39 results about "History disease" patented technology

The embodiment of the invention provides a personalized precise medication recommendation method and device, and relates to the technical field of base frame operation and maintenance. The method comprises the steps: obtaining medical record data of a plurality of patients suffering from the same disease, wherein the medical record data comprises structural data, text data and image data; obtaining medication information of the patient from the text data; screening from the medication information of the plurality of historical patients to obtain a first medicine recommendation result of a target patient; merging the medical record data of the patient to obtain disease characteristic information of the patient; screening out at least one similar patient similar to the current illness statecharacteristic information of the target patient from the plurality of historical patients; generating a second medicine recommendation result according to the medication information of the similar patients; and obtaining a personalized medicine recommendation result of the target patient according to the first medicine recommendation result and the second medicine recommendation result. Accordingto the technical scheme provided by the embodiment of the invention, the problem of low medication accuracy of the patients in the prior art can be solved.

The present invention provides a Kawasaki disease and fever diagnosis system based on embedding of an incremental local discrimination subspace. The Kawasaki disease and fever diagnosis system comprises a training subsystem and a diagnostic subsystem. The training subsystem has the tasks of generating clinical manifestations for use of training from historical medical records of children with Kawasaki disease and a common fever, detecting physiological data, then analyzing local structure information, and searching for an optimal local discrimination subspace to establish a Kawasaki disease and fever feature model therein. Furthermore, when a new patient medical record is acquired, the training subsystem updates the model in an incremental learning manner. The diagnostic subsystem has the tasks of observing clinical manifestations of patients to be diagnosed, detecting physiological data, and determining whether the patients suffer from Kawasaki disease according to the Kawasaki disease and fever feature model established by the training subsystem. The present invention enables children suffering from Kawasaki disease to be treated in time, reducing the probability of developing into coronary artery dilatation or aneurysm, and alleviating the cardiovascular damage of the patients.

The invention relates to the technical field of artificial intelligence, is applied to the field of smart medical treatment so as to promote the construction of smart cities, and discloses a similar case detection method, device and equipment and a storage medium. The method comprises the following steps: inputting a target case text of an obtained detection object into a text similarity clustering model to obtain a target grouping label; inputting the illness state data information of the target case text into an illness state encoding model, and encoding the illness state data information toobtain target encoding information; according to the target grouping label, extracting sample coding information corresponding to other objects except the detection object from a coding database; determining a coding information difference value according to the target coding information and the sample coding information; and if the encoding information difference value is greater than a preset difference threshold, determining that a historical case text similar to the target case text exists, and prompting that the target case text has a counterfeiting risk. According to the method, the case similarity and the disease condition data information similarity are combined, so that the similar case detection accuracy is improved.

The invention discloses a clinical research and follow-up fusion system and method. The system comprises the components of an information acquisition unit which is configured for acquiring historicalmedical record information of a patient and acquiring current health data of the patient based on follow-up information of the patient; an information extracting unit which is configured for extracting a clinical diagnosis-and-treatment plan for treating the affected disease of the patient from the historical medical record information, and extracting a current symptom of the patient from the current health data of the patient; a processing unit which is configured for determining a reoccurrence probability of the affected disease of the patient according to the current symptom of the patientand a pretrained predicting model, and in response to a fact that the reoccurrence probability is higher than a preset threshold, analyzing the clinical diagnosis-and-treatment plan for determining apotential hazard factor which causes the reoccurrence; and a pushing unit which is configured for pushing the potential hazard factor that causes the reoccurrence to a doctor client for assisting a doctor in adjusting the clinical diagnosis-and-treatment plan and pushing a further diagnosis notification to a patient terminal. The system according to the invention facilitates optimization of the diagnosis-and-treatment plan by the doctor to the patient.

The invention provides a hand-foot-and-mouth disease prediction method and device using fine-grained data, electronic equipment and a computer readable medium. The method comprises the steps of obtaining historical case data of the hand-foot-and-mouth disease; preprocessing the historical case data, and dividing the historical case data into time series data of two different time intervals; pre-aggregating the time series data of the two different time intervals according to time to obtain multivariate time series data, and converting the multivariate time series data into supervised data; training a hand-foot-and-mouth disease prediction model according to the supervised data; inputting the hand-foot-and-mouth disease case data collected in real time into the trained hand-foot-and-mouth disease prediction model to obtain the real-time predicted number of patients with the hand-foot-and-mouth disease. According to the scheme, the time series data of different granularity time intervalsof historical case data are obtained, the accuracy of predicting the number of patients with the hand-foot-and-mouth disease based on equal time granularity is improved according to the time series data with finer granularity, additional data assistance is not needed, and the prediction efficiency is improved.

