6711results about "Electronic clinical trials" patented technology

This application describes, among other things, systems and methods for deploying a task-specific machine-learning model. An example method includes receiving a prompt associated with one or more commands and a plurality of tokens. A first task-specific machine-learning model is identified based on a first command of the one or more commands. Some or all of the tokens of the plurality of tokens are applied to a node associated with the first task-specific machine-learning model, and a plurality of restricted data is received. Based on evaluating the plurality of restricted data, a correlation between the first node and a second node is determined. If the correlation satisfies a threshold condition, a plurality of text data different than the prompt is generated, otherwise the some or all of the tokens are again provided to the first node. Some or all of the tokens are then traversed and applied to the second node.

This application describes, amongst other things, methods and systems for building and deploying agents. An example method includes obtaining orchestration data about a set of task-specific components selected to provide a response to the prompt, where each respective task-specific components in the set of task-specific components is configured to assist with a respective clinical task of the one or more clinical tasks. The method further includes, determining an order in which each respective task-specific components of the set of task-specific components should be utilized to prepare a complete response to the prompt that address the one or more clinical tasks based on the obtained orchestration data about the set of task-specific components. The method also includes, in accordance with the determined order, providing first data related to the prompt to a first task-specific component and receiving a first response from the first task-specific component.

A dialogue system, comprising: an input configured to receive input data relating to speech or text provided by a user; an output configured to provide output data relating to speech or text to a user; and one or more processors, configured to: receive, by way of the input, input data relating to speech or text provided by a user; provide the input data to a subject safety module, the subject safety module configured to receive the input data and evaluate the input data before a system response is output, evaluating the input data comprising performing a first determination on the input data using a matching module and a second determination on the input data using a trained model, wherein the matching module performs the first determination to determine whether the input data matches one or more items from a pre-determined set of one or more items; generate a system response using a first process or using a second process, wherein the first process uses at least one trained language model to generate a dynamically determined system response and wherein the second process retrieves a pre-determined system response, wherein a selection between the first process and the second process is made based on the evaluation of the input data; output, by way of the output, the system response.

Described herein are a system, method, and device for configuring a generative machine learning model using a syntactic interface. A system may include a user interface, a memory, and a processor configured to, using a syntactic interface displayed using the user interface, receive a syntactic interface input from a user; identify an electronic medical record (EMR) by generating an EMR database query as a function of the syntactic interface input, querying an EMR database using the EMR database query, and receiving, from the EMR database, an EMR database response; generate a prompt as a function of the syntactic interface input; generate a first generative model output as a function of the prompt and the EMR using a trained generative machine learning model; and using a conversational interface displayed using the user interface, display the first generative model output to the user.

The invention discloses a chronic disease early detection method and system based on a multi-modal large model, and relates to the technical field of intelligent medical treatment and artificial intelligence, and the method comprises the steps: obtaining a multi-modal data stream of a target user in a target time window from a pathology database, and generating an original multi-modal data set; performing timestamp unification and numerical value standardization processing on the original multi-modal data set to obtain a time sequence feature sequence; inputting the time sequence feature sequence to the multi-modal large model to obtain an abnormal symptom feature; calculating the similarity between the abnormal symptom features and feature vectors of marked cases in a historical case library, and determining matched cases; a diagnosis result and a development process of the matched case are extracted, a disease risk level and a development trend corresponding to the original multi-modal data set are determined in combination with the medical knowledge graph, and a pathology assessment result is obtained; and generating an early warning signal containing the risk type and the intervention suggestion according to the pathological assessment result. By implementing the application, the accuracy of early detection of chronic diseases can be improved.

Apparatus and associated methods relate to automatically generating secured artificial intelligence input packages from sensitive data input. In an illustrative example, a sensitive questions answering system (SQAS) may receive a natural language input (NLI). For example, the SQAS may retrieve sensitive data related to the NLI. In some implementations, the SQAS may be configured to desensitize the sensitive data and / or generate a secured user input and media objects to be combined into a secured LLM (large language model) input array. For example, the secured LLM input array may be provided to an unsecured LLM to generate a human-readable response (HRR). In some implementations, a sensitized response may be generated by reintroducing some of the sensitive data to the HRR. For example, the sensitized response may include personal data. Various embodiments may advantageously ensure the secure handling of sensitive data while providing personal responses to user queries.

