39 results about "Death risk" patented technology

A method and system use a combined contribution of multiple disease risk factors to predict the risk of onset of particular diseases in an individual. The prediction models use information from separate studies. Multiple disease predictions for a predetermined number of diseases are made. The predictions are used to calculate the individual's mortality risk and life expectancy. The life expectancy is compared to that of age and gender matched peers to determine the inner age of the individual.

The invention discloses a system for estimating the state of a critically ill patient in an obstetrical department, which comprises an input end, an output end and a data processing module. Firstly, measured heart rate, blood pressure, body temperature, breathing rate, pH, blood HCO-3 concentration, oxygen partial pressure, alveolar arterial blood oxygen tension difference, potassium ion concentration, hematokrit, white cell count, platelet count, fibrinogen, glutamic-oxaloacetic transaminase, albumin, bilirubin, creatinine, blood glucose concentration and nervous system grading data are input the system through the input end; the data processing module evaluates a death risk factor; and at last, the output end directly reflects the result of the patient and the expert suggestion. The invention can not only accurately evaluate the critical degree of the state of the patient and predict the death risk, but also can provide quantitative indexes for changing to a three-class hospital, and is beneficial to improve the treatment level of the critical state of the obstetrical department and lower the death rate of pregnant and lying-in women and perinatal infants.

The invention relates to a perioperative period critical event prediction method based on cross-modal deep learning, and belongs to the field of artificial intelligence and medical application. The method comprises the following steps: step 1, constructing a multi-modal medical monitoring data set; 2, performing bimodal fusion feature learning on patient monitoring data and personalized data; 3, cross-modal collaborative learning feature extraction; 4, constructing a multi-modal critical event (death risk) prediction model; 5, verifying model feedback. The method serves as a critical adverse event prediction and early warning tool, and is an effective method for achieving real-time tracking, early diagnosis and early warning of main critical events after operation.

The invention comprises a system and method for hedging or mitigating mortality exposure risk in a portfolio of mortality-dependent instruments. A mortality risk or longevity risk of the portfolio is calculated or otherwise determined. Then the sensitivity of the portfolio to mortality risk or longevity risk is calculated or otherwise determined, in other words, how much is cost or value of the portfolio affected by a change in mortality rate. To account for that mortality exposure, a selection is made of building block mortality derivatives that include age-based mortality derivatives. The selected plurality of building block mortality derivatives are used to create a hedge against the mortality risk or longevity risk of the portfolio.

The invention relates to a method for predicting critically ill death based on an attention mechanism temporal convolution network algorithm, and belongs to the field of artificial intelligence and medical treatment. The method comprises the following steps: 1, acquiring and analyzing intensive care and surgery multi-source monitoring data; 2, inputting the data into temporal convolution network (TCN) and extracting characteristics; 3, calculating attention weight of each characteristic through an attention mechanism based on the characteristics extracted from the temporal convolution network;and 4, calculating death risk coefficients through a linear layer to predict the critically ill death risk. The method disclosed by the invention has the advantages that the method is used as a critically ill death prediction tool, death of critically ill patients can be predicted so that the survival probability of the critically ill patients is increased and an effective method of a medical care plan is objectively worked out.

Methods and compositions disclosed herein generally relate to methods of identifying, validating, and measuring clinically relevant, quantifiable biomarkers of diagnostic and therapeutic responses for blood, vascular, cardiac, and respiratory tract dysfunction, particularly as those responses relate to septic shock in pediatric patients. In particular, the invention relates to identifying two or more biomarkers associated with septic shock in pediatric patients, obtaining a sample from a pediatric patient having at least one indication of septic shock, then quantifying from the sample an amount of two or more of said biomarkers, wherein the level of said biomarker correlates with a predicted outcome.

The invention discloses an esophagus cancer postoperative early-stage recurrence and prognosis related miRNA marker and its application, and concretely discloses an miRNA marker has-miR-382, an application of the miRNA marker in the making of an esophagus cancer postoperative early-stage recurrence and prognosis auxiliary diagnosis kit, an application of the primer of the esophagus cancer postoperative early-stage recurrence and prognosis related miRNA marker in the making of the esophagus cancer postoperative early-stage recurrence and prognosis auxiliary diagnosis kit, and the esophagus cancer postoperative early-stage recurrence and prognosis auxiliary diagnosis kit of the primer of the esophagus cancer postoperative early-stage recurrence and prognosis related miRNA marker. A screening method in the invention is simple and is convenient to operate, and the screened has-miR-382 can auxiliarily determine the prognosis or death risk of an esophagus cancer patient, and promotes the development of the esophagus cancer diagnosis and treatment.

