180 results about "Pregnancy" patented technology

The invention provides a gestational diabetes risk prediction system and method based on multi-modal data fusion, and the system comprises a data collection module which is used for integrating clinical indexes and medical record text data; the data preprocessing module converts the multimode data into numerical values and text variables which can be used for modeling; the variable screening module is used for extracting data features by adopting LASSO regression in combination with a recursive feature elimination algorithm and a Clinical-BERT model; the data prediction module is used for constructing a GDM risk prediction model through a dual-channel calculation unit and a fusion unit, generating an accurate risk probability and providing an interpretable clinical index in combination with an SHAP value; and a prediction result is output through the output module in the forms of a dynamic column diagram, a webpage calculator and an API interface, so that clinical operation and application are facilitated. According to the method, the limitation of a traditional prediction method is broken through, the prediction precision and the real-time monitoring capability are improved, and the development of precise medical treatment is promoted.

Provided herein is a method of using digital twins for medical diagnosis, prediction, and / or prognosis of a disease or condition, such as diagnosis, prediction, and / or prognosis of one or more cancers, organ-specific age prediction, predicting of female aging, predicting hospital-acquired infection, predicting dialysis time series, predicting diabetes and complications, predicting pregnancy and child outcome, predicting heart failure, predicting myopia, predicting vision in anti-VEGF treatment, or any combination thereof. A system and non-transitory computer-readable storage medium configured for performing the method is also disclosed.

The invention provides a pregnant woman gestation period disease risk prediction method based on a time sequence knowledge graph, and belongs to the technical field of medical care informatics, and the method specifically comprises the steps: obtaining the behavior data and disease pathology information data of a pregnant woman in a gestation period; based on a historical time sequence event evolution process, carrying out sub-graph event sampling on the behavior data and the disease pathology information data, and constructing a time sequence knowledge graph; obtaining graph structure features of the time sequence knowledge graph based on a graph attention mechanism, and extracting text semantic features through a text embedding model; fusing the graph structure features and the text semantic features based on a cross attention mechanism; building an entity prompt, a relation prompt and a time prompt based on the prompt project, and training the input of a pre-training language model through the fusion features; and inputting the behavior data and the disease pathology information data of the target pregnant woman in the gestation period into the prediction model to obtain a gestation period disease risk prediction result. Through the scheme of the invention, the prediction accuracy and adaptability are improved.

The invention relates to the technical field of image classification, in particular to a gestational hypertension traditional Chinese medicine tongue diagnosis image classification method based on transfer learning. Firstly, a tongue diagnosis image of a gestational hypertensive patient is obtained, a tongue body area is extracted, and an indentation degree value is calculated based on shape and pixel position features to reflect the shape of fat tongue with indentation; further extracting a tongue middle area by considering that physiological water retention during pregnancy may cause tooth marks, determining a reflective connected domain by analyzing pixel reflective characteristics before and after filtering, and extracting shape characteristics of the reflective connected domain to obtain a dispersion degree value and characterize a greasy moss degree; the tongue diagnosis image purity is obtained by combining the color fluctuation and gray scale confusion conditions of the tongue middle area and integrating the indentation degree value and the dispersion degree value, so that the greasy coating state and the spleen deficiency and liver-yang hyperactivity conditions are reflected; and finally, training a neural network by using the purity of the tongue diagnosis image and the original visual features, classifying the tongue diagnosis image, obtaining a more accurate classification result, and assisting a doctor in performing accurate judgment.

The invention provides an optimal administration method for promoting cervical maturation by misoprostol based on a PopPK model, and belongs to the technical field of drug administration scheme optimization, the method comprises the following steps: constructing the PopPK model for oral administration of misoprostol by a pregnant woman in late pregnancy, the PopPK model is a model structure containing absorption lag time zero-order-first-order absorption parallel, one-atrioventricular distribution and first-order elimination, and the PopPK model is a model structure containing absorption lag time zero-order-first-order absorption parallel, one-atrioventricular distribution and first-order elimination; the PopPK model comprises two absorption chambers and one central chamber; and based on the PopPK model, determining a staged administration scheme through simulation optimization. The limitation of a traditional fixing scheme is effectively overcome, and the safety, effectiveness and clinical practicability of drug administration are considered.