Provided is a method including obtaining a prompt, determining a prompt embedding vector representing the prompt in an embedding space, modifying the prompt embedding vector using a trained model configured to adjust prompt embedding vectors to decrease proximity to vectors of blocks in a data set from which data is retrieved to augment generation by the generative AI model, determining that the modified prompt embedding vector is within a threshold distance to vectors in the embedding space corresponding to one or more blocks in the data set, selecting the one or more blocks in the data set, generating a response using the generative AI model based on the selected one or more blocks in the data set, quantifying an amount of influence of the respective block on corresponding text in the generated response, and providing the response and a representation of the quantified amount of influence as an output.

The invention relates to the technical field of health monitoring, in particular to a cardiovascular disease data fusion and multi-dimensional health assessment method, which comprises the following steps of: acquiring multi-source data of a patient through a sensor and wearable equipment, preprocessing the acquired data, ensuring data integrity, extracting physiological features by adopting a convolutional neural network, and evaluating the health of the patient. The method comprises the steps of extracting non-physiological data features through principal component analysis, constructing a multi-dimensional feature set, identifying cardiovascular disease related risk factors through a random forest algorithm, distributing weights through a logistic regression algorithm to generate individualized risk scores, analyzing time sequence trends of the risk factors based on a long and short-term memory network model, and generating dynamic risk scores in real time. When the score exceeds a preset threshold value, an early warning mechanism is automatically triggered, and a patient and medical staff are notified through an application program; according to the method, accurate assessment and personalized intervention of cardiovascular health are realized through multi-source data fusion and dynamic analysis, and the method has high efficiency and timeliness.

Provided is a method, including obtaining data associated with clinical trials, storing the obtained data into a repository by preprocessing the data to standardize diverse input formats into unified data model and organizing the stored data into a schema designed to integrate data of diverse input formats, indexing the stored data and analyses performed on the stored data, selecting one or more visualizations responsive to the query by selecting one or more visualizations as being responsive to the query based on metadata associated with each of the one or more visualizations, determining whether the stored data is associated with a plurality of metadata requirements of each of the one or more visualizations, dynamically generating executable code configured to generate the one or more visualizations responsive to the query, executing the generated executable code, and providing a response to the query.

The invention relates to the technical field of smart communities, and discloses a smart community resident health management method based on machine learning, and the method comprises the steps: continuously collecting the health feedback data of residents, such as the physical condition change after outdoor activities, carrying out the correlation analysis of the health feedback data with the previous health data and environment data, dynamically updating and optimizing a correlation model, and obtaining the health feedback data of the residents; the prediction precision of the model and the effectiveness of suggestions are improved, the relationship between the use condition of the community public space and the resident health indexes is analyzed, key public facilities and areas influencing resident health are identified, data support and decision basis are provided for community planning and facility reconstruction, and the method is suitable for popularization and application. Community resident health and environment condition analysis reports are generated regularly, and resident health index change trends are visually displayed for reference of community managers and residents. According to the invention, intelligent analysis and application of environment and health data are realized, and technical support is provided for building a healthy community.

An apparatus and method for real-time assessment and mapping of quality of life indicators includes: selecting a set of quality of life dimensions, receiving objective quality of life indicators based on the quality of life dimensions, receiving subjective quality of life indicators based on the quality of life dimensions, performing a statistical analysis on the objective quality of life indicators and the subjective quality of life indicators, storing the objective quality of life indicators, the subjective quality of life indicators, and the results of the statistical analysis in a database, and outputting the objective quality of life indicators, the subjective quality of life indicators, and the results of the statistical analysis.

