25 results about "Patient identifier" patented technology

The invention relates to the field of data query, and particularly provides a medical big data query method and system based on dynamic desensitization, a terminal and a medium, and the method comprises the steps: collecting multi-source heterogeneous medical data, carrying out semantic normalization, constructing a unique identifier of a patient, and generating standardized intermediate plaintext data; constructing an adaptive isomorphic index structure based on the data, constructing a semantic hash B + tree index for structured data, constructing a feature vector index for unstructured data, and dynamically optimizing index hierarchy and parameters according to access frequency; and after a query request is received, the permission context is analyzed, intermediate plaintext data is positioned and read by using the index, and a differential privacy protection strategy is dynamically applied according to the access permission. According to the method, the problem of balance between privacy protection and data effectiveness as well as between retrieval efficiency and storage cost in medical data processing is effectively solved, and data availability and access performance are improved while safety compliance is guaranteed.

The invention discloses a high-precision real-time urodynamic monitoring method and system, and belongs to the technical field of medical monitoring. A urine flow sensor is arranged at the downstream of a catheterization assembly to collect urine flow and generate an electric signal; the electric signals are transmitted to a micro-control unit for digital processing, and the instantaneous flow velocity of urine, the accumulated urine volume per hour and the total urine volume of 24 hours are calculated in real time through an integral flow velocity algorithm; a calculation result is output to a local display screen, and real-time data viewing and historical curve graph and statistical report display are supported; meanwhile, the urine volume data are packaged according to timestamps and patient identifications and uploaded to a hospital nursing information system through a standardized interface protocol; if it is detected that the urine volume is abnormally lower than a set threshold value or is completely in a urine-free state, the system automatically triggers an alarm and pushes the alarm to the nursing terminal; by means of the method, automation, informatization and intelligentization of urine volume monitoring can be achieved, and the method is suitable for continuous nursing requirements of ICU and other critical areas.

The embodiment of the invention discloses an auxiliary decision support information generation system and an auxiliary decision support information generation method. A specific embodiment of the system comprises a server, each heterogeneous data source and at least one terminal, the server is configured to execute the following processing: acquiring a heart and kidney metabolic syndrome patient information table which comprises each patient identifier; creating and updating a heart and kidney metabolic syndrome knowledge graph; for each patient identifier, generating a standardized diagnosis and treatment event record information set; generating an initial diagnosis and treatment event space-time diagram; determining each generated initial diagnosis and treatment event time-space diagram as an initial diagnosis and treatment event time-space diagram set, and storing the initial diagnosis and treatment event time-space diagram set; generating a diagnosis and treatment event space-time diagram corresponding to the treatment data; generating auxiliary decision support information; and sending the auxiliary decision support information to the terminal. According to the embodiment, scheduling resources of the medicine taking robot are reduced.

The invention discloses a time axis key node automatic acquisition system for chest pain diagnosis and treatment, and relates to the technical field of information and communication of medical data, and the time axis key node automatic acquisition system comprises the following steps: pre-storing an interval template containing a starting or ending anchor point rule; acquiring an event stream which comes from one or more medical information systems and carries a chest pain patient identifier and a source system timestamp in real time; creating and maintaining an active interval instance in a memory for the chest pain patient; inferring a candidate end event; and identifying the time reference drift of the source system, and adding a credibility mark to the time-consuming data. Automatic and real-time monitoring of time consumption in the diagnosis and treatment process is achieved, the system supports starting and ending anchor point matching, automatically recognizes time reference drift and adds credibility marks, and the reliability of time consumption data in a real and complex environment is guaranteed on the premise of not depending on strict time synchronization of a hospital-wide system.