The invention discloses a method and system for determining the suffocation death risk of fishes. The method comprises the steps of obtaining fish data and water data in a closed environment; establishing an oxygen consumption rate prediction model and a non-fish oxygen balance model; utilizing the oxygen consumption rate prediction model and the non-fish oxygen balance model for establishing a dissolved oxygen concentration dynamic model; establishing a suffocation point prediction model; utilizing the dissolved oxygen concentration dynamic model for predicting a dynamic trajectory of the dissolved oxygen concentration in water to be predicted; utilizing the suffocation point prediction model for predicating suffocation points of the fishes in the water to be predicted; judging whether ornot predicted suffocation point values are smaller than or equal to the minimum dissolved oxygen concentration value in the dynamic trajectory of the dissolved oxygen concentration; if yes, determining that the fishes in the water to be predicted do not have the suffocation death risk; if not, determining that the fishes with weights corresponding to the predicted suffocation point values greaterthan the minimum dissolved oxygen concentration value have the suffocation death risk. By means of the method, the death risk of different fishes under the oxygen deficit condition of the water can be determined, and the reliability is high.

The invention discloses a personalized health management method and system. According to the personalized health management method and system of the invention, standard questionnaires are designed according to different genders and age groups; each answer in the standard questionnaires is corresponding to a corresponding risk score; the gender and age information of evaluation objects is collected; corresponding personalized health assessment questionnaires are automatically generated according to the gender and age information, and the health-related information of the evaluation objects is collected through the health assessment questionnaires; the health-related information is converted into risk scores, the combined risk scores of death risk events, absolute disease appearance risk events, and disease high-risk group risk events are calculated, the death risk, chronic disease appearance risk, and disease high-risk group risk of the evaluation objects are evaluated; individualized interventions and implementation plans are developed based on risk factors corresponding to the death risk, the chronic disease appearance risk, and the disease high-risk group risk, the plans are pushed to the evaluation objects, and plan implementation results fed back by the evaluation objects are received; and the plans are adjusted according to the fed-back plan implementation results.

The invention discloses an NLARI heart rate module-based heart and an autonomic nerve function assessment method. Heart rate variation is modeled via a non-linearity autoregression integration model describing a random elastic system; and heart rate feature indexes and assessment reference range can be derived via parameter-quantization of relative functions of the heart and the autonomic nerve via the model. An assessment system formed by the heart rate feature indexes can be derived in internal-external environment of a cardiovascular system; cardiovascular system and autonomic nerve function assessment can be provided including myocardial metabolism and function, autonomic nerve system and humoral balancing adjusting functions, metabolism level and changes; and cardiogenic stroke death risk indexes can be also improved. Approximate algorithm or chip elements for frequency-domain analysis can be unnecessary, so the method is convenient and high-efficient; and the method integrates biological signal analysis technology and communication network technology, so the whole people health industry development can be promoted.

The invention discloses a group of genes for molecular typing of non-hyper-mutant rectal cancer. The genes comprise an SMAD4 gene, an MUC16 gene, an FAT4 gene, an FLG gene, an ROBO2 gene and an NEB gene, molecular typing can be performed on rectal cancer according to the gene mutation characteristic combination, so that low-risk group patients with relatively low postoperative recurrence and deathrisks are screened, treatment can be performed according to a current postoperative adjuvant therapy scheme, and excessive treatment is avoided; and another group of high-risk group patients with higher postoperative recurrence and death risks can find better other schemes for the patients on the basis of the current postoperative adjuvant therapy scheme. The invention also discloses a kit for capturing the gene.

The invention discloses a self-pressurized semiconductor cooling cold-therapy system which comprises a radiating bag strip (1), a pressurized radiating medium (2), a semiconductor refrigerating plate (3), a cooling cold-therapy belt (4), a refrigerating medium (5), a fastening belt (6), a heat-insulating fiber layer (7) and a semiconductor refrigerating controller (8). When blood circulation of a wounded tissue of a patient needs to be reduced, the temperature of the wounded tissue needs to be reduced, and a bedridden patient is prevented from pressure sores, the self-pressurized semiconductor cooling cold-therapy system can be bound to the wound part through the fastening belt (6), the semiconductor refrigerating controller (8) is regulated, and the cooling cold-therapy belt (4) which clings to the wound part is refrigerated and cooled when the cold end of the semiconductor refrigerating plate (3) absorbs heat; meanwhile, the hot end of the semiconductor refrigerating plate (3) releases heat for increasing pressure of the pressurized radiating medium (2) in the radiating bag strip (1), so that the wounded tissue can be pressed, blood circulation can be reduced, and the temperature of the wounded tissue is reduced, the purposes of reducing pains and reducing cell death risks are achieved.

