A medical prevention decision-making system based on information technology

Abstract

The present invention provides an information-based medical prevention decision system, which belongs to the field of intelligent decision technology and includes: a vector comparison module, which is used to obtain the detection information of target patients under different medical subjects based on an information platform, and standardize the detection information under each subject respectively and combine the set judgment vector under the corresponding subject to obtain the examination result of the corresponding subject; a measure acquisition module, which is used to obtain preventive measures consistent with each examination result; a subtree construction module, which is used to obtain several combination results according to the subject combination method and combine the preventive measures to construct several sub-decision trees; a combined tree construction module, which is used to set link lines to all sub-decision trees according to the prevention association relationship and treatment association relationship between each combination result to obtain a combined decision tree; a decision analysis module, which is used to perform final decision analysis on the combined decision tree and output a medical prevention decision. The decision time is effectively saved and the decision efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent decision-making, and in particular to an information-based medical prevention decision-making system. Background Art

[0002] The common prevention method now is to require people to go for physical examinations on time to determine whether they have any diseases. However, this method generally only checks some subjects and does not involve other subjects, which greatly reduces the inspection effect and subsequent prevention effect. After the inspection results come out, it is necessary to take the inspection results to the relevant professional doctors to determine whether there is a disease and whether prevention is needed. In this process, since the professional doctors under each subject are not necessarily the same person, this undoubtedly wastes a lot of time and reduces decision-making efficiency.

[0003] Therefore, the present invention proposes an information-based medical prevention decision-making system. Summary of the invention

[0004] The present invention provides an information-based medical prevention decision system, which is used to ensure the integrity of measure acquisition by comprehensively acquiring the examination results of multiple subjects, and to intelligently output prevention decisions to ensure their reliability by constructing sub-decision trees of different subject combinations and links between trees, thereby effectively saving decision-making time and improving decision-making efficiency.

[0005] The present invention provides an information-based medical prevention decision-making system, comprising:

[0006] The vector comparison module is used to obtain the test information of the target patient under different medical subjects based on the information platform, and standardize the test information under each subject and combine it with the set judgment vector under the corresponding subject to obtain the examination result of the corresponding subject;

[0007] A measures acquisition module, used to acquire preventive measures consistent with each inspection result;

[0008] A subtree construction module is used to obtain several combination results of all inspection results according to the subject combination method and to construct a sub-decision tree for each combination result in combination with preventive measures;

[0009] A combined tree construction module is used to set link lines to all sub-decision trees to obtain a combined decision tree according to the prevention association relationship and the treatment association relationship between each combined result;

[0010] The decision analysis module is used to perform a final decision analysis on the combined decision tree and output a medical prevention decision.

[0011] Preferably, the vector comparison module includes:

[0012] The factor determination unit is used to extract sub-information of each detection element from the detection information under each subject, and based on the current fluctuation range The numerical distribution probability diagram determines the stability coefficient on the left , right stability coefficient And the overall stability factor , determine the left adjustment factor and the right adjustment factor;

[0013] A boundary adjustment unit is used to adjust the current fluctuation range according to the left adjustment factor Tz and the right adjustment factor Ty. Adjust the boundaries to get the current effective range ;

[0014] ;

[0015] A vector construction unit, used to standardize the middle value of the current valid range corresponding to each detection element, and construct an actual detection vector of the corresponding subject;

[0016] a deviation determination unit, configured to calculate a first detection deviation of each detection element according to the actual detection vector and a set judgment vector under a corresponding subject, and adjust the first detection deviation to obtain a second detection deviation in combination with a detection influence relationship between different detection elements under a subject;

[0017] An error determination unit, used to determine the detection error of the corresponding subject according to the comparison result between the actual detection vector and the set judgment vector under the corresponding subject and in combination with the detection influence relationship, and at the same time, classify the deviations of all second detection deviations;

[0018] A result compensation unit, configured to use the detection error as a radius and a representative deviation under each deviation classification as a center point to search for a third detection deviation, and compensate the comparison result according to the third detection deviation to obtain a detection result;