The current disclosure provides methods for an automated clinical recommendation system that generates clinical recommendations for patients of a health care system based on natural language queries submitted by care providers of the health care system. The natural language queries may be typed into a user interface (UI) of the clinical recommendation system, or submitted by voice via a microphone. The clinical recommendation system provides a clinically explainable disease state of a patient based on patient data included in a query, and recommends a next course of action (e.g., a treatment) based on clinical guidelines and population statistics, in a manner that reduces a current burden of clinicians in consulting digital clinical manuals via a series of time-consuming and cumbersome interactions with a graphical user interface (GUI) of the digital clinical manuals.

A user question can be classified into topics and mapped to appropriate static and / or dynamic content related to the user and / or question. This data can then be collectively provided to a large language model in order to generate a suitable response, which may include, for example, summarization, rephrasing, analysis, and the like, as well as executable code for dynamically presenting content of the response to the user and / or functionally adapting a user platform according to the response.

Embodiments described herein provide for a healthcare ecosystem of computing devices participating as nodes of a distributed ledger (e.g., blockchain). The distributed ledger includes NFTs representing corresponding patients, where the initial NET behaves logically as a token scaffold that represents a “digital twin” of the particular patient. The initial patient token represents personal profile data of patient personal data for the patient. The nodes may generate new data and / or new sub-tokens (or other blockchain entry type) representing new data, which the nodes associate with the token scaffold. The sub-tokens contain data for representing physical or digital specimens, health data, and data derived from the health data (e.g., cell lines, organoids, other model systems). As the nodes generate and associate new sub-tokens to the patient's token scaffold over time, the token scaffold graphs and facilitates integration of patient-specific data and evolves into a robust electronic health record (EHR) and digital twin.

Devices, systems, and methods for providing a patient with a personalized digital healthcare assistant. A medical history and biometric information for a patient are received by a computing device. A text conversation is conducted with the patient using a large language model (LLM) through a user interface (UI) to obtain a plurality of responses. The medical history, the plurality of responses, and the biometric information are stored in the non-transitory computer-readable memory medium. An intervention proposal is determined using a machine learning software based at least in part on the medical history, the plurality of responses, and the biometric information, and the intervention proposal is displayed on a display.

The present invention provides a clinical trial full-cycle intelligent management and risk warning analysis method and an intelligent agent, which relate to the technical field of clinical trial management, including collecting clinical trial data, extracting time-frequency features through nonlinear dynamic projection, spectral decomposition network, and wavelet Hilbert transform, and obtaining key feature signals using a dynamic compressed sensing model; generating a feature association network through manifold learning, constructing a nonlinear state migration field using stochastic differential equations, and capturing risk state mutation points in combination with an adaptive sampling strategy; obtaining a risk accumulation level through a dynamic prediction system, bifurcation theory, and singular spectrum analysis; based on the risk accumulation level, setting a dynamic warning threshold using critical state theory, and when the risk enters the threshold interval, starting a multi-objective optimization decision maker to calculate the optimal intervention strategy, performing risk regulation on the state migration field through a nonlinear response function, and feeding back the intervention results to iteratively optimize the risk warning.

Systems and methods for optimizing large language models with meta learning and chain of thought. A large language model (LLM) can be fine-tuned by generating optimized prompts based on an associated score of a generated output relative to a target output of a LLM-based optimizer using tuples of questions and the prompts generated from a dataset. Core features from the dataset that obtained top-ranked associated scores for the optimized prompts can be learned by utilizing chain of thought mechanism with the LLM-based optimizer. A meta prompt from the core features can be generated with the LLM-based optimizer to perform downstream tasks with the LLM.

A computer-implemented system and method for predictive risk assessment and intervention includes a risk assessment unit that processes survey data through an integrated database architecture. The system employs machine learning algorithms to analyze relationships between community and personal risk factors, maintaining real-time correlation coefficients and reliability metrics in a geospatial database. Machine learning algorithms may process factor analysis results to generate risk prediction quotients and determine intervention thresholds. The system automatically recalibrates based on intervention outcomes, continuously updating statistical relationships while preserving geographic and demographic associations. The database architecture coordinates multiple specialized components, enabling real-time analysis of risk patterns and automated generation of evidence-based intervention recommendations. The machine learning implementation continuously improves prediction accuracy through automated learning, while maintaining statistical validity through reliability calculations and correlation analysis.

