44 results about "Patient behavior" patented technology

The invention provides a big-data-based Alzheimer's disease old-age care platform management method and system, and relates to the technical field of old-age care platform management.The method comprises the steps that patient behavior data information is received, missing data points are deduced according to pre-stored patient behavior file historical behavior pattern data and patient behavior data information, and the missing data points are sent to a server; by evaluating the reliability degree of the event chain and comparing the event chain with a dynamically generated reliability evaluation threshold value, when a comparison result reaches an early warning standard, early warning information with a reliability quantitative index is generated, and the problem that an existing platform is poor in reliability under a non-ideal operation condition is effectively solved. The problems of reliable transmission and accurate interpretation of key information are solved, and early warning failure caused by data deviation or missing is avoided, so that the nursing quality and safety of the Alzheimer's disease patient are remarkably improved, and the optimal time for early intervention and intervention is provided for nursing personnel.

The invention discloses a dementia intervention scheme recommendation method and system based on a knowledge graph, and relates to the technical field of intelligent medical treatment and artificial intelligence. And constructing a dementia intervention knowledge graph containing patients, symptoms, intervention measures and environmental elements. And performing intelligent semantic reasoning on the short-term state, the long-term behavior mode and the nursing environment of the patient by fusing multi-level reasoning and situational reasoning, generating a candidate intervention scheme matched with the current state of the patient, and outputting a personalized recommendation result. In the intervention implementation process, the knowledge graph association relation is dynamically updated based on patient behavior feedback and symptom changes, and continuous optimization and self-adaptive adjustment of an intervention scheme are achieved. According to the method, the individuation level, long-term adaptability and safety of dementia intervention recommendation are improved, and the method is suitable for clinical and long-term nursing scenes.

The invention provides an intelligent cognitive movement rehabilitation task generation method based on knowledge graph dynamic adaptation, and the method comprises the steps: collecting the behavior response data of a patient in real time through a multi-modal sensor array, and inputting a pre-trained state evaluation neural network model after preprocessing; outputting a four-dimensional ability state vector representing cognitive load, motion coordination, attention and fatigue degree, taking the vector as a dynamic query condition, starting multi-hop semantic reasoning in the cognitive motion rehabilitation knowledge graph, screening a candidate task set matched with the current state of a patient and associated with a rehabilitation target, and performing task selection on the candidate task set; according to the matching relation between the capability state and the task difficulty, execution parameters such as task presentation duration and action amplitude are dynamically adjusted, task sequence sorting is optimized based on the path distance, and finally generated personalized rehabilitation tasks are presented in a three-dimensional virtual scene mode through an interaction terminal. A closed-loop control process of real-time data acquisition, state evaluation, task generation and execution is formed, and dynamic personalized adaptation of the rehabilitation training process is realized.

The application relates to the field of data processing, and particularly provides a monitoring source patient signal data analysis method and system. The method comprises the following steps: obtaining target patient behavior signals matched with to-be-detected behavior signals, wherein the target patient behavior signals cover behavior signals of different categories; obtaining matching degrees between the behavior signals of different categories covered by the target patient behavior signals and the to-be-detected behavior signals based on influence factors of the behavior signals of different categories; screening selected category behavior signals from the behavior signals of different categories based on the matching degrees between the behavior signals of different categories and the to-be-detected behavior signals; and performing highlight display on signal segments in the selected category behavior signals matched with the to-be-detected behavior signals. The application can simplify the highlight display signals, highlight the signals with more analysis significance, and help more accurate recognition of signal behavior patterns.

A patient support apparatus for inferring a patient's future behavior tracks data related to patient bed exits from the patient support apparatus. A controller may be in communication with the patient support apparatus. The controller may include a processor and a non-transitory memory device. The memory device may include instructions that, when executed by the processor, acquire data related to patient bed exits.

The invention relates to a chronic disease staged behavior change intelligent guiding method, and belongs to the technical field of chronic disease health management. The method comprises the steps of capturing behavior, psychological, environmental and physiological data to construct a four-dimensional data set, filling missing values by adopting similar patient behavior mode interpolation, filtering abnormal values by adopting a decision tree branch pruning rule, and generating a patient health portrait vector; constructing a training set based on longitudinal behavior data, screening key dimensions through feature importance, and optimizing a behavior change dynamic decision tree in combination with an incremental dynamic iterative training mechanism; inputting the four-dimensional data set into a decision tree, generating a personalized obstacle analysis report and predicting a future stage retrograde risk; and calling a corresponding strategy library, and dynamically adjusting the guide strategy by taking the task completion rate and the index improvement amplitude as feedback signals. Accurate judgment of the chronic disease behavior change stage is achieved, the problems of single data dimension and strategy homogenization in traditional intervention are solved, and the patient behavior change compliance and the long-term management effect are improved.