[0019] Preferably, the factor determination unit comprises:

[0020] ;

[0021] Among them, Tz is the corresponding left adjustment factor; Ty is the corresponding right adjustment factor; is a moderating variable, with a value of 1 or -1; Based on all Fitting coefficients of the sequentially connected plotted curves; Based on all Fitting coefficients of the sequentially connected plotted curves; represents the amount of information on the i1th vertical axis in the left half of the numerical distribution probability graph, nz and ny represent the number of axes in the left half and the number of axes in the right half of the numerical distribution probability graph, respectively, and nz=ny; Indicates all The mean of Indicates all The mean of Indicates all The maximum value in ; Indicates all The maximum value in .

[0022] Preferably, the measure acquisition module includes:

[0023] A platform acquisition unit, used to obtain results matching the subject type from the information platform - prevention database;

[0024] A measure acquisition unit is used to acquire preventive measures consistent with the inspection results of the corresponding subject based on the result-prevention database.

[0025] Preferably, the subtree construction module includes:

[0026] A combination and measure combination unit, used to combine the examination results involved in each subject combination method according to the preset subject association table of medical subjects, and at the same time, combine the preventive measures corresponding to the examination results involved in the subject combination method;

[0027] A tree matching unit, used for obtaining an initial tree consistent with the corresponding subject combination mode based on the mode-tree comparison table, wherein the initial tree includes a node where each subject is located under the corresponding subject combination mode;

[0028] A coefficient determination unit, used to determine the correlation coefficient and the importance coefficient of each inspection result in the combination result, and determine the branch width adjustment coefficient of the corresponding node;

[0029] A calibration unit, configured to calibrate the significance of the corresponding node if the branch width adjustment coefficient is greater than or equal to a preset adjustment coefficient;

[0030] The measure optimization unit is used to determine the significance coefficient of each node based on the calibration result of the initial tree, and control the combination measures to be attached to the corresponding nodes in sequence based on the ranking result of the significance coefficient to obtain a sub-decision tree.

[0031] Preferably, the combined tree construction module includes:

[0032] A bias determination unit, for determining the subject bias association between the corresponding combination result and each remaining combination result according to the subject combination mode corresponding to each combination result, and then searching the prevention association relationship and treatment association relationship consistent with the subject bias association from the bias set;

[0033] a tag search unit, configured to search for a first link tag from a first database according to the prevention association relationship, and search for a second link tag from a second database according to the treatment association relationship;

[0034] The line establishing unit is used to establish a link line according to the mapping relationship between the first link label and the second link label, and link all the sub-decision trees to obtain a combined decision tree.

[0035] Preferably, the decision analysis module includes:

[0036] A starting point determination unit is used to select a sub-decision tree corresponding to the maximum coefficient as a decision starting point according to the severity coefficient of the examination results under each subject;

[0037] A multiple traversal unit, used to match a traversal engine consistent with all subjects from an engine database, and traverse the combined decision tree multiple times based on the starting point as the traversal entry, and obtain each traversal trajectory and a decision action set of each sub-decision tree under the corresponding traversal trajectory respectively, and combine the preventive health boundary set of each sub-decision tree to obtain a decision function based on each traversal;

[0038] The processing unit is used to pre-process all decision functions to obtain preventive decisions.

[0039] Preferably, the processing unit comprises:

[0040] A parameter unit, used to obtain the decision parameters of each decision function and input them into a blank parameter table;

[0041] A frequency determination unit, which determines the number of occurrences of the same decision parameter based on the input result;

[0042] A locking unit, used to lock the first parameter whose occurrence number is greater than the corresponding first preset threshold and the second parameter whose occurrence number is greater than the corresponding second preset threshold and less than the first preset threshold;

[0043] A decision mapping unit is used to perform decision mapping on a comprehensive function based on the first parameter and the second parameter to obtain a preventive decision.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The integrity of measures is ensured by comprehensively acquiring inspection results of multiple subjects, and by constructing sub-decision trees with different subject combinations and links between trees, the reliability of preventive decisions is ensured through intelligent output, which effectively saves decision-making time and improves decision-making efficiency.

