DRG automatic grouping method and system based on semantic information fusion

Abstract

The invention relates to the technical field of DRG automatic grouping, and discloses a DRG automatic grouping method and system based on semantic information fusion, and the method comprises the steps: collecting the personal information, medical record information and diagnosis information of a patient to form electronic health record data, carrying out the semantic information extraction of the electronic health record data of the patient, and obtaining a semantic information extraction result; obtaining a segmented semantic information feature vector; semantic enhancement processing is conducted on the segmented semantic information feature vectors, and DRG grouping information of the patients is generated; and carrying out patient clustering processing based on the DRG grouping information and the personal information. According to the method, the segmented semantic information feature vectors are spliced, enhanced and subjected to norm constraint processing, disease group information representing disease diagnosis classes, processing modes and complications of patients is formed, different disease group information is mapped to corresponding DRG codes, DRG grouping information of the patients is obtained, automatic DRG grouping is achieved, and the accuracy of DRG grouping is improved. And carrying out patient clustering and batch distribution of medical resources in combination with personal information.

Description

Technical Field

[0001] The present invention relates to the field of DRG automatic grouping, and in particular to a DRG automatic grouping method and system based on semantic information fusion. Background Art

[0002] In the medical industry, the Diagnosis Related Groups (DRG) system is a widely used patient classification tool that is used to divide hospital patients into several groups, each of which contains clinically similar cases with similar resource consumption. The emergence of the DRG system not only improves the management efficiency of medical services, but also provides a scientific basis for medical insurance reimbursement. At present, many countries in the world have established their own DRG systems for medical expense settlement, hospital performance evaluation and medical service quality control.

[0003] With the development of medical information technology, a large amount of medical data has been accumulated in hospital information systems. These data include structured personal information data and unstructured text data, such as doctors' diagnosis records, operation records and nursing records. These data contain rich medical knowledge and can provide more accurate and comprehensive information support for DRG grouping. However, when using these data for grouping, the existing DRG system mainly relies on structured data and ignores the semantic information in unstructured text data, resulting in certain limitations on the accuracy and scientificity of grouping. Summary of the invention

[0004] In view of this, the present invention proposes a DRG automatic grouping method based on semantic information fusion, which makes full use of structured and unstructured information in medical data for semantic mining and fusion through artificial intelligence technology to improve the accuracy and reliability of DRG grouping.

[0005] To achieve the above object, the present invention provides a DRG automatic grouping method based on semantic information fusion, comprising the following steps:

[0006] S1: Collecting patient personal information, medical history information and diagnosis information to form electronic health record data, wherein the electronic health record data includes structured data and unstructured data, wherein the patient personal information is structured data, and the patient medical history and diagnosis information are unstructured data;

[0007] S2: extracting semantic information from the electronic health record data of the patient to obtain a segmented semantic information feature vector describing the patient information, wherein a multi-scale semantic fusion method is an implementation method of the semantic information extraction;

[0008] S3: Perform semantic enhancement processing on the segmented semantic information feature vector and generate the DRG grouping information of the patient;

[0009] S4: Based on the DRG grouping information and patient personal information, different patients are clustered and processed to obtain several patient clusters. The medical resources required to be consumed by the patients in each patient cluster are approximately the same, wherein the improved peak density estimation is the implementation method of the clustering processing.

[0010] As a further improvement method of the present invention:

[0011] Optionally, the patient's personal information, medical history and diagnosis information collected in step S1 to form electronic health record data includes:

[0012] The personal information, medical history information and diagnosis information of N patients to be grouped into DRGs are collected to form the electronic health record data of the patients, where the electronic health record data of N patients are:

[0013] { X n =( X n 1 , X n 2 , X n 3 )|n∈[1,N]} ;

[0014] ;

[0015] ;

[0016] ;

[0017] in:

[0018] represents the electronic health record data of the nth patient;

[0019] Represents electronic health record data Personal information in represents the gender, age, occupation, height and weight of the nth patient in turn;

[0020] Represents electronic health record data Medical records information in Display medical record information In participle phrases, Display medical record information The i-th participle phrase in Display medical record information The total number of participle phrases in , i ∈ [1, Sum n ] ;

[0021] Represents electronic health record data Diagnostic information in Indicates diagnostic information In participle phrases, Indicates diagnostic information The jth participle phrase in Indicates diagnostic information The total number of participle phrases in .

[0022] Optionally, extracting semantic information from the patient's electronic health record data in step S2 includes:

[0023] Semantic information is extracted from the patient's electronic health record data to obtain a segmented semantic information feature vector describing the patient's information. The semantic information extraction process is as follows:

[0024] S21: Electronic health record data All phrases in are represented by one-hot encoding, and the one-hot encoding vector corresponding to the phrase is obtained;

[0025] S22: Perform word vector representation on the one-hot encoding vectors describing different information respectively to obtain word vector encoding sequences corresponding to different information, where the word vector encoding sequence of the e-th information is:

[0026] X n e = W e *[ C n e (1), C n e (2),..., C n e (S),..., C n e ( S e )],e ∈ {1,2,3} ;

[0027] ;

[0028] in:

[0029] represents the encoding matrix of the e-th type of information, * represents the convolution operation, where the 1st to 3rd types of information are personal information, medical record information, and diagnosis information respectively;