The invention relates to the technical field of intelligent medical treatment, in particular to a pregnancy management system and method based on big data, and the system comprises an abnormal segment recognition module, a deviation feature extraction module, a risk type recognition module, an abnormal trend prediction module and a physiological data management module. According to the method, the abnormal fluctuation of the data sequence is recognized by calculating the variability of the physiological data in the cycle, the method is not limited to isolated single-point measurement any more, the dynamic stability of the index in a period of time is concerned, and then quantitative extraction is conducted on the variation trend of abnormal data segments such as body weight, blood sugar and blood pressure; for example, the change of body weight along with time is fitted into a slope, original data is converted into a structured trend feature, then the dynamic change trend of an individual is compared with a normal evolution benchmark extracted from a large-scale healthy pregnant woman group, and the severity that the current physiological state deviates from a normal track is accurately quantified.

The present disclosure provides methods and systems directed to cell-free identification and / or monitoring of pregnancy-related states. A method for identifying or monitoring a presence or elevated risk of a pregnancy-related state of a pregnant subject may comprise assaying a cell-free biological sample derived from said pregnant subject to detect a set of biomarkers, and analyzing the set of biomarkers with a trained algorithm to determine the presence or elevated risk of the pregnancy-related state.

The invention relates to medical detection equipment, in particular to an integrated portable instant urinalysis device for pregnant women. The invention relates to a pregnant woman urinalysis device, and aims to provide an integrated portable instant pregnant woman urinalysis device so as to solve the problem that a conventional pregnant woman urinalysis method is complex and time-consuming at the present stage, realize low-cost and rapid multi-index detection and contribute to early detection of various diseases in the gestation period. According to the technical scheme, the integrated portable instant urinalysis device for the pregnant woman is characterized in that the device is formed by correspondingly assembling an upper chip layer and a lower chip layer; a sample introduction area located in a central area and a plurality of detection channels radially arranged outwards from the sample introduction area are arranged in the device, and each detection channel comprises a reaction detection area and a waste liquid area which are led out from the sample introduction area and are sequentially communicated through a shunting channel, and air holes formed above the detection channels.

The application provides a misoprostol cervical ripening optimization dosing method based on a PopPK model, belongs to the technical field of drug dosing scheme optimization, and comprises the following steps: constructing a PopPK model of oral misoprostol for pregnant women in the third trimester of pregnancy, the PopPK model is a model structure containing zero-order-first-order absorption in parallel, one-compartment distribution and first-order elimination, the PopPK model comprises two absorption compartments and one central compartment; and determining a phased dosing scheme based on the PopPK model through simulation optimization. The method effectively overcomes the limitations of traditional fixed schemes, and takes into account the safety, effectiveness and clinical practicability of dosing.

The invention discloses an amniotic epithelial cell-derived exosome for treating gestational hypertension and application thereof, and belongs to the technical field of biological medicines. The exosome (hAECs-exos) is obtained by secreting and extracting human amniotic epithelial cells (hAECs), the particle size distribution of the exosome (hAECs-exos) is 30-150 nm, and the exosome (hAECs-exos) expresses exosome specific markers CD9, CD63 and CD81. The invention also provides a preparation method of the exosome. The preparation method comprises the following steps: isolated culture of hAECs, and ultracentrifugal extraction and identification of the exosome. Animal experiments prove that when the exosome is applied to a gestational hypertension disease model animal in an intravenous injection mode, the blood pressure and urine protein level of the gestational hypertension disease model animal can be remarkably reduced, and the fetal rat dysplasia condition is improved. The invention provides a brand-new and effective biological preparation candidate scheme for the treatment of the gestational hypertension disease.

The invention discloses a live pig feeding fine management device and system, and relates to the technical field of live pig breeding, the live pig feeding fine management device comprises a pig trough and a readable electronic ear tag, the pig trough is provided with a channel, and a first electronic weighing device is arranged below the channel; according to the invention, through readable electronic ear tag identification, automatic feeding control and double-scale synchronous metering, the identity, accurate feed intake and weight data of pigs are automatically collected when the pigs eat each time, a continuous individual data link is formed, and on the basis, real-time monitoring of the feed intake interval, automatic early warning of abnormal feed deprivation and early detection of diseases can be realized; according to long-term accurate feed conversion ratio and daily weight gain data, a quantitative basis is provided for scientific breeding of high-yield breeding pigs, the non-pregnant period is intervened and effectively shortened in time by continuously analyzing the weight change trend of breeding sows and intelligently assisting early pregnancy diagnosis, and finally, the system changes traditional empirical group management into traditional group management. And the system is upgraded to a data-driven and individualized intelligent management closed loop.

