] like Figure 6 As shown, an embodiment of the present invention provides a type D personality prediction system based on millimeter wave radar, comprising:

[0151] The data acquisition module 601 is used to collect the human heart rate variability HRV data of the target patient by using the millimeter wave radar when the target patient is diagnosed with coronary heart disease, and perform short-term frequency domain analysis on the HRV data to obtain the frequency domain index parameters of the target patient;

[0152] The type D personality prediction module 602 is used to predict whether the target patient has type D personality according to a preset type D personality prediction algorithm and frequency domain index parameters;

[0153] The coronary heart disease prognosis module 603 is used to perform coronary heart disease prognosis on the target patient according to the type D personality if the target patient has type D personality.

[0154] Combination Figure 6The embodiments shown in the drawings are some preferred embodiments of the present invention.

[0155] The data acquisition module 601 is specifically used to adjust the target patient to enter a resting state, and use the millimeter wave radar to detect and record the HRV data of the target patient in the resting state. x1 , x1 Indicates resting state; HRV is analyzed by regression method or fast Fourier transform method. x1 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the resting state. The frequency domain index parameters include the total power TP in the resting state. x1 , Very Low Frequency Band Power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x1 and normalized high frequency band power HFnorm x1 , normalized low-frequency band power , normalized high-frequency band power

[0156] The calculation formula of the D-type personality prediction module 602 for obtaining the preset D-type personality prediction algorithm in the resting state is:

[0157] Type D personality prediction value S x1 =(TP x1 -TP1)+(VLF x1 -VLF1)+(LF x1 -LF1);

[0158] TP1 represents the average total power of a large number of non-type D personality patients in the resting state;

[0159] VLF1 represents the average very low frequency band power of a large number of non-type D personality patients in the resting state;

[0160] LF1 represents the average low-frequency band power of a large number of non-type D personality patients in the resting state;

[0161] When S x1 When ≥0, the target patient in the resting state is judged to be a non-type D personality;

[0162] When S x1 <0 and (TP x1 -TP1)<0、(VLF x1 -VLF1)<0 and (LF x1 -LF1)<0, the target patient is judged to be type D personality in the resting state.

[0163] Combination Figure 6 In some preferred embodiments of the present invention, after determining that the target patient in the resting state is a non-type D personality,

[0164] The data acquisition module 601 is also used to adjust the target patient to enter the abdominal breathing state, and use the millimeter wave radar to detect and record the HRV data HRV of the target patient in the abdominal breathing state. x2 , x2 Indicates abdominal breathing state; HRV is analyzed by regression method or fast Fourier transform method. x2 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient under abdominal breathing state. The frequency domain index parameters include the total power TP under abdominal breathing state. x2 , Very Low Frequency Band Power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x2 and normalized high frequency band power HFnorm x2 , normalized low-frequency band power Normalized high-band power

[0165] The D-type personality prediction module 602 is also used to obtain the calculation formula of the preset D-type personality prediction algorithm under the abdominal breathing state:

[0166] Type D personality prediction value S x2 =(TP x2 -TP2)+(HF x2 -HF2);

[0167] TP2 represents the average total power of a large number of non-type D personality patients under abdominal breathing, and HF2 represents the average high-frequency band power of a large number of non-type D personality patients under abdominal breathing;

[0168] When S x2 When ≥0, the target patient in the abdominal breathing state is judged to be a non-type D personality;

[0169] When S x2 <0 and (TP x2 -TP2)<0 and (HF x2 -HF2)<0, the target patient in the abdominal breathing state is judged to be type D personality;

[0170] Combination Figure 6 In some preferred embodiments of the present invention, after determining that the target patient in the resting state is a non-type D personality,

[0171] The data acquisition module 601 is also used to adjust the target patient to enter a passive stress state after rest, and use the millimeter wave radar to detect and record the HRV data of the target patient in the passive stress state after rest. x3 , x3 Represents the passive stress state after rest; HRV is analyzed by regression method or fast Fourier transform method. x3 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the passive stress state after rest. The frequency domain index parameters include the total power TP in the passive stress state after rest. x3 , Very Low Frequency Band Power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio , normalized low frequency band power LFnorm x3 and normalized high frequency band power HFnorm x3 , normalized low-frequency band power , normalized high-frequency band power