The embodiment of the invention provides an operation scheduling method and a medical data processing system, which are used for improving the efficiency and convenience of arranging an operation for each operating room. The method provided by the embodiment of the invention comprises the following steps: in response to a selection operation on any patient operation information in a patient operation information display component and an interaction operation between the selected patient operation information and an operating room information display component, generating a first interaction instruction, the patient operation information display assembly and the operating room information display assembly are displayed on a preset interactive interface, and the patient operation information display assembly is used for displaying a surgeon, a patient department and at least one of a patient identifier and an operation identifier. The operating room information display assembly is used for displaying the number of operations in an operating room, the total duration of the operations and visual operation progress information; according to the first interaction instruction, the selected patient operation information is switched from the patient operation information display assembly to the operating room information display assembly.

This disclosure presents an auxiliary decision support information generation system and method. One specific implementation of the system includes: a server, various heterogeneous data sources, and at least one terminal; the server is configured to perform the following processes: acquiring a patient information table for cardiorenal metabolic syndrome, wherein the patient information table includes individual patient identifiers; creating and updating a knowledge graph for cardiorenal metabolic syndrome; generating a standardized set of medical event records for each patient identifier; generating an initial spatiotemporal graph of medical events; determining the generated initial spatiotemporal graphs of medical events as an initial spatiotemporal graph set, and storing the initial spatiotemporal graph set; generating a spatiotemporal graph of medical events corresponding to the patient's medical data; generating auxiliary decision support information; and sending the auxiliary decision support information to the terminal. This implementation reduces the scheduling resources of the medication dispensing robot.

The invention discloses an ophthalmology intelligent auxiliary diagnosis method and system based on heterogeneous data collaboration, and the method comprises the steps: synchronously obtaining an ophthalmology multi-mode heterogeneous data set of a patient, including an OCT image, a fundus photograph and a visual field inspection report; the OCT image is subjected to retina layered structure segmentation, and an RNFL thickness distribution diagram is extracted; performing optic disc region positioning and blood vessel tree segmentation on the fundus photography to generate a CDR and a blood vessel curvature quantized value; mode deviation probability graph coding is carried out on the visual field inspection report, and a quadrant sensitivity missing matrix is output; an ophthalmic multimodal heterogeneous data set is associated through a patient unique identifier, and a RNFL thickness distribution map of OCT is mapped to an optic disc coordinate system of fundus photography by using feature-driven non-rigid registration. According to the invention, an ophthalmology multi-modal data cooperation barrier is broken through, an intelligent decision-making system with structure-function mutual verification is constructed, and the diagnosis reliability and clinical interpretability are significantly improved.

The invention discloses an infusion information management system, which relates to the technical field of medical informatization equipment and comprises a task information access module, a label data generation module, a dual-channel acquisition module, a context association processing module, a synchronous locking control module, a transaction state judgment module and an execution record collection module. According to the method, a cross time locking domain and a transaction serialization mechanism are introduced into the system, so that unified constraint of multi-terminal data in a time domain and a logic domain is realized; meanwhile, scanning, position and equipment identity information are subjected to multi-dimensional binding through a context association structure, atomic-scale correspondence of an infusion label and a patient identifier at the infusion execution moment is achieved, and false matching caused by time sequence drift or concurrent operation is avoided; according to the invention, the safety of infusion behaviors and the consistency of system-level information can be obviously improved.

The invention discloses a pathological image multi-task analysis method and system integrating medical priori knowledge, and the method comprises the steps: obtaining pathological image blocks of a plurality of patients, the pathological image blocks being associated with corresponding space coordinates, pathological labels and patient identifiers; respectively extracting visual features of each pathological image block; based on the space coordinates, the pathological labels and the visual features, constructing a graph structure fused with medical priori knowledge; taking the visual features as initial embedding of graph nodes of the graph structure, and inputting the visual features into a graph neural network for message passing so as to obtain updated graph node feature representation; and based on the updated graph node feature representation, executing multi-task learning so as to realize image block-level pathological classification and patient-level survival risk prediction. By constructing a medical priori knowledge graph structure fusing space coordinates, pathological labels and visual features and executing end-to-end multi-task learning, collaborative optimization of image block-level pathological classification and patient-level survival risk prediction is realized.

