19 results about "Blood Indices" patented technology

The invention discloses a dental ulcer image recognition autoimmune disease blood index correlation analysis system, and relates to the technical field of medical informatics. Comprising a time sequence data acquisition module, a steady state baseline construction module, a cross-modal synchronous analysis module, a deviation degree calculation module, a disease risk judgment module and a risk early warning output module. The system constructs an individualized immune steady-state baseline by acquiring a dental ulcer image of a user and time sequence data of blood indexes related to autoimmunity; the image lesion dynamic evolution rate is used as a guide factor, time extrapolation is carried out on the blood indexes collected asynchronously, and synchronous predictive immune data are generated; by calculating the deviation degree of the prediction data and the steady state baseline, accurate and real-time judgment and early warning of the autoimmune disease risk are realized. According to the invention, the problem of evaluation delay caused by desynchrony of dental ulcer image and blood index acquisition time is effectively solved, and the timeliness and accuracy of health risk monitoring are improved.

The application discloses a pentosus pentosaceus and postbiotic compound thereof for tonifying qi, nourishing face and improving anemia, and belongs to the technical field of microbial fermentation. The application screens a pentosus pentosaceus, obtains the bacterial body and postbiotic by culture, and forms a compound of the postbiotic and extract of semen ziziphi spinozae. The compound exhibits a synergistic effect, specifically, compared with the iron deficiency model group, the movement and various blood indexes of rats are improved, and are close to the normal rats of the control group. The indexes of rats in the compound group are better than those of rats fed with probiotics, and rats fed with postbiotic or semen ziziphi spinozae alone, which indicates that the compound can promote the recovery of iron content and protein indexes in the blood of rats more quickly. The application has practical value for comprehensive utilization of the pentosus pentosaceus and postbiotic, and also has important value for tonifying qi, nourishing face and improving anemia.

The invention provides a papillary thyroid carcinoma neck lymph node metastasis risk prediction method and system based on blood indexes and TI-RADS grading, and relates to the technical field of medical data analysis. According to the method, an original data set is constructed by obtaining TI-RADS classification, the maximum diameter of nodules, the number of nodules, gender, age and conventional hematology indexes including apolipoprotein B and carcino-embryonic antigen of a patient, characteristic variables are screened by adopting LASSO regression, and an independent prediction risk factor model is established in combination with multi-factor Logistic regression. And further constructing a column graph model, carrying out performance verification through multiple statistical indexes, and deploying the model to a webpage calculator based on a shiyapp to realize convenient output of the individualized risk probability. According to the method, efficient and accurate prediction of the preoperative lymph node metastasis risk is realized, and reliable decision support can be provided for clinic.

The application discloses an oral ulcer image recognition autoimmune disease blood index correlation analysis system and relates to the technical field of medical informatics. The system comprises a time series data acquisition module, a steady-state baseline construction module, a cross-modal synchronous analysis module, a deviation calculation module, a disease risk determination module and a risk warning output module. The system acquires the time series data of the oral ulcer image and the autoimmune related blood index of the user, and constructs an individualized immune steady-state baseline. The dynamic evolution rate of the image lesion is used as a guide factor to time extrapolate the non-synchronous collected blood index, generate synchronous predictive immune data, calculate the deviation of the predictive data and the steady-state baseline, and realize accurate and real-time determination and early warning of the autoimmune disease risk. The application effectively solves the evaluation delay problem caused by the asynchronous collection of the oral ulcer image and the blood index, and improves the timeliness and accuracy of health risk monitoring.

The application discloses a diabetes thrombosis risk prediction method and system based on combined analysis of blood rheology characteristics and vessel wall state, relates to the technical field of medical data processing, and obtains a target blood vessel segment image sequence to extract endothelial contour node coordinates and node radial displacement, and converts and combines to generate a vessel wall state boundary tensor; collects blood indexes to calculate red blood cell rigidity aggregation yield stress and plasma viscoelasticity relaxation time, and maps to generate a blood rheology characteristic tensor along a cardiac cycle; the two tensor spaces are aligned, an instantaneous wall shear stress vector is calculated based on a fluid-solid coupling mechanism, an oscillatory shear index and a local blood flow stasis time proportion are extracted through time domain integration to construct a rheology-vessel wall combined feature map; the feature map is input into a graph convolutional neural network to extract thrombus precursor topological features, and a risk prediction level is output through classification mapping. The system is used for implementing the above method.

