46 results about "Patient Visit" patented technology

The invention relates to the technical field of medical care informatics, in particular to a hospital consumable usage supervision system and method, and the method comprises the steps: obtaining related consumable data of each department of a hospital and patient treatment related data, and determining the basic consumable demand degree of each department through the analysis of the related consumable data; according to the change trend of the patient doctor-seeing related data in different periods, the doctor-seeing patient amount rising trend degree of each department in different periods is determined, and then the consumable use indirect influence degree of each department influenced by doctor-seeing loads of other departments is determined; and based on the doctor-seeing patient amount rising trend degree, the basic consumable demand degree and the consumable use indirect influence degree of each department in the current period, determining the consumable use permission degree of each department, and based on the consumable use permission degree, judging whether to carry out consumable abnormality early warning or not. According to the method, the consumable use permission of each department is determined in a self-adaptive manner, so that the hospital consumable use supervision accuracy is effectively improved.

The invention provides a medicine advice generation system and a medicine advice generation method, the system determines the scene type of the current doctor advice recommendation scene, responds to the scene type to recommend the emergency doctor advice, and according to the diagnosis identification result, the image detection data, the physiological index detection data and the call recording data of the target patient, the medical advice is recommended to the emergency doctor advice. Determining recommended drug advices according to the scene type, recommending the chronic disease advices in response to the scene type, determining the recommended drug advices according to the diagnosis and identification result of the target patient and the basic information of the patient in combination with a pre-constructed graph database, and further determining diagnosis and treatment actions according to the diagnosis and identification result and the basic information of the patient. The diagnosis and treatment actions and the evidence labels are used as auxiliary judgment information and are sent to a doctor end together with the recommended medicine advice, so that doctor advice recommendation is realized, the problems of low doctor seeing efficiency of patients, heavy workload of doctors and the like can be solved, human decision errors are reduced, and the doctor experience is improved. And the accuracy and rationality of drug recommendation are ensured.

In accordance with at least one aspect of this disclosure, an artificial intelligence driven bi-directional medical assistant is provided. The assistant comprises an input module configured to recognize, in real time, spoken language and convert the spoken language to a computer readable form to generate a patient embedding. The computer readable form includes, in certain embodiments, a mathematical vector associated with the patient embedding, and the spoken language includes a conversation between a clinician and a patient during a patient visit.

The invention discloses an intelligent bed reservation method from outpatient service to hospitalization, and the method comprises the following steps: S1, visiting a doctor in an outpatient service: a patient visits the doctor in an outpatient department through a reservation or registration system, and a doctor carries out the diagnosis of the patient after the inquiry. The intelligent bed appointment management platform is combined with the HIS system and the bed management system, bed resources of a hospital can be automatically matched, inquired and managed, real-time and intelligent bed allocation is achieved, low efficiency and errors of manual management are avoided, meanwhile, AI prediction is combined, and the management efficiency is improved. According to the method, the bed use condition can be monitored and dynamically predicted in real time, bed cleaning and hospital discharge time can be arranged in advance, the maximum bed use rate is ensured, the resource waste phenomenon caused by improper bed management is reduced, a patient can easily inquire the bed state and the predicted hospital admission time through an App or a self-service terminal and know the bed distribution progress at any time, and the patient experience is improved. And anxiety is reduced.

The invention provides a data analysis processing method and system for a hospital HIS system, and belongs to the technical field of energy storage devices, and the method specifically comprises the steps: determining a coincidence time period according to the coincidence condition of a quality inspection analysis recommendation time period of medical records of each hospital department and a time period of a doctor of the hospital department with infectious disease diagnosis and treatment, and when the quality inspection analysis recommendation time periods of the hospital departments belong to the overlapping time periods, determining the quality inspection processing time periods of the medical records of the hospital departments based on the distribution data and the registration data of the hospital departments in different quality inspection analysis recommendation time periods in the overlapping time periods, thereby improving the quality inspection processing efficiency.

The invention relates to the technical field of computer vision, in particular to a facial nerve paralysis detection method and device based on a dynamic structured light technology, and the method comprises the following steps: carrying out the real-time data collection of the face of a patient, and obtaining a high-precision and complete face point cloud; obtaining a grid model based on the face point cloud; non-rigid registration is conducted on the grid model, a patient face 3D model with the same topological structure as the standard face is generated, and the patient face 3D model is a topological symmetry model; a motion vector for each point in the 3D model of the patient's face is calculated and face symmetry is quantified based on a symmetry operator. According to the method, a non-rigid registration method is used for completing transformation from a standard face model to an actual face model; and carrying out statistics on the motion vector of each point in the transformed topological symmetry model, and quantifying the facial symmetry through the information. According to the method, an objective visual tool is provided for a doctor to diagnose facial paralysis, and the doctor seeing and revising efficiency and accuracy of a patient are improved.