[0030] Display information The one-hot encoding vector corresponding to the Sth phrase in , S ∈[1, S e ] ;

[0031] The word vector encoding sequence representing the e-th information, where ,

[0032] Display information The word vector corresponding to the Sth word group in ;

[0033] S23: Perform multi-scale convolution on word vector encoding sequences of different information to obtain feature information of the word vector encoding sequences at D scales;

[0034] S24: Extract semantic information from multi-scale feature information of different information to obtain electronic health record data The semantic feature vectors representing the patient's personal information, medical record information, and diagnosis information are expressed in the formula for extracting semantic information:

[0035] F n =[ F n 1 , F n 2 , F n 3 ] ,e ∈ {1,2,3} ;

[0036] F n e = ∑ h=1 H [ 1 1+exp(- weight e * X n e,h ) + X n e,h ] ;

[0037] in:

[0038] The semantic feature vector representing the e-th type of information;

[0039] Semantic feature vectors representing patient personal information, medical record information, and diagnosis information in turn;

[0040] The semantic mapping matrix representing the e-th type of information;

[0041] Represents the segmented semantic information feature vector describing the patient information.

[0042] Optionally, in step S23, multi-scale convolution is performed on word vector encoding sequences of different information, including:

[0043] S231: Set the current convolution scale to h, where the initial value of h is 0 and the maximum value is H;

[0044] S232: Generate feature information of each type of information at scale h+1, where the feature information of the e-th type of information at scale h+1 is:

[0045] ;

[0046] ;

[0047] in:

[0048] Represents the characteristic information of the e-th information at scale h+1;

[0049] represents the convolution matrix at scale h; in the embodiment of the present invention, the convolution matrix The size is ;

[0050] S233: Order , return to step S231 until the maximum convolution scale H is reached.

[0051] Optionally, the step S3 performs semantic enhancement processing on the segmented semantic information feature vector, including:

[0052] The segmented semantic information feature vector is semantically enhanced, where the segmented semantic information feature vector corresponding to the nth patient is The semantic enhancement process is as follows:

[0053] S31: Generate disease group information representing the major categories of patient disease diagnosis :

[0054] ;

[0055] A n 2 = exp W 2 1 * F n 2 ∙ ( W 2 2 * F n 2 ) T Len n 2 ] exp W 2 1 * F n 2 ∙ ( W 2 2 * F n 2 ) T Len n 2 +exp W 3 1 * F n 3 ∙ ( W 3 2 * F n 3 ) T Len n 3 ] ;

[0056] A n 3 = exp W 3 1 * F n 3 ∙ ( W 3 2 * F n 3 ) T Len n 3 ] exp W 2 1 * F n 2 ∙ ( W 2 2 * F n 2 ) T Len n 2 +exp W 3 1 * F n 3 ∙ ( W 3 2 * F n 3 ) T Len n 3 ] ;

[0057] in:

[0058] Represents semantic feature vector The enhancement factor, Represents semantic feature vector The enhancement factor of

[0059] Represents semantic feature vector The enhanced weight matrix, Represents semantic feature vector The enhanced weight matrix of

[0060] T stands for transpose;

[0061] Represents semantic feature vector Length, Represents semantic feature vector Length;

[0062] S32: Generate disease group information that characterizes the patient's disease management method :

[0063] ;

[0064] in:

[0065] represents the L1 norm;

[0066] Represents the ReLU function;

[0067] S33: Generate disease group information to characterize complications :

[0068] f n 3 = exp W 1 1 * F n 1 ∙ ( W 1 2 * F n 1 ) T Len n 1 ] F n 1 || f n 2 || ∙f n 2 1 + || f n 2 || 2 ;

[0069] in:

[0070] Represents semantic feature vector The enhanced weight matrix of

[0071] Represents semantic feature vector Length;

[0072] S34: The disease group information of multiple semantic feature vectors is integrated as the semantic enhancement processing result of the patient f n =[ f n 1 , f n 2 , f n 3 ] ;

[0073] According to the semantic enhancement processing results, DRG grouping information of N patients is generated.

[0074] Optionally, generating DRG grouping information of N patients according to the semantic enhancement processing result includes:

[0075] The DRG grouping information of the nth patient is generated as follows:

[0076] Generate DRG codes representing the patient's main diagnosis category :

[0077] Code n 1 = argmax r∈ Code 1 exp ( Q 1 r ) T f n 1 ] ∑ r∈ Code 1 exp ( Q 1 r ) T f n 1 ] ;

[0078] in:

[0079] Indicates a set of DRG codes for major diagnostic categories; in this embodiment of the present invention, The DRG codes in are divided into A to Z;

[0080] Indicates the DRG code set DRG code The corresponding encoding matrix;

[0081] Generate DRG codes that characterize how the patient's disease is managed :

[0082] Code n 2 = argmax r∈ Code 2 exp ( Q 2 r ) T f n 2 ] ∑ r∈ Code 2 exp ( Q 2 r ) T f n 2 ] ;

[0083] in:

[0084] A DRG code set representing a disease treatment method; in an embodiment of the present invention, The DRG codes in the CDC are divided into A to Z, where A to J represent the surgical part, K ​​to Q represent the non-operating room operation part, and R to Z represent the internal medicine part;

[0085] Indicates the DRG code set DRG code The corresponding encoding matrix;

[0086] Generate DRG codes based on the treatment order of disease treatment methods Corresponding sequence code ; In the embodiment of the present invention, the sequence code is 1 to 9;

[0087] Generate DRG codes that characterize patient complications :

[0088] ;

[0089] in:

[0090] represents the age of the nth patient;

[0091] A DRG code set representing a patient's complications; in an embodiment of the present invention, The DRG codes in the code are divided into 1, 3, and 5, where 1 indicates severe complications, 3 indicates general complications, and 5 indicates no complications;

[0092] Indicates the DRG code set The coding matrix corresponding to the DRG code c;

[0093] The DRG grouping information of the nth patient is:

[0094] ;

[0095] in:

[0096] Represents the DRG grouping information of the nth patient.