The invention relates to the technical field of medical services, in particular to a statistical database-based disease cause formation intelligent query analysis system, which comprises a case processing module, a case analysis module and a disease cause query module. The case processing module is used for collecting historical case information and extracting a plurality of classification topics according to the historical case information, each classification topic comprises but is not limited to disease causes and influence factors, a plurality of analysis nodes are divided according to the acquired classification topics and the corresponding disease causes and influence factors, and the analysis nodes are used for analyzing the disease causes and influence factors; determining a corresponding relation of the historical case information among the analysis nodes, and constructing the historical case information into an analysis network according to pathogenesis and influence factors; the case analysis module is used for analyzing the historical case information according to the obtained analysis network, obtaining behavior information corresponding to the patient, setting behavior nodes corresponding to the behavior information, and setting a plurality of behavior tags according to different corresponding behavior nodes of patient behaviors; and the diagnosis efficiency and accuracy are improved.

Devices, systems, and techniques for analyzing video information to objectively identify patient behavior are disclosed. A system may analyze obtained video information of patient motion during a period of time to track one or more anatomical regions through a plurality of frames of the video information and calculate one or more movement parameters of the one or more anatomical regions. The system may also compare the one or more movement parameters to respective criteria for each of a plurality of predetermined patient behaviors and identify the patient behaviors that occurred during the period of time. In some examples, a device may control therapy delivery according to the identified patient behaviors and / or sensed parameters previously calibrated based on the identified patient behaviors.

The invention relates to the technical field of image monitoring, in particular to an elderly patient behavior image monitoring and falling risk analysis system and method, and the method comprises the steps: a front-end collection module collects a time sequence image of an activity area of an elderly patient; the posture detection module analyzes and extracts three-dimensional posture information of the elderly patient based on a differential geometry theory, and comprises a key point detection unit, a manifold mapping unit and a constraint optimization unit; the gait analysis module processes attitude parameters through a parameter extraction unit, a time sequence track unit and a curvature analysis unit; the risk assessment module calculates a fall risk level based on the gait feature data; according to the invention, an APMK-HCW algorithm is innovatively applied to realize high-precision 3D attitude estimation under a monocular camera, geodesic curvature analysis is introduced to quantify gait stability, and a personalized baseline assessment and adaptive optimization mechanism is adopted to realize early precise early warning of the falling risk of the elderly patient.

Disclosed herein is a healthcare management system and method utilizing machine learning based predictive analytics to improve patient adherence rates for chronic care management (e.g., diabetes). An example system may include a computing device configured to establish a customer analytical record to synthetize over a plurality of selected attributes to form a patient centric view of patient behaviors, attitude, characteristics based upon data related to chronic disease state management and social determinants of health, consumer experience to determine, using a predictive artificial intelligence model, a patient's predictive adherence for next 1-3 months, and determine tailored intervention plans to engage patients for continuing adherence.

Automating patient care by training an artificial intelligence using a data structure organized in a patient care matrix comprising levels of domain knowledge. The care matrix data structure is defined and populated with training data. The artificial intelligence includes a plurality of artificial intelligence nodes each trained using aspects of the care matrix data structure such that an entity AI node instance is trained using a data set comprising subset of training data utilized in training child entities node instances of the entity AI node being trained. A long form description of a patients behavior or disorder is obtained and a natural language processor is employed to generate input phrases to be supplied to the AI for analysis. The AI analyzes the obtained phrases using a plurality of the trained AI node instances to automatically generate a patient treatment profile including one or more therapies and associated measures.

The invention relates to the technical field of large models, in particular to a chronic disease management method, system and device and a storage medium. The method comprises the steps of firstly analyzing user query content, extracting query intention features and generating medical suggestions in combination with personalized parameters; collecting medical equipment data in real time, analyzing health state characteristics in combination with medical suggestion information, and outputting a health monitoring result; according to the health monitoring result and a preset medical scheme, task type features and patient behavior features are fully considered, intervention execution features are determined in a progressive task decomposition mode, and then a standardized intervention instruction is generated; acquiring related historical data from the memory system based on the intervention instruction for matching, and finally integrating a matching result and real-time data to update the health record of the patient; and an execution plan better conforming to the actual condition of the patient is made through a task decomposition mode, so that the pertinence of the medical scheme is improved.