The embodiment of the invention discloses a disease classification method and device, equipment and a storage medium. The method comprises the steps of obtaining a numerical vector of case informationof a to-be-classified target object; respectively inputting the numerical vectors of the case information into a trained first disease classification model and a trained second disease classificationmodel, and obtaining a first disease classification probability and a second disease classification probability that the case information belongs to each disease type, wherein the first disease classification model is obtained by training based on a plurality of non-standardized historical case history sample data and the second disease classification model is obtained by training based on a plurality of structured historical case sample data; and determining a target disease type of the case information of the target object based on the first disease classification probability and the seconddisease classification probability that the case information belongs to each disease type. Therefore, the effect of quickly and accurately determining the disease type of the patient according to themedical record information is achieved.

The invention relates to a method and a device for identifying doctor seeing information, electronic equipment and a computer readable storage medium, relates to the technical field of data mining, and aims to recombine historical medical record data and screen out medical record data associated with current appointment registration. The method comprises the following steps: acquiring appointment registration information of a target patient, and determining a patient disease category of the target patient according to the appointment registration information; determining doctor information corresponding to the target patient according to the appointment registration information, the doctor information comprising a first disease category; acquiring historical medical record data of the target patient, and determining associated medical record data related to the appointment registration from the historical medical record data according to the disease category of the patient and the first disease category, the associated medical history data serving as predicted doctor seeing information of the appointment registration. According to the method and the device, the core medical record data associated with the appointment registration can be quickly positioned from the numerous and jumbled historical medical record data of the patient, so that possible information omission is avoided.

The invention provides a diagnosis and treatment assisting method and system based on data right confirmation, and a storage medium. The method comprises the following steps: collecting identity information and various diagnosis and treatment data of each patient from a hospital database, wherein each diagnosis and treatment data comprises a historical illness state and a corresponding historical diagnosis and treatment scheme; acquiring patient login verification information, and identifying identity information of a logged patient according to the patient login verification information; acquiring various diagnosis and treatment data of the logged-in patient according to the identity information of the logged-in patient; acquiring a diagnosis and treatment request made by a logged-in patient to the medical personnel, and identifying identity information of the requested medical personnel according to the diagnosis and treatment request; according to the identity information of the requested medical personnel, granting the reading authority of the various diagnosis and treatment data of the logged-in patient to the requested medical personnel; and acquiring an illness state diagnosis result, judging whether a historical illness state which is the same as the illness state diagnosis result exists in various diagnosis and treatment data of the logged-in patient, and if so, calling a historical diagnosis and treatment scheme corresponding to the historical illness state for the requested medical personnel to check.

The invention relates to a patient monitoring and reminding system which at least comprises: a reminding device which is configured to at least collect and process state data information of a patient and provide corresponding reminding / guidance for the patient according to a reminding instruction; a management system which is used for presetting a prompt instruction and receiving and storing the state data information acquired by the reminding device; the system can check and correct a preset plan prompt instruction according to historical disease condition information and current disease condition information of a patient in a manner of associating a past prompt instruction corresponding to state data information of the patient with the plan prompt instruction, and provides a feedback result to the patient and / or medical staff. Therefore, the plan prompting instruction can be executed at least after the current checking and correcting operation is confirmed.

The invention provides a hepatopathy cognition system based on an electronic medical record. The system comprises: a preprocessing module for obtaining historical medical record data, extracting liverdisease data information, preprocessing the liver disease data information, and obtaining the preprocessed liver disease data information as to-be-divided data; a feature division module used for dividing liver disease description feature information from the to-be-divided data through an ICTCLAS word segmentation tool and generating a corresponding liver disease description feature information data set; a screening module used for carrying out feature screening on the liver disease description feature information data set through an IV value analysis method, generating a corresponding feature table and taking the feature table as a diagnosis system model; and a prediction cognition module used for acquiring the to-be-diagnosed liver disease description feature information and performingdiagnosis cognition on the to-be-diagnosed liver disease description feature information by utilizing the diagnosis system model. Redundant features in the hepatopathy description feature informationdata set are eliminated through an IV value analysis method, so the accuracy of feature analysis is improved, and the stability of the whole cognition system is improved.