[0097] Optionally, in step S4, clustering is performed on different patients based on DRG grouping information and patient personal information to obtain a number of patient clusters, including:

[0098] Based on DRG grouping information and patient personal information, different patients are clustered and processed to obtain several patient clusters. The medical resources required to be consumed by patients in each patient cluster are similar. The improved peak density estimation is the implementation method of the clustering processing. The clustering process is:

[0099] S41: extracting the DRG codes representing the major diagnosis categories of the patients from the DRG grouping information of N patients, and treating the patients with the same DRG codes as patients in the same diagnosis area, thereby obtaining a set of patients in 26 diagnosis areas, where 26 is the number of major diagnosis categories;

[0100] S42: Obtain the DRG grouping information and patient personal information of any patient in each patient set, and calculate the information distance between the patient and any patient in the same patient set, where the information distance between the nth patient and any patient in the same patient set is:

[0101] ;

[0102] ;

[0103] ;

[0104] in:

[0105] represents the information distance between the nth patient and the mth patient in the same patient set, represents the semantic feature vector of personal information of the mth patient in the same patient set, Indicates the DRG code corresponding to the disease treatment method of the mth patient in the same patient set, Indicates the DRG code corresponding to the complication of the mth patient in the same patient set;

[0106] represents the L2 norm;

[0107] S43: Calculate the weighted information density of any patient in each patient set, where the weighted information density of the nth patient is:

[0108] ;

[0109] in:

[0110] represents the weighted information density of the nth patient, represents the patient set to which the nth patient belongs, Represents a patient collection Any patient in

[0111] Represents a patient collection The number of patients whose information distance from the nth patient is within the preset distance threshold, Represents a patient collection The set of neighboring patients whose information distance with the nth patient is within the preset distance threshold, u represents the set of neighboring patients Any patient in

[0112] Indicates the preset density cutoff distance;

[0113] S44: Select K patients with the highest weighted information density as initial cluster centers, use Kmean algorithm to iteratively process the cluster centers and cluster each patient set, and divide each patient set into K patient clusters.

[0114] Optionally, the word segmentation process of medical record information and diagnosis information is:

[0115] S11: using a word segmentation tool to perform word segmentation processing on the medical record information and the diagnosis information to obtain an initial word segmentation sequence of the medical record information and the diagnosis information; in the embodiment of the present invention, the word segmentation tool used is the jieba word segmentation tool;

[0116] S12: Calculate the importance weight of each initial word segmentation result in the initial word segmentation sequence corresponding to the medical record information and the diagnosis information respectively, where the initial word segmentation sequence corresponding to the medical record information The yth initial segmentation result The important information is:

[0117] I 1 (y) = ln[ E 1 1 (y)exp( E 2 1 (y))+ E 2 1 (y)exp( E 1 1 (y)) | E 1 1 (y)- E 2 1 (y)| ] ;

[0118] ;

[0119] ;

[0120] in:

[0121] Indicates the initial word segmentation sequence corresponding to the medical record information The yth initial segmentation result Information about the importance of

[0122] represents an exponential function with a natural constant as base;

[0123] Indicates the initial word segmentation result The left neighbor information, Indicates the initial word segmentation result The right neighbor information of ;

[0124] Indicates the initial word segmentation result With the initial word segmentation result The probability of appearing in the same sentence in all medical record information;

[0125] Indicates the initial word segmentation result The probability of appearing in all medical record information;

[0126] The initial word segmentation sequence corresponding to the diagnostic information The yth initial segmentation result The important information is:

[0127] I 2 (y) = ln[ E 1 2 (y)exp( E 2 2 (y))+ E 2 2 (y)exp( E 1 2 (y)) | E 1 2 (y)- E 2 2 (y)| ] ;

[0128] ;

[0129] ;

[0130] in:

[0131] Indicates the initial word segmentation sequence corresponding to the diagnostic information The yth initial segmentation result Information about the importance of

[0132] Indicates the initial word segmentation result The left neighbor information, Indicates the initial word segmentation result The right neighbor information of ;

[0133] Indicates the initial word segmentation result With the initial word segmentation result The probability of appearing in the same sentence in all diagnostic information;

[0134] Indicates the initial word segmentation result Probability of appearing in all diagnostic information;

[0135] S13: Filtering the initial word segmentation results whose importance information is lower than a preset threshold, using the retained initial word segmentation results as the word segmentation phrases of the medical record information and the diagnosis information, and obtaining the word segmentation phrase sequence of the medical record information and the diagnosis information.