[0046] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0047] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0049] Figure 1 is a structural diagram of an information-based medical prevention decision-making system in an embodiment of the present invention;

[0050] Figure 2 It is a probability diagram of numerical distribution in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0052] The present invention provides an information-based medical prevention decision-making system, such as Figure 1 As shown, including:

[0053] The vector comparison module is used to obtain the test information of the target patient under different medical subjects based on the information platform, and standardize the test information under each subject and combine it with the set judgment vector under the corresponding subject to obtain the examination result of the corresponding subject;

[0054] A measures acquisition module, used to acquire preventive measures consistent with each inspection result;

[0055] A subtree construction module is used to obtain several combination results of all inspection results according to the subject combination method and to construct a sub-decision tree for each combination result in combination with preventive measures;

[0056] A combined tree construction module is used to set link lines to all sub-decision trees to obtain a combined decision tree according to the prevention association relationship and the treatment association relationship between each combined result;

[0057] The decision analysis module is used to perform a final decision analysis on the combined decision tree and output a medical prevention decision.

[0058] In this embodiment, medical subjects are derived based on medical departments, which are generally divided into orthopedics, surgery, internal medicine, dermatology, pediatrics, gynecology, dentistry, acupuncture and massage, ENT, ophthalmology, rehabilitation, etc., and each examination item involved in each department can be regarded as a subject, such as endocrine examination items, five cell examination items, chest CT examination items, heart rate examination items, etc.

[0059] In this embodiment, the detection information refers to the inspection results obtained based on the corresponding inspection items. For example, the heart rate inspection item is to obtain the number of heart beats per minute in 20 minutes, so 20 heart rate values ​​will be obtained.

[0060] In this embodiment, during the process of checking each item, multiple tests may be performed to ensure the reliability of the test information, so that each test element will have multiple related test values.

[0061] In this embodiment, the purpose of standardization is to perform numerical standardization on the detection information to facilitate comparison with the set judgment vector.

[0062] In this embodiment, the setting judgment vector is pre-set, that is, it is composed of standard values ​​of different detection elements under corresponding subjects.

[0063] In this embodiment, the inspection result is the physical abnormality existing after the two vectors are compared.

[0064] In this embodiment, preventive measures refer to plans for preventing abnormal physical conditions. For example, if the measured blood pressure is 1 value higher than the normal range, a light diet is required for prevention.

[0065] In this embodiment, the subject combination method is pre-set. For example, the subject combination method includes subject 1, subject 2 and subject 3. At this time, the inspection results under subject 1, subject 2 and subject 3 are combined together, and the result is the combined result.

[0066] In this embodiment, each subject combination has its corresponding initial tree, but the initial tree only has the connection relationship between subjects and does not have specific parameters. It is necessary to fill in information based on the matching combination results and preventive measures to obtain a sub-decision tree to provide a basis for subsequent decision analysis.

[0067] In this embodiment, for example, the combination results include high blood pressure and dizziness, and generally high blood pressure can lead to dizziness. In this case, the prevention association is to prevent high blood pressure to reduce dizziness, and the treatment association may be that only high blood pressure drugs are needed, or both high blood pressure drugs and dizziness treatment drugs are needed as an aid.

[0068] In this embodiment, the purpose of setting the link line is to associate all the sub-decision trees to obtain a combined decision tree, so as to determine the overall physical condition of the patient and ensure the rationality of prevention.

[0069] In this embodiment, the final decision analysis is to effectively screen the decision parameters of the combined decision tree to ensure the reliability of the preventive decision.

[0070] The beneficial effects of the above technical solution are: by comprehensively obtaining the inspection results of multiple subjects to ensure the integrity of the measures obtained, and by constructing sub-decision trees with different subject combinations and links between trees, the intelligent output of preventive decisions ensures their reliability, effectively saving decision-making time and improving decision-making efficiency.

