12 results about "Baseline values" patented technology

The invention belongs to the technical field of data processing. According to the interpretable financial risk attribution abstract generation method and system, multiple risk driving factors related to the risk probability are obtained, and each risk driving factor corresponds to one contribution degree for the risk probability; generating risk assessment summary text data according to the comparison between the risk probability and the risk baseline value; extracting corresponding risk-driven factor text description from a knowledge base according to the risk-driven factors; risk judgment text data formed by combining a plurality of risk judgment bases are generated according to the sequence of the contribution degrees from large to small, and each risk judgment base comprises risk driving factor text description, the numerical value of the risk driving factor and the corresponding contribution degree; combining the risk assessment summary text data with the risk judgment text data to obtain a financial risk attribution abstract; the response time is greatly shortened, and the risk intervention opportunity is prevented from being missed.

An example system includes an implantable medical device configured to obtain measurement values of one or more patient metrics; and processing circuitry configured to: determine a baseline value for each of the respective one or more patient metrics based on measurement values of the one or more patient metrics over a first period of time; determine a short-term value for each of the one or more patient metrics based on measurement values of the one or more patient metrics over a second period of time, determine a difference between each of the short-term values and the respective baseline value for each of the one or more patient metrics; determine that a risk of an adverse event occurring in the patient is high in response to the determined difference meeting a respective adverse event risk threshold; and generate for output an adverse event high risk alert.

The invention discloses a risk early warning and health baseline analysis system based on language characteristic parameters, and relates to the technical field of language health assessment, clinical auxiliary diagnosis, artificial intelligence and medical health cross, the system comprises a parameter input module, a real-time calculation and display module, a visualization module and a data management module, the system is used for performing language ability evaluation by utilizing risk values dynamically generated from speech entropy, semantic density and syntactic complexity, and / or baseline values generated from global baselines, age and culture factors. According to the method, the voice entropy, the semantic density and the syntactic complexity are subjected to weighted fusion for the first time, the one-sidedness problem of single parameter evaluation is solved, and personalized baseline calibration is realized through age segmentation * culture factors; and a new technical enlightenment is provided for language competence evaluation.

This invention provides an early warning system for critical care nursing in internal medicine based on multi-parameter monitoring, belonging to the field of early warning system technology. It includes: a vital sign monitoring module for real-time collection of the patient's vital sign factors, taking the average value of the amplitude of each real-time vital sign factor as a benchmark reference value; a similarity early warning analysis module for establishing a mathematical model of the patient's self-monitoring, calculating the early warning similarity index corresponding to each real-time vital sign factor; calculating a reliability index by comparing the total short-term change value with the overall average change value of each real-time vital sign factor; and an early warning decision module for establishing two mechanisms to determine early warnings. This invention extracts various parameters from the patient's past multiple disease occurrence points and calculates the average value, and collects the median value of the disease occurrence point with the largest interval as a reference benchmark value, forming a unique benchmark reference value; thus, the abnormality judgment is entirely based on individual physical differences and historical response patterns, solving the problem of misjudgment due to uniform standards caused by physical differences.

Exemplary embodiments may provide adaptability in basal fraction values. Exemplary embodiments may also provide adaptability in total daily drug delivery (TDM). The adaptability provided by exemplary embodiments helps customize drug delivery to the needs of a user of a drug delivery device. Exemplary embodiments may adapt a user's basal rate based on the user's drug delivery history data. Additionally, exemplary embodiments may update the basal rate based on more recent trends that deviate from the drug delivery history data. The degree of adaptability provided by exemplary embodiments may be limited to not exceed upper and / or lower thresholds. The degree of adaptability may be adjusted by controlling the rate of adaptability to a sufficiently small increment each time the basal rate is updated.