[0172] The D-type personality prediction module 602 is also used to obtain the calculation formula of the preset D-type personality prediction algorithm in the passive stress state after rest:

[0173]

[0174] S x3_2 =(HFnorm3-HFnorm x3 );

[0175] represents the average low-frequency / high-frequency ratio of a large number of non-type D personality patients in the passive stress state after rest; LFnorm3 represents the average normalized low-frequency band power of a large number of non-type D personality patients in the passive stress state after rest; HFnorm3 represents the average normalized high-frequency band power of a large number of non-type D personality patients in the passive stress state after rest;

[0176] When S x3_1 <0、 and (LFnorm3-LFnorm x3 )<0, and S x3_2 >0, the target patient in the passive stress state after rest is judged to be type D personality;

[0177] When S x3_1 ≥0 or S x3_2 When ≤0, the target patient in the passive stress state after rest is judged as non-type D personality.

[0178] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0179] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0182] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A method for predicting type D personality based on millimeter wave radar, characterized in that: include: Using millimeter wave radar to collect human heart rate variability HRV data of a target patient; the target patient is a patient diagnosed with coronary heart disease; Performing short-term frequency domain analysis on the HRV data to obtain frequency domain index parameters of the target patient; Predicting whether the target patient has a type D personality according to a preset type D personality prediction algorithm and the frequency domain index parameters; If the target patient has a type D personality, the coronary heart disease prognosis is performed on the target patient according to the type D personality.

2. The method for predicting type D personality based on millimeter wave radar according to claim 1, characterized in that: The method of collecting human heart rate variability (HRV) data of the target patient by using a millimeter wave radar, performing short-term frequency domain analysis on the HRV data, and obtaining frequency domain index parameters of the target patient includes the following steps: Adjust the target patient to enter a resting state, and use a millimeter wave radar to detect and record the HRV data of the target patient in the resting state. x1 , x1 Indicates resting state; The HRV x1 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the resting state, wherein the frequency domain index parameters include the total power TP in the resting state. x1 , Very Low Frequency Band Power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio Normalized low frequency band power LFnorm x1 and normalized high frequency band power HFnorm x1 , the normalized low-band power The normalized high-band power 3. The method for predicting type D personality based on millimeter wave radar according to claim 2, characterized in that: The method of predicting whether the target patient has a type D personality according to the preset type D personality prediction algorithm and the frequency domain index parameters comprises the steps of: The calculation formula for obtaining the preset D-type personality prediction algorithm in the resting state is: Type D personality prediction value S x1 =(TP x1 -TP1)+(VLF x1 -VLF1)+(LF x1 -LF1); The TP1 represents the average total power of a large number of non-type D personality patients in a resting state; The VLF1 represents the average very low frequency band power of a large number of non-type D personality patients in the resting state; The LF1 represents the average low-frequency band power of a large number of non-type D personality patients in the resting state; When the S x1 When ≥0, the target patient is judged to be a non-type D personality in the resting state; When the S x1 <0 and the (TP x1 -TP1)<0、the (VLF x1 -VLF1)<0 and the (LF x1 -LF1)<0, it is determined that the target patient in the resting state is a type D personality.

4. The method for predicting type D personality based on millimeter wave radar according to claim 3, characterized in that: After determining that the target patient in the resting state is a non-type D personality, the step further includes: Adjust the target patient to enter the abdominal breathing state, and use the millimeter wave radar to detect and record the HRV data HRV of the target patient in the abdominal breathing state x2 , x2 Indicates abdominal breathing state; The HRV x2 Perform short-term frequency domain analysis to obtain frequency domain index parameters of the target patient under abdominal breathing state, wherein the frequency domain index parameters include the total power TP under abdominal breathing state. x2 , Very Low Frequency Band Power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio Normalized low frequency band power LFnorm x2 and normalized high frequency band power HFnorm x2 , the normalized low-band power The normalized high-band power The calculation formula for obtaining the preset D-type personality prediction algorithm under abdominal breathing state is: Type D personality prediction value S x2 =(TP x2 -TP2)+(HF x2 -HF2); The TP2 represents the average total power of a large number of non-type D personality patients under abdominal breathing, and the HF2 represents the average high frequency band power of a large number of non-type D personality patients under abdominal breathing; When the S x2 When ≥0, the target patient in the abdominal breathing state is judged to be a non-type D personality; When the S x2 <0 and the (TP x2 -TP2)<0 and the (HF x2 -HF2)<0, it is determined that the target patient is of type D personality in the abdominal breathing state.

