28 results about "Clinical record" patented technology

The invention discloses a multi-modal heterogeneous medical equipment data fusion and decision support method and device, and aims to solve the problems that the fusion precision is low due to space-time semantic difference of medical equipment multi-modal heterogeneous data (equipment operation parameters, clinical records, fault signals and the like), equipment management decisions depend on experience, and standards are not uniform. According to the method, breakthrough is achieved through three-level data alignment of'time-space-semantics', hierarchical fusion of'data level-feature level-decision level ', three-level decision driven by a knowledge graph and dynamic feedback optimization: time alignment uses a dynamic time warping algorithm, space alignment depends on a unified data dictionary, and semantic alignment introduces an attention mechanism; the feature level fusion quantifies the feature support degree based on the D-S evidence theory; the decision-making layer constructs a'rule-case-prediction 'three-level system, and combines cosine similarity retrieval and information entropy quantification uncertainty. The method and device can support medical equipment maintenance, clinical diagnosis and treatment and other scenes, and the medical service standardization level and the equipment management efficiency are improved.

A medical code allocation method based on hierarchical association and diversity enhancement comprises the following steps: S1, data preprocessing and graph construction: based on a tree hierarchical classification architecture of ICD codes, adopting a hierarchical graph model to perform visual representation on the tree hierarchical classification architecture, and constructing a co-occurrence matrix of the clinical record text and the ICD codes for the clinical record text; s2, applying a Graph-BERT graph neural network structure to perform graph structure conversion on a tree structure of an ICD code system, and learning based on an encoder structure of a graph transformer to obtain embedded representation of ICD codes; s3, performing word segmentation processing on a clinical text, inputting the processed clinical text into a bioBERT model to obtain a feature vector of the clinical text, and unifying semantic features of clinical records, hierarchical features of ICD codes and related association information between the semantic features and the hierarchical features through a multi-modal fusion mode; s4, after the final feature vector of the clinical record text is obtained, correlation enhancement prediction is performed by using a CorNet network, so that a related probability matrix is generated, a binary cross entropy loss function is expanded, the binary cross entropy loss function, hierarchical diversity loss and semantic diversity loss jointly form a diversified loss function, and the diversified loss function and a classic model are subjected to comparative analysis, so that the final feature vector of the clinical record text is obtained. Therefore, the accuracy and effectiveness of the method are verified.

The invention relates to the technical field of sleep respiratory disease analysis, and discloses a method for analyzing obstructive sleep apnea. The method comprises the following steps: acquiring an original physiological signal flow which is output by a multi-channel sleep monitoring device and comprises a respiratory waveform, blood oxygen fluctuation, an electrocardio rhythm and a sound vibration signal; and then, carrying out adaptive window function segmentation and multi-resolution conversion on the original signal flow to generate a standardized multi-modal signal sequence. State decoding is carried out on the sequence through a hidden Markov model, and steady state physiological mode features and transient abnormal mode features are extracted. And fusing the steady state features and clinical archive data of the patient, calculating an apnea risk index, and forming an initial evaluation report. Meanwhile, a dynamic evolution path of transient abnormal mode characteristics is monitored, and a real-time pathology indicator in the signal is detected. And finally, a risk weight coefficient in the initial evaluation report is adjusted according to the real-time pathology indicator, and a more accurate optimization evaluation report is generated.

The system brings together patient data both clinical records and imaging studies from disparate sources to the user workstation or mobile device in real-time and on-demand. In order to do so, the system needs to establish application layer connectivity utilizing HL7 or FHIR and DICOM for imaging. Once a secure connection is established, the system is able to search and retrieve records and present it to end user.

The invention relates to the crossing field of artificial intelligence and medical education, and provides a medical education droop class large model-based case teaching plan generation method. In order to solve the problems that traditional cases are high in reuse rate and typical cases are insufficient, multi-modal data fusion processing (clinical records / textbooks / expert experiences), domain adaptive model training (Tranform + LoRA parameter migration), constraint decoding generation (regular beam search + medical ontology verification), teaching target dynamic adaptation (Bloom vector fusion + reinforcement learning) and a three-dimensional quality evaluation system are adopted, and a three-dimensional quality evaluation system is established. And efficient generation and accurate optimization of the case teaching plan are realized. The method comprises the following five steps: 1) heterogeneous data fusion; 2) two-stage model training; 3) generating a structured instruction; 4) dynamically adjusting the teaching content; and 5) knowledge updating and stability guarantee. The system solves the problems of insufficient case diversity, low clinical fitting degree and other pain points, and improves the medical education quality.

