30results about How to "Reduce the risk of misdiagnosis" patented technology

The invention discloses a transformer fault diagnosis method considering an operation state grade. The method comprises the following steps: collecting five typical fault data of a transformer, constructing a fault diagnosis sample data set, and performing tagging processing; extracting seven gas contents and 19 gas ratios of the transformer oil chromatographic data as fault features, and performing feature dimension reduction fusion on the preprocessed 26-dimensional fault features by using a principal component analysis (PCA) method; constructing an adaptive relevance vector machine fault diagnosis model based on a particle swarm algorithm and K-fold cross validation; and when the operation state level of the transformer is evaluated as a serious fault, using the fault diagnosis model for diagnosis. According to the fault diagnosis model constructed by the invention, automatic optimization of kernel parameters is realized in a model training process, and compared with a multi-stage binary classifier, the structure is simple. Through fault diagnosis considering the operation state level, the error diagnosis risk of real-time online fault diagnosis of a traditional transformer canbe reduced.

The invention discloses a pulse simulation device and a pulse simulation implementation method, belonging to the technical field of medical instruments for the traditional Chinese medicine. The pulsesimulation device and the pulse simulation implementation method are designed for solving the problems of poor accuracy of a pulse condition recurrence result and the like. The pulse simulation devicecomprises a plurality of pulse tubes, a pulse tube frame, a top rod, a driving device and a pulse tube frame rotating device, wherein the pulse tube frame is used for fixing at least two ends of thepulse tubes; the top rod is used for discontinuously pushing unfixed positions of the pulse tubes so as to simulate the pulse beat of a patient; the driving device is used for driving the top rod to do a reciprocating motion; and the pulse tube frame rotating device is used for driving the pulse tube frame to rotate around a support shaft so as to place the selected pulse tubes to the tip of the top rod. According to the pulse simulation device and the pulse simulation implementation method, different pulse tubes are utilized for simulating arteries at each parts of different patients so as toaccurately simulate patient pulse tube data collected at a collection end, so that the accuracy of the pulse condition recurrence result is increased, the device and the method are applicable to thepatients in all ages and constitutions, and the misdiagnosing risk is reduced.

A gastrointestinal tract endoscope image preprocessing method including information screening and fusion repairing includes the steps that firstly, a key information extractor is used for extracting effective information areas in data set pictures twice, and the results of the two times of extraction complement each other and are stored as a new picture data set; brightness equalization and improvement are carried out on a new picture data set by using an improved EACE method, the overall brightness is improved while the defect of uneven brightness is improved, and more information beneficial to polyp identification is obtained; and light spot detection and light spot region repair are performed on the enhanced result by using a two-image matching fusion repair method. The interference of light spots in endoscope images on polyp detection results is reduced, and the misdiagnosis rate during polyp detection by doctors or computers is reduced.

The invention discloses a method related to limitation to content duplication of an electronic medical record editor. The method is completed according to the following steps of: giving a unique identification number A1 to to-be-duplicated medical record contents B in an electronic medical record; cascading the unique identification number A1 and the to-be-duplicated medical record contents B to obtain cascaded contents A1B; carrying out encryption on the cascaded contents A1B to obtain a ciphertext A1BJ; writing a specific paste format T into a clipboard of Windows; sending the ciphertext A1BJ into the clipboard of Windows; matching a specific paste format T1 of the ciphertext A1BJ with the specific paste format T; after matching is successful, acquiring the ciphertext A1BJ and carrying out decryption on the ciphertext A1BJ to obtain the cascaded contents A1B; and matching the unique identification number A1 in the cascaded contents A1B with a patient medical record unique identification number A of the electronic medical record editor, and if matching is successful, allowing medical record contents B to be pasted to a designated position of the electronic medical record editor. The method has the characteristics of reducing a misdiagnosis risk and preventing leakage of patient privacy.

The invention relates to a medical image processing method and device, a storage medium and computer equipment. According to the method provided by the invention, after the lung medical image is acquired, pulmonary nodule segmentation processing and pulmonary nodule symptom classification processing can be automatically performed, then the malignant grade information of the pulmonary nodule is automatically determined according to the pulmonary nodule size information and symptom information obtained through processing, and compared with a manual observation method, the processing efficiency of the method provided by the invention is higher; besides, the method is carried out by integrating multiple aspects of information such as underlying features (namely size information) and advanced semantic information (namely symptom information), the accurate pulmonary nodule malignancy level can be obtained, later-period further diagnosis and definite diagnosis can be effectively supported, and the later-period misdiagnosis risk is remarkably reduced.

The invention relates to a primer combination for embryo preimplantation hereditary hearing loss gene detection, a kit and application. A primer pair for PCR amplification is designed aiming at the coding region sequence of the hearing loss virulence genes GJB2 and SLC26A4, and the related SNP site on the 7th and/or 13th chromosome, enrichment can be conducted on the virulence gene target region through a target capturing technique, a library is built, then embarkation sequencing and haplotype analysis are conducted, and the primer combination can further be used for analyzing the related geneinformation, and has the important guidance and research value on auxiliary diagnosis and treatment of hereditary hearing loss. The primer combination can achieve synchronous detection and analysis of pathogenic variants and polymorphic sites, so that detection and linkage analysis of the pathogenic variants can be complete in the same reaction system, interference of artificial factors to the result can be reduced, the detection accuracy of detection can be improved, and the misdiagnose risks caused by ADO can be effectively decreased.