Described is a system comprising an input module receiving a first data set indicative of at least one patient condition for each of a plurality of patients obtained during a predetermined time period, a comparison module comparing each of the at least one patient condition to at least one filter criteria, a filter module selecting a patient to include in a second data set if the at least one patient condition of the patient satisfies the at least one filter criteria, a report module generating a report based on the second data set, wherein the report includes at least one patient identifier for each patient in the second data set and at least one descriptor of the at least one patient condition for each patient in the second data set, and a classification module storing at least one classification value for the at least one patient condition.

An apparatus for the anonymization of user data is disclosed. The apparatus includes at least processor and a memory communicatively connected to the processor. The memory contains instructions configuring the processor to receive a plurality of user data. The memory contains instructions configuring the processor to identify a plurality of patient identifiers within the plurality of user data. The memory contains instructions configuring the processor to generate contextual data associated with each patient identifier of the plurality of patient identifier. The memory contains instructions configuring the processor to identify one or more false positive patient identifiers within the plurality of patient identifiers as a function of the contextual data.

This invention discloses a method for tamper-proof verification of personal radiation dose logs from CT scans, comprising: real-time acquisition of radiation dose data and related operation information during CT scans to generate a structured raw dose log; generating an encrypted log string through asymmetric encryption signature and SHA-256 / SM3 hash operation, combining patient identifier, timestamp, and device number to generate a unique verification identifier and adding a blockchain calibration timestamp; synchronizing relevant data to a consortium blockchain node cluster and a third-party trusted server for distributed redundant storage; supporting verification triggered by multiple entities including patients, hospitals, and regulatory agencies, outputting results through encrypted string comparison, field-level consistency verification, and multi-dimensional verification of format / field / logic; accurately tracing the source of tampering based on stored data, and automatically sending warning information to relevant parties when warning conditions are met. This invention achieves transparent verification, efficient verification, and reliable traceability of dose logs, improving data credibility, reducing medical disputes, and ensuring the effectiveness of medical quality supervision.

The invention discloses an image output management method for a medical image, which relates to the technical field of medical information management, and comprises the following steps: recording an output context parameter based on an image output request, generating an output event record including an operator identifier, a department identifier, a patient identifier, an examination number, a DICOM image identifier, an output type, an output target address, a workstation identifier and an output timestamp, and writing a global unique number generated based on the timestamp into the output event record; comparing a local cache index according to the global unique number to screen unregistered records, generating deduplicated output event records, and sequentially writing the deduplicated output event records into a cache log file; generating a serial number word string according to the global unique serial number recorded by the output event in the cache log file, and executing SHA-256 operation based on the serial number word string to generate batch Hash abstract data; according to the invention, synchronous guarantee of medical image output behaviors in three aspects of context binding, content consistency and visual auditing traceability is realized.

The application relates to a computer-based hospital bed dynamic allocation method, which receives a bed event and a patient event; maintains a bed record containing a bed identifier, a bed state, an associated patient identifier and a state version number; in response to a bed allocation request, determines a target bed from candidate beds in an allocable state, updates the state of the target bed to reserved and starts a reservation timer; in the reserved state, when a receiving department confirmation receiving event and a patient admission receiving completion event are received, the bed state is updated to confirmed; in the confirmed state, when a patient transfer start event is received, the bed state is updated to locked and re-allocation is prohibited; if a cancellation event is received or the reservation timer expires, the bed state is restored to allocable and the associated patient identifier is cleared; if a cancellation event is received before the patient transfer start event is received, the bed state is restored to allocable and the associated patient identifier is cleared; and finally, each state change is recorded.

An apparatus for the anonymization of user data is disclosed. The apparatus includes at least processor and a memory communicatively connected to the processor. The memory contains instructions configuring the processor to receive a plurality of user data. The memory contains instructions configuring the processor to identify a plurality of patient identifiers within the plurality of user data. The memory contains instructions configuring the processor to generate contextual data associated with each patient identifier of the plurality of patient identifier. The memory contains instructions configuring the processor to identify one or more false positive patient identifiers within the plurality of patient identifiers as a function of the contextual data.

