Traditional Chinese medicine cold-heat deficiency-excess syndrome differentiation method and system

Abstract

The invention discloses a traditional Chinese medicine cold-heat deficiency-excess syndrome differentiation method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining the disease information of a patient, and determining the traditional Chinese medicine cold-heat deficiency-excess type of the patient; associating the traditional Chinese medicine cold-heat deficiency-excess type with the final heart rate variability characteristics, and constructing a training data set; constructing a traditional Chinese medicine cold-heat deficiency-excess syndrome differentiation model, and training the traditional Chinese medicine cold-heat deficiency-excess syndrome differentiation model based on the training data set to obtain an optimal traditional Chinese medicine cold-heat deficiency-excess syndrome differentiation model; and obtaining a to-be-detected face video of a to-be-detected patient, extracting to-be-detected final heart rate variability features corresponding to the to-be-detected face video, and inputting the to-be-detected final heart rate variability features into the optimal traditional Chinese medicine cold-heat deficiency-excess differentiation model to obtain an effect evaluation result corresponding to the to-be-detected patient. The problem that traditional Chinese medicine cold-heat deficiency-excess syndrome differentiation cannot be achieved in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for differentiating cold, heat, deficiency and excess syndromes in traditional Chinese medicine. Background Art

[0002] In clinical anesthesia, accurate assessment of anesthetic depth is crucial. Currently, anesthesiologists mostly rely on clinical signs such as respiration and cardiovascular system to assess anesthetic depth. However, relying solely on these signs to assess anesthetic effectiveness is unreliable. Heart rate variability (HRV), as a subtle fluctuation in the instantaneous heart rate during continuous heartbeats, can reflect the balance and tension of the cardiac vagus nerve and sympathetic nerve regulation, reflecting the regulatory function of the autonomic nervous system, and is of great significance in the field of anesthesia depth monitoring.

[0003] Studies have shown that combining the bispectral index (BIS) and HRV to monitor the depth of anesthesia can not only reflect the degree of central nervous system inhibition, but also reflect the responsiveness of the autonomic nervous system to harmful stimuli, making monitoring more effective and reasonable. In addition, the nonlinear analysis of HRV is less affected by bioelectrical signal interference than BIS, and it can also quantitatively describe the stability of the autonomic nervous system and directly reflect the level of analgesia, which has outstanding research value.

[0004] Therefore, there is an urgent need for a method that can achieve non-contact effect evaluation of clinical anesthetic drugs based on heart rate variability. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for differentiating cold, heat, deficiency and excess in traditional Chinese medicine, which can realize the differentiation of cold, heat, deficiency and excess in traditional Chinese medicine.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method of differentiating cold, heat, deficiency and excess syndromes in Traditional Chinese Medicine, comprising:

[0008] Obtaining patient symptom information and determining the TCM cold / heat deficiency / excess type of the patient, wherein the TCM cold / heat deficiency / excess type includes excess heat, excess cold, deficiency heat, deficiency cold, excess heat syndrome, deficiency cold syndrome, mixed cold / heat syndrome, Yin deficiency and fire excess syndrome, and Yin and Yang deficiency syndrome;

[0009] Collect facial videos of patients;

[0010] Obtaining a photoplethysmography signal corresponding to the facial video of the human face, and extracting a plurality of original heart rate variability features based on the photoplethysmography signal;

[0011] calculating correlation coefficients between a plurality of the original heart rate variability features and the effects of anesthetic drugs;

[0012] Extracting original heart rate variability features whose correlation coefficients exceed a preset standard range as final heart rate variability features;

[0013] Correlate the TCM cold-heat deficiency-excess types with the final heart rate variability features to construct a training dataset;

[0014] Constructing a TCM cold-heat deficiency-excess syndrome differentiation model, and training the TCM cold-heat deficiency-excess syndrome differentiation model based on the training data set to obtain an optimal TCM cold-heat deficiency-excess syndrome differentiation model;

[0015] Obtain a facial video of the patient to be tested, extract the final heart rate variability characteristics to be tested corresponding to the facial video of the patient to be tested, and input the final heart rate variability characteristics to be tested into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain an effect evaluation result corresponding to the patient to be tested.