The present disclosure generally relates to polynucleotide constructs comprising a feline alphaherpesvirus 1 (FeHV-1) genome modified by inserting one or more nucleic acid sequences into the non-coding region between two convergent FeHV-1 genes of the FeHV-1 genome, wherein the one or more nucleic acid sequences encode one or more feline reproductive protein antigens that can stimulate an immune response to reduce the incidence of pregnancy, and uses thereof.

The invention relates to a gestational blood glucose data grouping method and a server. The method comprises the following steps: acquiring blood glucose data of a gestational user and input basic information; based on a preset group division rule, the gestational user data is divided into a plurality of subgroups, and the group division rule is determined based on the difference and difference of influence trends of various hormones on insulin resistance or insulin sensitivity, so that different-direction associated subgroups and / or same-direction associated subgroups are obtained; a shared database is constructed, data information in all subgroups is stored in the form of multi-dimensional blood glucose comprehensive evaluation indexes, and the multi-dimensional blood glucose comprehensive evaluation indexes are obtained through calculation based on the average blood glucose index related to blood glucose, the blood glucose fluctuation factor, the postprandial peak gradient and the night blood glucose load.

The invention relates to a composition with an effect of improving sleep quality during pregnancy and application of the composition. The composition comprises aminobutyric acid, tea leaf theanine, casein hydrolysate and spearmint extract. The aminobutyric acid, the tea theanine, the casein hydrolysate and the spearmint extract are compounded for use, so that the problem that a single-mechanism sleep-aiding product has a limited effect on insomnia during pregnancy is solved, the sleep structure is improved to a great extent, and the sleep quality is improved.

The present invention relates to the technical field of medical detection. Disclosed is a use of an ERAP2 detection reagent in the preparation of a product for predicting the prognosis of POI. Also disclosed in the present invention is a use of ERAP2 as a biomarker in the preparation of a product for predicting the prognosis of POI. The prognosis of POI is intermittent recovery of ovarian function and / or a pregnancy outcome. In the present invention, it has been found by means of experimental studies that a serum ERAP2 level has a significant association with the prognosis of a POI patient, is an independent influencing factor, and has relatively high specificity and sensitivity. Therefore, ERAP2 can serve as a biomarker for predicting the prognosis of POI. The present invention provides a theoretical basis and clinical practice guidance for the prognosis of POI, and has important application value.

Methods and compositions for detecting or determining a subject's risk of developing placenta accreta spectrum (PAS) are provided. Biomarkers are described that can be useful in detecting PAS in the second or third trimester of pregnancy.

The invention discloses an animal embryo biopsy sampling method and application thereof, and belongs to the technical field of animal breeding. The animal embryo biopsy sampling method provided by the invention is safer, more accurate and more efficient, and can effectively reduce the difficulty of an embryo biopsy sampling technology, reduce mechanical damage to embryos, effectively avoid development retardation of the embryos after sampling and remarkably improve the ratio and utilization efficiency of available embryos on the premise of ensuring the stability of the detection rate of a genetic evaluation chip; the survival rate, the developmental ability and the embryo pregnancy success rate of the sampled embryos are remarkably improved, and the transplantation conception rate of the frozen embryos after sampling reaches 40%; the method can be used for hereditary performance detection and evaluation and embryo screening before embryo implantation, and has important significance in shortening generation intervals, accelerating the breeding process and reducing the overall production cost of animal breeding and breeding.

A flushable apparatus (10) for testing a liquid specimen such as urine for a condition such as pregnancy. The apparatus includes a pliable sheet (11) that can be secured to the rim of a toilet bowl. The sheet is shaped and dimensioned to cause a flow of urine to impact a testing unit (30) such as a pH indicator patch, a biodegradable immunoassay, a metal organic framework composite containing assay, or a removable, non-flushable chromatographic strip, and to dram excess urine away from the testing unit. The apparatus can be disposed of in a convenient, environmentally responsible way. The testing unit can provide results in a color-coded manner that can be easier to read by inexperienced users.

