51 results about "Clinical events" patented technology

The invention relates to the technical field of software, and discloses a nursing shift change system based on homologous heterogeneous data fusion and a large language model, and the system comprises a shift change generation module which comprises a first generation unit and a second generation unit, calling a large language model to generate global summary information of nursing shift change; and the second generation unit is used for calling a large language model to generate corresponding detailed handover information only based on the original data of the key event. And the report synthesis module is used for integrating the global summary information and the detailed handover information according to a preset structure to generate a nursing handover report. According to the method, the panoramic data view of the patient is constructed based on the unified time axis, so that structured data and unstructured data which are originally dispersed in different systems can be organized and called in the same semantic space, and a consistent data basis is provided for subsequent data analysis and processing.

The invention provides a clinical decision knowledge graph construction method and system, and the method comprises the steps: extracting standardized entities corresponding to diseases, symptoms and diagnosis and treatment elements from medical knowledge data; constructing a clinical concept knowledge graph for representing a medical concept logic relationship and a causal relationship according to the semantic association relationship and the causal dependency relationship among the standardized entities; a diagnosis event, an examination event and a treatment event related to the patient are extracted, link evidences among the events are determined based on the event chain relation among the events, and a clinical event knowledge graph used for representing the disease course evolution process of the patient is constructed according to all the link evidences; and performing knowledge element fusion based on an entity association relationship between the clinical concept knowledge graph and the clinical event knowledge graph, and generating a target knowledge graph for clinical decision analysis. By adopting the scheme of the invention, the cross-map fusion of the static medical concept knowledge and the dynamic disease course event chain relationship can be realized, and the clinical decision knowledge structure with the reasoning ability can be constructed.

The invention belongs to the technical field of medical care informatics, and discloses a remote central monitoring system for community medical treatment, which comprises a data acquisition and integration module, a physiological state analysis engine and a monitoring information presentation module, and can construct a state-dependent baseline model cluster based on the activity state information of a user, according to the real-time activity state of the user in the monitoring period, the corresponding sub-model is dynamically selected to serve as a judgment reference, and then a continuously-changing physiological stability index is generated by comparing the multi-dimensional statistical characteristics of the real-time physiological data with the deviation degree of the reference; according to the method, by establishing an individualized physiological steady state judgment benchmark which is adaptively adjusted along with the activity situation, the capability of a monitoring system for continuously and quantitatively evaluating the overall stability of a human body as a complex system is improved, and the transformation from passive detection of discrete clinical events to state insight of a risk evolution process is realized.

The invention discloses a multi-modal drug recommendation method and system based on large language model driving, and relates to the technical field of medical informatics and artificial intelligence. The invention aims to solve the limitation of an existing drug recommendation model in the aspects of patient characterization construction, drug multi-modal modeling and large language model application. Comprising the following steps: constructing patient characterization, and aligning a patient state and a potential medication space in a characterization learning stage through a cooperative prompt project driven by a large language model; multi-modal drug characterization is constructed, and clinical logic and chemical characteristics of drugs are deeply depicted through semantic expert and molecular structure expert dual-channel design; a'static anchoring dynamic 'time sequence reasoning mechanism is provided, context modulation is performed on a dynamic evolutionary clinical event sequence by utilizing a static treatment baseline formed by global medication history, and finally, an accurate and safe medication combination is generated through a label sensing prediction module. According to the method, the accuracy, safety and clinical logic self-consistency of drug recommendation are remarkably improved.

The invention discloses a visual asynchronous event triggering and calling method based on a medical information system, which comprises the following steps of: asynchronously acquiring multi-source data streams such as clinical events, equipment monitoring, doctor advice execution and patient states in the medical information system to form a multi-source asynchronous medical data stream set; generating a system event triggering association group based on the set and creating an asynchronous event scheduling strategy table; performing system event association degree calculation on the data stream to obtain a multi-dimensional asynchronous event association matrix; and carrying out system asynchronous time delay compensation and event chain visualization processing on the incidence matrix based on the scheduling strategy table, and finally generating a dynamic asynchronous event correlation topological graph. According to the invention, by constructing a system event detection operator set, establishing cross-flow system relevance calculation and establishing a priority-based asynchronous scheduling optimization mechanism, intelligent triggering, calling and early warning functions of medical system events are realized.