[0071] The present invention provides an information-based medical prevention decision-making system, wherein the vector comparison module comprises:

[0072] The factor determination unit is used to extract sub-information of each detection element from the detection information under each subject, and based on the current fluctuation range The numerical distribution probability diagram determines the stability coefficient on the left , right stability coefficient And the overall stability factor , determine the left adjustment factor and the right adjustment factor;

[0073] A boundary adjustment unit is used to adjust the current fluctuation range according to the left adjustment factor Tz and the right adjustment factor Ty. Adjust the boundaries to get the current effective range ;

[0074] ;

[0075] A vector construction unit, used to standardize the middle value of the current valid range corresponding to each detection element, and construct an actual detection vector of the corresponding subject;

[0076] a deviation determination unit, configured to calculate a first detection deviation of each detection element according to the actual detection vector and a set judgment vector under a corresponding subject, and adjust the first detection deviation to obtain a second detection deviation in combination with a detection influence relationship between different detection elements under a subject;

[0077] An error determination unit, used to determine the detection error of the corresponding subject according to the comparison result between the actual detection vector and the set judgment vector under the corresponding subject and in combination with the detection influence relationship, and at the same time, classify the deviations of all second detection deviations;

[0078] A result compensation unit, configured to use the detection error as a radius and a representative deviation under each deviation classification as a center point to search for a third detection deviation, and compensate the comparison result according to the third detection deviation to obtain a detection result;

[0079] Preferably, the factor determination unit comprises:

[0080] ;

[0081] Among them, Tz is the corresponding left adjustment factor; Ty is the corresponding right adjustment factor; is a moderating variable, with a value of 1 or -1; Based on all Fitting coefficients of the sequentially connected plotted curves; Based on all Fitting coefficients of the sequentially connected plotted curves; represents the amount of information on the i1th vertical axis in the left half of the numerical distribution probability graph, nz and ny represent the number of axes in the left half and the number of axes in the right half of the numerical distribution probability graph, respectively, and nz=ny; Indicates all The mean of Indicates all The mean of Indicates all The maximum value in ; Indicates all The maximum value in .

[0082] In this embodiment, the sub-information of the detection element is a numerical value, such as heart rate, which is measured 20 times. Then, the numerical distribution probability diagram based on the heart rate is obtained as follows: the horizontal axis is the heart rate parameter, and the vertical axis is the number of measurements. Figure 2 As shown, all the sub-information of the heart rate is fully reflected in the figure, and the circles in the figure represent the heart rate values ​​at the corresponding times.

[0083] In this embodiment, the current fluctuation range is constructed based on the maximum and minimum values ​​of all sub-information under the same detection element, and the maximum value is , the minimum value is .

[0084] In this embodiment, the actual detection vector={the intermediate value corresponding to each detection element}.

[0085] In this embodiment, the first detection deviation=|the middle value of the same detection element-the standard setting value| / the standard setting value.

[0086] In this embodiment, when the detection influence relationship does not exist, the second detection deviation is the first detection deviation.

[0087] The detection influence relationship and the corresponding influence coefficient are set in advance by experts. The second detection deviation = the first detection deviation × (1 + the influence coefficient under the detection influence relationship).

[0088] In this embodiment, the comparison result is the absolute value of the difference of each inspection element.

[0089] In this embodiment, the detection error is determined by analyzing the comparison result through the detection influence relationship to determine whether the comparison result obtained tends to the normal rule. For example, the difference of detection element 1 is a1, and the difference of detection element 2 is a2. After the analysis based on the inspection influence relationship, the difference a1 and the difference a2 are in line with the normal rule. At this time, the error is regarded as 0. If it does not conform to the normal rule, the corresponding detection error is obtained according to the absolute value deviation of the difference a1, the difference a2 and the normal rule / the set threshold under the normal rule.

[0090] That is to say, for example, the measured hypertension of detection element 1 is d1, and the dizziness index is h1. The normal rule should be: hypertension is d1, and the dizziness index is h0, or the dizziness index is h0, and the hypertension is d2. At this time, (the absolute value deviation of a2 of the difference between h1 and h0 / h0) × corresponding conversion coefficient + (the absolute value deviation of a1 of the difference between d1 and d2 / d2) × corresponding conversion coefficient, and then based on the calculation result, the detection error is obtained from the error comparison table, which includes the calculation results under different detection elements and the corresponding detection errors.