A personal health assistant (PHA) chatbot system employing large language model (LLM) to a) receive a patient query; b) prompt for a patient identifier and a personal medical inquiry record; c) create a prompt record based on a patient-specific datum stored in secure medical profile; d) creating a dynamic prompt characterized by the prompt record; and e) updating an avatar-based interface based on the dynamic prompt. Patient-specific data (e.g., medical history, medications, and allergies) associated with the patient identifier may be updated with a patient profile change retrieved from an external data source(s) across a network interface (e.g., an electronic medical record (EMR)). The system matches common health issue types (e.g., location, medications, genetics, medical history, activities, environmental exposures), as well as other pertinent variables (e.g., language, culture, age, gender, and / or ethnicity) to the patient-specific data to deliver a medical recommendation and / or a personalized health advice through a user-tailored avatar.

The invention relates to the technical field of skin disease health evaluation, in particular to a skin disease health evaluation system integrating multiple clinical evaluation tools. Comprising a patient information management and dynamic risk assessment module, a skin microbiome analysis module, a symptom quantification and assessment module, a physiological index monitoring module, an environmental adaptability monitoring module, an intelligent decision support module and a feedback and optimization module. The method comprises the steps of performing dynamic risk assessment in combination with a machine learning algorithm, performing quantitative assessment on the skin health state of a patient in combination with microbiome analysis and real-time physiological index monitoring, performing quantitative assessment on symptoms through an image analysis technology and a standardized questionnaire, and generating a personalized health assessment report and a treatment scheme by using a deep neural network and an optimization algorithm. Continuously improved closed-loop management is realized through a feedback optimization module; according to the invention, not only is a scientific evaluation basis provided for doctors, but also a patient can obtain customized treatment suggestions.

This application describes, among other things, machine-learning models for performing specific clinical tasks. An example method includes receiving a prompt at a first computing system in communication with a machine-learning model trained to assist in performing a clinic task that includes generating a report of a patient's medical records, guiding a patient through a care plan, creating patient care guidelines based on a patient's health profile, identifying patients requiring follow-up at a hospital, identifying changes in a standard of care for a disease setting, or evaluating unstructured data associated with a patient to identify a cohort of similar patients. Based on the prompt, a natural language response is generated that is responsive to the prompt and is based on an analysis by the machine-learning model of a repository of data that is determined to be relevant to the prompt. And the natural language response is provided to second computing system.

The present disclosure generally relates to systems and methods for trigger risk, substance use, and / or undesirable behavior detection. In exemplary embodiments, a system is configured to be operable for identifying trigger risk(s), undesirable and / or desirable behavior(s) and / or substance (ab)use and / or addictive activity(ies) of one or more entity(ies) and determining and implementing action(s) or pre-empting and / or mitigating undesirable behavior(s) and / or encouraging and / or facilitating desirable behavior(s). The system comprises a plurality of digital and / or physical constructs and / or engines operable for providing various capabilities. The system is configured to be operable for providing a plurality of data from sensor(s), sensor array(s), device(s), system(s), and / or network(s) to the plurality of digital and / or physical constructs and / or engines.

A computer-implemented method includes receiving patient responses over a network from a recorded screening interview, utilizing a custom Large Language Model (LLM) to generate transcriptions and insights from the audio, performing video sentiment analysis to assess emotional states, and based on these data, generating an AI model to predict risk levels for various mental health conditions. The method further comprises presenting personalized questions based on previous screening insights, creating longitudinal summaries of patient histories, continuously improving the AI models through reinforcement learning, and integrating a recommendation engine to suggest targeted interventions. Additionally, the method includes tracking outcomes over time and enabling causal inference across multiple screenings, thereby providing a comprehensive platform for mental health assessment, intervention, and outcomes tracking.