5. The method for predicting type D personality based on millimeter wave radar according to claim 3, characterized in that: After determining that the target patient in the resting state is a non-type D personality, the step further includes: Adjust the target patient to enter a passive stress state after rest, and use a millimeter wave radar to detect and record the HRV data HRV of the target patient in the passive stress state after rest x3 , x3 It indicates the passive stress state after rest; The HRV x3 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the passive stress state after rest, wherein the frequency domain index parameters include the total power TP in the passive stress state after rest. x3 , Very Low Frequency Band Power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio Normalized low frequency band power LFnorm x3 and normalized high frequency band power HFnorm x3 , the normalized low-band power The normalized high-band power The calculation formula for obtaining the preset D-type personality prediction algorithm under the passive stress state after rest is: Said represents the average low frequency / high frequency ratio of a large number of non-type D personality patients in the passive stress state after rest; the LFnorm3 represents the average normalized low frequency band power of a large number of non-type D personality patients in the passive stress state after rest; the HFnorm3 represents the average normalized high frequency band power of a large number of non-type D personality patients in the passive stress state after rest; When the S x3_1 <0, described And the (LFnorm3-LFnorm x3 )<0, and the S x3_2 >0, the target patient in the passive stress state after rest is judged to be type D personality; When the S x3_1 ≥0 or the S x3_2 When ≤0, the target patient in the passive stress state after rest is determined to be a non-type D personality.

6. The method for predicting type D personality based on millimeter wave radar according to claim 4, characterized in that: After determining that the target patient in the abdominal breathing state is a non-type D personality, the method further includes the following steps: Adjust the target patient to enter the passive stress state after abdominal breathing, and use the millimeter wave radar to detect and record the HRV data before entering the passive stress state after abdominal breathing. 前 , and the HRV data after entering the passive stress state after abdominal breathing 后 ; The calculation formula for the change of HRV data before and after is: ΔHRV=HRV 后 -HRV 前 ; When |ΔHRV|>H, the target patient is determined to be a type D personality, and H is a preset threshold; When the |ΔHRV|≤H, the target patient is determined to be a non-type D personality.

7. The method for predicting type D personality based on millimeter wave radar according to any one of claims 1 to 6, characterized in that: The method further comprises the steps of: After determining that the target patient has type D personality, obtaining type D personality test scale information of the target patient; If it is inferred that the target patient has a type D personality based on the type D personality test scale information, then the prediction result is accurate; If it is inferred that the target patient has a non-type D personality based on the type D personality test scale information, the prediction result is inaccurate.

8. A type D personality prediction system based on millimeter wave radar, characterized in that: include A data acquisition module is used to collect human heart rate variability HRV data of the target patient using a millimeter wave radar when the target patient is diagnosed with coronary heart disease, perform short-term frequency domain analysis on the HRV data, and obtain frequency domain index parameters of the target patient; A type D personality prediction module, used to predict whether the target patient has a type D personality according to a preset type D personality prediction algorithm and the frequency domain index parameters; The coronary heart disease prognosis module is used to perform coronary heart disease prognosis on the target patient according to the type D personality if the target patient has the type D personality.