A method for generating a user interface of predicted disease progressions includes receiving medical data corresponding to patient visits to a healthcare provider, generating a diagnosis for the patient based on the medical data, and generating a predicted diagnosis for a future condition of the patient based upon the diagnosis, and a predictive model. The method further includes generating a timeline view of a diagnosis in the current patient visit and the predicted diagnosis. The graphical element of the diagnosis and the predicted diagnosis both include a graphical indicator of a diagnosis and at least one graphical sub-element of a physiological parameter relevant to the diagnosis. The method further includes generating a graphical connector between the graphical elements to indicate progression of time between a first time of the current patient visit and a second time.

A method for generating graphical data of a patient treatment history includes receiving medical data for the patient corresponding to patient visits to a healthcare provider and generating graphical data corresponding to a timeline view of the patient visits. The generated graphical data include first and second graphical elements corresponding to first and second diagnoses based on the medical data during a current patient visit and a prior patient visit. Each graphical element includes a graphical indicator of a diagnosis for a medical condition and at least one graphical sub-element, the at least one graphical sub-element being relevant to a physiological parameter selected from the medical data and related to the diagnosis. The method includes generating a first graphical connector between the second graphical element and the first graphical element, to indicate a progression of time between patient visits in the timeline view.

The invention discloses a drug recommendation system based on causal co-occurrence enhancement, which fuses a co-occurrence relationship and a causal relationship between medical information to realize high-precision and high-safety personalized drug recommendation. Comprises: a medical information representation generation module based on a medical information co-occurrence relationship, used for constructing a medical entity co-occurrence graph and obtaining embedded representation through graph attention neural network learning; the patient treatment characterization generation module based on the medical information causal relationship constructs a treatment-level medical causal graph by using a causal discovery algorithm, and performs weighted fusion according to the causal roles (such as cause nodes and intermediate nodes) of entities to form patient treatment characterization; according to the drug recommendation module based on the co-occurrence causal relationship, co-occurrence enhancement factors and a causal effect matrix calibration mechanism are introduced on the basis of preliminary prediction, and it is ensured that a recommendation result has statistical rationality and causal interpretation at the same time. The accuracy, interpretability and clinical applicability of drug recommendation are remarkably improved.

The invention discloses a traditional Chinese medicine sequential diagnosis and treatment logic mining method and system based on dynamic curative effect feedback, and a medium, and the method comprises the steps: preprocessing traditional Chinese medicine sequential diagnosis and treatment data, constructing a diagnosis-time pair sequence containing multiple times of treatment of a patient, each diagnosis-time pair comprising a treatment state and curative effect feedback; based on the theory of traditional Chinese medicine, the symptoms and the prescriptions are mapped into structured vectors respectively, and a state conversion tuple is generated; calculating a dynamic evolution mode of a composite state of the state transition tuple through a state transition probability formula in combination with the curative effect feedback information; and extracting a composite state vector mapping rule by adopting a sequential rule mining algorithm, and generating a rule conforming to traditional Chinese medicine syndrome differentiation thinking in combination with the interpretable decision tree model. According to the method, a traditional Chinese medicine syndrome differentiation and treatment dynamic adjustment rule hidden in a medical record is mined, and visualization and regularization of diagnosis and treatment logic are achieved.

[Problem] To allow a large-scale language model to be additionally trained with patient records of a large number of diagnosed cases, to assist the additionally trained large-scale language model in proposing an efficient examination plan for establishing a diagnosis from symptom findings obtained from an undiagnosed patient visiting the clinic, and in obtaining an established diagnosis by integrating obtained examination results. [Solution] An electronic medical chart system in which a large-scale language model is used in combination is provided with: a "possible diagnosis name, additional symptom, body finding, and examination answering means" for answering at least one of a list of possible diagnosis names and probabilities thereof, a recommended additional symptom, a body finding, and examination; and a sequential diagnosis improving means for repeating the "symptom, body finding, and examination result data providing means" and the "possible diagnosis name, additional symptom, body finding, and examination answering means" until the list of possible diagnosis names and probabilities thereof has sufficient accuracy as an established diagnosis.

