93 results about "Mortality rate" patented technology

The present disclosure describes techniques for generating a sepsis mortality prediction model. The sepsis mortality prediction model can predict tire likelihood of sepsis mortality for a subject. The sepsis mortality prediction model can be generated by using feature selection to select a model subset of genetic marker(s) from training data. Candidate sepsis mortality prediction models can be trained using the model subset. The sepsis mortality prediction model can be selected from the candidate prediction models based on determining a performance metric associated with each candidate prediction using a test subset of the training data.

The invention discloses a septicopyemia death risk prediction method based on artificial intelligence, and the method comprises the following steps: data collection and preprocessing: collecting clinical data and inspection indexes of a septicopyemia patient, and carrying out the cleaning and standardization processing of the data; feature selection and engineering: selecting features related to septicopyemia death risks based on clinical knowledge and statistical analysis, and performing feature engineering; model training and verification: training the preprocessed data by using a machine learning algorithm, and verifying the model by using a training set, a verification set and a test set; model evaluation and optimization: evaluating model performance by using indexes such as AUC, accuracy rate, recall rate, F1 score and the like, and optimizing model hyper-parameters; and model explanation and application: explaining a model prediction result by using an explanatory tool, and applying the model in a clinical environment to assist death risk assessment. The invention provides a method for improving the early diagnosis and prognosis prediction of septicopyemia, thereby reducing the death rate.

The invention discloses a multi-modal-based medical algorithm model construction system, which comprises a multi-modal data acquisition and preprocessing module for collecting data related to infectious lung diseases from multiple data sources, a multi-modal feature extraction module for carrying out deep feature extraction on different modal data, a multi-modal fusion module for carrying out multi-modal fusion on the multi-modal data, and a multi-modal feature extraction module for carrying out multi-modal fusion on the multi-modal data. A self-attention mechanism is adopted to integrate different modal features including images, texts, structuralization, time sequences and associated features extracted by a large language model, a multi-task learning and decision module constructs a multi-task learning framework, and two core tasks of infectious lung disease risk prediction and decision support based on the prediction are executed in parallel. According to the multi-modal-based medical algorithm model construction system, by integrating outpatient service and emergency treatment multi-time-point data and chest radiography imaging data, the death rate of infectious lung disease patients, the ICU admission rate and the breathing machine requirement are predicted in advance, and key decision nodes are preposed.

The invention provides a dynamic prediction algorithm for monitoring late-onset infection of a premature infant and an upgrading system. The dynamic prediction algorithm for monitoring late-onset infection of the premature infant and the upgrading system comprise the following steps: a, collecting clinical data of the premature infant, including birth weight, gestational age, 1-minute and 5-minute Apgar scores, right hand perfusion index, lower limb perfusion index and other related clinical information, and b, determining the early-onset infection of the premature infant through medical history collection and physical sign analysis. The method comprises the following steps: collecting data of 11 classification independent variables: prenatal antibiotic use conditions (existence and absence); according to the dynamic prediction algorithm for monitoring late-onset infection of the premature infant and the upgrading system, the infection risk index is effectively calculated through high-risk factors analyzed by the Lasso regression model in combination with clinical basic data of the premature infant, early warning of infection of the premature infant is provided for medical staff, and the accuracy and timeliness of infection prediction are remarkably improved. Besides, the system can automatically remind medical staff to intervene the high-risk child patient through red warning, so that the death rate caused by delayed discovery and delayed treatment is reduced, and the clinical intervention effect is improved.

The invention relates to a method for predicting the lifespan of an individual, comprising I. providing biological input data of the subject, ii. providing a list of confounding variables, iii. predicting an age-related mortality or disease, preferably the time to death and / or the mortality risk and / or the risk of age-related disease, for the subject by analyzing the data with an algorithm, wherein the algorithm comprises a neural network, which is trained on at least one reference dataset comprising biological data of at least one reference subject by applying: a) a selector layer to filter input data of i., and b) an adversarial learning framework, that removes from the input data the information related to the confounding variables, wherein preferably the adversarial learning framework, is a neural network comprising three elements: a feature extractor (FE), a predictor (P), and a confounder predictor (C). The invention further relates to a device or system comprising means for carrying out the steps of the method according to the invention, a computer program and a computer-readable storage medium.

