Similarity prediction-based infectious disease patient sequelae probability evaluation and early warning method and device

Abstract

The invention relates to an infectious disease patient sequelae probability assessment early warning method and device based on similarity prediction. The method comprises the following steps: determining all associated indexes of infectious disease patient sequelae risk early warning; determining weight values of all the associated indexes, and selecting the associated indexes of which the ranking of the weight values is higher than a ranking threshold value from all the associated indexes as prediction index data; carrying out infectious disease patient sampling based on the prediction index data to obtain a sampling data set, wherein the infectious disease patient sampling refers to sampling of patients with sequelae and patients without sequelae in infectious disease patients; obtaining prediction index data of a to-be-predicted infectious disease patient; and performing sequelae risk early warning on the prediction index data of the to-be-predicted infectious disease patient based on the sampling data set to obtain a sequelae risk early warning result. According to the mode provided by the invention, on one hand, the patient can be prevented from frequently going to the past to see a doctor, the time cost of the user is saved, and on the other hand, the calculated sequelae risk early warning result is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of risk early warning, and particularly to a method and device for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction. Background Art

[0002] The sequelae of infectious disease patients refer to the situation where the functions of some organs of infectious disease patients have not returned to normal for a long time after the end of the recovery period.

[0003] At present, the methods for early warning the risk of sequelae of infectious diseases often require long-term follow-up and monitoring of patients to timely detect and handle sequelae problems. This method requires users to frequently go to the hospital to see a doctor for consultation, which is necessary for high-risk patients, but unnecessary for low-risk patients.

[0004] Therefore, there are also some methods for early warning the risk of sequelae of infectious disease patients on the market at present. However, most of these methods monitor some key indicators of patients, and then give an early warning reminder if the preset indicator threshold is exceeded. The monitoring effect of this method is poor and cannot give users a relatively accurate risk early warning. Summary of the Invention

[0005] The purpose of the present invention is to at least solve one of the deficiencies of the prior art, and provide a method and device for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] Specifically, a method and device for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction are proposed, including the following:

[0008] Determine all associated indicators for early warning the risk of sequelae of infectious disease patients;

[0009] Determine the weight values of all associated indicators, and select the associated indicators with weight values higher than the ranking threshold from all associated indicators as prediction index data;

[0010] Based on the prediction index data, sample infectious disease patients to obtain a sample data set. The sampling of infectious disease patients refers to sampling patients with sequelae and patients without sequelae among infectious disease patients. The sample data set refers to a data set jointly composed of the prediction index data of each sampled infectious disease patient;

[0011] Obtain the prediction index data of the infectious disease patient to be predicted;

[0012] Based on the sampling data set, perform sequela risk early warning on the prediction index data of the infectious disease patients to be predicted, and obtain the sequela risk early warning result.

[0013] Further, specifically, determining the weight values of all associated indicators includes

[0014] If there are m types of associated indicators;

[0015] Standardize the m types of associated indicators to obtain m standardized associated indicators;

[0016] Calculate the information entropy of each associated indicator, and its calculation formula is as follows

[0017]

[0018] Among them, H j represents the information entropy of the jth associated indicator, and p ij is the proportion of the ith standardized associated indicator on the jth associated indicator, and k is a preset constant;

[0019] Calculate its corresponding weight according to the information entropy of each associated indicator, and its calculation formula is as follows

[0020]

[0021] Among them, w j represents the weight of the jth associated indicator.

[0022] Further, specifically, select the associated indicators whose weight values rank higher than the top 4 from all associated indicators as the prediction index data, and record them as the first prediction index, the second prediction index, the third prediction index, and the fourth prediction index according to the ranking.

[0023] Further, specifically, perform sequela risk early warning on the prediction index data of the infectious disease patients to be predicted based on the sampling data set, including

[0024] Record the sampling data set as the set Sp_set. The number of elements in the set Sp_set, that is, the number of sampled infectious disease patients, is mm. Sp_set(mk) in the set Sp_set represents the relevant data of the sampled infectious disease patient with the serial number mk, and mk ∈ [1, mm].