[0016] On the basis of the above technical solution, the present invention can also be improved as follows:

[0017] Optionally, obtaining a photoplethysmography signal corresponding to the facial video includes:

[0018] Obtaining facial single-channel pixels corresponding to a human face video, and obtaining a light change curve corresponding to the human face video based on the facial single-channel pixels;

[0019] A fast independent component analysis algorithm is used to obtain a source signal with the highest Pearson coefficient with the green channel, and the source signal is used as a photoplethysmography signal related to the heart beat;

[0020] The photoplethysmography signal is processed by wavelet transform, fast Fourier transform and narrowband filtering to obtain a pure photoplethysmography signal.

[0021] Optionally, the extracting a plurality of original heart rate variability features based on the photoplethysmography signal includes:

[0022] After the pure photoplethysmography signal is up-sampled by cubic spline interpolation, the peak points are extracted and the time intervals between the peak points are calculated to obtain the RR interval series.

[0023] Acquire an HRV time domain curve based on the RR interval sequence, and extract a time domain feature corresponding to the photoplethysmography signal based on the HRV time domain curve;

[0024] The Welch power spectrum is used to extract the frequency domain features corresponding to the photoplethysmography signal;

[0025] The nonlinear characteristics corresponding to the photoplethysmography signal are extracted based on the Poincare scatter plot analysis method;

[0026] Original heart rate variability features are acquired based on the time domain features, the frequency domain features, and the nonlinear features.

[0027] Optionally, the time domain features include the mean heart rate of the sample, the standard deviation of all normal sinus beat intervals, the percentage of the number of adjacent sinus beat intervals with a difference greater than 50 milliseconds in the total number of heartbeats, the percentage of the number of adjacent sinus beat intervals with a difference greater than 20 milliseconds in the total number of heartbeats, the square root of the mean of the sum of squares of the differences of adjacent sinus beat intervals, the standard deviation of the differences between adjacent sinus beats, the coefficient of variation of consecutive differences, the coefficient of variation, and the standard deviation of the heart rate;

[0028] The frequency domain features include frequency band power, high frequency band power, total signal power and low to high frequency power ratio;

[0029] The nonlinear features include the standard deviation of the Poincare map on a straight line perpendicular to the marking line, the standard deviation along the marking line, the ratio of the major axis length of the ellipse drawn in the scatter plot to the minor axis length of the ellipse drawn in the scatter plot, and the sample entropy.

[0030] Optionally, inputting the final heart rate variability characteristics to be measured into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain an effect evaluation result corresponding to the patient to be measured includes:

[0031] The information gain is calculated by formula (1);

[0032] Gain(F)=Info(S)-Info F (S) Formula (1);

[0033] Where Gain(F) is the information gain, which is used to measure the importance of a feature F to the classification of the data set, Info(S) is the information entropy of the data set S, and Info F (S) is the conditional entropy of the data set S when the attribute F is known.

[0034] Optionally, the information gain is calculated by formula (1) to provide a characteristic value basis for the optimal TCM cold-heat deficiency-excess syndrome differentiation model, thereby obtaining the effect evaluation result corresponding to the patient to be tested; including:

[0035] Calculated by formula (2)

[0036]

[0037] Where Info(S) is the information entropy of the dataset S, n is the number of categories in the dataset, and p i is the proportion of samples belonging to the i-th category in the dataset.

[0038] Optionally, the information gain is calculated using formula (1), further comprising:

[0039] Calculated by formula (3);

[0040]

[0041] In the formula, Info F (S) is the conditional entropy of the data set S under the condition that the attribute F is known, k is the number of subsets into which the original data set S is divided according to different values ​​of the attribute F, |S j | is the jth subset S j The number of samples contained in the original dataset S, |S| is the total number of samples contained in the original dataset S, Info(S j ) is the jth subset S j Information entropy.