The invention discloses a severe patient organ failure assessment and risk stratification method based on the occurrence time point of blood flow infection, and relates to the field of severe medicine prognosis risk assessment modeling. Comprising the following steps: firstly, collecting daily sequential organ failure evaluation scores of a blood flow infection patient during an infection occurrence period, and dividing data into a training set and a verification set; importing the training set into a group trajectory model for fitting, determining the optimal grouping number of trajectory groups, and verifying the model through a verification set; then, according to a verification result, the patients are allocated to the track group with the highest membership probability for research; finally, a Cox proportional risk regression model is adopted, the correlation between different track groups and the death rate is evaluated, and decisive factors influencing prognosis are determined. According to the method, a robust framework is provided for hierarchical management of ICU blood flow infection patients, the death rate of the patients can be independently predicted, reference is provided for early intervention and formulation of personalized management strategies, and the clinical outcome of the patients is finally improved.

The invention provides a baby chick growth environment regulation and control method and system based on multi-source data fusion, and relates to the technical field of multi-source data processing, and the method comprises the steps: extracting clustering degree features and foraging frequency features of baby chicks, building a physiological comfort score based on the clustering degree features and the foraging frequency features, and carrying out the recognition of the baby chick growth environment. And matching with the environmental parameters to obtain the optimal environmental parameters. Therefore, the problem of high death rate caused by mismatching of environmental parameters and actual physiological needs of chicks in the current chick brooding period is solved to a certain extent.

The invention belongs to the technical field of gene engineering, and particularly relates to application of a DcTH gene in prevention and control of diaphorina citri, and the nucleotide sequence of the DcTH gene is shown as SEQ ID NO.1. The tyrosine hydroxylase DcTH gene is accurately identified and screened by taking diaphorina citri as a research object. Further, dsRNA is successfully synthesized by designing a specific primer, and an RNA interference technology is applied to the expression of the DcTH gene. Researches find that after the DcTH gene is silenced, the key physiological process of ecdysis of the diaphorina citri is interfered, the malformation rate and the death rate are remarkably increased, and finally effective prevention and control of the diaphorina citri are achieved. The DcTH gene provided by the invention can further provide a brand-new molecular target and theoretical support for development of a diaphorina citri prevention and control technical means based on RNAi (Ribonucleic Acid Interfere).

The invention relates to the technical field of biological medicine, in particular to construction and application of a candida patient death risk prediction model. The model is based on traditional SOFA scoring, core variables are screened through single-factor and multi-factor logistic analysis and LASSO regression analysis, respiratory system, blood coagulation function and circulatory system SOFA scoring and key indexes such as the maximum lactic acid value, the minimum albumin value and the maximum blood urea nitrogen (BUN) are integrated, and a prediction model is constructed through logistic regression. Through multi-center data verification, the AUC of an internal verification queue reaches 0.826, the AUC of an external verification queue is 0.813, and a calibration curve shows that the predicted death rate is highly consistent with the actual death rate. Patients can be divided into a high risk group and a low risk group through a 13-score threshold value, and the 28-day survival rate difference is significant (plt; 0.05) of the method. An efficient and convenient early risk assessment tool is provided for critical candida patients, and clinical precise intervention and prognosis improvement are assisted.

The invention provides a risk prediction model for the death rate of senile sepsis patients in 28 days after the senile sepsis patients are transferred into ICU and a construction method of the risk prediction model, independent risk factors related to death occurrence in 28 days are determined through single-factor and multi-factor logistic regression analysis, a column chart is made, the prediction model of the patent is constructed, and the risk prediction model of the senile sepsis patients in 28 days can be used for predicting the death rate of the senile sepsis patients. A comparison result with a standard APACHE II score and a decline index (FI-lab) in recent years or an AUC of an ROC curve of other multi-index models shows that the prediction model provided by the invention is better in efficiency.

The invention relates to the field of deep venous thrombosis medical diagnosis, in particular to an early-stage deep venous thrombosis prediction model establishment strategy and prediction method and device. Screening out DVT-related features from the electronic medical record data of the fracture patient by adopting a filtering type, a wrapping type, an embedded type, a model method and a causal relationship feature selection method; putting the screened features as input ends into Logistic regression, random forest, Bagging and LightGBM machine learning models, evaluating the optimal strategy of each model for predicting the DVT onset risk of the fracture patient, and obtaining an early-stage deep venous thrombosis prediction model; and a DVT prediction visualization convenient interaction program is constructed to assist a clinician in making a medical decision. According to the method, the clinical electronic medical record data of the fracture patient is collected, the fracture patient DVT risk monitoring model is built by innovatively using a causal relationship feature selection method in combination with machine learning, and a new attempt is provided for improving the detection rate of DVT and reducing the death rate of the fracture patient.