The invention provides an ultrasonic image classification method, device and equipment and a readable storage medium, and relates to the technical field of medical image processing. According to the method, high-dimensional semantic features of a fetal ultrasound image are extracted based on a CLIP model, a hidden state sequence is obtained in combination with one-way LSTM network modeling sequence dependency, invalid tokens of the hidden state sequence are filtered out through a two-stage selective attention mechanism, key semantic features are reserved, and significant features are obtained; and aggregating the significant features into global representation, and inputting the global representation into a full connection layer to output a classification result, thereby realizing accurate classification of the ultrasonic image. According to the method, the accuracy rate in the ultrasonic standard section identification task in the middle pregnancy period can reach 100%, the accuracy rate is obviously superior to the artificial identification performance of primary and advanced clinicians, the problems of image noise, low contrast, difficulty in complex anatomical structure evaluation and the like can be effectively solved, and an efficient and accurate solution is provided for medical image analysis.

A device may include an artificial intelligence (AI) model for pregnancy classification. The AI model may be trained by inputting labeled training data. During training, the AI model may determine, using a loss function, an error margin for the binary classification AI model based on inputting the labeled training data. The loss function may impose, for false positive pregnancy classifications, a first penalty factor that is weighted relative to a menstruation start date and that is greater than a reward factor for true positive pregnancy classifications. The loss function may impose a second penalty factor for classification confidences that change by a threshold amount between two consecutive days. The AI model may adjust one or more parameters of the binary classification AI model based on the error margin determined using the loss function.

The present application relates to the technical field of digital medical treatment, in particular to a pregnancy-induced diabetes risk early warning method based on multi-modal data fusion. Multi-modal data such as blood glucose time series data, exercise amount, body weight and placenta thickness of pregnant women during pregnancy are acquired, the peak value and back-off characteristics of blood glucose time series are analyzed, the exercise amount is combined, the blood glucose back-off trend degree is quantified, and the dynamic metabolic control capability is accurately reflected; further, on the basis of placenta thickness data, the body weight change condition, the exercise amount and the blood glucose back-off trend degree are combined to determine the placenta thickness estimation value time series data, and the physiological correlation characteristics between various data are improved; finally, the blood glucose back-off trend degree mean value and the placenta thickness sustained increasing trend characteristics are fused to reveal the correlation characteristics of blood glucose and abnormal placenta development, a neural network model is trained to capture multi-factor nonlinear relationships, and early and accurate risk prediction of pregnancy-induced diabetes (GDM) is realized.

Embodiments of the invention comprise a test strip configured to detect one or more metabolites of progesterone in urine, and optionally further detect one or more additional metabolites or hormones in urine within the same test strip. Embodiments of the invention are methods of utilizing such a test strip in association with avoidance of pregnancy, detection of menopause, and in association with fertility planning purposes. Embodiments of the invention are associated with the incorporation of a test strip within a testing kit, optionally further comprising a digital reader.

The invention discloses a system, method and device for premature delivery risk prediction and a storage medium, and belongs to the technical field of biomedical information. The system comprises a data acquisition module and a data processing device. The data acquisition module is used for acquiring hemoglobin concentration, serum ferritin concentration, age, BMI, pregnancy times, delivery times, marriage conditions, education degree and other clinical characteristic data of the pregnant woman in the early pregnancy period, the middle pregnancy period and the late pregnancy period; the input characteristics of the model comprise all data of the three stages of pregnancy; the risk score is then compared with a specific threshold value set based on a Youden index, and a risk level of preterm delivery, spontaneous preterm delivery, or iatrogenic preterm delivery is output. The Hb-SF-Clinical multi-feature prediction model is constructed by fusing the three-stage pregnancy dynamic biomarkers and clinical features, the AUC (early birth prediction) of the Hb-SF-Clinical multi-feature prediction model in a test set reaches up to 96.0%, the Hb-SF-Clinical multi-feature prediction model is remarkably superior to the prior art, high-precision and subtype early birth risk assessment is realized, and the clinical applicability is high.

This invention relates to a group of genes associated with preterm birth, methods for predicting preterm birth in early pregnancy using these genes, and their related applications. Specifically, this invention obtains transcript start site features from at least one of the following genes from the pregnant woman's cfDNA sample: TEX2, WNK1, LINC00970, LOC124900437, IGFL4, LOC105376571, LOC105376577, SERPINB10, LOC642554, and SLC26A7. These transcript start site features are then input into a prediction model, and the output results are used to determine the risk of preterm birth. The prediction model obtained by this invention has higher accuracy than existing models, providing more accurate clinical intervention guidance and reducing medical costs.