[0136] In order to solve the above problems, the present invention provides a DRG automatic grouping system based on semantic information fusion, the system comprising:

[0137] Information collection module, used to collect patient personal information, medical history information and diagnostic information to form electronic health record data;

[0138] An information extraction module is used to extract semantic information from the patient's electronic health record data, obtain a segmented semantic information feature vector describing the patient's information, and perform semantic enhancement processing on the segmented semantic information feature vector;

[0139] The automatic grouping device is used to generate DRG grouping information of patients, and based on the DRG grouping information and patient personal information, cluster different patients to obtain a number of patient clusters.

[0140] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0141] A memory storing at least one instruction;

[0142] Communication interface, enabling electronic equipment to communicate; and

[0143] The processor executes the instructions stored in the memory to implement the DRG automatic grouping method with semantic information fusion described above.

[0144] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned DRG automatic grouping method with semantic information fusion.

[0145] Compared with the prior art, the present invention proposes a DRG automatic grouping method based on semantic information fusion, which has the following advantages:

[0146] First, this scheme proposes a method for semantic extraction of patient information. By collecting the patient's personal information, medical history information and diagnosis information as electronic health record data, and extracting multi-scale semantic feature information respectively, a segmented semantic information feature vector describing different information of the patient is constructed, thereby realizing multi-level deep information extraction of the patient's personal condition, disease description and diagnosis.

[0147] At the same time, this scheme proposes a DRG grouping method. According to the multi-segment code composition form of the DRG grouping, the segmented semantic information feature vector is spliced, enhanced and norm-constrained to form disease group information that characterizes the patient's disease diagnosis category, disease treatment method and complications, and maps different disease group information to the corresponding DRG code to achieve the mapping of the DRG code, obtain the patient's DRG grouping information, and combine the DRG grouping information and patient personal information to calculate the information distance between different patients based on DRG and personal information. Users with similar personal information and similar DRGs are formed into patient clusters. The medical resources required by patients in each patient cluster are similar, so as to realize the batch allocation of medical resources and improve the efficiency of medical resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0148] Figure 1 A flowchart of a DRG automatic grouping method based on semantic information fusion provided by one embodiment of the present invention;

[0149] Figure 2 A functional module diagram of a DRG automatic grouping system for semantic information fusion provided by an embodiment of the present invention;

[0150] Figure 2 In: 100 DRG automatic grouping system based on semantic information fusion, 101 information collection module, 102 information extraction module, 103 automatic grouping device;

[0151] Figure 3 A schematic diagram of the structure of an electronic device for implementing a DRG automatic grouping method for semantic information fusion provided by an embodiment of the present invention.

[0152] Figure 3 In: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface;

[0153] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0154] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0155] The embodiment of the present application provides a DRG automatic grouping method based on semantic information fusion. The execution subject of the DRG automatic grouping method based on semantic information fusion includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the DRG automatic grouping method based on semantic information fusion can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0156] Embodiment 1:

[0157] S1: Collect patient personal information, medical history information and diagnosis information to form electronic health record data, where the electronic health record data includes structured data and unstructured data, wherein the patient personal information is structured data, and the patient medical history and diagnosis information are unstructured data.

[0158] In step S1, the patient's personal information, medical history and diagnosis information are collected to form electronic health record data, including:

[0159] The personal information, medical history information and diagnosis information of N patients to be grouped into DRGs are collected to form the electronic health record data of the patients, where the electronic health record data of N patients are:

[0160] { X n =( X n 1 , X n 2 , X n 3 )|n∈[1,N]} ;

[0161] ;

[0162] ;

[0163] ;

[0164] in:

[0165] represents the electronic health record data of the nth patient;

[0166] Represents electronic health record data Personal information in represents the gender, age, occupation, height and weight of the nth patient in turn;

[0167] Represents electronic health record data Medical records information in Display medical record information In participle phrases, Display medical record information The i-th participle phrase in Display medical record information The total number of participle phrases in , i ∈ [1, Sum n ] ;

[0168] Represents electronic health record data Diagnostic information in Indicates diagnostic information In participle phrases, Indicates diagnostic information The jth participle phrase in Indicates diagnostic information The total number of participle phrases in .

[0169] The word segmentation process of medical record information and diagnosis information is as follows:

[0170] S11: using a word segmentation tool to perform word segmentation processing on the medical record information and the diagnosis information to obtain an initial word segmentation sequence of the medical record information and the diagnosis information;

[0171] S12: Calculate the importance weight of each initial word segmentation result in the initial word segmentation sequence corresponding to the medical record information and the diagnosis information respectively, where the initial word segmentation sequence corresponding to the medical record information The yth initial segmentation result The important information is:

[0172] I 1 (y) = ln[ E 1 1 (y)exp( E 2 1 (y))+ E 2 1 (y)exp( E 1 1 (y)) | E 1 1 (y)- E 2 1 (y)| ] ;

[0173] ;

[0174] ;

[0175] in:

[0176] Indicates the initial word segmentation sequence corresponding to the medical record information The yth initial segmentation result Information about the importance of

[0177] represents an exponential function with a natural constant as base;

[0178] Indicates the initial word segmentation result The left neighbor information, Indicates the initial word segmentation result The right neighbor information of ;

[0179] Indicates the initial word segmentation result With the initial word segmentation result The probability of appearing in the same sentence in all medical record information;

[0180] Indicates the initial word segmentation result The probability of appearing in all medical record information;