[0042] A system for differentiating cold, heat, deficiency and excess in Traditional Chinese Medicine, including:

[0043] A type determination module is used to obtain patient symptom information and determine the TCM cold-heat, deficiency-excess, and excess type of the patient, including excess heat, excess cold, deficiency heat, deficiency cold, excess heat syndrome, deficiency cold syndrome, mixed cold-heat syndrome, Yin deficiency and fire excess syndrome, and Yin and Yang deficiency syndrome;

[0044] An acquisition module is used to acquire facial videos of patients;

[0045] an original feature extraction module, configured to obtain a photoplethysmography signal corresponding to the facial video of the human face, and extract a plurality of original heart rate variability features based on the photoplethysmography signal;

[0046] a calculation module, configured to calculate correlation coefficients between a plurality of the original heart rate variability features and the effects of anesthetic drugs;

[0047] A final feature extraction module is used to extract the original heart rate variability features whose correlation coefficients exceed a preset standard range as final heart rate variability features;

[0048] A training data set construction module is used to associate the TCM cold-heat deficiency-excess types with the final heart rate variability features to construct a training data set;

[0049] A training module is used to construct a TCM cold-heat deficiency-excess syndrome differentiation model, and train the TCM cold-heat deficiency-excess syndrome differentiation model based on the training data set to obtain an optimal TCM cold-heat deficiency-excess syndrome differentiation model;

[0050] The result acquisition module is used to obtain a facial video of the patient to be tested, extract the final heart rate variability characteristics to be tested corresponding to the facial video of the patient to be tested, and input the final heart rate variability characteristics to be tested into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain the effect evaluation result corresponding to the patient to be tested.

[0051] An electronic device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the steps of the method are implemented when the processor executes the computer program.

[0052] A non-transitory computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0053] The present invention has the following advantages:

[0054] The method of TCM cold-heat deficiency-excess syndrome differentiation in the present invention, on the one hand, breaks through the traditional TCM cold-heat deficiency-excess syndrome differentiation's reliance on experience, uses facial video as the entry point, extracts heart rate variability characteristics with the help of photoelectric volume pulse wave signals, associates TCM syndrome types with objective physiological indicators, provides a quantitative and accurate basis for syndrome differentiation, and improves the reliability and consistency of diagnostic results; on the other hand, it constructs a training data set and trains a TCM cold-heat deficiency-excess syndrome differentiation model to achieve intelligent syndrome differentiation, greatly improves syndrome differentiation efficiency, and adapts to large-scale patient screening and diagnosis needs. At the same time, by analyzing the correlation between heart rate variability characteristics and the effects of anesthetic drugs, it provides data support for the optimization of anesthetic medication regimens and efficacy evaluation, and helps precision medicine practice. In addition, it promotes the objectivity of TCM syndrome differentiation, promotes the integration of Chinese and Western medicine diagnosis and treatment technologies, and provides a new paradigm for the modernization of TCM and interdisciplinary medical research, which has significant clinical value and social significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] For purposes of illustration and not limitation, the present invention will now be described with reference to embodiments thereof and the accompanying drawings, in which:

[0056] Figure 1 Schematic diagram of the process of the method for differentiating cold, heat, deficiency and excess syndromes in Traditional Chinese Medicine in an embodiment of the present invention;

[0057] Figure 2 A schematic diagram of the main components of a system for differentiating cold, heat, deficiency and excess syndromes in Traditional Chinese Medicine in an embodiment of the present invention;

[0058] Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0060] It should be noted that the terms "first," "second," and the like in the description of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate for the embodiments of the present invention described herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0061] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features thereof can be combined with each other. The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0062] Figure 1 Schematic diagram of the process of the method for differentiating cold, heat, deficiency and excess syndromes in traditional Chinese medicine in an embodiment of the present invention, as shown in FIG. Figure 1 As shown, the method for differentiating cold, heat, deficiency and excess syndromes in Traditional Chinese Medicine provided by the embodiment of the present invention includes the following steps S101 to S108.

[0063] S101, obtaining the patient's symptom information and determining the TCM cold, heat, deficiency or excess type of the patient.

[0064] According to their cold and heat symptoms, the patients were divided into 4 groups: excess heat, excess cold, deficiency heat, and deficiency cold; and 5 groups: excess heat syndrome, deficiency cold syndrome, mixed cold and heat syndrome, yin deficiency and hyperactivity of fire syndrome, and yin and yang deficiency syndrome.

