11 results about "Laboratory results" patented technology

The invention relates to a large-scale language model-based solid waste cementing material intelligent design and performance prediction system, and relates to the technical field of material science and artificial intelligence, the system integrates multi-source heterogeneous data through a multi-task data set construction module, and establishes association mapping of a solid waste material formula and performance; the performance prediction module based on the large-scale language model realizes high-precision cross-modal prediction of key indexes such as compressive strength and permeability; the reverse design module generates a formula scheme conforming to chemical components and industrial constraints through dynamic embedding of material scientific rules and reinforcement learning multi-objective optimization, and forms a closed loop verification link based on physical rule verification and an experimental feedback mechanism. The research and development efficiency of the solid waste cementing material is remarkably improved, the trial and error cost and resource waste are effectively reduced, rapid conversion of laboratory achievements to industrial production is promoted, and intelligent technical support is provided for solid waste resource utilization and green building material development.

The invention relates to the technical field of chronic disease health management, and discloses a chronic disease health management method based on data analysis, and the method comprises the following steps: S1, obtaining medical records, wearable device data, laboratory results, self-reporting information and environment data of a patient through a multi-source collection gateway; and S2, performing desensitization processing and feature extraction on the data under a federated learning framework, and generating a multi-modal patient portrait containing time sequence, spatial features and biomarkers. According to the chronic disease health management method and system based on data analysis, through desensitization processing under a federated learning framework, on the premise of protecting patient data privacy, medical records, wearable device data, environment data and other multi-source information are effectively integrated, a comprehensive multi-modal patient portrait is formed, and the patient experience is improved. The problem that data are mutually separated in a traditional management mode is solved, and comprehensive data support is provided for subsequent risk prediction and intervention decision making.

Methods, apparatus, and computer-implemented methods are provided for training machine learning (ML) techniques to generate a property model for predicting whether a compound has a particular property. An iterative process / feedback loop can be performed to generate a property model, the process including generating, based on the property model, a list of prediction results for a plurality of compounds and their association with the particular property, validating the property model based on compounds from the list of prediction results having an association with the particular property, and updating the property model based on the property model validation. The process / loop can be repeated using the updated property model until it is determined that the property model has been effectively trained. The property model validation can include selecting a list of compound candidates, performing simulation analysis and / or laboratory analysis on the list of compound candidates for association with the particular property, and updating the property model using the simulation and / or laboratory results.

Aspects relate to a method, a data processing system, a laboratory instrument, a computer program, and a computer readable medium. The method includes obtaining, by a computing device, a relationship result of a first clinical test. A first clinical test is performed on a biological sample by a first laboratory instrument, the biological sample being in a sample container. The relationship result includes first information and second information, the first information specifying that a laboratory result of the first clinical test is outside a reliability range of the first clinical test performed by the first laboratory instrument, and the second information specifying one or more of an upper bound and a lower bound of the reliability range. The method further includes evaluating, by the computing device, whether a condition of the laboratory rule is determinable by using the first information and the second information. The laboratory rule specifies one or more actions to be taken depending on the result of the determination of the condition. At least one of the one or more actions is to be taken on one or more of the biological sample, the sample container, and the relationship result, and / or the one or more actions include displaying information about one or more of the biological sample, the sample container, the relationship result, and the patient. If the condition may be determined and one or more actions are to be taken according to a result of the determination of the condition, the method includes causing, by the computing device, the one or more actions to be taken.

According to one aspect, there is provided a computer-implemented system for evaluating and improving strain production using three integrated components: a prototype system for evaluating candidate strains, an optimization system for enhancing strain performance, and a scale-up system for adapting laboratory results to commercial-scale parameters. The system employs artificial intelligence models trained on data from all three components. The system continuously receives performance data from these systems to update its AI models. Using these updated models, the system generates modified operational parameters for the prototype, optimization, and scale-up systems, creating a feedback loop for continuous process improvement.