This invention relates to the field of medical intelligent technology and discloses a method and system for intelligent recommendation of laboratory tests based on patient diagnosis and treatment information. The method includes: extracting clinical events from time-series diagnosis and treatment information to obtain standardized clinical events; determining the medical logical relationships of the standardized clinical events and labeling causal, temporal, and co-occurrence relationships to obtain labeled clinical events; constructing a disease evolution network with labeled clinical events as nodes and medical logical relationships as edges; analyzing the topology of the disease evolution network to obtain critical paths and hub nodes, and resolving the hub nodes as core clinical diagnosis and treatment intentions; associating and matching the core clinical diagnosis and treatment intentions with a pre-constructed dynamic correlation graph of test-intentions to obtain test item combinations; and ranking the test item combinations according to the clinical path fit based on the current diagnosis and treatment stage and individual characteristics to obtain a personalized test item recommendation list. This invention can improve the efficiency of test item recommendation.

The present application relates to the technical field of medical information processing and intelligent disease prediction, in particular to a neurofibromatosis prediction method based on clinical medical information. The method comprises the following steps: acquiring multi-modal clinical medical information with time labels; performing anatomical system classification processing, extracting clinical feature nodes and calculating correlation, and establishing an initial multi-system prediction network graph; determining the asynchronous graph node feature aggregation rate according to the feature update rate difference of adjacent nodes under different time labels, performing local feature diffusion processing, and determining a global multi-system prediction network graph; further determining the cross-domain evolution incubation period weight, the phenotype cascade transfer probability matrix and the disease topology state information entropy, and determining the neurofibromatosis prediction result accordingly. The present application solves the contradiction of long-term and ineffective consumption of a large amount of computing resources to cope with low-frequency but high-impact clinical events, and optimizes the trade-off relationship between risk identification accuracy and system response timeliness.

A method for adaptively scheduling non-invasive blood pressure measurement time intervals based on using a risk model to compute a risk of a patient suffering a pre-defined one or more adverse clinical events, for example within a pre-defined time window, and also based on a clinician risk assessment for a patient.

The invention discloses a clinical decision support system fusing structured knowledge and generative intelligence. A guide map generation module is used for converting an unstructured authoritative clinical guide into a machine-readable and executable structured knowledge map; the medical record information extraction module is used for processing an unstructured medical record original text written by a clinician and extracting a clinical event sequence with a timestamp from the unstructured medical record original text; the decision reasoning module is used for receiving the structured knowledge graph and the clinical event sequence and driving a large language model to perform multi-step logical reasoning under the guidance of the structured knowledge graph so as to plan a diagnosis and treatment path; and the interactive display module is used for displaying the diagnosis and treatment path and the decision basis corresponding to each decision node on the diagnosis and treatment path in a visual mode. According to the method, the unstructured medical record information and the structured guide knowledge can be deeply fused, and normative and highly personalized decision support is provided for clinicians.

The invention provides a clinical event timeline extraction method and equipment based on multi-agent cooperation, and the method comprises the steps: calling an event extraction agent to extract a clinical event from a medical record text, and extracting a context state and a time sequence state of the clinical event, and determining patient-related events from the clinical events based on the contextual state and timing state of the clinical events; the context state represents a function scene of the clinical event in a clinical diagnosis and treatment process; calling a time standardization agent to determine the standardization time of the patient-related event from the medical record text; a clinical event timeline for the patient is determined based on the standardized time of the patient-related event. According to the method and the equipment provided by the invention, the specialty and the reliability of each link in the clinical event timeline extraction process are ensured through division of labor, cooperation and respective functions of multiple agents, so that the generalization effect and the flexibility of clinical event timeline extraction in multiple scenes can be improved.