The invention provides a similar case analysis method and system. The similar case analysis method comprises the following steps: a, confirming similar criterion parameters of a case; b, calculating the similarity between the current case and the historical case; c, sorting the historical cases. The similar case analysis method has the beneficial effects that; 1, the system adopting the similar case analysis method disclosed by the invention can record the diagnosis conclusion of an expert physician, the medication and treatment scheme, the previous examination results of a patient and the disease development condition after treatment in the system; 2, the system adopting the similar case analysis method has the following functions: when students in a medical college practice or a doctor diagnoses and treats a new patient, the system automatically finds out a plurality of similar cases diagnosed and treated by an expert-type doctor according to the cases of the patient input into the system, and gives out a sorting result; therefore, doctors can refer to diagnosis and treatment schemes of expert doctors.

The invention discloses a semantic triage method and system. The method comprises the following steps: acquiring actual inquiry data; and inputting the actual inquiry data into a department classification model to obtain a target department, wherein an establishment method of the department classification model comprises the following steps: acquiring historical inquiry data comprising historical disease descriptions and corresponding historical departments; and training a long-short term memory network model according to the historical inquiry data to obtain the department classification model. According to an existing triage method, a hospital guide needs to manually judge corresponding departments according to the disease descriptions, and the manual speed is limited. According to the invention, the target department can be automatically obtained through the department classification model only by inputting the disease descriptions, and the triage efficiency is improved. Moreover, the hospital guide performs department triage completely by virtue of experience, and errors are easy to occur. According to the invention, a triage operation is performed by utilizing the department classification model trained by a large amount of historical data, so that the triage accuracy is improved.

The invention relates to a medical data acquisition and sharing system, which is used for acquiring and storing data of a patient seeing a doctor, providing data support for clinical aid decision making and improving the working efficiency of medical staff. The physical sign data of the patient with the acute medical history is monitored in real time, related guardians are notified in time when abnormity occurs so as to deal with the abnormity in time, a case graph is constructed based on historical cases, a related recommended treatment scheme or a recommended treatment mechanism is given based on symptoms of people, and the problem that the people are difficult to see a doctor is solved.

The invention discloses a cardiovascular disease risk monitoring system based on big data, belonging to the field of disease risk health. The cardiovascular disease risk monitoring system comprises auser terminal, a big data center, a feature information extraction module, a disease matching module and a report generation module. The user terminal inputs identity information, physical characteristics, medical detection data and symptom information into the system, and the information is stored in the big data center for supervision; a disease information database of the big data center storespersonal disease and development data; the feature information extraction module calls out the features of cardiovascular diseases from the big data center and matches the features with the cardiovascular diseases through the disease matching module; and according to comparison of the extracted information features, cardiovascular disease risks are analyzed and evaluated, and a disease statistical report is formed. According to the invention, the monitoring of the masses on cardiovascular disease risks is enhanced; and disease trend analysis is performed on patients by referring to historicalcases, so accurate medical plans and disease prevention measures can be provided for the patients.

The invention relates to the field of big data, and discloses an intelligent grouping method and device for similar patients, equipment and a storage medium. The similar patient intelligent grouping method comprises the following steps: acquiring new patient data to be matched, wherein the new patient data comprises multiple disease characteristic data; performing vectorization processing on the disease characteristic data to obtain a disease characteristic word vector corresponding to the new patient; calculating a Mahalanobis distance between the new patient data and each historical patientdata in a preset disease characteristic database; sorting the Mahalanobis distances to obtain a sorting result; determining disease information groups correspondingly matched with the new patient data, wherein the disease information groups include different clinical outcome information. The method is used for utilizing the data information of historical patients to the maximum extent, quickly judging the disease information group to which a new patient belongs according to the Mahalanobis distance, and assisting a doctor to make a decision according to the characteristics of the correspondingdisease information group, so that the accuracy of medical decision making of the doctor is improved.

The invention provides a patient similarity analysis method and system based on an improved heterogeneous information network. The method comprises the steps: taking hospitalization information of a patient as data input, constructing an annotation heterogeneous information network, and associating relationships among patients, diseases and drugs; constructing a meta-structure by taking the expanded structure of the annotation heterogeneous information network as a directed graph of a template; and based on the meta-structure, carrying out similarity calculation to obtain similarity. Accordingto the invention, annotation of patient information is added in connection of diseases and medicines, so that the problem that associated information between patients and medicines is lost in a classical heterogeneous information network is solved, and historical medical records can be well associated; and the relationship among the patient, the disease and the medicine is associated, so that theaccuracy of patient similarity calculation is improved.