The invention belongs to the technical field of engine emission, and discloses an SCR system downstream temperature sensor credibility fault diagnosis method comprising the following steps: S1, calibrating a diagnosis enabling area according to SCR system working condition information; s2, according to an upstream nitrogen-oxygen sensor and a downstream nitrogen-oxygen sensor, obtaining the actually-measured flow of nitrogen-oxygen compounds, and calculating the SCR average efficiency within the set time period in the enabling area; according to a downstream temperature sensor, obtaining an SCR downstream temperature actual measurement value, and calculating the SCR downstream average temperature of the set time period in the enabling area; s3, calculating a theoretical threshold value of the SCR downstream temperature; s4, carrying out comparison, and if the SCR downstream average temperature is within the SCR downstream temperature theoretical threshold value, judging that the downstream temperature sensor is normal; otherwise, judging that the downstream temperature sensor fails. According to the credibility fault diagnosis method for the downstream temperature sensor of the SCR system, the diagnosis responsiveness is fast, the misdiagnosis risk is reduced, and the fault monitoring reliability is high.

The present invention relates to a diagnostic method for the detection and identification of tuberculosis and non-tuberculosis mycobacteria and the simultaneous confirmation of rifampin and isoniazidresistances of tuberculosis bacillus on the basis of a quanta matrix assay platform and a kit therefor.

The invention discloses a data-driven puffer disease monitoring, early warning and self-service diagnosis decision support system which comprises the steps of: 1, collection and integration of variousdata, 2, combing and representation of rules, experience or knowledge, and 3, early warning, diagnosis and decision support based on the rules, the experience or the knowledge. The system solves thedisadvantage of the existing puffer disease diagnosis technology; the data-driven method and a procedure achieving semi-automatic diagnosis of a puffer disease are provided; characteristic and basic diagnosis informatization management level of the puffer disease is raised; self-service diagnosis ability of the puffer disease is improved; and the monitoring, early warning and self-service diagnosis decision support system can effectively improve culture efficiency in large-scale culture.

The invention relates to artificial intelligence, and provides a medical database construction method based on artificial intelligence and related equipment. According to the method, user information corresponding to a plurality of information fields can be obtained from a plurality of preset medical systems, the user information comprises feature information and to-be-matched information, the information fields are analyzed to obtain field types, the text quantity of each information field is counted, the user information is subjected to structured processing to obtain structured information, a plurality of information fields are spliced to obtain matching fields, a field weight of each matching field is obtained, a common field of the feature information and the to-be-matched information is obtained and an initial weight is adjusted to obtain a matching weight, an information matching degree of the feature information and the to-be-matched information are generated according to the matching weight, and the user information is merged to obtain a matching result, and a global medical database is obtained, so that a global patient information database is accurately constructed. In addition, the invention also relates to the fields of block chain technology and digital medical treatment.

The invention relates to the technical field of rehabilitation medical chains and discloses a rehabilitation medical chain system and method based on the block domain technology. The system comprisesa distributed ledger; the medical record information of a user is recorded in the distributed ledgers, and a trust model is established in virtue of mathematics, so higher efficiency and lower cost are realized, and data does not need to be recorded again every time the patient sees a doctor; after a medical terminal verifies a secret key, the medical information data of the user in the distributed ledger can be accessed, so the privacy of the user is protected and privacy disclosure is prevented; the medical terminal can access similar medical record information of other users after verifyingthe secret key, so reference is increased, and treatment effect is better; when new doctor-seeing data is added to the medical terminal, if the new doctor-seeing data conflicts with previous doctor-seeing data, input can be prevented, so information errors are prevented, the accuracy of medical record data is guaranteed, and the risk of misdiagnosis is reduced; and the system and the method havethe advantages of novel design, high efficiency, reduction in cost, capability of preventing information errors, convenience in referring to and good privacy.

The invention discloses an early breast cancer detection medical imaging method based on electromagnetic inverse scattering. The method is used for reconstructing information such as the position, theshape and the size of a lesion location which may occur in internal tissues of a living body. After the data information is processed by an algorithm, a visual three-dimensional image can be presented, and the method has the advantages that hospital experts can observe the illness state of the patient more intuitively, and the possibility of artificial misdiagnosis is reduced. According to the scheme, in combination with a subspace optimization method, a novel three-dimensional method based on a differential integral equation model is provided to realize image reconstruction, and in addition,a singular value decomposition and truncation method is used, so that the stability and the accuracy of an iteration process are improved. The result shows that the proposed method not only has verygood convergence performance and fast operation speed, but also can reduce nonlinearity, and can very clearly invert the position size, shape and other information of the biological tissue in the lesion. Test results of multiple experiments verify the effectiveness of the method.

The invention provides a method and device for correcting uterine contraction pressure. The method for correcting uterine contraction pressure comprises the following steps: step 1, collecting uterine contraction pressure data in real time, detecting that whether pressure zeroing instructions are received or not at the current time, and skipping to the step 2 after the pressure zeroing instructions are received; step 2, carrying out processing and analysis on the uterine contraction pressure data before the pressure zeroing instructions are received, thus obtaining uterine contraction pressure correcting values; and step 3, replacing the uterine contraction pressure data before the pressure zeroing instructions are received with the uterine contraction pressure correcting values, and displaying the corrected uterine contraction pressure data. With the method and the device, the uterine contraction pressure data before pressure zeroing is corrected, so that the accuracy of the uterine contraction pressure data before pressure zeroing is guaranteed, the risk of misdiagnosis by a doctor is reduced, the repeated monitoring is avoided, thus the monitoring time and medical resources are saved, and the monitoring efficiency is improved.