[0181] The initial word segmentation sequence corresponding to the diagnostic information The yth initial segmentation result The important information is:

[0182] I 2 (y) = ln[ E 1 2 (y)exp( E 2 2 (y))+ E 2 2 (y)exp( E 1 2 (y)) | E 1 2 (y)- E 2 2 (y)| ] ;

[0183] ;

[0184] ;

[0185] in:

[0186] Indicates the initial word segmentation sequence corresponding to the diagnostic information The yth initial segmentation result Information about the importance of

[0187] Indicates the initial word segmentation result The left neighbor information, Indicates the initial word segmentation result The right neighbor information of ;

[0188] Indicates the initial word segmentation result With the initial word segmentation result The probability of appearing in the same sentence in all diagnostic information;

[0189] Indicates the initial word segmentation result Probability of appearing in all diagnostic information;

[0190] S13: Filtering the initial word segmentation results whose importance information is lower than a preset threshold, using the retained initial word segmentation results as the word segmentation phrases of the medical record information and the diagnosis information, and obtaining the word segmentation phrase sequence of the medical record information and the diagnosis information.

[0191] S2: Extract semantic information from the patient's electronic health record data to obtain a segmented semantic information feature vector that describes the patient's information.

[0192] The step S2 extracts semantic information from the patient's electronic health record data, including:

[0193] Semantic information is extracted from the patient's electronic health record data to obtain a segmented semantic information feature vector describing the patient's information. The semantic information extraction process is as follows:

[0194] S21: Electronic health record data All phrases in are represented by one-hot encoding, and the one-hot encoding vector corresponding to the phrase is obtained;

[0195] S22: Perform word vector representation on the one-hot encoding vectors describing different information respectively to obtain word vector encoding sequences corresponding to different information, where the word vector encoding sequence of the e-th information is:

[0196] X n e = W e *[ C n e (1), C n e (2),..., C n e (S),..., C n e ( S e )],e ∈ {1,2,3} ;

[0197] ;

[0198] in:

[0199] represents the encoding matrix of the e-th type of information, * represents the convolution operation, where the 1st to 3rd types of information are personal information, medical record information, and diagnosis information respectively;

[0200] Display information The one-hot encoding vector corresponding to the Sth phrase in , S ∈[1, S e ] ;

[0201] The word vector encoding sequence representing the e-th information, where ,

[0202] Display information The word vector corresponding to the Sth word group in ;

[0203] S23: Perform multi-scale convolution on word vector encoding sequences of different information to obtain feature information of the word vector encoding sequences at D scales;

[0204] S24: Extract semantic information from multi-scale feature information of different information to obtain electronic health record data The semantic feature vectors representing the patient's personal information, medical record information, and diagnosis information are expressed in the formula for extracting semantic information:

[0205] F n =[ F n 1 , F n 2 , F n 3 ] ,e ∈ {1,2,3} ;

[0206] F n e = ∑ h=1 H [ 1 1+exp(- weight e * X n e,h ) + X n e,h ] ;

[0207] in:

[0208] The semantic feature vector representing the e-th type of information;

[0209] Semantic feature vectors representing patient personal information, medical record information, and diagnosis information, respectively;

[0210] The semantic mapping matrix representing the e-th type of information;

[0211] Represents the segmented semantic information feature vector describing the patient information.

[0212] In the step S23, multi-scale convolution is performed on word vector encoding sequences of different information, including:

[0213] S231: Set the current convolution scale to h, where the initial value of h is 0 and the maximum value is H;

[0214] S232: Generate feature information of each type of information at scale h+1, where the feature information of the e-th type of information at scale h+1 is:

[0215] ;

[0216]

[0217] in:

[0218] Represents the characteristic information of the e-th information at scale h+1;

[0219] represents the convolution matrix at scale h;

[0220] S233: Order , return to step S231 until the maximum convolution scale H is reached.

[0221] S3: Perform semantic enhancement processing on the segmented semantic information feature vector and generate the patient's DRG grouping information.

[0222] In the step S3, semantic enhancement processing is performed on the segmented semantic information feature vector, including:

[0223] The segmented semantic information feature vector is semantically enhanced, where the segmented semantic information feature vector corresponding to the nth patient is The semantic enhancement process is as follows:

[0224] S31: Generate disease group information representing the major categories of patient disease diagnosis :

[0225] ;

[0226] A n 2 = exp W 2 1 * F n 2 ∙ ( W 2 2 * F n 2 ) T Len n 2 ] exp W 2 1 * F n 2 ∙ ( W 2 2 * F n 2 ) T Len n 2 +exp W 3 1 * F n 3 ∙ ( W 3 2 * F n 3 ) T Len n 3 ] ;

[0227] A n 3 = exp W 3 1 * F n 3 ∙ ( W 3 2 * F n 3 ) T Len n 3 ] exp W 2 1 * F n 2 ∙ ( W 2 2 * F n 2 ) T Len n 2 +exp W 3 1 * F n 3 ∙ ( W 3 2 * F n 3 ) T Len n 3 ] ;

[0228] in:

[0229] Represents semantic feature vector The enhancement factor, Represents semantic feature vector The enhancement factor of

[0230] Represents semantic feature vector The enhanced weight matrix, Represents semantic feature vector The enhanced weight matrix of

[0231] T stands for transpose;

[0232] Represents semantic feature vector Length, Represents semantic feature vector Length;

