3 results about "Tuberculosis incidence" patented technology

The application provides a method for evaluating the risk of tuberculosis under the combined exposure of extreme weather and air pollution, comprising the steps of: obtaining meteorological data, air pollution data and tuberculosis incidence data of a target area within a target period; identifying extreme weather events based on the meteorological data, identifying air pollution events based on the air pollution data, and identifying combined exposure events based on the meteorological data and the air pollution data, wherein the combined exposure events are combinations of the extreme weather events and the air pollution events that occur within a time interval less than a preset threshold and are spatially co-located; based on the spatial co-location, constructing a regression model with the number of cases in the tuberculosis incidence data as the dependent variable and whether the combined exposure event occurs as the binary explanatory variable, and evaluating the influence of the combined exposure event on the risk of tuberculosis. The application realizes high-precision quantitative evaluation of the risk of tuberculosis under the combined exposure of extreme weather and air pollution, and provides a scientific basis for early warning and precise prevention and control.

The invention belongs to the technical field of medical information, and relates to a multi-scale tuberculosis morbidity prediction method and system.The system collects data through a data collecting and processing module to generate a spatio-temporal feature data set, and high-quality input is provided for subsequent model training; a space-time association graph structure between regions is constructed through a space-time association network construction module, and structured input is provided for a GCN-LSTM model; the GCN-LSTM model training module uses a graph convolutional neural network and a long short-term memory network to train multi-source spatio-temporal data, and is used for capturing spatial dependence between regions and a dynamic evolution trend of a time sequence; and the space-time prediction and result output module uses the trained GCN-LSTM model and the latest multi-source data to predict the tuberculosis morbidity of each region under different time scales in the future. According to the invention, the precision and real-time performance of tuberculosis morbidity prediction can be effectively improved, and technical support is provided for accurate prevention and control.

The invention discloses a multi-dimensional space-time prediction system and method based on a quantum fusion architecture, and belongs to the technical field of artificial intelligence and quantum computing crossing. According to the system, ten quantum heuristic models such as TFT-Net, WaveNet, ResNet, Attn-LSTM, GNN and QNN are creatively integrated, a PIMV-E quantum fusion algorithm is proposed, and high-precision space-time prediction in the fields of public health, environmental change and the like is realized through core technical means such as multi-dimensional feature engineering construction, adaptive weight temperature control adjustment and related redundancy elimination optimization. The system is provided with functional modules of time-point-by-time confidence band visualization, quantum performance thermodynamic diagram analysis, RESTfulAPI service and the like, and experimental verification shows that compared with a traditional method, the prediction precision is improved by 15%-25%, the trend capture capability reaches 92%, the anomaly detection sensitivity reaches 95%, and the average decision coefficient (R) is 0.89-0.92. The method can be widely applied to scenes such as tuberculosis incidence prediction, air pollution concentration early warning and chronic disease death risk assessment, and provides powerful technical support for decision making in related fields.