The embodiments of the present invention provide a method for predicting patient consultation time, a cross-region consultation system and a storage medium. The method for predicting patient consultation time includes obtaining an appointment instruction; determining a preset consultation time, a target diagnosis and treatment unit and an acquisition time corresponding to the preset consultation time according to the appointment instruction; determining the appointment queue information between the acquisition time and the preset consultation time; obtaining the treatment speed of the target diagnosis and treatment unit; and determining the theoretical consultation time according to the treatment speed, the appointment queue information and the acquisition time. In the technical solution of the present invention, by reasonably predicting the theoretical consultation time, patients can arrange their consultation time well and reasonably choose different diagnosis and treatment units for consultation. It can also make the distribution of patients between the diagnosis and treatment units more even, and the utilization rate of medical resources higher.

To support obtaining a confirmed diagnosis by causing a large language model to additionally learn patient records of a large number of diagnosed cases, causing the additionally trained large language model to propose an efficient test plan for confirming a diagnosis from symptom findings obtained from an undiagnosed patient visiting a hospital, and integrating obtained test results. An electronic health record system using a large language model in combination includes: a "possible diagnosis name, additional symptom, physical finding, and test answering means" that answers at least one of a list of possible diagnosis names and probabilities of the diagnosis names, and a recommended additional symptom, physical finding, and test; and a sequential diagnosis improvement means for repeating a "symptom, physical finding, and test result data provision means" and the "possible diagnosis name, additional symptom, physical finding, and test answering means" until the list of possible diagnosis names and probabilities of the diagnosis names has sufficient accuracy for confirmed diagnosis.

This invention relates to the field of medical intelligent technology, specifically to an artificial intelligence-based patient treatment path planning system, comprising: state inversion, etiology refinement, department matching, path planning, and conflict resolution modules. The state inversion module acquires the patient's initial state vector and, through multiple rounds of reverse traversal of the clinical decision tree, infers all prior pathological states and forms a set; the etiology refinement module removes duplicates from the set and merges them to generate a set of potential etiology nodes; the department matching module matches this set with a departmental capability knowledge graph to calculate the transfer cost; the path planning module invokes a reinforcement learning engine to generate a recommended path, using transfer cost as feedback and minimizing treatment time; and the conflict resolution module rearranges time overlap checks and generates a planning table. This system can comprehensively uncover etiologies, accurately match departments, optimize the treatment process, avoid overlapping examinations, and improve treatment efficiency.

The invention provides a chronic patient screening and personalized processing method and system based on a large model, and relates to the technical field of information management, and the method comprises the steps: obtaining and integrating hierarchical diagnosis and treatment coding data of a patient and continuous physiological signal data collected by wearable equipment; respectively mapping the multi-modal data into embedded representations located in a non-Euclidean feature space through a specific model, and executing efficient feature fusion in the non-Euclidean feature space; and calling a large model trained by federated distillation to carry out deep analysis on the fused features to generate a patient recall priority index. According to the method and the device, accurate identification and recall of high-risk patients can be realized, and after the patients see a doctor, a personalized management path scheme is automatically matched or generated according to the diagnosis results of the patients. By making full use of complex internal association of patient data, on the premise that data privacy is protected, accuracy and efficiency of early screening of chronic diseases are remarkably improved, and intelligentization and individuation of subsequent management are achieved.

A method for generating a user interface of predicted disease progression includes receiving medical data corresponding to a patient visit to a healthcare provider, generating a diagnosis for the patient based on the medical data, and generating a predictive diagnosis regarding the patient's future symptoms based on the diagnosis and a prediction model. The method further includes generating a timeline view of the diagnosis and the predictive diagnosis in the current patient visit. Each of the graphic elements of the diagnosis and the predictive diagnosis includes a graphic indicator of the diagnosis and at least one graphic sub-element of a physiological parameter related to the diagnosis. The method further includes generating a graphic connector between the graphic elements to indicate the progression of time between a first time and a second time of the current patient visit.

The utility model discloses a degradable fixing ring for fixing an external auditory canal flap in external auditory meatus plasty, which is formed by bending and connecting a degradable belt, nesting structures which can be nested together are arranged at the head end and the tail end of the degradable belt, and a degradable supporting ring can be stretched and enlarged by stretching the connection at the nesting structures, so that the degradable fixing ring can be used for fixing the external auditory meatus flap in the external auditory meatus plasty. Limiting structures are further arranged at the head end and the tail end of the degradable belt, the limiting structures can limit the degradable supporting ring to shrink backwards after the degradable supporting ring extends and becomes larger, and a connecting part used for being fixedly connected with an external auditory canal transplantation flap is arranged on the degradable supporting ring. The external auditory canal graft flap fixing device can fix an external auditory canal graft flap, reduce the number of times of returning to hospital of a patient, and improve the compliance and medical experience of the patient.