The invention is applicable to the technical field of biological medicines, provides application of ophiopogon japonicus borneol glycoside in preparation of a medicine for preventing and treating gestational metabolic diseases, and aims to solve the technical problems that the conventional medicine is limited in use during pregnancy, and the curative effect and the safety are difficult to take into account. According to verification of multi-model systems such as animals, cells and human-derived trophoblast organs, it is found that ophiopogon japonicus borneol glycoside can significantly improve gestational glycometabolism disorder, improve insulin sensitivity and reduce insulin resistance, and therefore effective intervention on gestational diabetes mellitus is achieved. As a natural component derived from the Zhejiang radix ophiopogonis, the radix ophiopogonis borneol glycoside has definite pharmacological activity and excellent safety, and the Zhejiang radix ophiopogonis is listed in a national homology of medicine and food, so that reliable safety guarantee is provided for use during pregnancy.

The invention discloses an early pregnancy ultrasonic image gestational sac edge feature segmentation method and system, and the method comprises the steps: obtaining original ultrasonic image data, carrying out the image data preprocessing, and obtaining the preprocessed ultrasonic image data; constructing an improved segmentation network to perform automatic segmentation processing on the preprocessed ultrasonic image data to obtain an ultrasonic image gestational sac segmentation result; and performing target edge expansion processing on the ultrasonic image gestational sac segmentation result based on distance transformation and a morphology method to obtain an ultrasonic image gestational sac edge feature segmentation result. The method can improve the accommodation capability of the segmented region for the target structure, and achieves the improvement of the segmentation precision of the ultrasonic image gestational sac. The method and system for segmenting the gestational sac edge features of the early pregnancy ultrasonic image can be widely applied to the technical field of automatic segmentation of edge effective areas.

The invention provides a pregnant and lying-in woman health dynamic monitoring system and method based on big data, and relates to the technical field of data processing, and the method comprises the steps: inputting the physiological data of a pregnant and lying-in woman, the doctor's advice information and the current pregnancy period into a health planning model, and obtaining standard energy consumption and standard nutrition parameters; obtaining current-day exercise data and current-day diet data of the pregnant and lying-in woman; on the basis of the current-day exercise data, the physiological data and the current pregnancy period, the current-day energy consumption of the pregnant and lying-in woman is determined; inputting the daily diet data and the standard nutrition types into a nutrition analysis model to obtain daily intake parameters corresponding to each standard nutrition type; comparing the energy consumption of the day with standard energy consumption to obtain an exercise monitoring result of the pregnant and lying-in woman; and comparing the daily intake parameter corresponding to each standard nutrition type with the standard intake parameter corresponding to each standard nutrition type to obtain a nutrition monitoring result of the pregnant and lying-in woman. The accuracy of the health assessment result of the pregnant and lying-in woman can be improved.

The invention relates to the technical field of medical artificial intelligence, and particularly discloses a method for establishing a disease prediction model of GCK-MODY in gestational diabetes population based on machine learning. The model takes five clinical characteristics as input variables: a body mass index before pregnancy, fasting blood glucose and glycosylated hemoglobin levels during GDM diagnosis, continuous multi-generation diabetes family history and a newly discovered predictive factor, namely GDM diagnosis week of pregnancy. A classification model is constructed through a support vector machine algorithm, and a SHapley additive interpretation method is adopted to provide global and local interpretation of a prediction result, so that model transparency is enhanced. The area of the model under a curve in a test is obviously superior to that of an existing screening standard. The invention also provides an electronic device, a storage medium and a prediction system comprising the model, which can assist clinicians in early recognition of GCK-MODY high-risk patients, provide decision support for targeted gene detection, avoid unnecessary enhanced hypoglycemic treatment of pregnant women, reduce the risk of maternal and infant complications, and promote precise medical development of gestational diabetes mellitus.

The invention discloses a pregnancy individualized medication dosage prediction factor screening method, a prediction model construction method and a prediction system, and relates to the technical field of medicine. Factors which are obviously related to blood concentration and have no obvious multicollinearity among variables are screened out from factors influencing pregnancy drug dosage to serve as drug dosage prediction factors, and a corresponding prediction model and system are constructed. According to the screening method, the prediction model construction method and the prediction system provided by the invention, auxiliary decision making can be provided for individualized drug dosage during pregnancy.