[0065] S102, collecting a facial video of the patient.

[0066] The face is rich in capillaries and is located near the carotid artery, resulting in a high blood signal strength. Considering the convenience of video capture, we chose the facial area for video capture. Video capture requires a well-lit environment, avoiding heavy makeup and contouring products as much as possible, ensuring facial lighting brightness and uniformity to prevent light source fluctuations from affecting subtle skin color changes. During the capture process, maintain normal breathing, minimize head and body movement, and avoid large facial expressions.

[0067] S103: Obtain a photoplethysmography signal corresponding to the facial video of the human face, and extract a number of original heart rate variability features based on the photoplethysmography signal.

[0068] Obtaining facial single-channel pixels corresponding to a human face video, and obtaining a light change curve corresponding to the human face video based on the facial single-channel pixels;

[0069] A fast independent component analysis algorithm is used to obtain a source signal with the highest Pearson coefficient with the green channel, and the source signal is used as a photoplethysmography signal related to the heart beat;

[0070] The photoplethysmography signal is processed by wavelet transform, fast Fourier transform and narrowband filtering to obtain a pure photoplethysmography signal.

[0071] After the pure photoplethysmography signal is up-sampled by cubic spline interpolation, the peak points are extracted and the time intervals between the peak points are calculated to obtain the RR interval series.

[0072] Acquire an HRV time domain curve based on the RR interval sequence, and extract a time domain feature corresponding to the photoplethysmography signal based on the HRV time domain curve;

[0073] The Welch power spectrum is used to extract the frequency domain features corresponding to the photoplethysmography signal;

[0074] The nonlinear characteristics corresponding to the photoplethysmography signal are extracted based on the Poincare scatter plot analysis method;

[0075] Original heart rate variability features are acquired based on the time domain features, the frequency domain features, and the nonlinear features.

[0076] S104, calculating correlation coefficients between a plurality of original heart rate variability features and the effects of anesthetic drugs.

[0077] S105 , extracting original heart rate variability features whose correlation coefficients exceed a preset standard range as final heart rate variability features.

[0078] Time domain feature parameters include: HR (indicates the mean heart rate of the samples during the acquisition time), SDNN (standard deviation of RR intervals, unit: ms), PNN50 (the percentage of RR intervals greater than 50 ms in the total number), PNN20 (the percentage of RR intervals greater than 20 ms in the total number), RMSSD (the square root of the mean of the sum of squared differences of adjacent RR intervals, unit: ms), SDSD (standard deviation of the differences between adjacent RR intervals, unit: ms), CVSD (coefficient of variation of continuous differences), CVnni (coefficient of variation), std_hr (standard deviation of heart rate, unit: bmp);

[0079] Frequency domain characteristic parameters include: LF (low frequency band power, unit ms 2 , reference range 0.04~0.15Hz), HF (high frequency band power, unit ms 2 , reference range 0.15~0.4Hz), TP (total signal power, unit ms 2, reference range 0~0.4Hz), LF / HF (low-high frequency power ratio);

[0080] The nonlinear characteristic parameters include: SD1 (standard deviation of the Poincare map on the straight line perpendicular to the marking line, unit: ms), SD2 (standard deviation along the marking line, unit: ms), SD1 / SD2 (ratio of SD2 to SD1), and SampEn (sample entropy).

[0081] The following is the HRV feature extraction calculation method:

[0082] 1) Time domain feature analysis:

[0083] SDNN represents the degree to which heart rate variability deviates from the mean. is the average value of the RR interval of N heartbeats. i is the i-th RR interval.

[0084]

[0085] PNN50 can reflect the activity of the parasympathetic nervous system. PNN20 is the same as PNN50.

[0086]

[0087] RMSSD is used to measure the regulation of heart rate by the parasympathetic nervous system.

[0088]

[0089] SDSD is a more detailed representation of the overall change in HRV. i =RR i -RR i+1 ,

[0090]

[0091] CVSD stands for coefficient of variation of continuous differences.

[0092]

[0093] CVnni can be used to measure the size of HRV.