This application describes, among other things, systems and methods for interacting with a task-specific orchestration. An example method includes obtaining medical data from one or more data collections. A set of user interface elements is presented at a user interface, where each respective user interface element of the set of user interface elements represents a respective task-specific orchestration that includes one or more respective machine-learning models fine-tuned for a specific task or domain based on the medical data. When a user interface element representing a respective task-specific orchestration is selected, at least some of the medical data is provided to the respective task-specific orchestration, and a different user interface is presented for communicating with the respective task-specific orchestration. Based on receiving a prompt at the different user interface, a response object is generated by the task-specific orchestration based on the prompt and at least some of the medical data.

A computer implemented method for governing risk actions by an artificial intelligence (AI) browser, by classifying a proposed action by the AI browser based on a large language model (LLM) as safe or risky based on AI weights or based on policy rules; initiating a step up authentication flow for a risk action; presenting an action summary and required capabilities to the user for approval; and enforcing user configured spend or scope limits on the risk action.

A computer-implemented method is disclosed for generating structured data representations from unstructured input text sequences through a neural network-based extraction pipeline. The method involves acquiring input text sequences and processing them with an extraction neural network to produce output text sequences. Each output text sequence includes embedded delimiter tokens that annotate specific text segments, mapping them to semantic categories defined within a structured schema. The annotated text segments encapsulate semantically relevant information extracted from the input sequence. The output text sequences are subsequently processed to generate structured data records.

A system for retrieving patient information using large language models including a computing device configured to receive a natural language query as a function of a user input, input the natural language query into a large language model communicatively connected to the least a processor, receive a computer language query comprising a plurality of nodes from the large language model, map the plurality of nodes to one or more entries in a patient database, receive a database response from the patient database as a function of the mapping, generate a final database query as a function of the database response. query the patient database using the final database query, receive a user response as a function of the final database query, and transmit the user response to a graphical user interface as a function of the final database query.

The present disclosure generally relates to systems and methods for the use of digital agents. In exemplary embodiments, a system is configured to be operable for creating, developing, formulating, programming, informing, educating, influencing, facilitating, modifying, controlling, directing, understanding, using, and / or learning from / with / using one of more digital construct(s) of one or more entity(ies) and / or group(s) that are based and / or focused on one or more motivation(s), ethic(s), moral(s), reputation(s), and / or their root cause(s) of the one or more entity(ies) and / or group(s). The one or more digital construct(s) are configured to have a primary function of providing information about the one or more motivation(s), ethic(s), moral(s), reputation(s), and / or their root cause(s) of the one or more entity(ies) and / or group(s) to the one or more digital construct(s) and / or to another digital construct(s), system(s), device(s), sensor(s), sensor array(s), and / or network(s).

This application describes, among other things, methods of selecting a task-specific machine-learning model for addressing a clinical task. An example method includes receiving a prompt from a user. Based on determining that the prompt requests assistance with a clinical task, a machine-learning model trained to select from among a plurality of task-specific machine-learning models each trained to assist with one of a plurality of clinical tasks selects a respective task-specific machine-learning model from among the plurality of task-specific machine-learning models based on the prompt. The prompt is provided to the selected task-specific machine-learning model. And a response received from the selected task-specific machine-learning model is provided to the user.

The invention relates to a heart rate prediction and model training method and system, wearable equipment and a medium. The training method comprises the following steps: acquiring a training sample set and a corresponding label set; wherein each training sample of the training sample set comprises a photoelectric volume pulse wave sequence and a corresponding acceleration sequence, and the label set is a real heart rate; preprocessing each training sample to obtain a corresponding photoelectric volume pulse wave frequency spectrum sequence and an acceleration frequency spectrum sequence; all the photoelectric volume pulse wave frequency spectrum sequences and the acceleration frequency spectrum sequences are input into a heart rate prediction model to be trained, and corresponding predicted heart rates are obtained; and calculating the difference degree between the predicted heart rate and the corresponding real heart rate, and updating parameters of the heart rate prediction model based on the difference degree to obtain a trained heart rate prediction model. According to the method, the problems of high signal processing cost and high calculation complexity caused by the use of a complex adaptive filtering process in the prior art are solved, and the heart rate prediction accuracy can be remarkably improved.