The application relates to the technical field of internet medical treatment and artificial intelligence, and discloses an internet hospital whole-process intelligent diagnosis and treatment service management system based on artificial intelligence. The method collects multi-source digital phenotype data through a double-granularity aggregation strategy, generates continuous representation of patient behavior state by using a time sequence representation learning model based on a mask autoencoder, separates a disease activity score and a compliance probability score through a causally decoupled double-branch network, calculates a crisis emergency degree score by using a mental and psychological crisis early warning network and triggers a fuse mechanism, realizes post-diagnosis management path switching, emergency resource matching and crisis handover information package generation, and solves the problems of insufficient time resolution, data loss vulnerability, cause coupling confusion and response channel loss in mental and psychological department post-diagnosis acute crisis detection and emergency response.

Embodiments of the present disclosure may include a method of mapping patient data and representing data from electronic health records of an individual through a pictorial representation of their human body including receiving, over at least one communication network from each of a plurality of user computing devices operated by each of a plurality of users, electronic health records (EHR) respectively representing information from the plurality of user's electronic medical records, procured from the user's health care provider or the user's electronic health records (EHR) partners. Embodiments may also include providing, a decentralized and distributed patient facing method of communicating and providing robust critical formulation of health-related clinical data of a patient using artificial intelligence (AI) and natural language processing (NLP) to engage a patient that encourages a change in a patient's behavior to improve the patient's overall health.

Disclosed herein is a healthcare management system and method utilizing machine learning based predictive analytics to improve patient adherence rates for chronic care management (e.g., diabetes). An example system may include a computing device configured to establish a customer analytical record to synthetize over a plurality of selected attributes to form a patient centric view of patient behaviors, attitude, characteristics based upon data related to chronic disease state management and social determinants of health, consumer experience to determine, using a predictive artificial intelligence model, a patient's predictive adherence for next 1-3 months, and determine tailored intervention plans to engage patients for continuing adherence.

The invention relates to the technical field of medical monitoring, in particular to a multi-source data integration grading early warning method and system for hand surgery vascular crisis. The invention discloses a multi-source data integration grading early warning method for hand surgery vascular crisis. The method comprises the following steps: S1, synchronously collecting tissue oxygen saturation, an original and uninjured side temperature difference value, behavioral environment data and clinical auxiliary data of a sentinel area through a multi-source sensor; s2, establishing a behavior recognition algorithm model, recognizing interference behaviors of the patient in real time based on the collected behavior environment data, and quantifying the interference behaviors to obtain influence data; and S3, based on the influence data, carrying out dynamic correction on the original and uninjured side temperature difference value to obtain a corrected and uninjured side temperature difference value, and carrying out dynamic correction on the tissue oxygen saturation to obtain the corrected tissue oxygen saturation. Through multi-source data fusion and intelligent correction, interference of patient behaviors and environmental factors on monitoring data can be effectively recognized and filtered out.

In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products for identifying a value of a heart rate variability metric that indicates a variation in a heart waveform of a patient; providing values for a collection of metrics to a computational model, the values for the collection of metrics including the value for the heart rate variability metric and receiving, from the computational model as a result of having provided the values for the collection of metrics to the computational model, an indication of mental state of the patient.

The utility model belongs to the technical field of rehabilitation nursing beds, and particularly relates to a rehabilitation nursing bed for nursing, which comprises a rehabilitation nursing bed and two bedside folding guardrails, support components are arranged on two sides of the rehabilitation nursing bed, each support component comprises an L-shaped mounting plate and a guardrail support bottom plate, a plurality of fixing bolts are arranged on the two L-shaped mounting plates, the fixing bolts are in threaded connection to the inner side of the rehabilitation nursing bed, and the two guardrail supporting bottom plates make contact with one sides of the corresponding L-shaped mounting plates; the position states of the bedside folding guardrail and the guardrail supporting bottom plate are monitored and sensed through the monitoring mechanism, and an abnormal pressure signal borne by the bedside folding guardrail is transmitted to a nurse station, so that a nurse is ensured to know the improper extrusion condition of a patient on the bedside folding guardrail in time, the behavior of the patient is corrected, and the safety of the patient is improved. By means of the design, excessive lateral pressure is prevented from being continuously applied to the bedside folding guardrail, and the structural stability and durability of the bedside folding guardrail are greatly improved.