The invention discloses a death rate prediction method and device based on structured medical data and a large language model, a storage medium and electronic equipment, and belongs to the technical field of natural language processing and the technical field of artificial intelligence. The technical problem to be solved by the invention is how to automatically extract important features related to death rate from electronic health record data of a patient and construct a multi-source information fusion prediction model to assist doctors in early intervention and accurate treatment decision. According to the technical scheme, (1) the death rate prediction method based on the structured medical data and the large language model comprises the following steps: S1, constructing a patient electronic health record data set; s2, constructing a death rate prediction framework; and S3, training the death rate prediction model. And (2) a death rate prediction device based on the structured medical data and the large language model, wherein the death rate prediction device comprises a patient electronic health record data set construction unit, a death rate prediction framework construction unit and a death rate prediction model training unit.

This invention provides a method for predicting individual mortality rates based on activity data from wearable devices, comprising the following steps: acquiring multi-source characteristic data of the target individual, wherein the multi-source characteristic data includes at least activity data and baseline characteristic data, the activity data being collected by the wearable device worn by the target individual over a continuous monitoring period, and the baseline characteristic data including at least one of demographic characteristics, health characteristics, living environment characteristics, and lifestyle characteristics; processing the activity data to calculate an average activity data feature value representing the overall activity level of the target individual; inputting the average activity data feature value and the baseline characteristic data together into a trained nonlinear machine learning prediction model, and the prediction model outputting a predicted mortality risk value for the target individual within a preset future time window. This invention integrates the average activity data feature value with traditional baseline characteristic data, enabling risk assessment to be updated synchronously with an individual's daily activity level.

The application provides a risk prediction model for 28-day mortality of an elderly sepsis patient after being transferred into an ICU and a construction method thereof, determines independent risk factors related to death within 28 days through single factor and multi-factor logistic regression analysis, makes a nomogram, and constructs the prediction model of the patent, and the comparison result of the AUC of the ROC curve of the standard APACHE II score and the frailty index (FI-lab) or other multi-index model in recent years indicates that the prediction model proposed in the patent has better performance.

The invention relates to the technical field of biomolecular markers, and provides a chicken butyric acid level and / or death rate related SNP marker and application thereof, the SNP marker comprises a 106476774th nucleotide site corresponding to a No.3 chromosome of a GRCg6a-galGal6 genome, and the basic group of the nucleotide site is A or T. The invention also provides an application of the SNP marker in chicken butyric acid level and / or death rate related SNP marker in chicken butyric acid level and / or death rate related SNP marker in chicken butyric acid level and / or death rate related SNP marker in chicken butyric acid level and / or death rate related SNP marker. By optimizing the dominant alleles of the SNP, broilers with the butyric acid level and / or high and low mortality can be rapidly identified, broilers with high mortality can be eliminated, the frequency of the dominant alleles is increased generation by generation through breeding, the butyric acid level and / or mortality of the broilers, especially the 28-42-day-old stage, of the broilers is reduced, the genetic improvement progress of the domestic broilers is accelerated, and the breeding efficiency of the domestic broilers is improved. Therefore, the economic benefit of chicken breeding is effectively improved, and the application value is high.

The present application relates to the field of insect control, and particularly relates to a SIRT1 gene of Rhopalosiphum padi and application thereof and a method for controlling Rhopalosiphum padi. The gene encodes a protein with an amino acid sequence as shown in SEQ ID NO: 2. The present application finds that the SIRT1 gene plays a role in the growth and development of Rhopalosiphum padi. Inhibition of the expression of SIRT1 can significantly increase the mortality rate of Rhopalosiphum padi nymphs, significantly reduce the proportion of winged aphids, and ultimately cause the population to decline and the toxin transmission ability to weaken. By using RNA interference technology, it is found that inhibition of the expression of the SIRT1 gene of Rhopalosiphum padi can significantly increase the mortality rate of the nymphs, and significantly reduce the proportion of winged adults after development. In addition, by spraying dsRNA of the SIRT1 gene interference sequence of Rhopalosiphum padi encapsulated by a nano material, the mortality rate of the Rhopalosiphum padi nymphs is significantly increased.

