490results about "Patient healthcare" patented technology

Described herein are methods and systems useful for characterizing clinical outcomes of a subject. Provided herein includes computer-assessed methods, medical information systems, and computer-readable instructions that can aid an end-user in diagnosis, prognosis, and treatment of a clinical outcome.

A therapy delivery system having an open architecture and method of providing thereof are disclosed. The present invention provides a therapy dosage module having a control algorithm that can be replaced with a predefined or independently defined control algorithm. The tools necessary to create and test such control algorithms in the therapy dosage module in a simulated environment before implementing it in a live therapy system are also disclosed.

A system for optimizing a patient's insulin dosage regimen over time, comprising at least a first memory for storing data inputs corresponding at least to one or more components in a patient's present insulin dosage regimen, and data inputs corresponding at least to the patient's blood-glucose-level measurements determined at a plurality of times, and a processor operatively connected to the at least first memory. The processor is programmed at least to determine from the data inputs corresponding to the patient's blood-glucose-level measurements determined at a plurality of times whether and by how much to vary at least one of the one or more components in the patient's present insulin dosage regimen in order to maintain the patient's future blood-glucose-level measurements within a predefined range.

A system and method is provided for processing audit records indicating events associated with particular users initiating actions performed on particular objects. The system of the invention comprises an acquisition processor for acquiring message data including data representing an audit record of a particular type, an audit data processor for, creating a copy of the received audit record, communicating data representing the received audit record to a destination in response to predetermined configuration information that determines audit record processing requirements, receiving message data indicating confirmation that the destination has successfully received the communicated audit record, and re-communicating a copy of the received audit record to the indicated destination, in response to failure to receive a confirmation.

Systems and methods are provided for calculating athletic activity parameters. Multiple housings are position at different locations on a user's body. The housings are configured to be removably engaged with an electronic module that includes a sensor and a processor configured to calculate athletic activity parameters. Each housing is connected to or includes an identification memory that stores information identifying a location of the housing. The electronic module uses the location information to select an algorithm to use when calculating the athletic activity parameters.

The invention belongs to the technical field of medical data management, and relates to a medical record storage, sharing and security claim settlement model and method based on a block chain. Firstly, credible sharing of medical data of patients among medical institutions is achieved through the blockchain technology, and a lifelong medical record is established for the patients; based on a Hashchain type storage structure, the medical data cannot be tampered; secondly, an improved CP-ABE-based cryptographic primitive SHDPCPC-CP-ABE is proposed, security encryption and fine-grained access control on the medical data are realized, and a patient can conveniently and efficiently access and authorize a medical institution to read the medical data; and finally, a Paillier homomorphic encryption technology is utilized to realize safe medical insurance claim settlement, and the privacy of the patient is protected when the patient interacts with a third-party non-medical institution. According to the invention, security, confidentiality, reliability and integrity of medical data can be realized, and confidential sharing of private data is supported.

A system for optimizing a patient's insulin dosage regimen over time, comprising at least a first memory for storing data inputs corresponding at least to one or more components in a patient's present insulin dosage regimen, and data inputs corresponding at least to the patient's blood-glucose-level measurements determined at a plurality of times, and a processor operatively connected to the at least first memory. The processor is programmed at least to determine from the data inputs corresponding to the patient's blood-glucose-level measurements determined at a plurality of times whether and by how much to vary at least one of the one or more components in the patient's present insulin dosage regimen in order to maintain the patient's future blood-glucose-level measurements within a predefined range.

The invention discloses a medical data platform based on the block chain technology. The medical data platform comprises a terminal, a server module, a data storage module and a block chain network. The terminal exchanges data with the data storage module and the block chain network through the server module. The server module comprises a communication server, an intermediate certificate server and a root certificate server and is used for processing data interaction between the modules and allocating certificates to the block chain network nodes. The data storage module comprises a medical information system and a distributed image database and is used for data storage. The block chain network comprises multiple institutional accounting nodes and multiple consensus nodes. The accounting nodes perform mutual data synchronization. The medical data platform based on the block chain technology has the advantages that the existing medical information is stored in the block chain shared account book so that all the medical institutions can share the medical information related to the patients, and the privacy protection function of the medical data can be realized by using the encryption algorithm and thus sharing of the medical data can be facilitated and the security of the sensitive information can also be protected.