[0091] In this embodiment, the second detection deviation is numerically normalized and then classified according to a set deviation range, so that several deviation classifications can be obtained.

[0092] In this embodiment, the value that appears most frequently in each deviation classification is regarded as the center point, and the detection error is used to search for the values ​​under the corresponding classification. The search result is regarded as the third detection deviation. For example, the values ​​of classification A1 are: 0.3, 0.6, 0.5, 0.5. At this time, the detection error is 0.1, and the center point is 0.5. At this time, the values ​​of 0.4 to 0.6 are searched around 0.5, and finally 0.5, 0.5, and 0.6 are obtained. The variance of these three is calculated and added to the result after the original value is standardized.

[0093] In this embodiment, the comparison result compensation is to obtain the variance of all third detection deviations and add them to the comparison result of the corresponding detection element.

[0094] The beneficial effect of the above technical solution is: by extracting sub-information of each detection element from the detection information to construct a numerical distribution probability map, and then calculating the stability coefficient to obtain the adjustment factor, the effectiveness of the subsequent construction of the actual detection vector is ensured, and further compared with the set judgment vector to determine the detection error and the classification of the deviation, so as to achieve accurate adjustment of the comparison results, ensure the reliability of the results, and provide a basis for subsequent intelligent decision-making.

[0095] The present invention provides an information-based medical prevention decision-making system, wherein the measure acquisition module comprises:

[0096] A platform acquisition unit, used to obtain results matching the subject type from the information platform - prevention database;

[0097] A measure acquisition unit is used to acquire preventive measures consistent with the inspection results of the corresponding subject based on the result-prevention database.

[0098] In this embodiment, the information platform is a platform for calling various test results and various medical-related databases.

[0099] In this embodiment, the result-prevention database contains different inspection results and set preventive measures.

[0100] The beneficial effect of the above technical solution is: obtaining a database from the platform facilitates preventive measures to obtain inspection results.

[0101] The present invention provides an information-based medical prevention decision-making system, wherein the subtree construction module comprises:

[0102] A combination and measure combination unit, used to combine the examination results involved in each subject combination method according to the preset subject association table of medical subjects, and at the same time, combine the preventive measures corresponding to the examination results involved in the subject combination method;

[0103] A tree matching unit, used for obtaining an initial tree consistent with the corresponding subject combination mode based on the mode-tree comparison table, wherein the initial tree includes a node where each subject is located under the corresponding subject combination mode;

[0104] A coefficient determination unit, used to determine the correlation coefficient and the importance coefficient of each inspection result in the combination result, and determine the branch width adjustment coefficient of the corresponding node;

[0105] A calibration unit, configured to calibrate the significance of the corresponding node if the branch width adjustment coefficient is greater than or equal to a preset adjustment coefficient;

[0106] The measure optimization unit is used to determine the significance coefficient of each node based on the calibration result of the initial tree, and control the combination measures to be attached to the corresponding nodes in sequence based on the ranking result of the significance coefficient to obtain a sub-decision tree.

[0107] In this embodiment, the preset subject association table is pre-set, and the table contains a number of subject combination methods. The results and measures can be directly combined in sequence according to the table.

[0108] In this embodiment, the method-tree comparison table includes initial trees under different subject combination methods, which facilitates the assignment of actual parameters to the tree in combination with actual conditions.

[0109] In this embodiment, the correlation coefficient is calculated based on a similarity function, which belongs to the prior art. The correlation coefficient between the inspection result and each of the other results can be obtained.

[0110] Importance coefficient = number of results associated with the same test result / total number of results.

[0111] In this embodiment, the branch width adjustment coefficient=importance coefficient+ln(1+correlation coefficient).

[0112] In this embodiment, the preset adjustment coefficient is pre-set and has a value of 0.5.

[0113] In this embodiment, the significance calibration is to display the color of the node by color marking.