[0094]

[0095] std_hr represents the degree to which the heart rate deviates from the average value. i represents the heart rate in the i-th previous period.

[0096]

[0097] 2) Frequency domain feature analysis: Frequency domain analysis can reflect the activities of the sympathetic and parasympathetic nerves, as well as the balance of the autonomic nervous system. The formula is as follows:

[0098]

[0099] Where, f(λ) is the power spectrum of the RR interval; LF / HF is the ratio of the low-frequency to high-frequency power spectrum;

[0100] 3) Nonlinear Analysis: Using the Poincare scatter plot analysis method, the current heartbeat cycle is influenced by its previous one. To represent the correlation between the two, a sequence of RR intervals is used. Two adjacent intervals are used as the coordinates of a factor of the Poincare point, with the current interval as the horizontal axis and the next interval as the vertical axis. Each point is plotted on the graph to create a scatter plot. The scatter plot draws an ellipse with the mean heartbeat interval at its center. The major and minor axes of the ellipse are then calculated as SD2 and SD1, respectively.

[0101] The calculation is as follows:

[0102]

[0103] The extracted HRV features were screened for patient sample data labeled as "excess heat," "excess cold," "deficient heat," "deficient cold and excess heat," "deficient cold," "mixed cold and heat," "yin deficiency and hyperactivity of fire," and "yin and yang deficiency." SPSS statistical analysis was used, and paired t-tests were used to identify features with significant differences as relevant indicators for analysis of these three syndromes: "excess heat," "deficient heat," "deficient cold and excess heat," "deficient cold," "mixed cold and heat," "yin deficiency and hyperactivity of fire," and "yin and yang deficiency." For example, "excess" and "deficient" were correlated with total autonomic nervous system tone, while "cold and heat" were correlated with the balance of sympathetic and vagal tone in autonomic nervous system function. There was no significant difference in total autonomic nervous system energy between heat and cold syndromes, but sympathetic activity was relatively enhanced in the heat syndrome group. SDNN, SDANN, and RMSSD were not significantly different between the heat and cold syndrome groups, with the "deficient cold" group exhibiting greater values ​​than the "deficient heat" group. There were no significant differences between the heat syndrome and cold syndrome groups in TP, LF, and HF, and the LF / HF heat syndrome group was higher than the cold syndrome group; there were significant differences between the frequency domain indicators TP, HF, and LF / HF deficiency-heat and deficiency-cold, and the TP and HF deficiency-cold groups were higher than the deficiency-heat groups, and the LF / HF deficiency-heat group was higher than the deficiency-cold group, and there were no significant differences between the LF groups.

[0104] S106, correlating the TCM cold-heat deficiency-excess types with the final heart rate variability features to construct a training data set.

[0105] The sample entropy is calculated as follows:

[0106] For a time series consisting of N known data, it is recorded as {x(n)}, and an m-dimensional vector X is constructed according to the sequence number. m (i):

[0107] X(i)={x(i),x(i+1),...,x(i+m-1)},1≤i≤N-m+1;

[0108] Represents m consecutive x values ​​starting from i. Calculate vector X m (i) and X m (j), denoted as d[X m (i),X m (j)]:

[0109] d[X m (i),X m (j)]=max k＝0,...，m-1 {|x(i+k)-x(j+k)|};

[0110] Then the distance d[X m (i),X m The number of (j)]≤r is denoted as N m (i), where r is the set threshold. The probability is calculated as follows:

[0111]

[0112] Calculate the mean:

[0113] Increase the dimension to m+1 and calculate the probability in the above steps and mean B m+1 (r). Sample entropy is defined as:

[0114]

[0115] If N is a finite value, it can be written as:

[0116]

[0117] S107, constructing a TCM cold-heat deficiency-excess syndrome differentiation model, and training the TCM cold-heat deficiency-excess syndrome differentiation model based on the training data set to obtain an optimal TCM cold-heat deficiency-excess syndrome differentiation model.

[0118] A decision tree algorithm is used to train the data from HRV feature analysis to build a Traditional Chinese Medicine (TCM) model for cold-heat, deficiency-excess, and syndrome differentiation. A decision tree is a tree model that determines which value in which dimension should be divided to minimize information entropy. The more ordered the tree, the lower the information entropy and the more certain the classification.