The invention belongs to the field of data information safety technology, and discloses a medical data sharing system based on Blockchain technology and a designing method. The medical data sharing system based on the Blockchain technology comprises components of a data uploader, a data manager, a data requester, alliance chain nodes and a system administrator. In the system, the data uploader utilizes AES for encrypting the medical data, thereby effectively protecting medical data privacy, and realizing high-efficiency medical data storage. Furthermore according to a symmetric key in the AESis encrypted according to the CPABE, thereby ensuring a fact that only the data requestor with an attribute that satisfies a preset accessing strategy structure can perform deciphering for obtaining the symmetric key, realizing fine-grained access control of the medical data, and realizing supports for accessing control of the temporary request data in an emergency. Obviously, the system and the method effectively settle existing problems based on a Blockchain medical data sharing system and safely and efficiently provides services such as medical data storage, fine-grained access control andsharing.

The invention relates to a medical text relation extraction method based on a pre-training model and a fine tuning technology. The method comprises the steps of preprocessing of medical relation extraction corpora, model pre-training and fine tuning. According to the method, the pre-training model is used as the input of the one-dimensional convolutional neural network model, but the word embedding is used as the input of the one-dimensional convolutional neural network model in the prior art, and the pre-training model is more favorable for improving the extraction performance of the medicaltext relationship compared with the word embedding; according to the method, the one-dimensional convolutional neural network model and the pre-training model are combined for use, and the one-dimensional convolutional neural network is used for finely adjusting the pre-training model, so that the performance of the model is improved; the training error of the one-dimensional convolutional neuralnetwork is propagated back to a pre-training model to realize a model fine tuning process which is a dynamic model training process; in a traditional method, word embedding is combined with input of different layers, a main task model is still trained from the beginning, pre-trained embedding is regarded as a fixed parameter, and the usability of the method is limited.

An embodiment of the invention provides a mass medical data storage system and a data storage method suitable for files of different sizes and belongs to the technical field of data storage. Aiming atapplication scenes with coexistence of mass large files and small files in the medical field, the system solves a problem that a traditional relational database is not suitable for unstructured data,a problem that redis is not suitable for mass data storage, a problem of system instability when only hbase is adopted for storage and problems of inadaptability to large files and inconvenient fileretrieval when hdfs is adopted merely for solving a problem of small file storage.

The invention discloses a medical big data multi-center integration platform and method. Data of each data branch center server are accessed to a data center server and subjected to quality assessment, and a next step is entered if the quality assessment passes; if the quality assessment fails, the data center server feeds back the conclusion of failure to each corresponding data branch center server; the quality assessment includes the assessment of data integrity, data repetition rate, data bias and data size; the data center server establishes and maintains standard variables and a standarddictionary, meanwhile, preprocesses the data according to the standard variables and the standard dictionary; the data standardization processing includes standardization of the variables and standardization of data values; a one-to-one mapping relationship between data variables of the data branch center servers and the standard variables of the data center server is established by means of a similarity matching algorithm and manual auditing; and the data standardized by the data center server are utilized.

The invention provides a knowledge graph establishing method and device based on medical and health big data. The method includes the steps of establishing a data model for defining at least one entity, at least one property corresponding to the entities and at least one relation, for all medical data sources, collecting entity type field content, property type field content and relation type field content in the current medical data sources, executing corresponding filling on the collected field contents based on the data model to establish knowledge graphs, and for all the established knowledge graphs, when a first field content in another knowledge graph is consistent with the second field content in the current knowledge graph, fusing the two field contents. The knowledge graphs are established based on the medical and health big data, redundant data is removed through alignment and fusion of the knowledge graphs, the information association degree of the established knowledge graphs is high, and the knowledge graphs established through the method can make obtained individual information more comprehensive.

The invention discloses a multi-center medical term standardization system based on a general medical term library. The system comprises a source database, a database connection management module, a pre-analysis module, a term mapping unit, an incremental updating module, an exception handling module and a multi-center interaction module. According to the method, the problem of medical term standardization of multiple medical data centers is solved, and the consistency of medical term expression of each medical data center is kept; the scanning and analysis of a medical data center source database are automatically realized, and the automatic mapping of medical terms with standard codes is realized on the basis; the inevitable complexity of medical term mapping is fully considered, and a spiral rising process from automatic mapping to fuzzy matching mapping and then to custom term mapping is realized; the incremental updating mechanism makes full use of previous mapping records, greatly reduces the pressure of subsequent work, and greatly improves the standardization degree of medical term mapping.