The invention discloses a user inquiry processing method and device, electronic equipment and a storage medium, and relates to the technical field of internet medical treatment. A specific embodiment of the method comprises the following steps: acquiring inquiry information of a user through a preset interactive interface, identifying a current intention of the user, and determining a corresponding current inquiry stage; key information corresponding to the current inquiry stage is extracted based on the inquiry information, and a corresponding inquiry result is matched from a preset knowledge base; in response to successful matching, generating feedback information based on the inquiry result by using a preset large model, and sending the feedback information to the user through the interactive interface; and in response to matching failure, updating a current inquiry stage corresponding to the user, generating updated dialogue information corresponding to the current inquiry stage by using a preset large model, and sending the dialogue information to the user through the interactive interface. According to the embodiment, the problems of low information acquisition efficiency and information omission which are easily caused by the fact that adjustment cannot be carried out according to doctor seeing dynamics and requirements can be solved.

The present disclosure relates to a kind of medicine consumable wisdom purchase method and system, method includes: obtaining hospital historical medicine purchase data, patient visit data and epidemiology data;Adopt medicine demand prediction model, according to the hospital historical medicine purchase data, patient visit data, epidemiology data, first medicine purchase data are determined to be predicted;Determine medicine purchase adjustment adaptability coefficient, according to the medicine purchase adjustment adaptability coefficient, the first medicine purchase data are adjusted, and second medicine purchase data are obtained.The technical scheme of the present application can make the system or business logic more suitable for actual scene changes by determining the medicine purchase adjustment adaptability coefficient.The coefficient follows dynamic change, reduces the error caused by fixed value, makes medicine purchase prediction more accurate, and improves data accuracy.

A mortality prediction device of trauma patients includes a data collection module that collects patient-related data of patients visiting an emergency department for a certain period of time, a learning data generation module that generates a learning data group for one patient by extracting a plurality of preset data from the patient-related data, and a prediction module that inputs the learning data group into one or more machine learning models, respectively, to learn the machine learning models to predict mortality of the corresponding patient.

This invention belongs to the field of heart failure prediction and provides a method for predicting heart failure in electronic health records based on interpretable dual knowledge graphs. This invention constructs a temporal knowledge graph (TKG) and a structural knowledge graph (SKG), extracting features through graph neural networks (GNNs) and combining them with a Transformer encoder to learn long-term dependencies in the patient visit sequence. Finally, the temporal features, structural representations, and demographic embeddings are fused using a multilayer perceptron to achieve early and accurate prediction of heart failure risk.

The invention discloses an intelligent reconciliation system based on hospital settlement information, and relates to the technical field of hospital settlement and reconciliation, and the intelligent reconciliation system based on hospital settlement information comprises a reservation registration system, an inspection registration system, a doctor billing system, a payment transaction end and an information gathering system. The system has the advantages that by recording the ratio of the number of people for appointment registration to the number of people seeing a doctor, the classification and record of drugs and examination items of a doctor every day are recorded through the doctor billing system, and the payment amount of a patient and the payment conditions of drug taking and examination items are recorded through the payment transaction terminal; according to the invention, account checking can be carried out on the billing and actual payment conditions of a doctor, and the number of times, categories, actual payment data and the like of drugs and inspection items generated by the billing of the doctor are summarized through the information summarizing system, so that account checking can be conveniently carried out on settlement information of a hospital.

In some aspects, an artificial intelligence (AI) performs an analysis of a conversation between a doctor and a patient, determines a first trigger phrase in the conversation, and determines a template of a patient visit note based on the first trigger phrase. The AI determines a second trigger phrase in the conversation, determines a particular treatment plan from a plurality of treatment plans based on the second trigger phrase, and adds the particular treatment plan to the template. A first instance of the AI adds a first portion of the conversation to the template and a second instance of the AI, in parallel with the first portion of the conversation being added to the template, adds a second portion of the conversation to the template. The AI provides the template of the patient visit note to a device associated with the doctor.