The invention relates to a method and system for determining a personalized diagnosis and treatment method based on a utility model, and the method comprises the steps: carrying out the preprocessingof historical user disease feature data, and obtaining user features; according to the historical user disease data, constructing a utility matrix of the improvement method based on a particle swarm algorithm; and obtaining a personalized diagnosis and treatment method for the current user according to the utility matrix, the user characteristics and the requirements of the current user. Accordingto the method, the dimensionality reduction and normalization processing are carried out on multi-symptom characteristic data; an improvement method utility matrix is constructed through the particleswarm algorithm; a total utility value is obtained according to the utility matrix and the historical user symptom data, and an improvement effect threshold is adjusted and judged according to a historical improvement condition; and according to the historical disease condition data, the decision strategy is adjusted to be the threshold value at the lowest cost, so the personalized diagnosis andtreatment method for the current user can be effectively determined.

The invention relates to the field of Internet retail industry, in particular to a method for managing chronic diseases of store members based on an Internet platform. The method provided by the invention comprises the following steps: 1, creating member information and recording basic conditions of members; 2, recording all consumption information of the member and automatically creating an electronic medical record for each consumption; 3, automatically analyzing, by a system, historical consumption records and reminding the member to prepare medicines in advance; 4, automatically remindingthe patient of regular review and matters needing attention according to historical medical record information; 5, pushing health care knowledge related to member medical records regularly, and makingregularly calling the member to know the medication situation by a specially-assigned person. The method solves the problem that a store cannot manage members with chronic diseases, maintains a goodmember relationship, and can be widely applied to the Internet retail industry.

The invention provides a block chain-based diagnosis and treatment data treatment method, a storage medium and a system, and the method comprises the following steps: collecting the identity information of each patient and each diagnosis and treatment data, each diagnosis and treatment data comprising a historical illness state diagnosis result and a corresponding diagnosis time point; associating and uploading the identity information of each patient and the diagnosis and treatment data thereof to a block chain; acquiring patient login verification information; identifying identity information of the logged-in patient according to the patient login verification information; obtaining a current illness state diagnosis result and a corresponding diagnosis time point which are made by the medical personnel for the logged-in patient; judging whether a historical illness state diagnosis result of a logged-in patient, which is the same as the illness state diagnosis result, exists on the block chain, if yes, judging whether the distance between a diagnosis time point corresponding to the last illness state diagnosis result and a diagnosis time point corresponding to the illness state diagnosis result is less than a preset time length, and if yes, outputting related prompt information about frequent disease relapse to medical staff.

The invention relates to a medication decision scheme generation method and device, computer equipment and a storage medium. The method comprises the steps of obtaining patient-related information of a current patient, generating evaluation data corresponding to the patient-related information according to the patient-related information, obtaining decision-making path-related information from a preset drug use knowledge graph according to the evaluation data, wherein the patient related information comprises basic information and disease information of the current patient; pushing the decision path related information to a selection interface of a preset medical staff terminal, constructing a preset medication knowledge graph based on the medication related information and the historical disease clinical treatment data, wherein the decision path related information comprises different selectable medication schemes, responding to selection operation on the different medication schemes, and according to the selected medication schemes, obtaining a medication decision scheme for the current patient. By adopting the method, comprehensive, accurate and efficient decision path related information can be provided, different medication schemes can be visually represented, and accurate and efficient medication decisions can be generated.

The invention discloses a colorectal cancer risk screening method and system based on a decision tree, and the method comprises the steps: obtaining a historical medical record data set of a first department; taking a preset screening age as a first screening feature, taking a polyp definite medical record as a second screening feature, and taking a family medical history disease as a third screening feature; obtaining a first feature information entropy, a second feature information entropy and a third feature information entropy in sequence through information theory coding operation; inputting the first root node feature into a numerical value comparison model to obtain a first root node feature; constructing a colorectal cancer screening decision tree; obtaining an initial medical record of the first user; inputting the image into a colorectal cancer screening decision tree to obtain a first screening result; and reminding the first user to screen the condition of the colorectal cancer. The technical problems that in the prior art, based on the disease characteristics of the colorectal cancer, massive user medical records cannot be efficiently and rapidly screened, potential hazards of the colorectal cancer cannot be found as early as possible, and user treatment is delayed are solved.