The invention discloses a diabetic ICU patient death risk prediction method based on artificial intelligence. The method comprises the following steps: S1, collecting ICU data of a diabetic ICU patient according to a set standard; s2, importing the collected ICU data into a database, and taking out vital sign data of a diabetic ICU patient; s3, deleting data which do not meet the specification in the acquired ICU data and the vital sign data; s4, constructing a prediction model based on a logistic regression algorithm, a prediction model based on a decision tree algorithm, a prediction model based on a random forest algorithm and a model based on hybrid bidirectional LSTM; s5, inputting the ICU data and the vital sign data processed in the step S3 into the model in the step S4 for model training and iterative training, and selecting an optimal model; and S6, inputting the basic information of the diabetic ICU patient and the vital sign data of the patient into the optimal model to predict the death risk. According to the invention, an early warning effect can be achieved, so that the treatment condition of a diabetic ICU patient is improved.

The invention discloses a patient death risk prediction method and system based on an electronic medical record, a terminal and a readable storage medium. According to the patient death risk prediction model constructed by the method, the time information is added to the medical feature data to obtain the patient feature data with the time characteristic, then the time sequence model is utilized to learn feature representation of various types of patient feature data, an irregular time pattern is mined, and the patient death risk prediction accuracy is improved. According to the method, the feature data of a patient is extracted, then an attention mechanism with a hierarchical structure is introduced to fuse the heterogeneous feature data to obtain a more comprehensive fused feature, and finally, the fused representation of the patient is applied to death risk prediction, so that the model prediction precision and reliability are improved. According to the method, the irregular time sequence modeling problem and the multivariate heterogeneous data fusion problem in the prior art are effectively solved, the method and other methods are tested and compared on the same data set, and experimental results show that the method has good performance in the aspect of death risk prediction of critical patients.

The present invention is generally related to methods and systems for preventing onset or worsening of RHF in patients with implanted ventricular assist devices. More particularly, the present invention relates to identifying patients at risk for RHF following implantation of a ventricular assist device based on pulmonary artery pressure measurement and/or trends and adjusting a pump operating parameter to prevent or reduce the onset or worsening of RHF in such patients, improve patient outcomes, or reduce mortality risks associated with VAD implantation. In particular, a pump operating parameter may be adjusted to reduce or minimize particularly high pressure loads on a patient's heart or amount of time the patient is exposed to such high pressure loads following implantation.

The invention discloses a time window cutting-based health risk key event detection method and system. The method comprises the following steps: S100, inputting an electronic medical record of a patient into a trained deep learning model to obtain important indexes and death risk indexes of physiological indexes of a patient every time the patient sees a doctor; S200, dividing targets of detectionof health risk key events of the patient into four types according to time windows, detecting the four types on the basis of the obtained important index and the death risk index of each physiological index to screen out the physiological indexes of the health risk key events which need to be proposed; and S300, based on a visual interface, displaying the detection process and detection results of the health risk key events of the patient. The method and system can mine more valuable information with reference significance from data of the electronic medical record of the patient in the hospital to help the doctor make diagnosis.

The invention relates to the technical field of hematopoietic stem cell transplantation, and discloses a non-recurrent death risk monitoring model based on aGVHD biomarker, which is used for dynamically monitoring aGVHD biomarker indexes (sST2, REG3alpha) at different time points of a patient group (199 patients, non-recurrent death in one year accounts for about 12%). The method comprises the following steps: calculating a value of a distance between sST2 and REG3alpha at each detection time point within 100 days after a patient is transplanted, selecting aGVHD biomarker when the value of the distance between the sST2 and the REG3alpha at the detection time points reaches the maximum as an index of the worst condition of the patient, and establishing a model data set. According to the non-recurrent death risk monitoring model based on the aGVHD biomarker, risk grouping is carried out on patients by establishing a layering standard, the cumulative occurrence rate of non-recurrent death in 180 days is low risk (2.38%) vs medium risk (16.67%) vs high risk (52.0%), and the layering result is superior to that of existing research [5] (in initial treatment, aGVHD biomarker grouping: low risk (6%) vs medium risk (20%) vs high risk (49%)).