The present invention relates to the field of medical care informatics technology, and specifically to a hospital consumables usage supervision system and method. By obtaining relevant consumables data and patient visit-related data of each hospital department and analyzing the relevant consumables data, the basic consumables demand of each department is determined; based on the changing trend of patient visit-related data in different periods, the rising trend of the number of patients visiting each department in different periods is determined, and then the indirect impact of the consumables usage of each department affected by the visit load of other departments is determined; based on the rising trend of the number of patients visiting each department in the current period, the basic consumables demand and the indirect impact of consumables usage, the consumables usage allowance of each department is determined, and whether to issue a consumables abnormality warning is determined based on the consumables usage allowance. The present invention effectively improves the accuracy of hospital consumables usage supervision by adaptively determining the consumables usage allowance of each department.

This application is applicable to the field of artificial intelligence technology, and provides an abnormal patient recognition method, device, terminal device and storage medium. By performing vector representation on the name, type and cost of each charging item for each patient visit, a representation vector of the data for each patient visit is obtained; in chronological order, the representation vectors of the data for each patient visit of the patient are input into a long short-term memory network to obtain a representation vector of the data for multiple patient visits of the patient; based on the representation vectors of the multiple patient visit data of the patient, it is identified whether the patient is abnormal. By mining the multiple patient visit behaviors of the patient, abnormal patient recognition is carried out, which improves the recognition accuracy and enriches the abnormal patient recognition method library.

This invention discloses a method, system, and medium for mining the sequential diagnosis and treatment logic of Traditional Chinese Medicine (TCM) based on dynamic efficacy feedback. The method includes: preprocessing TCM time-series diagnosis and treatment data; constructing a sequence of consultation pairs containing multiple patient visits, each pair including consultation status and efficacy feedback; mapping symptoms and prescriptions into structured vectors based on TCM theory to generate state transition tuples; calculating the dynamic evolution pattern of the composite state of the state transition tuples using a state transition probability formula, combined with efficacy feedback information; extracting rules from the composite state vector mapping using a sequential rule mining algorithm, and generating rules consistent with TCM syndrome differentiation thinking using an interpretable decision tree model. This invention mines the hidden dynamic adjustment patterns of TCM syndrome differentiation and treatment in medical records, realizing the visualization and rule-based approach to diagnosis and treatment logic.

The application provides a drug delivery method and device based on privacy protection and image recognition, which comprises the following steps: after a patient visits a doctor and purchases drugs, the prescribed dosage, drug name, oral disease name and personal information are input into a central processing device; the oral lesion images of the patient are collected by multiple terminals of the hospital and treatment institutions and the drug delivery device, and privacy protection is performed according to the number of cases; an oral positioning model is trained by federated learning, which is used for oral lesion partition positioning; a disease analysis model is trained, which is used for determining the drug dosage; the drug delivery device is initialized; the patient uses the drug delivery device to deliver drugs, and the oral lesion images are uploaded by collection; the drug delivery device establishes a patient drug delivery project, and performs expiration reminding, expiration locking and device reuse; the drug delivery device is a handheld spray drug delivery device that meets the requirements of human oral drug delivery, comprising a drug storage chamber, an image acquisition and analysis device, a drug delivery probe and an information interconnection device.

The application discloses a kind of adaptive decision methods for outpatient appointment scheduling, it is related to intelligent medical technology field, including: obtaining the expected appointment time of patient and basic information, constructs patient medical image, predicts patient estimated visit length by the patient medical image;Based on encoder-decoder recurrent neural network, build sequencing decision model, import patient estimated visit length in combination with patient's expected appointment time, define patient's sequencing information in outpatient appointment scheduling;Patient waiting total time, doctor idle time and doctor overtime are introduced according to sequencing information to calculate total time cost for evaluation, when the evaluation result meets the preset standard, then recommend patient appointment visit period.The application generates scheduling data in line with patient satisfaction by adapting to patient visit time heterogeneity through data-driven method, reduces cost while improving outpatient operation efficiency.

The invention relates to a user behavior-based medical service resource optimal configuration method, which comprises the following steps of: acquiring historical doctor seeing data and real-time doctor seeing data of a patient, predicting future traffic through a linear regression model, and acquiring a traffic predicted value; acquiring a peak time period identifier from the flow predicted value, optimizing a doctor scheduling scheme and a medical equipment use scheme by adopting a genetic algorithm, and adjusting a doctor personnel allocation proportion and a medical equipment allocation proportion to obtain an optimized scheduling table; and based on the optimized scheduling table, monitoring the actual flow of the patient in real time, and if the actual flow deviates from the predicted value, correcting the scheduling adjustment scheme. The hospital resource utilization rate is remarkably improved, the waiting time of the patient is shortened, and dynamic and accurate medical resource management is achieved.