The invention discloses a clinical data standardization system and a standardized data acquisition method. The system comprises a standardized data acquisition platform, a data inspection platform anda business system; the standardized data acquisition platform comprises an in-row standard configuration module, a follow-up visit plan configuration module, a scientific research metadata managementmodule, a scientific research case management module, a standardized maintenance module, an acquisition module, a service interface module and an eCRF management module. The data acquisition method comprises the following steps: enabling a doctor workstation to generate a service application form and service system data based on the content to be followed by a patient, performing data cleaning and conversion through a standardization pool, and automatically filling a disease library of the eCRF management module after standardization processing. Under the condition of fully fusing standard codes and service interfaces in the biomedical field at home and abroad, the background annotation is carried out on differentiated standards, the differentiated standards are integrated into a dictionary, different standard backgrounds are compiled, and then correction is carried out through an algorithm, so that errors are reduced, and the bias rate is reduced.

The disclosure relates to systems and methods for facilitating communication between a web application and a local peripheral device through a native service where the local peripheral device is locally connected to a computer having the native service. To access data associated with the local peripheral device, a browser may make a cross-domain request to the native service that resides in a domain that is different from the domain that served the web application. Prior to sending the actual cross-domain request, the browser may send a pre-flight cross-domain request to the native service. The native service may send a response to the pre-flight request to the browser. The response may comprise information related to whether the cross-domain request can be serviced by the native service. The browser may send the cross-domain request to the native service, which may comprise functions to be executed on the local peripheral device.

A therapy delivery system having an open architecture and method of providing thereof are disclosed. The present invention provides a therapy dosage module having a control algorithm that can be replaced with a predefined or independently defined control algorithm. The tools necessary to create and test such control algorithms in the therapy dosage module in a simulated environment before implementing it in a live therapy system are also disclosed.

The invention discloses a medical data sharing method based on a block chain, and the method comprises the steps that a medical data owner authorizes to upload personal medical data on the premise of desensitizing private data; medical institutions and hospitals serve as data keepers, unify the format of data through the standard protocol layer, standardize data writing based on the blockchain smart contract, and store the data in the blockchain system; a medical industry ecological data sharing and intercommunicating mechanism is established through the block chain, and alliance members joining the block chain equalize the rights and interests of the shared data after getting through; unified and standardized user medical data are provided for the outside, mechanism nodes on the block chain achieve comprehensive data intercommunication, and effective utilization and privacy protection of the medical data are guaranteed.

The invention provides a medical text named entity recognition method based on a pre-training model and fine tuning technology, and the method comprises the steps: firstly carrying out the pre-training of a BERT pre-training model through a large-scale unstructured electronic medical record and other medical texts, so as to train a pre-training model containing semantic representation informationin a text; and carrying out fine tuning on the generated pre-trained model by utilizing the stacked extended convolutional neural network so as to obtain a deep neural network model capable of carrying out automatic identification on the named entities in the medical field. According to the pre-training model provided by the invention, semantic information in the text can be captured more accurately, the semantic information can be migrated to a specific task more effectively, and the named entity recognition accuracy of the model is improved. The stacking expansion convolutional neural network and the pre-training model are combined to finely adjust the model, and finally, the named entities of the medical text are identified, so that semantic information in the text can be well captured,and parallel computing can be performed to improve the model training speed.

A method, system and computer readable medium for tracking changes in average glycemia in diabetes is based on a conceptually new approach to the retrieval of SMBG data. Using the understanding of HbA1c fluctuation as the measurable effect of the action of an underlying dynamical system, SMBG provides occasional glimpses at the state of this system and, using these measurements, the hidden underlying system trajectory can be reconstructed for individual diabetes patients. Using compartmental modeling a new two-step algorithm is provided that includes: (i) real-time estimate of HbA1c from fasting glucose readings, updated with any new incoming fasting SMBG data point(s), and (ii) initialization and calibration of the estimated HbA1c trace with daily SMBG profiles obtained periodically. The estimation of these profiles includes a factorial model capturing daily BG variability within two latent factors.

The invention discloses a medical language text processing method and device and a storage medium, the method comprising the following steps: receiving medical language text input by a user, and performing word segmentation operation on the medical language text according to a preset word segmentation thesaurus to obtain words corresponding to the medical language text; extracting keywords corresponding to the medical language text according to a preset medical vocabulary; classifying the obtained plurality of the keywords to obtain corresponding classification results. The invention improvesthe accuracy and professionalism of processing medical language texts, and does not need to consume a great deal of energy of medical practitioners, thereby improving the working efficiency of medicalpractitioners.