9. The millimeter wave radar-based type D personality prediction system according to claim 8, characterized in that: The data acquisition module is used to adjust the target patient to enter a resting state, and use a millimeter wave radar to detect and record the HRV data of the target patient in the resting state. x1 , x1 Represents resting state; using regression method or fast Fourier transform method, the HRV x1 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the resting state, wherein the frequency domain index parameters include the total power TP in the resting state. x1 , Very Low Frequency Band Power VLF x1 , low frequency band power LF x1 , high frequency band power HF x1 , low frequency / high frequency ratio Normalized low frequency band power LFnorm x1 and normalized high frequency band power HFnorm x1 , the normalized low-band power The normalized high-band power The calculation formula of the D-type personality prediction module for obtaining the preset D-type personality prediction algorithm in the resting state is: Type D personality prediction value S x1 =(TP x1 -TP1)+(VLF x1 -VLF1)+(LF x1 -LF1); The TP1 represents the average total power of a large number of non-type D personality patients in a resting state; The VLF1 represents the average very low frequency band power of a large number of non-type D personality patients in the resting state; The LF1 represents the average low-frequency band power of a large number of non-type D personality patients in the resting state; When the S x1 When ≥0, the target patient is judged to be a non-type D personality in the resting state; When the S x1 <0 and the (TP x1 -TP1)<0、the (VLF x1 -VLF1)<0 and the (LF x1 -LF1)<0, it is determined that the target patient in the resting state is a type D personality.

10. The type D personality prediction system based on millimeter wave radar according to claim 9, characterized in that: After determining that the target patient in the resting state is a non-type D personality, The data acquisition module is also used to adjust the target patient to enter an abdominal breathing state, and use a millimeter wave radar to detect and record the HRV data HRV of the target patient in the abdominal breathing state. x2 , x2 Represents abdominal breathing state; using regression method or fast Fourier transform method, the HRV x2 Perform short-term frequency domain analysis to obtain frequency domain index parameters of the target patient under abdominal breathing state, wherein the frequency domain index parameters include the total power TP under abdominal breathing state. x2 , Very Low Frequency Band Power VLF x2 , low frequency band power LF x2 , high frequency band power HF x2 , low frequency / high frequency ratio Normalized low frequency band power LFnorm x2 and normalized high frequency band power HFnorm x2 , the normalized low-band power The normalized high-band power The D-type personality prediction module is also used to obtain the calculation formula of the preset D-type personality prediction algorithm under the abdominal breathing state: Type D personality prediction value S x2 =(TP x2 -TP2)+(HF x2 -HF2); The TP2 represents the average total power of a large number of non-type D personality patients under abdominal breathing, and the HF2 represents the average high frequency band power of a large number of non-type D personality patients under abdominal breathing; When the S x2 When ≥0, the target patient in the abdominal breathing state is judged to be a non-type D personality; When the S x2 <0 and the (TP x2 -TP2)<0 and the (HF x2 -HF2)<0, it is determined that the target patient in the abdominal breathing state is a type D personality; After determining that the target patient in the resting state is a non-type D personality, The data acquisition module is also used to adjust the target patient to enter a passive stress state after rest, and use a millimeter wave radar to detect and record the HRV data HRV of the target patient in the passive stress state after rest. x3 , x3 Represents the passive stress state after rest; using regression method or fast Fourier transform method, the HRV x3 Perform short-term frequency domain analysis to obtain the frequency domain index parameters of the target patient in the passive stress state after rest, wherein the frequency domain index parameters include the total power TP in the passive stress state after rest. x3 , Very Low Frequency Band Power VLF x3 , low frequency band power LF x3 , high frequency band power HF x3 , low frequency / high frequency ratio Normalized low frequency band power LFnorm x3 and normalized high frequency band power HFnorm x3 , the normalized low-band power The normalized high-band power The D-type personality prediction module is also used to obtain the calculation formula of the preset D-type personality prediction algorithm in the passive stress state after rest: S x3_2 =(HFnorm3-HFnorm x3 ); Said represents the average low frequency / high frequency ratio of a large number of non-type D personality patients in the passive stress state after rest; the LFnorm3 represents the average normalized low frequency band power of a large number of non-type D personality patients in the passive stress state after rest; the HFnorm3 represents the average normalized high frequency band power of a large number of non-type D personality patients in the passive stress state after rest; When the S x3_1 <0, described And the (LFnorm3-LFnorm x3 )<0, and the S x3_2 >0, the target patient in the passive stress state after rest is judged to be type D personality; When the S x3_1 ≥0 or the S x3_2 When ≤0, the target patient in the passive stress state after rest is determined to be a non-type D personality.

Images