The present invention provides a medical system comprising: a wearable structure including a first predetermined area, the first predetermined area being the area of the wearable structure corresponding to the temple of a target subject; a monitoring device including a first monitoring component, the first monitoring component being disposed in the first predetermined area and configured to collect first target information; a processor communicatively connected to the first monitoring component, the processor being configured to receive the first target information and, based on at least the first target information, determine whether a predetermined event has occurred in the target subject, and generate an alarm instruction when the predetermined event is determined to have occurred in the target subject; and an alarm device communicatively connected to the processor, the alarm device being configured to receive and execute the alarm instruction. By wearing this medical system, a user can utilize it to autonomously call for help when a stroke occurs, thereby obtaining effective assistance in a shorter period of time and reducing the disability and mortality rates of stroke.

The present invention relates to the field of biomedicine, and in particular to a serotype 4 avian adenovirus strain, a vaccine, a vaccine composition, a multi-unit vaccine and applications thereof. The serotype 4 avian adenovirus strain of the present invention has a deposit number of CGMCC No.45070. The Hexon gene sequence of the strain of the present invention is shown in SEQ ID NO:1. The present invention also relates to a vaccine, a vaccine composition and a multi-unit vaccine prepared using the strain. The strain of the present invention has high pathogenicity, with a lethality rate of 100% for 21-day-old SPF chickens, and the vaccine and vaccine composition prepared using the strain have good immune protection.

The application provides a nematocide of a light-loving flower extract and a preparation method and application thereof, and particularly relates to application of the light-loving flower extract in preparation of a nematocide. Through determination of a mortality rate and a hatching rate of southern root-knot nematodes, it is found that ethyl naphthalene in the light-loving flower has good insecticidal activity on nematodes and has obvious inhibition on hatching of eggs of the southern root-knot nematodes. The nematocidal activity of ethyl naphthalene increases with increase of a concentration of the medicine, and the inhibition rate on hatching of the nematode eggs increases with increase of a treatment time and the concentration of the medicine.

The invention provides a cat trace lymphopoiesis detection method which comprises the following steps: uniformly mixing receptor cat serum and donor cat lymphocytes for first incubation, adding complement after the first incubation is completed, uniformly mixing for second incubation, and obtaining a to-be-detected group after the second incubation is completed; uniformly mixing a phosphate buffer solution and donor cat lymphocytes for first incubation, adding complement after the first incubation is completed, uniformly mixing for second incubation, and obtaining a blank control group after the second incubation is completed; and after the second incubation is completed, respectively adding a coloring agent into the group to be detected and the blank control group, uniformly mixing, respectively counting the death rate of donor cat lymphocytes of the group to be detected and the death rate of donor cat lymphocytes of the blank control group, and calculating the toxicity percentage of the cat lymphocytes by adopting a specific formula. By setting a blank control group, non-specific death interference is eliminated by adopting a cat lymphocyte poison calculation formula, so that the credibility of a detection result is remarkably improved.

The invention discloses a protein marker for diagnosing heavy metal related cognitive impairment of middle-aged and elderly people and application thereof, a kit and a risk assessment model, and belongs to the technical field of biomedicine, the protein marker comprises a combination of TSKU, SOD3, CES2, PSMB10 and C1QA, the expression level of TSKU and CES2 in heavy metal related cognitive impairment patients is reduced, and the expression level of CES2 in the heavy metal related cognitive impairment patients is reduced. The expression levels of SOD3, PSMB10 and C1QA in heavy metal middle-aged and elderly cognitive impairment patients are up-regulated, a clinical model is constructed by detecting the expression levels of TSKU, SOD3, CES2, PSMB10 and C1QA and combining clinical information, and early diagnosis of cognitive impairment symptoms of heavy metal related middle-aged and elderly people can be realized, so that the sensitivity and efficiency of detection are improved. The constructed model is verified, and intervention measures can be taken actively through the early detection method, so that the progress of cognitive disorder symptoms can be delayed, the disability and fatality rate can be reduced, and even early curing can be realized.

The disclosed apparatus, systems and methods relate to predicting, screening, and monitoring for mortality and other negative patient outcomes. Systems and methods may include receiving one or more signals from one or more sensing devices; processing the one or more signals to extract one or more features from the one or more signals; analyzing the one or more features to determine one or more values for each of the one or more features; comparing at least one of the one or more values or a measure based on at least one of the one or more values to a threshold; determining a presence, absence, or likelihood of the subsequent mortality, falls or extended hospital stays for a patient based on the comparison; and outputting an indication of the presence, absence, or likelihood of the subsequent development of poor outcomes or death for the patient.