The present application belongs to the technical field of medical care information science, and discloses a community medical remote central monitoring system, which comprises a data acquisition and integration module, a physiological state analysis engine and a monitoring information presentation module.The system can construct a state-dependent baseline model cluster based on the activity state information of a user, dynamically select a corresponding sub-model as a judgment benchmark according to the real-time activity state of the user in a monitoring period, and then generate a continuously changing physiological stability index by comparing the deviation of the multi-dimensional statistical characteristics of real-time physiological data from the benchmark.The present application establishes an individualized physiological steady state evaluation benchmark that is self-adapted to activity contexts, improves the ability of the monitoring system to continuously quantitatively evaluate the overall stability of the human body as a complex system, and realizes the transition from passive detection of discrete clinical events to state insight into the risk evolution process.

The invention discloses an atrial fibrillation recurrence prediction method based on artificial intelligence, and belongs to the technical field of medical information, and the method specifically comprises the steps: inputting a discrete clinical event record after an ablation operation of a target patient, and carrying out the inversion of a continuous internal state evolution path from the discrete clinical event record through an event-driven hidden state deduction model. The path is divided into a plurality of recovery stages and a feature vector is generated. And taking the last stage as a query object, retrieving similar historical stages in the pre-constructed group recovery process graph, and extracting a complete stage chain of the similar historical stages until a clear outcome. And mapping back to a physiological state space, and forming a plurality of candidate future evolution chains starting from the current state of the patient through coordinate translation. And finally, calculating the likelihood score of each candidate chain in combination with the historical event mode of the patient, and outputting a personalized recurrence risk prediction path set after sorting and screening. The invention provides a new approach for dynamically predicting the recurrence risk of the atrial fibrillation with both individual adaptability and time sequence interpretation.

A system and method are provided for evaluating a prediction model configured to predict occurrence of a clinical event in multiple patients during corresponding patient stays, where the prediction model outputs risk scores for the patients. The method includes identifying patient stays that include at least one risk score generated by the prediction model that crosses a predetermined risk threshold; providing notifications for risk scores that cross the risk threshold; determining a patient-level confusion matrix based on the notifications, where each patient stay contributes one patient data point to the patient-level confusion matrix; determining an event-level confusion matrix based on the notifications, where the event-level confusion matrix includes prediction lead time and notification limit, where each patient stay contributes one event data point to the event-level confusion matrix; calculating classification metrics for false positives and false negatives; and identifying errors in the predication model based on the classification metrics.

Some embodiments of the present disclosure provide a framework for using unsupervised artificial intelligence to automatically abstract and align clinical facets. The approach of the present application may be shown to reduce human involvement and, accordingly, enhance privacy compliance. Aspects of the present application relate to a process of self-learning from the data available. Accordingly, aspects of the present application may be shown to be resilient to the appearance of new concepts and facets in future data. Additionally, aspects of the present application may be shown to adapt well when presented with different languages, different styles of documentation and different clinical domains. Aspects of the present application relate to processing unstructured, non-fielded data, such as clinical notes, admission and discharge summaries, surgical notes, lab reports and imaging reports. These notes may be considered to contain hidden insights in the clinical domain. Additionally, these notes may be considered to contain data that may not be captured elsewhere in a readily usable way. Aspects of the present application may be shown to support analysis of large size populations at a relatively low incremental cost.

The invention belongs to the technical field of artificial intelligence and medical health information processing, particularly relates to an ICU critical patient multi-mode risk early warning system based on deep learning, and aims to solve the problems that in intensive care, illness state prediction lags behind, multi-source data fusion is difficult, and single-index early warning precision is low. According to the system, high-frequency physiological signals, clinical observation values, inspection images and unstructured texts are collected through the data sensing layer, cross-modal embedding and comparative learning alignment are carried out through the heterogeneous fusion layer, and a shared semantic space is constructed; the time sequence reasoning layer utilizes an improved space-time diagram neural network to model a dynamic knowledge graph, and causal and time sequence dependence among clinical events is captured; and the risk decision-making layer outputs multi-dimensional risk probabilities of sepsis, respiratory failure and sudden cardiac arrest in parallel. The system supports online incremental learning and individualized time decay modeling, the timeliness, accuracy and interpretability of early warning are improved, and the method is obviously superior to a traditional method in clinical verification.