[0025] Construct a three-dimensional space coordinate system with the second prediction index, the third prediction index, and the fourth prediction index as the X-axis, Y-axis, and Z-axis respectively;

[0026] Then the position coordinates corresponding to Sp_set(mk) in the three-dimensional space coordinate system are x(mk), y(mk), and z(mk);

[0027] Among them, x(mk) represents the coordinate of the element with serial number mk on the X-axis, y(mk) represents the coordinate of the element with serial number mk on the Y-axis, and z(mk) represents the coordinate of the element with serial number mk on the Z-axis, that is, the height of the element with serial number mk from the x-axis plane. That is, z(mk) represents the plane composed of target prediction points with the same distance from the x-axis plane;

[0028] Add the prediction index data of the infectious disease patient to be predicted to the set Sp_set, and denote it as Sp_set(mk);

[0029] At this time, obtain the two elements with the smallest Euclidean distance from Sp_set(mk) in the three-dimensional space coordinate system. Denote one of the elements as Sp_set(mk1), and denote the other element as Sp_set(mk2); the coordinates of the element Sp_set(mk1) are x(mk1), y(mk1) and z(mk1), and the coordinates of the element Sp_set(mk2) are x(mk2), y(mk2) and z(mk2);

[0030] Obtain the first prediction index corresponding to the element Sp_set(mk1) and denote it as W(mk1), and obtain the first prediction index corresponding to the element Sp_set(mk2) and denote it as W(mk2);

[0031] Obtain the corresponding plane of z(mk1) and denote it as Pla(mk1), and obtain the corresponding plane of z(mk2) and denote it as Pla(mk2);

[0032] Obtain the set composed of the elements in the three-dimensional space coordinate system that fall on Pla(mk1) as Set(mk1). The number of elements in Set(mk1) is r1, the serial numbers of the elements in Set(mk1) are v1, v1 ∈ [1, r1], the element with serial number v1 in Set(mk1) is Set(mk1, v1), and the corresponding position coordinates of Set(mk1, v1) are x(mk1, v1), y(mk1, v1) and z(mk1, v1);

[0033] Obtain the set composed of the elements in the three-dimensional space coordinate system that fall on Pla(mk2) as Set(mk2). The number of elements in Set(mk2) is r2, the serial numbers of the elements in Set(mk2) are v2, v2 ∈ [1, r2], the element with serial number v2 in Set(mk2) is Set(mk2, v2), and the corresponding position coordinates of Set(mk2, v2) are x(mk2, v2), y(mk2, v2) and z(mk2, v2);

[0034] Calculate the sequelae correlation index seq_rel(mk) of Sp_set(mk) as follows:

[0035]

[0036] Among them, E_D(O, P) represents calculating the Euclidean distance between element O and element P;

[0037] Obtain the elements on the Pla(mk1) plane in the sampling data set and calculate the mean value of the first prediction index corresponding to each element as W(Pla(mk1)), obtain the elements on the Pla(mk2) in the sampling data set and calculate the mean value of the first prediction index corresponding to each element as W(Pla(mk2));

[0038] Then, the calculation formula of the sequela risk index W(mk) of Sp_set(mk) is as follows,

[0039] W(mk) = [W(Pla(mk1)) + W(Pla(mk2))] * seq_rel(mk) * β / 2,

[0040] where β is a compensation coefficient, a value set manually;

[0041] After that, determine whether W(mk) is greater than the preset sequela risk index threshold. If so, it is determined that the infectious disease patient to be predicted has a high sequela risk. If not, it is determined that the infectious disease patient to be predicted has a low sequela risk.

[0042] Furthermore, the method further includes,

[0043] For infectious disease patients with a high sequela risk, remind them to visit the hospital for a review in the form of a text message according to a preset first cycle; for infectious disease patients with a low sequela risk, remind them to continue to provide prediction index data for a review in the form of a text message according to a preset second cycle.

[0044] The present invention also proposes an evaluation and early warning device for the sequela probability of infectious disease patients based on similarity prediction, including the following:

[0045] An index determination module, used to determine all associated indexes for the sequela risk early warning of infectious disease patients;

[0046] A prediction data determination module, used to determine the weight values of all associated indexes, and select the associated indexes with weight values ranking higher than the ranking threshold from all associated indexes as prediction index data;

[0047] A sample data acquisition module, used to perform sampling on infectious disease patients based on the prediction index data to obtain a sampling data set. The sampling of infectious disease patients refers to sampling both patients with sequelae and patients without sequelae among infectious disease patients. The sampling data set refers to a data set jointly composed of the prediction index data of each sampled infectious disease patient;

[0048] A prediction data acquisition module, configured to acquire prediction index data of an infectious disease patient to be predicted;

[0049] An early warning analysis module, configured to perform sequela risk early warning on the prediction index data of the infectious disease patient to be predicted based on the sampling data set, so as to obtain a sequela risk early warning result.