[0119] Starting from the parent node, the HRV feature analysis data is traversed according to specific rules. The currently decisive feature is identified and then split into child nodes based on its value. The child node becomes the new parent node and continues to split according to the above rules until the conditions are met or no split is possible. Therefore, selecting the right root node is crucial for splitting. The criterion for this is to calculate the impurity of the sample set using the information gain method. As the decision tree nodes are divided, the uncertainty decreases. As classification progresses, more information is learned, and the overall entropy decreases.

[0120] Suppose there are n types in the sample set S, where n corresponds to the TCM cold-heat deficiency-excess syndrome differentiation grouping into four groups: excess heat, excess cold, deficiency heat, and deficiency cold, or five groups: excess heat syndrome, deficiency cold syndrome, mixed cold-heat syndrome, Yin deficiency-fire syndrome, and Yin-Yang deficiency syndrome. Then the information entropy calculation formula is:

[0121]

[0122] Where p is the proportion of samples of different categories.

[0123] When feature F is selected as the splitting condition, the information entropy of this event is:

[0124]

[0125] Where, k—sample S is divided into k parts.

[0126] Information gain means the reduction of information entropy under the action of feature attribute F. The calculation formula of information gain is as follows:

[0127] Gain(F)=Info(S)-Info F (S).

[0128] S108, obtaining a facial video of the patient to be tested, extracting the final heart rate variability characteristics to be tested corresponding to the facial video of the patient to be tested, and inputting the final heart rate variability characteristics to be tested into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain an effect evaluation result corresponding to the patient to be tested.

[0129] The effect evaluation results include: when comparing HRV indicators in the upright and calm state, there was no significant difference in TP among the syndrome groups; the LF of the excess heat syndrome group was significantly higher than that of the yin deficiency and hyperactivity of fire syndrome group; the LFNU of the excess heat syndrome group was significantly higher than that of the deficiency cold syndrome group and the yin deficiency and hyperactivity of fire syndrome group; the HF of the deficiency cold syndrome group was significantly higher than that of the yin deficiency and hyperactivity of fire syndrome group; the HFNU of the deficiency cold syndrome group was significantly higher than that of the excess heat syndrome group, the mixed deficiency and excess syndrome group, the yin deficiency and hyperactivity of fire syndrome group, and the yin and yang deficiency syndrome group; the LF / HF of the deficiency cold syndrome group was significantly lower than that of the excess heat syndrome group and the yin deficiency and hyperactivity of fire syndrome group.

[0130] Figure 2Schematic diagram of the main components of the system for TCM cold-heat deficiency-excess syndrome differentiation in the embodiment of the present invention. Figure 2 As shown, the system 1 for TCM cold-heat deficiency-excess syndrome differentiation provided by an embodiment of the present invention includes a type determination module 10, an acquisition module 20, an original feature extraction module 30, a calculation module 40, a final feature extraction module 50, a training data set construction module 60, a training module 70 and a result acquisition module 80.

[0131] Type determination module 10, for obtaining patient symptom information and determining the TCM cold-heat deficiency-excess type of the patient, wherein the TCM cold-heat deficiency-excess type includes excess heat, excess cold, deficiency heat, deficiency cold, excess heat syndrome, deficiency cold syndrome, mixed cold-heat syndrome, Yin deficiency-fire syndrome, and Yin-Yang deficiency syndrome;

[0132] The acquisition module 20 is used to acquire the patient's facial video;

[0133] an original feature extraction module 30 for acquiring a photoplethysmography signal corresponding to the facial video of the human face, and extracting a plurality of original heart rate variability features based on the photoplethysmography signal;

[0134] A calculation module 40 is used to calculate the correlation coefficients between the original heart rate variability features and the effects of anesthetic drugs;

[0135] A final feature extraction module 50 is used to extract the original heart rate variability features whose correlation coefficients exceed a preset standard range as final heart rate variability features;

[0136] A training data set construction module 60 is used to associate the TCM cold-heat deficiency-excess type with the final heart rate variability characteristics to construct a training data set;

[0137] A training module 70 is used to construct a TCM cold-heat deficiency-excess syndrome differentiation model, and train the TCM cold-heat deficiency-excess syndrome differentiation model based on the training data set to obtain an optimal TCM cold-heat deficiency-excess syndrome differentiation model;

[0138] The result acquisition module 80 is used to obtain a facial video of the patient to be tested, extract the final heart rate variability characteristics to be tested corresponding to the facial video of the patient to be tested, and input the final heart rate variability characteristics to be tested into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain the effect evaluation result corresponding to the patient to be tested.