The invention relates to a model training method and device, a feature classification method and device and computer equipment. The method comprises the steps that computer equipment determines the contribution degree of each disease feature to each department according to historical disease feature data of multiple users, determines a sample data set according to the contribution degree of historical disease features, and trains an initial classification model according to the sample data set to obtain a target classification model; wherein the contribution degree is the occurrence frequency of the disease feature for the department, the initial classification model comprises a first-layer classification model and a second-layer classification model, the second-layer classification model is a least square double support vector machine element classification model, and the target classification model is used for performing department classification according to the disease feature of the user. According to the target classification model involved in the scheme, a least square double support vector machine is adopted as a second-layer element classifier of Stacking ensemble learning, the learning difficulty of the model in the training process is reduced, and the solving efficiency of model training is improved.

The invention discloses a side slope state evaluation method. The method comprises the steps of S1 marking current disease detection information of a side slope and historical disease detection information of the side slope in a side slope panorama; and S2 combining the current disease detection information and the historical disease detection information, and evaluating the state of the slope. The invention further discloses a slope state evaluation system. The system comprises a labeling module used for labeling current disease detection information of the slope and historical disease detection information of the slope in a slope panorama, and an evaluation module used for receiving the current disease detection information and the historical disease detection information, and the evaluation module combines the current disease detection information and the historical disease detection information and evaluates the state of the slope. The slope state is evaluated after the current disease detection information and the historical disease detection information are combined, and the accuracy of the slope state evaluation result is higher.

The invention provides a diagnosis and treatment data acquisition method based on illness state diagnosis results, a storage medium and an electronic medical record system, and the method comprises the following steps: collecting and storing various diagnosis and treatment data of each patient from a hospital database, each diagnosis and treatment data comprising a historical illness state diagnosis result and a corresponding historical diagnosis and treatment scheme; obtaining a current illness state diagnosis result of the patient made by the medical personnel; finding out a first part of diagnosis and treatment data of which the historical illness state diagnosis result is the same as the illness state diagnosis result from various diagnosis and treatment data of each patient; acquiring a historical diagnosis and treatment scheme in the first part of diagnosis and treatment data; comparing the historical diagnosis and treatment scheme in the first part of diagnosis and treatment data with historical diagnosis and treatment schemes in other diagnosis and treatment data, and finding out a second part of diagnosis and treatment data of which the similarity of the historical diagnosis and treatment schemes exceeds a preset threshold value; and providing the first part of diagnosis and treatment data and the second part of diagnosis and treatment data for the medical personnel to check.

The invention discloses a health data processing method and device based on intelligent equipment, a terminal and a medium, and the method comprises the steps: obtaining the real-time state information of a target object; comparing the real-time state information with disease postures in a disease state database to obtain real-time disease state information; historical pathological information is obtained, and a pathological detection report is generated according to the real-time pathological information and the historical pathological information; and sending the ill-conditioned detection report to a bound terminal, and giving an alarm for help according to the ill-conditioned degree in the ill-conditioned detection report and the help-seeking information of the target object. The real-time state information of the user and the disease postures in the disease database are compared and analyzed, the real-time disease state information of the user can be obtained, the disease state detection report of the user can be obtained in combination with the historical disease state information of the user, and disease state early warning and disease state help seeking can be conveniently carried out according to the disease state detection report.

The invention discloses a big data-based medical record management method and system, and the method comprises the steps: building a first medical record set based on big data, and enabling the first medical record set to comprise a plurality of medical records; establishing a medical record classification model of the plurality of medical records by using a support vector machine; obtaining first disease information of the first patient; obtaining disease features of the first patient to form a first disease feature set; taking the first disease feature set as an input quantity, and obtaining a first classification result of the medical record classification model; a first similar medical record set is obtained, and the first similar medical record set comprises a plurality of similar medical records; and obtaining a first diagnosis and treatment reference of the first patient according to the plurality of similar medical records. The technical problems that in the prior art, when similar historical medical records are searched based on patient diseases, the searching range is small, efficiency is low, meanwhile, the matching degree and accuracy of the searched medical records are insufficient, and beneficial reference cannot be provided, so that the utilization rate of the medical records is low are solved.

According to the remote medical inquiry method and system and the readable storage medium disclosed by the invention, disease information of a patient can be subjected to distributed processing, and when a doctor carries out remote inquiry, the doctor can perform decrypting through the first key authorized by the user and a plurality of acquired disease storage data packets to obtain historical disease information of the user; therefore, the patient can carry out remote inquiry on different platforms, and the privacy and safety of the individual illness state are ensured. In addition, data collection of other body characteristics is carried out on the user through the auxiliary equipment, and therefore the doctor is helped to judge the illness state of the patient more accurately. In addition, the physical condition of the patient is analyzed through the image information and the sound information, the doctor is helped to make accurate judgment, the diagnosis accuracy is improved, and the remote inquiry use experience feeling is also improved.