[0050] The beneficial effects of the present invention are as follows:

[0051] The present invention provides a method and device for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction. First, by calculating the weights of all associated indicators for the sequela risk early warning of infectious disease patients, the associated indicators with high influence are found as the prediction index data, and then the sequela risk of the infectious disease patient to be predicted is calculated by means of historical big data correlation calculation based on the prediction index data to obtain the sequela risk early warning result. The method provided by the present invention can, on the one hand, avoid patients frequently going to previous medical treatments to save the time cost of users, and on the other hand, the calculated sequela risk early warning result is more accurate. Description of the Drawings

[0052] By elaborating on the embodiments shown in conjunction with the drawings, the above and other features of the present disclosure will become more apparent. The same reference numerals in the drawings of the present disclosure denote the same or similar elements. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0053] Figure 1 The flowchart of the method for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction according to the present invention is shown. Detailed Embodiments

[0054] The following will clearly and completely describe the concept, specific structure and technical effects generated by the present invention in combination with embodiments and drawings, so as to fully understand the purpose, solution and effects of the present invention. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The same reference numerals used throughout the drawings denote the same or similar parts.

[0055] Embodiment 1, referring to Figure 1 , the present invention provides a method and device for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction, including the following:

[0056] Step 110: Determine all associated indicators for the sequela risk early warning of infectious disease patients;

[0057] Step 120: Determine the weight values of all associated indicators, and select the associated indicators whose weight values rank higher than the ranking threshold from all the associated indicators as the prediction indicator data;

[0058] Step 130: Conduct sampling on infectious disease patients based on the prediction indicator data to obtain a sampling data set. The sampling of infectious disease patients refers to sampling both patients with sequelae and those without sequelae among infectious disease patients. The sampling data set refers to the data set jointly composed of the prediction indicator data of each sampled infectious disease patient;

[0059] Step 140: Obtain the prediction indicator data of the infectious disease patient to be predicted;

[0060] Step 150: Conduct sequelae risk early warning on the prediction indicator data of the infectious disease patient to be predicted based on the sampling data set, and obtain the sequelae risk early warning result.

[0061] In this Embodiment 1, first, by calculating the weights of all associated indicators for the sequelae risk early warning of infectious disease patients, the associated indicators with high influence are found as the prediction indicator data. Then, based on the prediction indicator data, the sequelae risk of the infectious disease patient to be predicted is calculated through the historical big data correlation calculation method to obtain the sequelae risk early warning result. The method proposed by the present invention can, on the one hand, avoid patients frequently going to previous medical treatments to save the time cost of users, and on the other hand, the calculated sequelae risk early warning result is more accurate.

[0062] As a preferred implementation manner of the present invention, specifically, determining the weight values of all associated indicators includes,

[0063] If there are m types of associated indicators;

[0064] Standardize the m types of associated indicators to obtain the standardized m types of associated indicators;

[0065] Calculate the information entropy of each type of associated indicator, and its calculation formula is as follows,

[0066]

[0067] Among them, H j represents the information entropy of the jth type of associated indicator, and p ij is the proportion of the ith type of standardized associated indicator on the jth type of associated indicator, and k is a preset constant;

[0068] Calculate the corresponding weight according to the information entropy of each type of associated indicator, and its calculation formula is as follows,

[0069]

[0070] Among them, w jIt represents the weight of the j-th associated index.

[0071] In this preferred embodiment, by the above method, the weight values of all associated indexes can be accurately determined.

[0072] As a preferred embodiment of the present invention, specifically, the associated indexes with weight values ranked higher than the top 4 are selected from all associated indexes as prediction index data, and are respectively denoted as the first prediction index, the second prediction index, the third prediction index, and the fourth prediction index according to the ranking.

[0073] As a preferred embodiment of the present invention, specifically, based on the sampling data set, sequela risk early warning is performed on the prediction index data of the infectious disease patient to be predicted, including,

[0074] Denote the sampling data set as set Sp_set, the number of elements in set Sp_set, that is, the number of sampled infectious disease patients is mm, and Sp_set(mk) in set Sp_set represents the relevant data of the sampled infectious disease patient with the serial number mk, mk ∈ [1, mm].