This application provides a clinical method, system, device, and medium for detecting bowel and bladder movements. First, raw pulse rate time-series data of the patient is collected. The raw pulse rate time-series data undergoes quality verification and signal cleaning to obtain effective pulse rate time-series data. Based on the effective pulse rate time-series data, the mean pulse rate within the current detection window is calculated, and a pre-determined individualized resting pulse rate baseline value is obtained. The difference between the mean pulse rate within the current detection window and the individualized resting pulse rate baseline value is determined as the dynamic pulse rate offset. The dynamic pulse rate offset is judged using predefined bowel and bladder behavior detection rules, and the event confidence level for the current time period is output. The event confidence level is compared with a preset clinical decision threshold. If the event confidence level exceeds the clinical decision threshold, a graded early warning signal is generated and pushed to the clinical nursing system. The above scheme can achieve non-invasive detection of clinical bowel and bladder events.

A computing system for generating handicap-adjusted health scores processes multi-source health metric data collected from heterogeneous devices and activity modalities. The system normalizes and calibrates unstructured health data using schema-conformant transformation logic and device-specific correction parameters. User-specific baseline values are computed over configurable rolling windows and compared to cohort-level reference parameters derived from demographic and device-based population segmentation. Deviation values are corrected using demographic and device normalization models to generate structured adjustment vectors. The system applies context-aware scoring logic to compute normalized health scores that reflect individual performance patterns relative to statistically similar user cohorts. Scoring outputs are configured for competitive presentation via a user interface and may support leaderboard ranking, team-based scoring, or context-specific evaluations across diverse activity types.

The invention relates to the technical field of staff health monitoring, and particularly discloses an abnormality reminding method based on staff health monitoring data, comprising the following steps: step 1, constructing a staff personalized health datum line, including data acquisition and preprocessing, individual reference value calculation and datum line dynamic adjustment; step 2, performing anomaly identification of multi-dimensional correlation analysis, including index correlation modeling, multi-index fusion judgment and anomaly level judgment; step 3, implementing hierarchical reminding and dynamic response, including reminding strategy adaptation and a closed-loop tracking mechanism; and 4, carrying out model self-optimization, calculating a model performance index and updating a correlation coefficient. According to the invention, the fixed threshold value is replaced by the individual reference line, so that the problems of false alarm and missing alarm caused by individual difference are solved; the multi-index correlation analysis breaks through the limitation of single-index judgment, and the composite health risk can be identified.

This application belongs to the field of intelligent analysis technology for blood collection data, and provides a method and system for predicting daily blood collection volume based on residual learning and fusion. This application standardizes multi-source blood collection data and integrates features from time series statistics, meteorology, and calendar to construct a feature matrix; it uses K-fold cross-validation to train an XGBoost model to generate baseline prediction results; it constructs a residual sequence and uses LSTM to complete residual time series learning and prediction; it corrects residual bias through adaptive dynamic amplitude constraints and integrates baseline values ​​to output the final prediction result. This application supports variable prediction period length, configures differentiated rolling update strategies, and integrates the technical advantages of tree models and time series networks. It ensures the interpretability and nonlinear feature fitting ability of the daily blood collection volume prediction results while effectively suppressing prediction overshoot, providing a reliable decision-making basis for blood station blood collection planning and blood inventory scheduling.

Systems and methods of optimizing resources of a medical device system are disclosed, including analyzing physiological information of a patient generated over a particular period of time relative to a previous heart failure event, adjusting a baseline value of the patient from a long term baseline value to one of a shorter term baseline value or a static value in response to a detected or received trigger event, and outputting the adjusted baseline value. The static value is indicative of a baseline value at a previous time relative to the detected or received trigger event, determining a re-admission score for the patient based on the analyzed physiological information, and providing a control signal based on the re-admission score to control a mode or operation of the medical device system to optimize resources of the medical device system.

A graded anesthesia quality control method, including a server, media, and products, relates to the field of medical information technology. The method includes: determining the indicators to be managed and their baseline values ​​based on preset anesthesia quality control standards; periodically acquiring first, second, and third anesthesia data; extracting the first, second, and third actual values ​​of the indicators to be managed; determining the sentinel hospital test results, district-level quality control center test results, and municipal-level quality control center test results based on the baseline values, first, second, and third actual values ​​of the indicators to be managed; determining rectification plans for the sentinel hospital, district-level quality control center, and municipal-level quality control center; and generating a resource scheduling plan based on these rectification plans. Implementing this method aims to improve the quality of anesthesia services.