[0233] S32: Generate disease group information that characterizes the patient's disease management method :

[0234] ;

[0235] in:

[0236] represents the L1 norm;

[0237] Represents the ReLU function;

[0238] S33: Generate disease group information to characterize complications :

[0239] f n 3 = exp W 1 1 * F n 1 ∙ ( W 1 2 * F n 1 ) T Len n 1 ] F n 1 || f n 2 || ∙f n 2 1 + || f n 2 || 2 ;

[0240] in:

[0241] Represents semantic feature vector The enhanced weight matrix of

[0242] Represents semantic feature vector Length;

[0243] S34: The disease group information of multiple semantic feature vectors is integrated as the semantic enhancement processing result of the patient f n =[ f n 1 , f n 2 , f n 3 ] ;

[0244] According to the semantic enhancement processing results, DRG grouping information of N patients is generated.

[0245] The step of generating DRG grouping information of N patients according to the semantic enhancement processing result includes:

[0246] The DRG grouping information of the nth patient is generated as follows:

[0247] Generate DRG codes representing the patient's main diagnosis category :

[0248] Code n 1 = argmax r∈ Code 1 exp ( Q 1 r ) T f n 1 ] ∑ r∈ Code 1 exp ( Q 1 r ) T f n 1 ] ;

[0249] in:

[0250] Indicates a set of DRG codes for major diagnostic categories; in this embodiment of the present invention, The DRG codes in are divided into A to Z;

[0251] Indicates the DRG code set DRG code The corresponding encoding matrix;

[0252] Generate DRG codes that characterize how the patient's disease is managed :

[0253] Code n 2 = argmax r∈ Code 2 exp ( Q 2 r ) T f n 2 ] ∑ r∈ Code 2 exp ( Q 2 r ) T f n 2 ] ;

[0254] in:

[0255] A DRG code set representing a disease treatment method; in an embodiment of the present invention, The DRG codes in the CDC are divided into A to Z, where A to J represent the surgical part, K ​​to Q represent the non-operating room operation part, and R to Z represent the internal medicine part;

[0256] Indicates the DRG code set DRG code The corresponding encoding matrix;

[0257] Generate DRG codes based on the treatment order of disease treatment methods Corresponding sequence code ; In the embodiment of the present invention, the sequence code is 1 to 9;

[0258] Generate DRG codes that characterize patient complications :

[0259] ;

[0260] in:

[0261] represents the age of the nth patient;

[0262] A DRG code set representing a patient's complications; in an embodiment of the present invention, The DRG codes in the code are divided into 1, 3, and 5, where 1 indicates severe complications, 3 indicates general complications, and 5 indicates no complications;

[0263] Indicates the DRG code set The coding matrix corresponding to the DRG code c;

[0264] The DRG grouping information of the nth patient is:

[0265] ;

[0266] in:

[0267] Represents the DRG grouping information of the nth patient.

[0268] S4: Based on the DRG grouping information and patient personal information, different patients are clustered and divided into several patient clusters. The medical resources required by the patients in each patient cluster are similar.

[0269] In the step S4, different patients are clustered based on the DRG grouping information and the patient personal information to obtain several patient clusters, including:

[0270] Based on DRG grouping information and patient personal information, different patients are clustered and processed to obtain several patient clusters. The medical resources required to be consumed by patients in each patient cluster are similar. The improved peak density estimation is the implementation method of the clustering processing. The clustering process is:

[0271] S41: extracting the DRG codes representing the major diagnosis categories of the patients from the DRG grouping information of N patients, and treating the patients with the same DRG codes as patients in the same diagnosis area, thereby obtaining a set of patients in 26 diagnosis areas, where 26 is the number of major diagnosis categories;

[0272] S42: Obtain the DRG grouping information and patient personal information of any patient in each patient set, and calculate the information distance between the patient and any patient in the same patient set, where the information distance between the nth patient and any patient in the same patient set is:

[0273] ;

[0274] ;

[0275] ;

[0276] in:

[0277] represents the information distance between the nth patient and the mth patient in the same patient set, represents the semantic feature vector of personal information of the mth patient in the same patient set, Indicates the DRG code corresponding to the disease treatment method of the mth patient in the same patient set, Indicates the DRG code corresponding to the complication of the mth patient in the same patient set;

[0278] represents the L2 norm;

[0279] S43: Calculate the weighted information density of any patient in each patient set, where the weighted information density of the nth patient is:

[0280] ;

[0281] in:

[0282] represents the weighted information density of the nth patient, represents the patient set to which the nth patient belongs, Represents a patient collection Any patient in

[0283] Represents a patient collection The number of patients whose information distance from the nth patient is within the preset distance threshold, Represents a patient collection The set of neighboring patients whose information distance with the nth patient is within the preset distance threshold, u represents the set of neighboring patients Any patient in

[0284] Indicates the preset density cutoff distance;

[0285] S44: Select K patients with the highest weighted information density as initial cluster centers, use Kmean algorithm to iteratively process the cluster centers and cluster each patient set, and divide each patient set into K patient clusters.

[0286] Embodiment 2:

[0287] like Figure 2 As shown, it is a functional module diagram of a DRG automatic grouping system with semantic information fusion provided by an embodiment of the present invention, which can implement the DRG automatic grouping method with semantic information fusion in Example 1.