[0075] Construct a three-dimensional space coordinate system with the second prediction index, the third prediction index, and the fourth prediction index as the X-axis, Y-axis, and Z-axis respectively;

[0076] Then the position coordinates corresponding to Sp_set(mk) in the three-dimensional space coordinate system are x(mk), y(mk), and z(mk);

[0077] Among them, x(mk) represents the coordinate of the element with serial number mk on the X-axis, y(mk) represents the coordinate of the element with serial number mk on the Y-axis, and z(mk) represents the height of the element with serial number mk from the x-axis plane, that is, z(mk) represents the plane composed of target prediction points with the same distance from the x-axis plane;

[0078] Add the prediction index data of the infectious disease patient to be predicted to set Sp_set, and denote it as Sp_set(mk);

[0079] At this time, obtain the two elements with the smallest Euclidean distance from Sp_set(mk) on the three-dimensional space coordinate system, denote one of the elements as Sp_set(mk1), and denote the other element as Sp_set(mk2); the coordinates of element Sp_set(mk1) are x(mk1), y(mk1), and z(mk1), and the coordinates of element Sp_set(mk2) are x(mk2), y(mk2), and z(mk2);

[0080] Obtain the first prediction index corresponding to the element Sp_set(mk1) and denote it as W(mk1), and obtain the first prediction index corresponding to the element Sp_set(mk2) and denote it as W(mk2);

[0081] Obtain the corresponding plane of z(mk1) and denote it as Pla(mk1), and obtain the corresponding plane of z(mk2) and denote it as Pla(mk2);

[0082] Obtain the set composed of the elements in the three-dimensional space coordinate system that fall on Pla(mk1) as Set(mk1). The number of elements in Set(mk1) is r1, the serial numbers of the elements in Set(mk1) are v1, v1 ∈ [1, r1], the element with the serial number v1 in Set(mk1) is Set(mk1, v1), and the corresponding position coordinates of Set(mk1, v1) are x(mk1, v1), y(mk1, v1), and z(mk1, v1);

[0083] Obtain the set composed of the elements in the three-dimensional space coordinate system that fall on Pla(mk2) as Set(mk2). The number of elements in Set(mk2) is r2, the serial numbers of the elements in Set(mk2) are v2, v2 ∈ [1, r2], the element with the serial number v2 in Set(mk2) is Set(mk2, v2), and the corresponding position coordinates of Set(mk2, v2) are x(mk2, v2), y(mk2, v2), and z(mk2, v2);

[0084] Calculate the sequelae correlation index seq_rel(mk) of Sp_set(mk) as follows:

[0085]

[0086] where E_D(O, P) represents calculating the Euclidean distance between element O and element P;

[0087] Obtain the elements in the sampling data set that are on the Pla(mk1) plane and calculate the mean value of the first prediction index corresponding to each element as W(Pla(mk1)), and obtain the elements in the sampling data set that are on Pla(mk2) and calculate the mean value of the first prediction index corresponding to each element as W(Pla(mk2));

[0088] Then the calculation formula for the sequelae risk index W(mk) of Sp_set(mk) is as follows,

[0089] W(mk) = [W(Pla(mk1)) + W(Pla(mk2))] * seq_rel(mk) * β / 2,

[0090] where β is a compensation coefficient, a value set manually;

[0091] After that, it is judged whether W(mk) is greater than the preset sequela risk index threshold. If so, it is judged that the infectious disease patient to be predicted has a high sequela risk. If not, it is judged that the infectious disease patient to be predicted has a low sequela risk.

[0092] In this preferred embodiment, first, considering the contribution of index data, the associated indexes with the top 4 ranking weight values are selected from all associated indexes as the predicted index data. Then, the second predicted index, the third predicted index, and the fourth predicted index are subjected to coefficient conversion based on the idea of Euclidean distance, and then multiplied by the first predicted index to finally obtain the sequela risk index. This not only utilizes the predicted indexes with high weights but also calculates the sequela risk of infectious disease patients through the Euclidean distance with a more relevant historical data group, making the obtained sequela risk index more accurate.

[0093] As a preferred embodiment of the present invention, the method further includes

[0094] For infectious disease patients with a high sequela risk, they are reminded to visit the hospital for a review in the form of a text message according to a preset first cycle; for infectious disease patients with a low sequela risk, they are reminded to continue to provide the predicted index data for a review in the form of a text message according to a preset second cycle.

[0095] In this preferred embodiment, by verifying and warning infectious disease patients in the above manner, it is possible to give a review warning to users corresponding to the sequela risk situation in a suitable manner as much as possible, where the first cycle is less than the second cycle.