The invention discloses a clinical tag labeling method, system and equipment based on a standardized time sequence and a medium, and relates to the technical field of clinical event fusion and dynamic tag generation, and the specific steps are as follows: obtaining clinical event data of a patient from different clinical business systems in real time, dividing cycle attribution for the clinical event data, and determining the clinical event data; and establishing a dynamic weight calculation model to allocate dynamic weight values, establishing a periodic clinical state inference model by adopting a convolutional neural network and training the periodic clinical state inference model, inputting weighted summary clinical feature vectors in a current patient period according to the trained periodic clinical state inference model, and outputting clinical tags corresponding to patients. According to the invention, clinical label labeling based on a standardized time sequence is realized, multi-source clinical event data from different clinical business systems can be collected in real time, event weights are reasonably distributed through a dynamic weight calculation model, a periodic clinical state is deduced by using a convolutional neural network, and clinical labels of patients are automatically generated.

The application provides a kind of electronic medical record intelligent generation method and system based on HIS system, which comprises the following steps: obtaining and time alignment multimodal diagnosis and treatment data in HIS system, form time sequence event sequence.Based on clinical rule base, the sequence is parsed into standardized diagnosis and treatment behavior node, and the node sequence is scanned to build a clinical event relationship graph containing causal connection. Dynamic model of clinical attention is used to assign time-varying weight to the parallel task subgraph in the graph, and the key narrative path running through the whole process is identified accordingly. The structured logic of the graph is converted into medical record text with the path as the core framework to guide the language generation model. The facts and original data in the text are logically consistent and integrated. The application can reveal and reconstruct the internal causal logic and narrative main line in the diagnosis and treatment process in the generated electronic medical record.

The invention discloses a hospital building-oriented off-grid light storage direct flexible power supply method and system, and relates to the technical field of building energy systems and intelligent microgrids, and the method comprises the steps: obtaining hospital clinical event data and future medical operation plans, dynamically dividing the power supply priority of electrical loads, and generating a key load guarantee strategy; in combination with weather forecast information and medical load time sequence requirements, a minimum charge state threshold value required by an energy storage system is calculated, an off-grid power supply framework comprising a photovoltaic power generation module, an energy storage module and a bipolar direct-current bus is constructed, and the bus voltage is dynamically adjusted to a flexible floating band based on power deviation, so that an off-grid power supply system is constructed. The method comprises the following steps: cooperatively controlling energy storage charge and discharge behaviors according to a charge state and a preset threshold value, cutting off a non-critical load when energy is insufficient, ensuring continuous power supply of a primary load, simultaneously monitoring a bus voltage and charge state change trend, seamlessly starting a standby power supply and gradually recovering the non-critical load when a system instability risk is detected, and the main energy system returns to normal.

The application discloses a medical resource scheduling and risk early warning method and system and electronic equipment. The method comprises the following steps: acquiring a clinical event record and mapping to a multi-dimensional organ state space; constructing a double-path representation atlas of a patient in the multi-dimensional organ state space in parallel; updating a state transition edge and generating a continuous dynamic risk load sequence by using a clinical event trigger mechanism; monitoring a dynamic evolution direction coupling degree based on time delay mutual information; and generating an active medical resource scheduling suggestion and outputting expert recommendation information when a non-synchronous state offset is captured. The application can realize rolling early warning of risks and active identification of medical intervention conflicts and resource scheduling, and improve the diagnosis and treatment coordination efficiency and resource allocation accuracy in a multi-disease coexistence environment.

This invention relates to the field of intelligent diagnosis and treatment technology, and particularly to a precision diagnosis and treatment method and system for non-high-risk chest pain populations. The method includes: acquiring known clinical information, known coronary artery imaging information, and known long-term clinical events of non-high-risk chest pain populations to construct a dataset; training an XGBoost model using the dataset to obtain a risk prediction scoring model; acquiring clinical information of the non-high-risk chest pain patient to be tested, inputting it into the risk prediction scoring model to obtain a risk prediction score; determining the group to which the non-high-risk chest pain patient belongs based on the risk prediction score; and determining subsequent diagnosis and treatment strategies based on the group to which the non-high-risk chest pain patient belongs and the patient's clinical information. This invention can more accurately predict the risk of non-high-risk chest pain patients, and for low-risk non-high-risk chest pain patients, it can reduce unnecessary invasive examinations and achieve effective resource allocation.