[0288] The DRG automatic grouping system 100 with semantic information fusion of the present invention can be installed in an electronic device. According to the functions to be implemented, the DRG automatic grouping system with semantic information fusion can include an information acquisition module 101, an information extraction module 102 and an automatic grouping device 103. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0289] The information collection module 101 is used to collect the patient's personal information, medical history information and diagnosis information to form electronic health record data;

[0290] The information extraction module 102 is used to extract semantic information from the electronic health record data of the patient, obtain a segmented semantic information feature vector describing the patient information, and perform semantic enhancement processing on the segmented semantic information feature vector;

[0291] The automatic grouping device 103 is used to generate DRG grouping information of patients, and based on the DRG grouping information and the patient's personal information, perform clustering processing on different patients to obtain a number of patient clusters.

[0292] In detail, the modules in the DRG automatic grouping system 100 for semantic information fusion in the embodiment of the present invention are used in the same manner as described above. Figure 1 The DRG automatic grouping method based on semantic information fusion described in the invention has the same technical means and can produce the same technical effects, so it will not be repeated here.

[0293] Embodiment 3:

[0294] like Figure 3 , is a schematic diagram of the structure of an electronic device for implementing a DRG automatic grouping method for semantic information fusion provided by an embodiment of the present invention.

[0295] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0296] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also be used to temporarily store data that has been output or is to be output.

[0297] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the programs or modules stored in the memory 11 (such as the program 12 for DRG automatic grouping for semantic information fusion) and calls the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0298] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0299] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0300] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0301] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0302] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0303] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0304] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0305] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0306] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A DRG automatic grouping method based on semantic information fusion, characterized in that: The method comprises: S1: Collecting patient personal information, medical history information and diagnosis information to form electronic health record data, wherein the electronic health record data includes structured data and unstructured data, wherein the patient personal information is structured data, and the patient medical history and diagnosis information are unstructured data; S2: Extract semantic information from the patient's electronic health record data to obtain a segmented semantic information feature vector describing the patient's information; S3: Perform semantic enhancement processing on the segmented semantic information feature vector and generate the DRG grouping information of the patient; S4: Based on the DRG grouping information and patient personal information, different patients are clustered and divided into several patient clusters. The medical resources required by the patients in each patient cluster are similar.

2. The DRG automatic grouping method based on semantic information fusion according to claim 1, characterized in that: In step S1, the patient's personal information, medical history and diagnosis information are collected to form electronic health record data, including: The personal information, medical history information and diagnosis information of N patients to be grouped into DRGs are collected and word segmented to form the electronic health record data of the patients. The electronic health record data of N patients are as follows: ； ； ； ； in: represents the electronic health record data of the nth patient; Represents electronic health record data Personal information in represents the gender, age, occupation, height and weight of the nth patient in turn; Represents electronic health record data Medical records information in Display medical record information In participle phrases, Display medical record information The i-th participle phrase in Display medical record information The total number of participle phrases in , ; Represents electronic health record data Diagnostic information in Indicates diagnostic information In participle phrases, Indicates diagnostic information The jth participle phrase in Indicates diagnostic information The total number of participle phrases in .

3. The DRG automatic grouping method based on semantic information fusion according to claim 2, characterized in that: The step S2 extracts semantic information from the patient's electronic health record data, including: Semantic information is extracted from the patient's electronic health record data to obtain a segmented semantic information feature vector describing the patient's information. The semantic information extraction process is as follows: S21: Electronic health record data All phrases in are represented by one-hot encoding, and the one-hot encoding vector corresponding to the phrase is obtained; S22: Perform word vector representation on the one-hot encoding vectors describing different information respectively to obtain word vector encoding sequences corresponding to different information, where the word vector encoding sequence of the e-th information is: ； ； in: represents the encoding matrix of the e-th type of information, * represents the convolution operation, where the 1st to 3rd types of information are personal information, medical record information, and diagnosis information respectively; Display information The one-hot encoding vector corresponding to the Sth phrase in , ; The word vector encoding sequence representing the e-th information, where , Display information The word vector corresponding to the Sth word group in ; S23: Perform multi-scale convolution on word vector encoding sequences of different information to obtain feature information of the word vector encoding sequences at D scales; S24: Extract semantic information from multi-scale feature information of different information to obtain electronic health record data The semantic feature vectors representing the patient's personal information, medical record information, and diagnosis information are expressed in the formula for extracting semantic information: ； ； in: The semantic feature vector representing the e-th type of information; Semantic feature vectors representing patient personal information, medical record information, and diagnosis information in turn; The semantic mapping matrix representing the e-th type of information; Represents the segmented semantic information feature vector describing the patient information.

4. The DRG automatic grouping method based on semantic information fusion according to claim 3, characterized in that: In the step S23, multi-scale convolution is performed on word vector encoding sequences of different information, including: S231: Set the current convolution scale to h, where the initial value of h is 0 and the maximum value is H; S232: Generate feature information of each type of information at scale h+1, where the feature information of the e-th type of information at scale h+1 is: ； ； in: Represents the characteristic information of the e-th information at scale h+1; represents the convolution matrix at scale h; S233: Order , return to step S231 until the maximum convolution scale H is reached.