[0114] In this embodiment, the significance coefficient is obtained based on the color-coefficient comparison table to obtain the corresponding coefficient, and then sorted by size. The table contains different colors and coefficients matching the values, which can be directly obtained.

[0115] In this embodiment, the combination measures are controlled to be added in order according to the size sorting results in order to ensure orderly addition and improve construction efficiency.

[0116] The beneficial effects of the above technical solution are: obtaining the initial tree based on the comparison table facilitates the subsequent additional information, and by analyzing the combination results to determine the node significance coefficients, the coefficients are sorted by size, and then the control measures are added in sequence to ensure orderly progress, thereby indirectly improving decision-making efficiency.

[0117] The present invention provides an information-based medical prevention decision-making system, wherein the combination tree construction module comprises:

[0118] A bias determination unit, for determining the subject bias association between the corresponding combination result and each remaining combination result according to the subject combination mode corresponding to each combination result, and then searching the prevention association relationship and treatment association relationship consistent with the subject bias association from the bias set;

[0119] a tag search unit, configured to search for a first link tag from a first database according to the prevention association relationship, and search for a second link tag from a second database according to the treatment association relationship;

[0120] The line establishing unit is used to establish a link line according to the mapping relationship between the first link label and the second link label, and link all the sub-decision trees to obtain a combined decision tree.

[0121] In this embodiment, the subject bias association is obtained based on a double combination method-bias comparison table, and the comparison table contains different double combination methods and subject bias associations based on different combination results under the method.

[0122] Moreover, the bias set is also pre-planned based on the double combination method, including different combination results under different double combinations involving prevention associations and treatment associations.

[0123] In this embodiment, the first database contains prevention associations and related setting marks, and is unique, and the second database contains treatment associations and related setting marks, and is unique. For example, the prevention association is to prevent high blood pressure to reduce dizziness. In this case, it is marked as #1. The treatment association may require only high blood pressure drugs, or both high blood pressure drugs and dizziness treatment drugs as an aid. In this case, it is marked as #2.

[0124] In this embodiment, the combined label-route mapping table can obtain the link route based on the first link label and the second link label, that is, the link route #1~#2. Finally, the sub-decision trees are linked according to the link route to obtain the mapping relationship between the first link label and the second link label: #1~#2.

[0125] The beneficial effect of the above technical solution is: two association relationships are obtained by subject combination, and then the link line is obtained by searching the mark from the database, and the combined decision tree is obtained by linking, which provides a basis for obtaining preventive decisions.

[0126] The present invention provides an information-based medical prevention decision-making system, wherein the decision analysis module comprises:

[0127] A starting point determination unit is used to select a sub-decision tree corresponding to the maximum coefficient as a decision starting point according to the severity coefficient of the examination results under each subject;

[0128] A multiple traversal unit, used to match a traversal engine consistent with all subjects from an engine database, and traverse the combined decision tree multiple times based on the starting point as the traversal entry, and obtain each traversal trajectory and a decision action set of each sub-decision tree under the corresponding traversal trajectory respectively, and combine the preventive health boundary set of each sub-decision tree to obtain a decision function based on each traversal;

[0129] The processing unit is used to pre-process all decision functions to obtain preventive decisions.

[0130] In this embodiment, the severity coefficient=the cumulative sum of the absolute average value of the same element under the corresponding examination result multiplied by the corresponding element.

[0131] In this embodiment, the maximum coefficient refers to the maximum value of all severity coefficients, which facilitates the determination of the starting point for entry and traversal.

[0132] In this embodiment, the engine database includes various engines that are set and are related to the combination subjects.

[0133] In this embodiment, multiple traversals refer to traversing the combined decision tree with the starting point as the entry. It is only necessary to ensure that the entry is consistent. As for whether the trajectories involved in the traversal process are consistent, there is no need to consider whether the traversal trajectory and decision action set after each traversal need to be obtained. The decision action set refers to the response of the engine to the corresponding sub-decision tree when passing through each sub-decision tree. For example, the decision action set of sub-decision tree 1 is: {decision action 1 decision action 2 decision action 3}.