The invention relates to an intelligent collection method and system for clinical test data, and relates to the field of data collection, and the method comprises the steps: 100, collecting physical sign parameters of a patient based on preset physiological features; 101, constructing a physical sign fluctuation curve in response to the physical sign parameters; step 102, identifying a curve slope from the physical sign fluctuation curve; step 103, determining a stable time period and a fluctuation time period in combination with the sign fluctuation curve and the curve slope; 104, generating and displaying a data acquisition suggestion according to the stable time period, and calling the position of the patient according to the fluctuation time period; step 105, calling a patient image based on the patient position; 106, identifying patient behaviors from the patient image, and determining a fluctuation coefficient based on the patient behaviors and a curve slope; and step 107, generating and displaying a patient activity suggestion in response to the fluctuation coefficient. The method and the device have the effects of improving the accuracy of clinical test data acquisition and reducing the condition of data fluctuation during data acquisition.

This disclosure provides a patient behavior alert method based on federated learning and multimodal temporal anomaly detection, applicable to the field of healthcare technology. The method includes constructing a drug knowledge base and extracting patient multimodal behavioral features; analyzing the matching degree and correlation between medication requirements and multimodal behavioral features, identifying historical behavioral deviations, and establishing personalized behavioral benchmarks accordingly; training a multimodal temporal anomaly detection model; dynamically adjusting subsequent behavioral judgment benchmarks based on the deviation between the patient's most recent medication information and the personalized behavioral benchmarks; inputting current multimodal behavioral features into the model, combining the adjusted benchmarks to identify real-time behavioral deviations and generate intervention criteria; and generating personalized intervention strategies based on the intervention criteria and the patient's historical feedback and pushing them to the patient. This approach addresses the problems of personalization, accuracy, and interpretability in existing solutions, achieving intelligent, personalized, and adaptive management of patient behavior intervention alerts.

The application discloses a virtual standard patient construction method based on a neural symbol architecture and belongs to the technical field of digital mental health education; the method comprises the following steps: step one, constructing a training scene logical space; step two, constructing a semantic observation layer; step three, constructing a logical thinking layer; step four, constructing a dependent action layer; and step five, constructing an interpretable feedback layer; the method is used to set the training scene logical space as a basis, predict the probability true value of a doctor-patient behavior atomic proposition through the semantic observation layer, deduce the probability of a patient's psychological state change through symbol logic thinking, drive a probability state machine to execute dependent action and generate feedback, and construct a virtual patient; the method can solve the problems of rigidity of an existing rule-based virtual standard patient and lack of doctor-patient behavior dependence of a virtual standard patient based on a large model, realize more real virtual patient construction, and is convenient for teaching use.

Methods and systems to train and use an ensemble of artificial intelligence / machine learning (AI / ML) models to extract information from social determinants of health (SDoH), including training each of multiple dimensionality reduction models to reduce dimensionality of socio-demographic variables associated with a respective one of multiple SDoH categories, training a predictive model to predict a patient behavior for a geographic region (e.g., risk of non-adherence to treatment regimens) based on dimensionally reduced SDoH (alone or in combination with selected socio-demographic variables and / or other data), training a patient classification model to classify patients based on prescription transactions, and / or training a regional similarity model to determine a measure of similarity between geographic regions based on SDoH and / or dimensionally reduced SDoH. Also disclosed are techniques to visually represent outputs of the models on a user-interactive display.

The invention discloses a rehabilitation action recognition model construction method and system based on a mixed loss function, and relates to the field of patient rehabilitation action recognition. The method comprises the following steps: acquiring a rehabilitation training video of a patient, joint movement data of the patient and physiological data of the patient; the rehabilitation training video of the patient, the joint movement data of the patient and the physiological data of the patient are preprocessed; performing behavior type labeling on the preprocessed rehabilitation training video of the patient, the joint movement data of the patient and the physiological data of the patient; constructing a sample set according to a sample set optimization method; dividing the sample set into a training set, a test set and a verification set; training a patient behavior training model in combination with the model classification loss calculated by the cross entropy loss function and the inter-sample loss calculated by the triple loss function; and predicting the behavior type of the rehabilitation action of the patient through the patient behavior training model. According to the invention, the recognition precision and robustness of the rehabilitation action recognition model can be improved.

Embodiments of the present specification provide a patient monitoring method and system. The method comprises obtaining a perception dataset of a target area. The perception dataset is collected by a plurality of sensors installed in the target area, the plurality of sensors comprising at least one optical sensor and at least one radio frequency sensor, the target area corresponding to at least one target patient to be monitored. The method further comprises monitoring patient behavior based on the perception dataset to obtain behavior monitoring data and monitoring patient vital signs based on the perception dataset to obtain vital sign monitoring data. The method further comprises determining a target monitoring result of the at least one target patient based on the behavior monitoring data and the vital sign monitoring data.