[0139] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 90 includes: a processor 901 (processor), a memory 902 (memory) and a bus 903;

[0140] The processor 901 and the memory 902 communicate with each other via the bus 903.

[0141] The processor 901 is used to call the program instructions in the memory 902 to execute the methods provided by the above-mentioned method embodiments, so as to execute the methods provided by the implementation methods of the present invention.

[0142] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the method provided by the embodiment of the present invention.

[0143] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc. Various storage media that can store program codes.

[0144] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for differentiating cold, heat, deficiency and excess syndromes in traditional Chinese medicine, characterized in that: include: Obtaining patient symptom information and determining the TCM cold / heat deficiency / excess type of the patient, wherein the TCM cold / heat deficiency / excess type includes excess heat, excess cold, deficiency heat, deficiency cold, excess heat syndrome, deficiency cold syndrome, mixed cold / heat syndrome, Yin deficiency and fire excess syndrome, and Yin and Yang deficiency syndrome; Collect facial videos of patients; Obtaining a photoplethysmography signal corresponding to the facial video of the human face, and extracting a plurality of original heart rate variability features based on the photoplethysmography signal; calculating correlation coefficients between a plurality of the original heart rate variability features and the effects of anesthetic drugs; Extracting original heart rate variability features whose correlation coefficients exceed a preset standard range as final heart rate variability features; Correlate the TCM cold-heat deficiency-excess types with the final heart rate variability features to construct a training dataset; Constructing a TCM cold-heat deficiency-excess syndrome differentiation model, and training the TCM cold-heat deficiency-excess syndrome differentiation model based on the training data set to obtain an optimal TCM cold-heat deficiency-excess syndrome differentiation model; Obtain a facial video of the patient to be tested, extract the final heart rate variability characteristics to be tested corresponding to the facial video of the patient to be tested, and input the final heart rate variability characteristics to be tested into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain an effect evaluation result corresponding to the patient to be tested.

2. The method for differentiating cold and heat deficiency and excess syndromes in traditional Chinese medicine according to claim 1, characterized in that: The obtaining of a photoplethysmogram signal corresponding to the facial video includes: Obtaining facial single-channel pixels corresponding to a human face video, and obtaining a light change curve corresponding to the human face video based on the facial single-channel pixels; A fast independent component analysis algorithm is used to obtain a source signal with the highest Pearson coefficient with the green channel, and the source signal is used as a photoplethysmography signal related to the heart beat; The photoplethysmography signal is processed by wavelet transform, fast Fourier transform and narrowband filtering to obtain a pure photoplethysmography signal.

3. The method for differentiating cold and heat deficiency and excess syndromes in traditional Chinese medicine according to claim 2, characterized in that: The extracting of several original heart rate variability features based on the photoplethysmography signal includes: After the pure photoplethysmography signal is up-sampled by cubic spline interpolation, the peak points are extracted and the time intervals between the peak points are calculated to obtain the RR interval series. Acquire an HRV time domain curve based on the RR interval sequence, and extract a time domain feature corresponding to the photoplethysmography signal based on the HRV time domain curve; The Welch power spectrum is used to extract the frequency domain features corresponding to the photoplethysmography signal; The nonlinear characteristics corresponding to the photoplethysmography signal are extracted based on the Poincare scatter plot analysis method; Original heart rate variability features are acquired based on the time domain features, the frequency domain features, and the nonlinear features.