[0134] In this embodiment, the preventive health boundary set includes the health boundaries of decision indicators corresponding to different decision actions, so as to determine whether it exceeds the health range or reaches the health boundary, which is convenient for effective prevention.

[0135] In this embodiment, the decision function is determined based on the unhealthy information of each sub-decision tree in each traversal and the preventive measures against the unhealthy information.

[0136] Preventive decisions can be obtained by analyzing decision variables for all decision functions.

[0137] The beneficial effects of the above technical solution are: determining the starting point through the severity coefficient provides an entry for subsequent traversal, ensuring the efficiency of subsequent traversal, and further traversing the combined decision tree multiple times to perform combined analysis to obtain the decision function, that is, multi-party verification of inspection results and preventive measures to ensure the rationality of preventive decisions.

[0138] The present invention provides an information-based medical prevention decision-making system, wherein the processing unit comprises:

[0139] A parameter unit, used to obtain the decision parameters of each decision function and input them into a blank parameter table;

[0140] A frequency determination unit, which determines the number of occurrences of the same decision parameter based on the input result;

[0141] A locking unit, used to lock the first parameter whose occurrence number is greater than the corresponding first preset threshold and the second parameter whose occurrence number is greater than the corresponding second preset threshold and less than the first preset threshold;

[0142] A decision mapping unit is used to perform decision mapping on a comprehensive function based on the first parameter and the second parameter to obtain a preventive decision.

[0143] In this embodiment, the blank parameter table is a representation containing various decision parameters, and specific values ​​do not exist. Therefore, the number of occurrences is counted by entering the parameters in the table.

[0144] In this embodiment, for example, the number of occurrences of decision parameter 1 is 2, and the number of occurrences of decision parameter 2 is 4. Assuming that the first preset threshold is 3 and the second preset threshold is 1, at this time, decision parameter 2 is the first parameter and decision parameter 1 is the second parameter.

[0145] In this embodiment, the comprehensive function is constructed based on the first parameter and the second parameter, and the decision mapping is based on the comprehensive function to determine measures related to the first parameter and the second parameter from all preventive measures as preventive decisions.

[0146] The beneficial effect of the above technical solution is that by counting the number of occurrences of decision parameters and comparing them with preset thresholds, it is convenient to effectively map and screen measures and ensure the reliability of preventive decisions.

[0147] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A medical prevention decision-making system based on information technology, characterized in that: include: The vector comparison module is used to obtain the test information of the target patient under different medical subjects based on the information platform, and standardize the test information under each subject and combine it with the set judgment vector under the corresponding subject to obtain the examination result of the corresponding subject; A measures acquisition module, used to acquire preventive measures consistent with each inspection result; A subtree construction module is used to obtain several combination results of all inspection results according to the subject combination method and to construct a sub-decision tree for each combination result in combination with preventive measures; A combined tree construction module is used to set link lines to all sub-decision trees to obtain a combined decision tree according to the prevention association relationship and the treatment association relationship between each combined result; A decision analysis module, used for performing a final decision analysis on the combined decision tree and outputting a medical prevention decision; Wherein, the vector comparison module includes: The factor determination unit is used to extract sub-information of each detection element from the detection information under each subject, and based on the current fluctuation range The numerical distribution probability diagram determines the stability coefficient on the left , right stability coefficient And the overall stability factor , determine the left adjustment factor and the right adjustment factor; A boundary adjustment unit is used to adjust the current fluctuation range according to the left adjustment factor Tz and the right adjustment factor Ty. Adjust the boundaries to get the current effective range ; ； A vector construction unit, used to standardize the middle value of the current valid range corresponding to each detection element, and construct an actual detection vector of the corresponding subject; a deviation determination unit, configured to calculate a first detection deviation of each detection element according to the actual detection vector and a set judgment vector under a corresponding subject, and adjust the first detection deviation to obtain a second detection deviation in combination with a detection influence relationship between different detection elements under a subject; An error determination unit, used to determine the detection error of the corresponding subject according to the comparison result between the actual detection vector and the set judgment vector under the corresponding subject and in combination with the detection influence relationship, and at the same time, classify the deviations of all second detection deviations; A result compensation unit, configured to use the detection error as a radius and a representative deviation under each deviation classification as a center point to search for a third detection deviation, and compensate the comparison result according to the third detection deviation to obtain a detection result; Wherein, the factor determination unit includes: ； Among them, Tz is the corresponding left adjustment factor; Ty is the corresponding right adjustment factor; is a moderating variable, with a value of 1 or -1; Based on all Fitting coefficients of the sequentially connected plotted curves; Based on all Fitting coefficients of the sequentially connected plotted curves; represents the amount of information on the i1th vertical axis in the left half of the numerical distribution probability graph, nz and ny represent the number of axes in the left half and the number of axes in the right half of the numerical distribution probability graph, respectively, and nz=ny; Indicates all The mean of Indicates all The mean of Indicates all The maximum value in ; Indicates all The maximum value in .