There is provided an apparatus, system and method for monitoring a behavior of a patient in an environment. Behavioral recommendations for the patient are obtained by applying input data comprising clinical conditions of the patient and contextual data stored in data sources related to health and medicine, to a tuned large language model, LLM. The behavioral recommendations are provided to a user through a user interface. Sensor data (SD) are obtained from a plurality of sensors (C1-C5) placed in the environment. A global adherence score (GSC) of the patient to the behavioral recommendations (BRC) is determined based on an analysis of the sensor data. The global adherence score (GSC) is evaluated based on reference thresholds and one or more historic levels of the patient and a result of evaluation (RS) is reported to the user.

The invention relates to the technical field of mental health monitoring, in particular to a mental health early warning system based on patient behavior trajectory analysis, which comprises a data acquisition unit, a behavior analysis unit, a fusion analysis unit and an early warning unit, the data acquisition unit is used for acquiring position data and sleep data of a user in each time period in a historical time period; the behavior analysis unit is used for determining the behavior complexity and the space complexity of the user in each time period, and determining a behavior specificity index of each time period based on the behavior complexity and the space complexity of each time period; the fusion analysis unit is used for determining the change consistency of behaviors and sleep of each time period based on the behavior specificity index of each time period and the sleep data of each time period in the historical time period; and the early warning unit is used for outputting early warning information.

The invention discloses a T2DM-NAFLD personalized lifestyle management system based on digital twinning, and particularly relates to the technical field of chronic disease management.The T2DM-NAFLD personalized lifestyle management system comprises the steps that behavior and psychological data of a patient are collected and subjected to time sequence processing, and a digital twinning model fusing a physiological mechanism and a data-driven network is constructed; dynamically calculating a behavior compliance index based on a metabolic stability parameter and a data change trend output by the digital twinborn model; selecting a matched incentive strategy from a predefined strategy library according to the index, and adjusting exercise intensity or nutrition distribution parameters in the digital twin model according to the matched incentive strategy; generating personalized lifestyle suggestions by using the adjusted digital twinborn model and pushing the personalized lifestyle suggestions through a visual interface; closed-loop linkage of behavior intervention and metabolism simulation is achieved, and the problems that in existing health management, intervention measures are disjointed with the real-time metabolism state and psychological motivation of the patient, and consequently compliance is low, and the long-term effect is poor are solved.

The application provides a cancer patient intelligent old-age care decision-making method based on dynamic psychological evaluation, and belongs to the technical field of intelligent decision-making, and comprises the following steps: obtaining direct evaluation replies of a patient evaluation block and analyzing psychological words, obtaining corresponding contradictory intentions through single reply and contradictory analysis of the evaluation block level; then, global contradictory analysis is performed on the evaluation block core word vector to determine a contradictory resolution probability; then, a first resolution direction is determined in combination with a patient behavior and a psychological dependence image, a second resolution direction is determined according to a contradictory intention connection relationship, a modified reply is generated after the resolution direction is fused and the resolution probability is adjusted; finally, a care sub-scheme is generated according to the modified reply, and the comprehensive old-age care scheme is updated and integrated according to an evaluation period, so that the fitting degree and reliability of the care scheme and the actual state of the patient are improved.

A system is provided.SOLUTION: A system, comprising: camera means for monitoring behavior of a dementia patient in real time; generation and AI means for analyzing a video from a monitoring camera; audio output means for speaking deterrence to the patient when an abnormal behavior is detected; and communication means for transmitting a notification to a family member when an abnormal behavior is detected; and conversation support means for performing a daily conversation with the patient using the generated AI.SELECTED DRAWING: Figure 1

The invention discloses a store medicine supply method and device based on patient behavior analysis and a storage medium, and the method comprises the steps: obtaining the medicine purchasing behavior data of a patient in each historical time period, and determining the medicine transfer number between stores in adjacent historical time periods; constructing a first graph structure by taking each store in each historical time period as a first node and taking a medicine transfer trend as a first edge; inputting the first graph structure into a graph neural network model, and performing iterative updating on the first graph structure by using the graph neural network model to generate a second graph structure; based on each second node feature and each second edge feature of the second graph structure, determining a plurality of third node features and a plurality of third edge features of the current time period; and inputting the third node features corresponding to each store in the current time period into the first prediction model, inputting a plurality of third edge features corresponding to each store into the second prediction model, and predicting to obtain a target drug supply quantity corresponding to each store in the current time period.