The invention discloses a method and a system for enhancing laboratory test term matching by utilizing category-based fine tuning and time sequence modeling, which comprises the following steps of: firstly, constructing a negative example sample of a non-synonymous term pair in the same category by utilizing high-level category information to which laboratory test terms belong, performing fine tuning on a pre-training model, and performing time sequence modeling on the pre-training model; the fine-grained distinguishing capability of the model on terms with similar semantics and different concepts is enhanced, and semantic representation of an embedded space is optimized; then time sequence modeling is carried out, a clinical event sequence of a patient is constructed, a context window and an embedded aggregation strategy are adopted, the time sequence similarity between events is captured, and the context sensing ability of term representation is enhanced; and finally, based on the semantic embedding representation obtained by independently inputting the laboratory test terms into the model and the semantic embedding representation obtained by adding term time sequence information, calculating the similarity between term pairs, and realizing term matching. Domain rules and time sequence information are fused in the matching process, and the term matching precision and practicability can be improved.

The application discloses a clinical auxiliary decision-making method and system based on integrated time-series multi-modal data, relates to the field of medical information technology, and comprises the following steps: collecting and time-aligning time-series multi-modal clinical data of a patient, performing feature analysis and cross-modal fusion, and generating a unified multi-dimensional time-series health state feature spectrum.Based on the feature spectrum and a medical knowledge graph, a clinical state evolution model is established, the evolution distance between the current state of the patient and each key clinical event node is calculated, and then a dynamic risk assessment surface is constructed to identify a high-risk evolution path.Aiming at the high-risk path, the key feature combination is located back, corresponding intervention measure evidence chains are searched from the knowledge graph, and finally a clinical decision support report is generated.The application realizes dynamic quantitative risk assessment of disease evolution and automatic evidence-based decision recommendation.

The invention relates to the technical field of medical information processing, in particular to a critical data extraction method and system based on natural language processing and a knowledge graph. The method comprises the steps of obtaining original medical record data, analyzing the original medical record data and outputting a structured text; identifying and extracting various clinical entities in the whole course of diagnosis and treatment in the structured text; associating the extracted clinical entities to a medical knowledge graph, mining a logical relationship between the entities, extracting time information, and constructing a clinical event time axis; the standardized and associated information is integrated, and a dynamically updated structured multi-dimensional clinical data file with time as the axis is generated; the system comprises a multi-modal data analysis module, a key clinical entity recognition module, a semantic fusion module and a structured file generation module. By means of the mode, efficient, complete and intelligent extraction and analysis of complete-cycle data of critical patients are achieved.

The invention relates to the technical field of medical care informatics, and discloses an osteoporosis prevention strategy analysis method and system, and the method comprises the steps: a discrete event sequence extraction module extracts clinical events from an electronic medical record; the parameter adaptive mapping module constructs a time scale scaling factor by using the glomerular filtration rate, performs reverse correction on the attenuation parameter of the risk pulse function, and determines positive correlation mapping of the attenuation rate and the clearing efficiency; the time domain overlay analysis module calculates an instantaneous bone loss index and generates a bone mineral density evolution trajectory; according to the method, physiological metabolism indexes are converted into time control variables of a mathematical model, dynamic distortion caused by individual metabolism differences is avoided, and quantification and early warning of the risk long-tail superposition effect in the body of a patient with metabolic hypofunction are achieved.

A computer-implemented method for determining a state of relevance associated with a clinical impact of one or more material properties, the method comprising: obtaining, via one or more processors, material property data for the one or more material properties associated with a pharmaceutical material, the material attribute data comprises measurement data of the one or more material attributes at one or more time points; obtaining, via the one or more processors, clinical data associated with the drug material, where the clinical data includes subject data including one or more clinical events associated with one or more subjects who have accepted administration of the drug material; applying, via the one or more processors, one or more transformations to the material property data and the clinical data to produce modified material property data and modified clinical data, where the one or more transformations include at least one of cleaning, merging, associating, selecting, or grouping; and determining, via the one or more processors, the relevance state based on the modified material attribute data and the modified clinical data using a computational model.