The application discloses application of psoralen in preparation of a medicine for treating sepsis. As a natural product, the psoralen has high safety and good tolerance, and can intervene in a pathological process of the sepsis through various action mechanisms such as inhibition of an inflammatory reaction, regulation of an immune reaction and promotion of tissue repair. When the psoralen is applied to treatment of the sepsis, the inflammatory reaction of the sepsis can be effectively controlled, tissue damage can be reduced and the mortality rate can be lowered, so that the survival rate and the life quality of the sepsis patients can be improved.

The invention discloses a method for constructing a chronic endometritis rat model based on Hungata (preservation number: DSM 13479), and belongs to the technical field of animal models. The bacterial strain is subjected to anaerobic culture to prepare a bacterial solution, 150 mu L vagina perfusion is performed twice every 3 days for 3 weeks, rat endometrial inflammation reaction is induced, and endometrial atrophy and endometrial inflammation cell infiltration are taken as pathological characteristics. According to the invention, the problems of high infection, high death rate and the like caused by traditional injection of lipopolysaccharide or pathogenic bacteria through the uterus horn are avoided, and an efficient experimental tool is provided for mechanism research and drug development of chronic endometritis.

Methods and applications of the present disclosure include promoting blood clotting, controlling hemorrhage, and or inhibiting fibrinolysis in soldiers and civilians having experienced massive bleeding from a wound by administering antifibrinolytic agents, such as tranexamic acid, and or one or more procoagulants, in preferably autoinjector format.

The application belongs to the technical field of biological medicine, and relates to a construction method of a thyroid-associated ophthalmopathy animal model, which comprises the following steps: after a pseudo-sterile animal model is constructed, fecal bacteria liquid of a mild patient with thyroid-associated ophthalmopathy is first administered to the pseudo-sterile animal model in a first stage, and Ad-TSHR is injected once in the second half of the first stage; then fecal bacteria liquid of a moderate patient with thyroid-associated ophthalmopathy is administered to the pseudo-sterile animal model in a second stage, and Ad-TSHR is injected once in the second half of the second stage; then fecal bacteria liquid of a severe patient with thyroid-associated ophthalmopathy is administered to the pseudo-sterile animal model in a third stage, and Ad-TSHR is injected once in the second half of the third stage; finally, Ad-TSHR is injected once in the second half of a fourth stage; and thus the thyroid-associated ophthalmopathy animal model is obtained. The model has a high incidence of 80% and a significantly reduced mortality rate under the condition of less immunization times.

A mortality prediction device of trauma patients includes a data collection module that collects patient-related data of patients visiting an emergency department for a certain period of time, a learning data generation module that generates a learning data group for one patient by extracting a plurality of preset data from the patient-related data, and a prediction module that inputs the learning data group into one or more machine learning models, respectively, to learn the machine learning models to predict mortality of the corresponding patient.

The invention discloses a prediction method and system for prolonging human life years by health intervention service, and relates to the technical field of data processing, and the method comprises the steps: building a health prediction model, and according to all-cause mortality and disease morbidity data of different genders and age groups, calculating a health prediction model; predicting the death probability of the crowd of each age group, the number of years of survivors of each age group, the total number of years of survivors and the expected life; in combination with the prevalence condition of general population health risk factors and the relative risk degree of all-cause death, calculating the life number of individuals who carry out health intervention earnings on different risk factors, and calculating the overall health score of the current individual; evaluating the health condition of the current individual according to the total health score of the current individual, discovering key risk factors, and making an intervention scheme. The life expectancy of healthy or chronic disease patients can be measured and calculated, and the method is suitable for application scenes of health intervention service evaluation.

This invention provides an interpretability system for mortality prediction models, comprising a prediction model module, a global interpretation module, an individual interpretation module, and a visualization interface module. By introducing a dual interpretation mechanism of the global and individual interpretation modules, the SHAP analysis unit of the global interpretation module generates a global feature importance ranking and an individual feature contribution distribution visualization, demonstrating the importance ranking of multi-source features in predicting mortality risk, enabling users to establish a macro-level understanding of the key aspects of the mortality prediction model. The individual interpretation module generates personalized interpretation reports, indicating the quantitative contributions of key features and crucial characteristics that drive increases or decreases in mortality prediction values. Through this combination of macro-level understanding and micro-level attribution, the mortality prediction model's predictions are transformed from an incomprehensible "black box" into a verifiable chain of evidence, effectively solving the core pain point of traditional models being difficult to apply due to their lack of interpretability.