4. The method for differentiating cold and heat deficiency and excess syndromes in traditional Chinese medicine according to claim 3, characterized in that: The time domain features include the mean heart rate of the sample, the standard deviation of all normal sinus beat intervals, the percentage of adjacent sinus beat intervals with a difference greater than 50 milliseconds in the total number of heartbeats, the percentage of adjacent sinus beat intervals with a difference greater than 20 milliseconds in the total number of heartbeats, the square root of the mean of the sum of squares of the differences between adjacent sinus beat intervals, the standard deviation of the differences between adjacent sinus beats, the coefficient of variation of consecutive differences, the coefficient of variation, and the standard deviation of the heart rate; The frequency domain features include frequency band power, high frequency band power, total signal power and low to high frequency power ratio; The nonlinear features include the standard deviation of the Poincare map on a straight line perpendicular to the marking line, the standard deviation along the marking line, the ratio of the major axis length of the ellipse drawn in the scatter plot to the minor axis length of the ellipse drawn in the scatter plot, and the sample entropy.

5. The method for differentiating cold, heat, deficiency and excess syndromes in traditional Chinese medicine according to claim 4, characterized in that: The step of inputting the final heart rate variability characteristics to be measured into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain the effect evaluation result corresponding to the patient to be measured includes: The information gain is calculated by formula (1) to provide a characteristic value basis for the optimal TCM cold-heat deficiency-excess syndrome differentiation model, and then the effect evaluation results corresponding to the patients to be tested are obtained; Gain(F)=Info(S)-Info F (S) Formula (1); Where Gain(F) is the information gain, which is used to measure the importance of a feature F to the classification of the data set, Info(S) is the information entropy of the data set S, and Info F (S) is the conditional entropy of the data set S when the attribute F is known.

6. The method for differentiating cold, heat, deficiency and excess syndromes in traditional Chinese medicine according to claim 5, characterized in that: The information gain is calculated by formula (1), including: Calculated by formula (2) Where Info(S) is the information entropy of the dataset S, n is the number of categories in the dataset, and p i is the proportion of samples belonging to the i-th category in the dataset.

7. The method for differentiating cold, heat, deficiency and excess syndromes in traditional Chinese medicine according to claim 5, characterized in that: The information gain is calculated by formula (1), further comprising: Calculated by formula (3); In the formula, Info F (S) is the conditional entropy of the data set S under the condition that the attribute F is known, k is the number of subsets into which the original data set S is divided according to different values ​​of the attribute F, |S j | is the jth subset S j The number of samples contained in the original dataset S, |S| is the total number of samples contained in the original dataset S, Info(S j ) is the jth subset S j Information entropy.

8. A system for differentiating cold, heat, deficiency and excess in traditional Chinese medicine, characterized by: include: A type determination module is used to obtain patient symptom information and determine the TCM cold-heat, deficiency-excess, and excess type of the patient, including excess heat, excess cold, deficiency heat, deficiency cold, excess heat syndrome, deficiency cold syndrome, mixed cold-heat syndrome, Yin deficiency and fire excess syndrome, and Yin and Yang deficiency syndrome; An acquisition module is used to acquire facial videos of patients; an original feature extraction module, configured to obtain a photoplethysmography signal corresponding to the facial video of the human face, and extract a plurality of original heart rate variability features based on the photoplethysmography signal; a calculation module, configured to calculate correlation coefficients between a plurality of the original heart rate variability features and the effects of anesthetic drugs; A final feature extraction module is used to extract the original heart rate variability features whose correlation coefficients exceed a preset standard range as final heart rate variability features; A training data set construction module is used to associate the TCM cold-heat deficiency-excess types with the final heart rate variability features to construct a training data set; A training module is used to construct a TCM cold-heat deficiency-excess syndrome differentiation model, and train the TCM cold-heat deficiency-excess syndrome differentiation model based on the training data set to obtain an optimal TCM cold-heat deficiency-excess syndrome differentiation model; The result acquisition module is used to obtain a facial video of the patient to be tested, extract the final heart rate variability characteristics to be tested corresponding to the facial video of the patient to be tested, and input the final heart rate variability characteristics to be tested into the optimal TCM cold-heat deficiency-excess syndrome differentiation model to obtain the effect evaluation result corresponding to the patient to be tested.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images