2. The information-based medical prevention decision-making system according to claim 1 is characterized in that: The measure acquisition module includes: A platform acquisition unit, used to obtain results matching the subject type from the information platform - prevention database; A measure acquisition unit is used to acquire preventive measures consistent with the inspection results of the corresponding subject based on the result-prevention database.

3. The information-based medical prevention decision-making system according to claim 1 is characterized in that: The subtree construction module includes: A measure combination unit, used to combine the inspection results involved in each subject combination mode according to the preset subject association table of medical subjects, and at the same time, combine the preventive measures corresponding to the inspection results involved in the subject combination mode; A tree matching unit, used for acquiring an initial tree consistent with the corresponding subject combination mode based on the mode-tree comparison table, wherein the initial tree includes a node where each subject is located under the corresponding subject combination mode; A coefficient determination unit, used to determine the correlation coefficient and the importance coefficient of each inspection result in the combination result, and determine the branch width adjustment coefficient of the corresponding node; A calibration unit, configured to calibrate the significance of the corresponding node if the branch width adjustment coefficient is greater than or equal to a preset adjustment coefficient; The measure optimization unit is used to determine the significance coefficient of each node based on the calibration result of the initial tree, and control the combination measures to be attached to the corresponding nodes in sequence based on the ranking result of the significance coefficient to obtain a sub-decision tree.

4. The information-based medical prevention decision-making system according to claim 3 is characterized in that: The combined tree construction module comprises: A bias determination unit, for determining the subject bias association between the corresponding combination result and each remaining combination result according to the subject combination mode corresponding to each combination result, and then searching the prevention association relationship and treatment association relationship consistent with the subject bias association from the bias set; a tag search unit, configured to search for a first link tag from a first database according to the prevention association relationship, and search for a second link tag from a second database according to the treatment association relationship; The line establishing unit is used to establish a link line according to the mapping relationship between the first link label and the second link label, and link all the sub-decision trees to obtain a combined decision tree.

5. The information-based medical prevention decision-making system according to claim 1 is characterized in that: The decision analysis module comprises: A starting point determination unit is used to select a sub-decision tree corresponding to the maximum coefficient as a decision starting point according to the severity coefficient of the examination results under each subject; A multiple traversal unit, used to match a traversal engine consistent with all subjects from an engine database, and traverse the combined decision tree multiple times based on the starting point as the traversal entry, and obtain each traversal trajectory and a decision action set of each sub-decision tree under the corresponding traversal trajectory respectively, and combine the preventive health boundary set of each sub-decision tree to obtain a decision function based on each traversal; The processing unit is used to pre-process all decision functions to obtain preventive decisions.

6. The information-based medical prevention decision-making system according to claim 5 is characterized in that: The processing unit comprises: A parameter unit, used to obtain the decision parameters of each decision function and input them into a blank parameter table; A frequency determination unit, which determines the number of occurrences of the same decision parameter based on the input result; A locking unit, used to lock the first parameter whose occurrence number is greater than the corresponding first preset threshold and the second parameter whose occurrence number is greater than the corresponding second preset threshold and less than the first preset threshold; A decision mapping unit is used to perform decision mapping on a comprehensive function based on the first parameter and the second parameter to obtain a preventive decision.

Images