5. The DRG automatic grouping method based on semantic information fusion according to claim 1, characterized in that: The step S3 performs semantic enhancement processing on the segmented semantic information feature vector, including: The segmented semantic information feature vector is semantically enhanced, where the segmented semantic information feature vector corresponding to the nth patient is The semantic enhancement process is as follows: S31: Generate disease group information representing the major categories of patient disease diagnosis : ； ； ； in: Represents semantic feature vector The enhancement factor, Represents semantic feature vector The enhancement factor of Represents semantic feature vector The enhanced weight matrix, Represents semantic feature vector The enhanced weight matrix of T stands for transpose; Represents semantic feature vector Length, Represents semantic feature vector Length; S32: Generate disease group information that characterizes the patient's disease management method : ； in: represents the L1 norm; Represents the ReLU function; S33: Generate disease group information to characterize complications : ； in: Represents semantic feature vector The enhanced weight matrix of Represents semantic feature vector Length; S34: The disease group information of multiple semantic feature vectors is integrated as the semantic enhancement processing result of the patient ; According to the semantic enhancement processing results, DRG grouping information of N patients is generated.

6. The DRG automatic grouping method based on semantic information fusion according to claim 5, characterized in that: The step of generating DRG grouping information of N patients according to the semantic enhancement processing result includes: The DRG grouping information of the nth patient is generated as follows: Generate DRG codes representing the patient's main diagnosis category : ； in: A collection of DRG codes representing major diagnostic categories; Indicates the DRG code set DRG code The corresponding encoding matrix; Generate DRG codes that characterize how the patient's disease is managed : ； in: A collection of DRG codes that represent disease treatment methods; Indicates the DRG code set DRG code The corresponding encoding matrix; Generate DRG codes based on the treatment order of disease treatment methods Corresponding sequence code ; Generate DRG codes that characterize patient complications : ； in: represents the age of the nth patient; A collection of DRG codes representing patient complications; Indicates the DRG code set The coding matrix corresponding to the DRG code c; The DRG grouping information of the nth patient is: ； in: Represents the DRG grouping information of the nth patient.

7. The DRG automatic grouping method based on semantic information fusion according to claim 6, characterized in that: In the step S4, different patients are clustered based on the DRG grouping information and the patient personal information to obtain several patient clusters, including: Based on the DRG grouping information and patient personal information, different patients are clustered and processed to obtain several patient clusters. The medical resources required to be consumed by patients in each patient cluster are similar. The clustering process is as follows: S41: extracting the DRG codes representing the major diagnosis categories of the patients from the DRG grouping information of N patients, and treating the patients with the same DRG codes as patients in the same diagnosis area, thereby obtaining a set of patients in 26 diagnosis areas, where 26 is the number of major diagnosis categories; S42: Obtain DRG grouping information and patient personal information of any patient in each patient set, and calculate the information distance between the patient and any patient in the same patient set; S43: Calculate the weighted information density of any patient in each patient set; S44: Select K patients with the highest weighted information density as initial cluster centers, use Kmean algorithm to iteratively process the cluster centers and cluster each patient set, and divide each patient set into K patient clusters.

8. The DRG automatic grouping method based on semantic information fusion according to claim 2, characterized in that: The word segmentation process of medical record information and diagnosis information is as follows: S11: using a word segmentation tool to perform word segmentation processing on the medical record information and the diagnosis information to obtain an initial word segmentation sequence of the medical record information and the diagnosis information; S12: Calculate the importance weight of each initial word segmentation result in the initial word segmentation sequence corresponding to the medical record information and the diagnosis information respectively, where the initial word segmentation sequence corresponding to the medical record information The yth initial segmentation result The important information is: ； ； ； in: Indicates the initial word segmentation sequence corresponding to the medical record information The yth initial segmentation result Information about the importance of represents an exponential function with a natural constant as base; Indicates the initial word segmentation result The left neighbor information, Indicates the initial word segmentation result The right neighbor information of ; Indicates the initial word segmentation result With the initial word segmentation result The probability of appearing in the same sentence in all medical record information; Indicates the initial word segmentation result The probability of appearing in all medical record information; The initial word segmentation sequence corresponding to the diagnostic information The yth initial segmentation result The important information is: ； ； ； in: Indicates the initial word segmentation sequence corresponding to the diagnostic information The yth initial segmentation result Information about the importance of Indicates the initial word segmentation result The left neighbor information, Indicates the initial word segmentation result The right neighbor information of ; Indicates the initial word segmentation result With the initial word segmentation result The probability of appearing in the same sentence in all diagnostic information; Indicates the initial word segmentation result Probability of appearing in all diagnostic information; S13: Filtering the initial word segmentation results whose importance information is lower than a preset threshold, using the retained initial word segmentation results as the word segmentation phrases of the medical record information and the diagnosis information, and obtaining the word segmentation phrase sequence of the medical record information and the diagnosis information.

9. A DRG automatic grouping system based on semantic information fusion, characterized in that: The system comprises: Information collection module, used to collect patient personal information, medical history information and diagnostic information to form electronic health record data; An information extraction module is used to extract semantic information from the patient's electronic health record data, obtain a segmented semantic information feature vector describing the patient's information, and perform semantic enhancement processing on the segmented semantic information feature vector; An automatic grouping device is used to generate DRG grouping information of patients, and based on the DRG grouping information and patient personal information, cluster different patients to obtain a number of patient clusters, so as to realize a DRG automatic grouping method with semantic information fusion as described in any one of claims 1-8.

Images