The present disclosure proposes an adult early warning system (EWS) (100) for predicting clinical deterioration and mortality risks in patients. The EWS (100) integrates via API, utilizing REST API and HTTPS for secure communication. It features an input module (112) for authenticating and validating data, which is transmitted through a network (102) to a server (104). The server (104) processes data through data collection, standardization, and pre-processing modules (122, 124) before it is analyzed by the prediction module (116). Results are aligned with the clinical pathway module (118) and presented by the risk prediction response and patient overview dashboard module (120), which provides risk scores, and graphical representations of vitals, lab results, and ECG data. The EWS (100) supports clinicians by enhancing decision-making and adhering to ISO standards for patient safety and reliability.

The invention relates to a text information and laboratory result feature extraction method and device based on a large language model. The method comprises the following steps: obtaining text information to be subjected to feature extraction and a laboratory result; converting a laboratory result into a laboratory result text through a preset format, and taking the laboratory result text and the text information as a text to be subjected to feature extraction; performing text preprocessing on the text to be subjected to feature extraction to obtain a preprocessed text; and inputting the preprocessed text into a pre-trained LLM model, and outputting a word-level vector and a sentence-level vector. According to the text information and laboratory result feature extraction method and device based on the large language model, text information and laboratory result feature extraction is carried out based on the LLM model, and the efficiency of related workers can be greatly improved. The invention belongs to the application of machine learning in the field of text recognition.

The invention discloses a multifunctional dynamic sealing element ultra-high-speed wide-temperature-range environment frictional wear detection system, which can simultaneously simulate multi-physics-field coupled extreme working conditions such as ultra-high-speed rotation, wide temperature range, oil pressure environment and axial / radial mechanical load, and accurately reproduce actual working environments of dynamic sealing elements in high-end equipment such as aero-engines and high-speed trains. Compared with traditional equipment which only carries out single-factor or material-level testing, the consistency of testing data and practical application is remarkably improved, the problem that the deviation between laboratory results and engineering practice is large is effectively solved, the extreme service working condition is truly reproduced, and the testing reliability is improved; according to the invention, three test modules are integrated, namely an end face sealing element test module, a three-valve ring sealing element test module and a circumference sealing element test module, and parts of the modules can be shared; by means of the multifunctional integrated design, the same device can be compatible with performance evaluation of dynamic sealing pieces of different structural forms, the utilization rate of the device is greatly improved, and the research and development cost is reduced.

This invention proposes a method for determining the source of large-particle slag inclusions at defects in rolled steel plates, belonging to the field of iron and steel metallurgy technology. The method includes: determining the optimal tracer and its content through laboratory experiments; based on the laboratory results, adding the optimal tracer to the slag in a predetermined manner at a specific process stage in industrial steelmaking, controlling the addition ratio to ensure tracer effectiveness; finally, collecting samples from the defects in the rolled steel plates and analyzing the inclusion composition using an electron microscope; if tracer elements are detected, the inclusion is determined to originate from the process stage where the tracer was added. This invention, by combining laboratory pre-screening with industrial testing, improves the accuracy and efficiency of inclusion source location, providing key support for steelmaking process optimization.

An explainable artificial intelligence system for early prediction of missed severe diagnoses in intensive care unit patients is provided. The system comprises a data processing module configured to receive and process electronic health record data including patient demographics, vital signs, laboratory results, and diagnostic codes. A machine learning module with ensemble, deep learning, and large language models analyzes processed data to predict likelihood of severe diagnoses including acute myocardial infarction, acute pulmonary embolism, bacterial pneumonia, aortic dissection, meningitis, spinal abscess, bacterial endocarditis, and arterial thromboembolism. An explainability module generates feature importance rankings and provides interpretable explanations for predictions.

The invention provides an accelerated simulation evaluation method for the service life of a wind power blade coating, and the method comprises the steps: calculating effective impact kinetic energy when a to-be-tested blade coating fails through laboratory accelerated rain erosion test parameters and rain erosion test time based on an effective impact kinetic energy equivalence principle; and establishing a relation between a laboratory result and an actual service life for evaluating the service life of the wind power blade coating. The accelerated simulation evaluation method for the service life of the wind power blade coating is accurate in evaluation result, can directly draw a conclusion according to meteorological data published by the country, is convenient and rapid, and is suitable for multiple wind fields.