Methods and systems are provided that are related to electronic health records (EHRs). A first EHR system can receive a request to report information to a second EHR system. Responsive to the request, the first EHR system can generate an EHR report that includes one or more EHR identifiers. The one or more EHR identifiers can include an EHR-user identifier, an EHR-patient identifier, and a behavior identifier. The first EHR system can send the EHR report to the second EHR system. The second EHR system can: access information based on the EHR-user identifier and / or the EHR-patient identifier, generate an output based on the accessed information, and provide the output.

The invention discloses a medical technical examination queue dynamic scheduling method and system oriented to a creative environment, and relates to the technical field of medical management, and the method comprises the steps: responding to the registration operation of a patient, and creating an examination instance of the patient; the examination instance comprises a patient identifier, a waiting state, waiting duration and a to-be-examined item; the waiting state comprises scheduling participation and scheduling elimination; in response to the fact that the state of the first medical technology resource is updated to be allocatable, screening a candidate instance set, matched with the first medical technology resource, of the to-be-detected item from the check instances in which scheduling participates, counting the number of allocatable resources, matched with the first medical technology resource, of the to-be-detected item, and sorting the check instances of the candidate instance set according to a preset sorting rule, and according to a sorting result, taking the examination examples corresponding to the allocatable resource number, allocating the examination examples to the corresponding medical technology resources, updating the waiting state of the examination examples allocated with the medical technology resources into scheduling exclusion, and dynamically adjusting the scheduling task in time in response to the change of the patient state and the medical technology resource state.

This invention provides a program, information processing system, and method for realizing a medical communication system that supports multiple medical communication schedules for a single patient. [Solution] In an information processing system, a server device for medical communication, which exchanges medical-related information including patient explanations, receives first tag information through communication with a patient-side terminal device, determines a first schedule for first medical communication regarding the patient's first medical event based on the received first tag information, registers the determined first schedule information in association with the patient's identifier, and when it further receives second tag information through communication with the patient-side terminal device, determines a second schedule for second medical communication regarding the patient's second medical event based on the received second tag information, registers the determined second schedule information in further association with the patient's identifier.

The application discloses a batch processing method, system, device and medium for determining the quality of microbiological specimen test data, relates to the field of microbiological testing, and comprises the following steps: querying microbiological specimen test records of different patients within a preset time length to obtain a specimen test record set carrying patient identifiers and specimen test record times; taking the earliest record time in the specimen test record set as a starting point, and dividing a continuous time axis corresponding to all microbiological specimen test record times in the specimen test record set according to a preset time window to obtain a plurality of time intervals; grouping the microbiological specimen test records in each record set based on the patient identifiers and the serial numbers to obtain grouped specimen test records; and aggregating the grouped specimen test records with the same serial type based on a preset aggregation algorithm, and generating a quality index based on the aggregation result. The application can improve the evaluation efficiency of the quality of microbiological specimen test data, and the processing time length does not linearly increase with the data volume.

A medical device data back-association system, apparatuses, and methods are disclosed. In an example embodiment, a server receives, while an infusion pump is administering a medication to a patient, an identifier message including at least two of a device identifier of the infusion pump, a patient identifier of the patient, and a medication order identifier of a medication being administered by the infusion pump. The server prompts a clinician device for creating an association between an electronic medical record (“EMR”) of the patient and the infusion pump. When an association to be created, the server uses contents of the identifier message to create the association. For subsequently received infusion pump data, the server stores this infusion pump data to the EMR of the patient based on the created association between the EMR of the patient and the infusion pump.