The invention discloses a sepsis patient prognosis method and system based on a multi-task Transform model, a storage medium and equipment, and belongs to the technical field of intelligent medicines.The method comprises the following steps that S1, multiple time sequence physiological data of ICU patients are extracted from an electronic health record database; s2, preprocessing the time sequence physiological data; s3, a multi-task Transform prognosis model is constructed on the basis of the preprocessed time sequence physiological data, and different backtracking windows are used for generating input sequences with different lengths according to prediction task types; the prediction task type comprises an acute task and a long-term task; s4, carrying out training on the multi-task Transform prognosis model, and carrying out training on the multi-task Transform prognosis model; and S5, predicting the shock and death risks of the current sepsis patient by using the trained multi-task Transform prognosis model. According to the method, the backtracking windows with different lengths are set for the acute task and the long-term task, so that the method better fits the time sequence characteristics of different clinical events, the prediction accuracy is improved, the method is adaptive to different clinical scene requirements, and the interpretability is high.

The application discloses a unified architecture method of medical knowledge and database by adopting a redundancy strategy, and comprises the following steps: value range classification is performed on a preset standard dictionary knowledge base; a clinical event is acquired, and the clinical event is compared with a standard guide to confirm a belonging state of the clinical event according to event content of the clinical event; a mapping relationship is constructed by judging and combining according to a standard dictionary value range attribute of the event content and the belonging state of the clinical event; and knowledge graph is constructed by adopting different redundancy strategies based on different mapping relationships. The application avoids selection during selection of the regular expression and NLP on the matter extraction, adopts different redundancy strategies for all different mapping relationships to construct the knowledge graph, and can realize unification of the medical knowledge structure and the database structure.

A system and methods are provided for locating and retrieving sensitive clinical data. The Dynamic Clinical Data Exchange Platform of the inventive System serves as a trusted proxy for the Requestor Device with the Source Device. Upon receiving a data request from the Requestor Device, the inventive Platform vets the Requestor Device, uses metadata to identify and locate the source storing the required clinical events for retrieval, opens a secure connection at an Endpoint of the identified Source Device, requests a security token from the Source Device, assembles Standards-based API calls, and passes an executable bundle containing the security token and the API call to the Requestor Device. The Requestor Device executes the API call, using the security token to directly retrieve clinical data from the Source Device without the data passing through the inventive Platform of the inventive System.

The application discloses a kind of clinical time series event imbalance prediction method, system and storage medium. Method is first based on time distance to the sinusoidal position coding of irregularly collected dynamic clinical characteristics;Second, design outer loop framework repeatedly extracts balanced training subset to utilize negative sample diversity;Further, perform inner loop training on each subset, and the feature selection of attention mechanism is fused, and the sample reweighting of focal loss and the decision tree splitting strategy of weighted gini impurity. Finally, integrate multiple decision trees and make group decision by weighted average. While maintaining the model interpretability, the application significantly improves the prediction performance of rare clinical events, and can be effectively integrated into electronic health record systems to provide support for clinical early warning.

The invention discloses a real world data-based personalized follow-up visit strategy generation and optimization method for patients with type 2 diabetes mellitus, which comprises the following steps of: calculating a patient state transition probability by utilizing a Markov decision process model through integrating demographic characteristics, a baseline health state, a laboratory examination result and life style data; and further, an individual follow-up visit frequency and a follow-up visit mode are dynamically generated. When a patient's clinical event or health status changes, the method may adjust the follow-up plan in real time. Compared with an existing standardized follow-up visit method, the method has remarkable advantages in the aspects of reducing the occurrence rate of complications, prolonging the health life and reducing the medical cost, is particularly suitable for basic medical institutions and resource-limited environments, and has universality and popularization value.