[0096] Example 2, the present invention also proposes a method for evaluating and warning the sequela probability of infectious disease patients based on similarity prediction, including the following:

[0097] An index determination module, configured to determine all associated indexes for the sequela risk warning of infectious disease patients;

[0098] A predicted data determination module, configured to determine the weight values of all associated indexes, and select the associated indexes with weight values higher than the ranking threshold from all associated indexes as the predicted index data;

[0099] A sample data acquisition module, configured to perform sampling on infectious disease patients based on the predicted index data to obtain a sampling data set. The sampling of infectious disease patients refers to sampling patients with sequelae and those without sequelae among infectious disease patients, and the sampling data set refers to a data set jointly composed of the predicted index data of each sampled infectious disease patient;

[0100] A predicted data acquisition module, configured to acquire the predicted index data of the infectious disease patient to be predicted;

[0101] An early warning analysis module, configured to perform sequela risk early warning on the predicted index data of an infectious disease patient based on the sampling data set, so as to obtain a sequela risk early warning result.

[0102] In Embodiment 2 of the present invention, which is consistent with the method for evaluating and warning the sequela probability of an infectious disease patient based on similarity prediction proposed by the present invention. First, by calculating the weights of all associated indicators for the sequela risk early warning of an infectious disease patient, the associated indicators with high influence are found as the predicted index data. Then, the sequela risk of the to-be-predicted infectious disease patient is calculated through the historical big data correlation calculation method using the predicted index data to obtain the sequela risk early warning result. The method proposed by the present invention can, on the one hand, avoid patients frequently going to previous medical treatments to save the time cost of users, and on the other hand, the calculated sequela risk early warning result is more accurate.

[0103] Although the description of the present invention has been quite detailed and several of the described embodiments have been described in particular, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be regarded as providing a broad interpretation of these claims in light of the prior art by reference to the appended claims, so as to effectively cover the intended scope of the present invention. In addition, the present invention is described above with embodiments foreseeable by the inventor for the purpose of providing a useful description, and those non-substantive modifications to the present invention that are not currently foreseeable may still represent equivalent modifications of the present invention.

[0104] As described above, it is only a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. As long as the same means are used to achieve the technical effects of the present invention, they should fall within the protection scope of the present invention. Within the protection scope of the present invention, various different modifications and changes can be made to its technical solutions and / or embodiments.

Claims

1. An evaluation and early warning method for the probability of sequelae in infectious disease patients based on similarity prediction, characterized in that Including the following: Determine all associated indicators for risk warning of sequelae in infectious disease patients; Determine the weight values of all associated indicators, and select the associated indicators with weight values ranked higher than the ranking threshold from all associated indicators as prediction indicator data; Based on the prediction indicator data, sample infectious disease patients to obtain a sample data set. The sampling of infectious disease patients refers to sampling patients with sequelae and those without sequelae among infectious disease patients. The sample data set refers to the data set composed of the prediction indicator data of each sampled infectious disease patient; Obtain the prediction indicator data of the infectious disease patient to be predicted; Based on the sample data set, conduct risk warning of sequelae for the prediction indicator data of the infectious disease patient to be predicted to obtain a risk warning result of sequelae.

2. The method for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction according to claim 1, wherein Specifically, determining the weight values of all associated indicators includes If there are m types of associated indicators in total; Standardize the m types of associated indicators to obtain m standardized associated indicators; Calculate the information entropy of each type of associated indicator, and its calculation formula is as follows Among them, H j represents the information entropy of the j-th associated index, and p ij is the proportion of the i-th associated index after standardization on the j-th associated index, and k is a preset constant; Calculate its corresponding weight according to the information entropy of each type of associated indicator, and its calculation formula is as follows Among them, w j represents the weight of the j-th associated index.

3. The method for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction according to claim 2, wherein, Specifically, select the associated indicators with weight values ranked higher than the top 4 from all associated indicators as prediction indicator data, and record them as the first prediction indicator, the second prediction indicator, the third prediction indicator, and the fourth prediction indicator according to the ranking.