This invention relates to a deep learning-based system and method for predicting hematoma expansion in spontaneous intracerebral hemorrhage. The system includes a data acquisition module for acquiring the patient's baseline head CT image data, corresponding clinical information, and blood index data; a quantization feature calculation module for performing three-dimensional hematoma segmentation on the CT image data to obtain a three-dimensional hematoma mask; a multi-dimensional feature extraction module, including a three-dimensional morphological feature extraction sub-network and a temporal feature extraction sub-network; a feature fusion module for acquiring high-dimensional features; and a risk prediction module for outputting the risk probability of hematoma expansion based on the high-dimensional features and generating a corresponding visualized risk factor weight map. This system deeply integrates data-driven three-dimensional morphological depth features and temporal features with knowledge-driven surface regularity index and density variation coefficient quantization indicators, improving feature mining capabilities while ensuring sensitivity to key pathological morphologies, thus enhancing the robustness and accuracy of prediction.

The application discloses a secondary blood index dataset generation method and system based on feature dynamic screening, and the application collects basic information and basic blood indexes of research objects, and obtains effective samples through preprocessing; and the effective samples are divided into a non-chronic non-infectious disease control group and a target disease group, and population statistical characteristic difference analysis is performed; secondary blood indexes are calculated according to the basic blood indexes, and population statistical characteristics after screening are integrated to generate an enhanced dataset; the enhanced dataset is divided into a training set and a test set according to disease state stratified sampling, continuous type indexes of the training set and the test set are synchronized and standardized, then an adaptive elastic network based on stability selection is used to screen an optimized feature set with non-zero coefficients, and finally, feature synchronization filtering is performed to integrate and form a final dataset. The application can solve the problems of low quality of an existing blood multidimensional index dataset, non-uniform processing flow and feature redundancy leading to difficulty in model selection.

The invention relates to the technical field of livestock disease prevention and control early warning, and discloses a dairy cow ketosis prevention and control monitoring early warning method and system based on a perinatal period blood index, and the method comprises the steps: collecting a perinatal period dairy cow blood sample, and obtaining a metabolite feature set; obtaining health state information of the dairy cow; then obtaining a health state mark data set; outputting a ketosis prediction result of the currently detected dairy cow through the ketosis prediction model; the health change trend of the dairy cow is obtained, different individual intervention strategies are planned, the individual intervention strategies are accurately matched with the current health state stage of the dairy cow, and the optimal intervention scheme is obtained. According to the application, prospective, dynamic and precise prevention and control of ketosis can be realized, so that nutrition regulation and control are precisely matched with individual metabolic response, and the prospective, individualized and economical efficiency of prevention and control of perinatal metabolic diseases is remarkably improved.

Disclosed are methods, materials and devices for approximation of blood volume in a fluid, such as in a biological fluid collected during a surgical procedure. The method and devices may include the use of an RBC flocculant, for example polyDADMAC, and an approximate blood hematocrit from the type of animal blood being evaluated, as well as a calculated RBC packing ratio corresponding to the collection device being used. Also provided is a Blood Indicator Panel (BIP), comprising a series of markings calculated from an observed red blood settlement volume, the average animal blood hematocrit, and a calculated RBC packing ratio “η” value for the collection device. A collection device with a BIP is disclosed. Pediatric (about 200 ml or 250 ml size container), adult human (about 1,000 ml-1,500 ml) and veterinary (about 500 ml-2,500 ml) collection containers are also disclosed, that include a RBC flocculant, for use in approximating blood volume in a fluid.

Techniques for determining stroke risk are provided. In some embodiments, the techniques may involve causing, using one or more light sources disposed on a headset worn by a user, light to be emitted into a head of the user, obtaining, using one or more light detectors disposed on the headset, information indicative of light reflected from one more structures within the head of the user, wherein at least a portion of the obtained information is obtained during a time period of hypercapnic stimulation, based on the obtained information, determining a representation of one or more cerebral blood metrics, providing the representation of the one or more cerebral blood metrics as input to a computational model, and determining a stroke risk score based on output of the computational model.