The present invention relates to an automatic culture device using a single-use closed system flow path for culturing a cell or a tissue, and realizes reduction in manufacturing cost and high integration property of a device. A cell culture system including an automatic culture device and an information processing device. The automatic culture device includes a plurality of types of closed system flow paths possible to be installed and removed, and a plurality of culture devices. The information processing device includes: an input device configured to receive, as an input, at least one piece of data selected from a group consisting of data of an identifier of a patient, data related to a transplantation method, data related to a type of cell, data related to the required number of cells, and data related to a treatment plan; an arithmetic device configured to select, based on the input data, from options of a cell culture method, the culture devices, and the closed system flow paths, the cell culture method, the culture device, and the closed system flow path to be used; and an output device configured to output a number of the closed system flow path to be used and a number of the culture device to be used.

The invention discloses a hospital comprehensive evaluation method, system and equipment based on an electronic medical record library and a medium, mainly relates to the technical field of comprehensive evaluation, and is used for solving the problems of low heterogeneous data integration efficiency, non-uniform data standards, lack of effective desensitization and standardization processing mechanisms and single hospital evaluation dimension in the existing scheme. Comprising the steps of completing butt joint of a data acquisition interface and a corresponding heterogeneous data system; obtaining standard medical data which is returned by the data obtaining interface and is processed by the desensitization program and the standardization processing program; according to patient identifiers in the standard medical data, summarizing all standard medical data of the same patient identifier in the current hospital as a patient data subset; extracting preset index key data from the patient data subset; generating a preset index value by using the specific content of all the associated data of the current hospital; and obtaining a weighting coefficient of the preset index value, and weighting to obtain a comprehensive evaluation value of the current hospital.

The invention relates to the technical field of medical data processing, and provides a patient medical data management method, a computer device and a storage medium, and the method comprises the steps: in response to a creation request for a patient identifier in a current scene, executing a patient identifier creation process, comprising the following steps: acquiring desensitization associated data, current timestamp information and random confusion information of patient identity data; fusing the desensitization associated data, the current timestamp information and the random confusion information to generate an original character string; mapping based on the original character string to obtain a patient identifier; and storing patient medical data generated by the patient in the current scene in association with the patient identifier. When the patient identifier is generated, the uniqueness of the obtained patient identifier is effectively guaranteed by combining feature information such as desensitization data and timestamps hosted by the patient and a coding mapping mode in which reversal information is difficult to obtain.

The invention belongs to the technical field of intelligent medical treatment, and particularly relates to a hospital health science popularization robot service system, which receives a plurality of service requests which are initiated by appointed calling equipment and comprise patient identifiers and physical positions, calls medical record data according to the patient identifiers, and sends the medical record data to a server; the method comprises the following steps: constructing a weighted scoring rule with medical record characteristics as a main part and waiting duration and spatial distance as auxiliary parts, planning a service priority sequence of a robot, collecting oral inquiry audio of a patient and converting the oral inquiry audio into a text after the robot arrives at a specified patient position according to the planning sequence; and combining patient medical record dimensions of intention recognition, slot filling and dynamic calling to carry out context enhancement so as to reconstruct a standard clinical question, carrying out supportive evidence chain retrieval and rationality verification on preliminary answer content by introducing a medical knowledge graph, generating final health science popularization content, and outputting the final health science popularization content. And it is ensured that the finally output health science popularization content not only is personalized, but also has medical reliability and safety.

The invention belongs to the technical field of medical information processing, and discloses an emergency waiting patient condition dynamic assessment method based on a mobile terminal. The method comprises the following steps: generating a waiting two-dimensional code packaged with a patient identifier, a priority weight and an illness state baseline feature vector by obtaining a triage result of a patient and baseline sign data; queuing information and a baseline feature vector are obtained through code scanning of a mobile terminal, and qualitative clinical observation information collected by a nurse is converted into a quantitative offset value based on a clinical observation semantic knowledge base; performing offset operation on the quantized offset value and the baseline feature vector, and calculating a disease deterioration risk index in combination with the waiting time, the triage level and the waiting environment; dynamically adjusting the doctor seeing priority weight according to the disease deterioration risk index, triggering queuing sequence reconstruction, synchronizing to an emergency information system for reordering, and pushing a change notice to related patients and consulting rooms; according to the invention, high-quality technical support is provided for emergency waiting management and intelligent triage.