4. The method and device for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction according to claim 3, characterized in that, Specifically, based on the sample data set, conducting risk warning of sequelae for the prediction indicator data of the infectious disease patient to be predicted includes Record the sample data set as set Sp_set. The number of elements in set Sp_set, that is, the number of sampled infectious disease patients, is mm. In set Sp_set, Sp_set(mk) represents the relevant data of the sampled infectious disease patient with the serial number mk, and mk ∈ [1, mm]; Construct a three-dimensional space coordinate system with the second prediction indicator, the third prediction indicator, and the fourth prediction indicator as the X-axis, Y-axis, and Z-axis respectively; Then the position coordinates corresponding to Sp_set(mk) in the three-dimensional space coordinate system are x(mk), y(mk), and z(mk); Among them, x(mk) represents the coordinate of the element with serial number mk on the X-axis, y(mk) represents the coordinate of the element with serial number mk on the Y-axis, and z(mk) represents the height of the element with serial number mk from the x-axis plane, that is, z(mk) represents the plane composed of target prediction points with the same distance from the x-axis plane; Add the prediction indicator data of the infectious disease patient to be predicted to set Sp_set and record it as Sp_set(mk); At this time, obtain the two elements with the smallest Euclidean distance from Sp_set(mk) on the three-dimensional space coordinate system, record one of the elements as Sp_set(mk1), and record the other element as Sp_set(mk2); the coordinates of element Sp_set(mk1) are x(mk1), y(mk1), and z(mk1), and the coordinates of element Sp_set(mk2) are x(mk2), y(mk2), and z(mk2); Obtain the first prediction index corresponding to the element Sp_set(mk1) and denote it as W(mk1), and obtain the first prediction index corresponding to the element Sp_set(mk2) and denote it as W(mk2); Obtain the corresponding plane of z(mk1) and denote it as Pla(mk1), and obtain the corresponding plane of z(mk2) and denote it as Pla(mk2); Obtain the set composed of the elements in the three-dimensional space coordinate system that fall on Pla(mk1) as Set(mk1). The number of elements in Set(mk1) is r1, the serial number of the elements in Set(mk1) is v1, v1 ∈ [1, r1], the element with serial number v1 in Set(mk1) is Set(mk1, v1), and the corresponding position coordinates of Set(mk1, v1) are x(mk1, v1), y(mk1, v1) and z(mk1, v1); Obtain the set composed of the elements in the three-dimensional space coordinate system that fall on Pla(mk2) as Set(mk2). The number of elements in Set(mk2) is r2, the serial number of the elements in Set(mk2) is v2, v2 ∈ [1, r2], the element with serial number v2 in Set(mk2) is Set(mk2, v2), and the corresponding position coordinates of Set(mk2, v2) are x(mk2, v2), y(mk2, v2) and z(mk2, v2); Calculate the sequelae correlation index seq_rel(mk) of Sp_set(mk) as follows: where E_D(O, P) represents calculating the Euclidean distance between element O and element P; Obtain the elements in the sampling data set that are on the Pla(mk1) plane and calculate the mean value of the first prediction index corresponding to each element as W(Pla(mk1)), and obtain the elements in the sampling data set that are on Pla(mk2) and calculate the mean value of the first prediction index corresponding to each element as W(Pla(mk2)); Then the calculation formula of the sequelae risk index W(mk) of Sp_set(mk) is as follows, W(mk) = [W(Pla(mk1)) + W(Pla(mk2))] * seq_rel(mk) * β / 2, where β is a compensation coefficient, which is a value set manually; After that, judge whether W(mk) is greater than the preset sequelae risk index threshold. If so, judge that the infectious disease patient to be predicted has a high sequelae risk. If not, judge that the infectious disease patient to be predicted has a low sequelae risk.

5. The method for evaluating and warning the probability of sequelae of infectious disease patients based on similarity prediction according to claim 4, wherein, The method further includes, For infectious disease patients with a high sequelae risk, remind them to go to the hospital for a follow-up visit by text message according to a preset first cycle; For infectious disease patients with a low sequelae risk, remind them to continue to provide prediction index data for a follow-up visit by text message according to a preset second cycle.

6. An early warning device for evaluating the probability of sequelae in infectious disease patients based on similarity prediction, characterized in that, Include the following: An index determination module, used to determine all associated indexes for the sequelae risk warning of infectious disease patients; A prediction data determination module, used to determine the weight values of all associated indexes, and select the associated indexes with weight values ranked higher than the ranking threshold from all associated indexes as prediction index data; A sample data acquisition module, which is used to sample infectious disease patients based on prediction index data to obtain a sampling data set. The sampling of infectious disease patients refers to sampling both patients with sequelae and those without sequelae among infectious disease patients. The sampling data set refers to a data set jointly composed of the prediction index data of each sampled infectious disease patient; A prediction data acquisition module, which is used to obtain the prediction index data of the infectious disease patient to be predicted; A warning analysis module, which is used to conduct a sequela risk warning on the prediction index data of the infectious disease patient to be predicted based on the sampling data set, and obtain a sequela risk warning result.

Images