The utility model relates to the technical field of kits, and discloses a kit for detecting blood indexes, which comprises a blood index kit shell, the inner side of the blood index kit shell is fixedly connected with a mounting plate, and the top end of the mounting plate is provided with a mounting hole. The inner side of the blood index kit shell is fixedly connected with a limiting assembly, the outer side of the limiting assembly is fixedly connected with a moving plate, the inner side of the moving plate is movably connected with a blood detection reagent tube, the outer side of the blood detection reagent tube is in threaded connection with a connecting sleeve, and the inner side of a mounting plate is rotationally connected with a rotating assembly. The outer side of the rotating assembly is fixedly connected with a connecting rope with the other end fixedly connected with the outer side of the moving plate. The kit for detecting the blood indexes has the advantages that the taking area of reagents is increased, the reagents can be conveniently taken out from the inner side of the blood detection kit, and the reagents are effectively prevented from being separated.

The application discloses a Chinese crowd PhenoAge prediction model and a construction method thereof. The method comprises the following steps: acquiring a physical examination data set (B1) of at least 50,000 Chinese adults, wherein the physical examination data comprises gender, chronological age and nine blood indexes; pre-processing the physical examination data (C1); calculating the PhenoAge label value of each sample (D1); dividing the samples into a male subgroup (F1) and a female subgroup (G1) according to gender, as shown in elements E1, F1 and G1 in FIG. 1 and FIG. 2; training a male model (H1) and a female model (I1) respectively by using a machine learning algorithm (S3), to obtain a prediction model (T3); and evaluating the model performance (Y3) by using an independent verification set (U3). The application also provides a PA-CRP variant model (G5), and a construction process thereof is shown in FIG. 5, which is suitable for a physical examination scene (H5) in which C-reactive protein is unavailable. The application firstly constructs a PhenoAge prediction model (K1) based on large-scale Chinese crowd physical examination data, solves the crowd specificity deviation problem of the original PhenoAge model in the application of Chinese crowds, and provides a precise tool for individual aging assessment, chronic disease risk prediction and lifestyle intervention effect quantification.

The invention discloses a blood analysis device and method, and the method comprises a body temperature collection step, an information input step, a leukocyte index calculation step, and a venous blood glucose concentration calculation step. The function of analyzing various blood indexes such as the leukocyte index and the venous blood glucose concentration in the blood of the to-be-detected person can be completed by utilizing the multiple body temperature data and the information data of the to-be-detected person, the non-invasive blood analysis function is achieved, the blood detection process is effectively simplified, and the consumed time is short.

The invention discloses a colorectal cancer preoperative prognosis prediction method and device, and the method comprises the steps: calculating a systematic inflammation index and a body composition index of a target based on obtained object preoperative baseline data, the baseline data comprising basic clinical data, blood indexes and abdominal CT images; carrying out importance evaluation on the target systemic inflammation index, the body composition index and the basic clinical data, carrying out dimensionality reduction and regularization processing on the evaluated indexes, and screening to obtain a target index; and constructing a comprehensive prognosis prediction model based on the target index, and outputting a target risk score through the comprehensive prognosis prediction model so as to carry out preoperative prognosis prediction. According to the application, the scientificity, accuracy and intelligent level of preoperative risk prediction of the colorectal cancer patient are improved.

The invention discloses a preparation method and application of an aquatic rahnella oral microcapsule sustained-release vaccine for fish, and relates to the field of fishery biological medicines. Sodium alginate and liquid paraffin which are two kinds of insoluble liquid are utilized, a stable emulsion is formed through a high-stirring-speed emulsifier, then the sodium alginate and calcium ions are physically cross-linked to be fixed, then a layer of chitosan coating is wrapped, and the rahnella aquatilis oral micro-capsule sustained-release vaccine is prepared, and the average particle size is 1-5 microns. The coating rate of Rahnella aquatica is measured by using a spectrophotometer after the Rahnella aquatica is subjected to decapsulation with decapsulation liquid, and the coating rate of thalli is 36.6%; the results of a zebra fish challenge experiment show that the protection rate of the vaccine is 92%, and the safety of the vaccine is 100%. In order to further clarify the efficacy of the vaccine, the detection of oral vaccine fish blood indexes and immune related genes such as TLR5, TNFa and uPAR has obvious up-regulated expression, compared with a non-immune group, the up-regulated expression in liver, head and kidney and muscle tissues is higher, and a related basis is provided for elaborating the pathogen and host PAMPs-PRRs process. The results show that the oral micro-capsule sustained-release vaccine has a good disease-resistant immune effect, and a foundation is laid and a thought is provided for development and application of fish oral vaccines. Therefore, the invention develops a novel sodium alginate microsphere oral sustained-release vaccine aiming at rahnella aquatica, and provides a new strategy for solving the problems of disease treatment and drug resistance of rahnella aquatica in aquaculture.

Techniques for determining stroke risk are provided. In some embodiments, the techniques may involve causing, using one or more light sources disposed on a headset worn by a user, light to be emitted into a head of the user, obtaining, using one or more light detectors disposed on the headset, information indicative of light reflected from one more structures within the head of the user, wherein at least a portion of the obtained information is obtained during a time period of hypercapnic stimulation, based on the obtained information, determining a representation of one or more cerebral blood metrics, providing the representation of the one or more cerebral blood metrics as input to a computational model, and determining a stroke risk score based on output of the computational model.

The invention provides a blood routine data analysis method, device and system and a storage medium, and relates to the technical field of digital twinning, and the blood routine data analysis method comprises the steps: constructing a historical blood routine data set of a to-be-tested target person; constructing a digital twinborn model corresponding to the target person to be tested; acquiring current actually measured blood routine data; and evaluating the current actually measured blood routine data based on the digital twinborn model to obtain an evaluation result. According to the invention, the health status of the patient can be evaluated and monitored in a highly personalized and dynamic manner. A historical data set containing blood index data of a patient in different health states is constructed, a digital twinborn model is created by using the data, and real-time blood routine data of the patient is accurately evaluated. The method not only improves the efficiency and accuracy of data processing, but also reduces the possibility of personal errors, so that doctors can make diagnosis decisions based on more comprehensive and accurate data.

The invention discloses a colorectal cancer prognosis prediction device based on machine learning and multi-center blood indexes, and the device comprises a collection module which is used for collecting a peripheral blood sample of a current patient, and obtaining input features from the peripheral blood sample; the screening module is used for eliminating redundant features in the input features through Spearman correlation coefficient analysis, screening out core features and constructing a prediction model according to the core features; the training verification module is used for carrying out training and cross verification on the prediction model, outputting the individual survival probability and risk layering result of the patient, and providing a clinical interpretable result through a Shapley addition interpretation SHAP and a local interpretable model irrelevant interpretation LIME algorithm; the method can remarkably improve the prediction precision and the clinical decision adoption rate, facilitates a clinician to understand a prediction mechanism, improves the clinical availability, is low in cost, is non-invasive, is easy to popularize, is high in prediction performance, and meets the clinical use requirements.

The invention discloses a prognosis model for predicting the curative effect of treating a patient with non-resectable hepatocellular carcinoma by combining transcatheter arterial chemoembolism with truditinib and revatinib. The research finds that four indexes of AFP, ALP, DBIL and NLR are all independent prognosis factors of a uHCC patient which is treated by a TACE (triplex angiotensin converting enzyme) combined Czodimab and lenvatinib triplex therapy. By constructing the AADN scoring model, the prognosis of the patient can be comprehensively evaluated. The AADN score has the advantages that a baseline index before treatment is easy to obtain; the treatment response is directly related; the score is dynamic and can be adjusted according to index changes in the treatment process. According to the AADN scoring model, blood indexes (AFP, ALP, DBIL and NLR) with low cost and high accessibility are adopted, the prognosis of the uHCC patient can be accurately layered, and a practical tool is provided for formulating an individualized scheme for treatment by combining TACE with the Czodimab and the lenvatinib.