An analytics computing device is provided. The analytics computing device includes a processor in communication with a database. The database configured to store electronic health record (EHR) data including structured EHR data and unstructured EHR data for a patient. The processor is configured to retrieve the EHR data from the database. The processor is further configured to parse, using a natural language processing model, the unstructured EHR data to retrieve one or more indicator phrases, the one or more indicator phrases correlated to an Alzheimer's disease (AD) diagnosis. The processor is further configured to identify, using a predictive model, the patient as being at risk for AD based on the retrieved indicator phrases and on the structured EHR data.

Systems and methods generate clinical documentation using large language models and artificial intelligence (AI). A template management module is provided to create customizable templates. A processing unit can receive input data from various sources and use AI to generate transcripts, summarize sessions, and produce clinical documentation such as clinical notes. The processing unit may also generate Current Procedural Terminology (CPT) and diagnosis codes, generate after-visit summaries, and generate referral letters. The AI may be trained on past clinical notes and can adapt to the clinician's style over time, with a feedback loop for continuous improvement. Additional features include cohort-based training, real-time language translation, predictive text, and analytics for documentation trends. The system supports customization of note length, style, and keywords, as well as integration with external medical databases and patient portals.

Approaches are described for facilitating remote ophthalmic examinations using three-dimensional (3D) imaging and mixed reality technology. A system obtains real-time or stored 3D data of a patient's eye, capturing detailed anatomical structures. The system analyzes the 3D data to identify specific regions of the eye, such as the cornea or retina, and retrieves corresponding diagnostic data and patient-specific clinical information. The 3D data, diagnostic metrics, and clinical records are integrated to generate an interactive visualization, which is presented through a mixed reality interface. The system allows healthcare professionals to manipulate diagnostic overlays, investigate flagged abnormalities, and adjust the visualization using gesture-based inputs. Machine learning models may be applied to detect potential abnormalities in the eye, while the system also determines stages of the examination based on changes in the anatomical structure of the eye.

This invention relates to the field of medical technology, specifically to a method for preoperative risk assessment and prediction in liver transplant patients with hepatocellular carcinoma, comprising the following steps: Sample collection: selecting plasma samples and corresponding clinicopathological information from liver transplant recipients of hepatocellular carcinoma, and clarifying the inclusion and exclusion criteria for samples; Plasma cell-free DNA extraction and whole-genome sequencing: extracting and quality-controlling cell-free DNA from the plasma samples collected in step S1, constructing a sequencing library, and performing low-coverage whole-genome sequencing. This invention utilizes plasma-extracted cfDNA for whole-genome sequencing, combined with clinical testing information, to construct a preoperative risk assessment and prediction model for postoperative recurrence in liver transplant recipients of hepatocellular carcinoma based on non-invasive testing. This model can be used to predict the probability of recurrence-free survival before liver transplantation. The model derivation cohort integrates clinical records and circulating tumor DNA data for preoperative recurrence risk prediction.

The invention provides an artificial intelligence-based system for generating personalized medical information through the integration of multi-modal data across pre-hospitalization, hospitalization, and post-hospitalization phases. The system employs encoder modules to process diverse input modalities, including audio recordings, video streams, biomedical images, text-based clinical records, and physiological signals. These encoded representations are integrated into a unified latent space using a large language model (LLM) trained on medical datasets comprising historical patient cases, anatomical knowledge, and treatment guidelines. The LLM enables cross-modal analysis to generate personalized outputs via decoder modules, which transform the latent space representation into actionable formats like text-based summaries, visualizations, audio explanations, and treatment suggestions. A key innovation is real-time intraoperative feedback via encoder-decoder modules detecting anatomical structures and deviations from standard protocols. The system also includes a federated learning module to aggregate model updates across medical centers while preserving patient privacy through deidentification protocols.

A hardware-anchored orchestration system for autonomous GenAI agents in clinical settings, implementable in ASIC or FPGA fabric to ensure deterministic enforcement independent of software execution layers. The system utilizes a hardware-isolated ethical supervisor—comprising a HSM or TPM—to monitor agentic workflows against human-configured safety thresholds stored in an ethical guardrail manifest in a silicon vault. Hardware-based logic gates detect statistically anomalous token-level entropy as a causal indicator of hallucination, and bias monitors evaluate equity thresholds against manifest-defined fairness indices. If a safety breach is detected, a hardwired interlock circuit asserts a non-maskable interrupt to block the agent's output before it is committed to the clinical record. The architecture supports multi-agent quorum verification and cryptographic provenance anchoring, ensuring autonomous agentic actions remain compliant with clinical regulatory standards via hardware-verified human oversight and zero-knowledge compliance verification.

The invention relates to an integrated multimodal artificial intelligence platform designed to function as an autonomous hospital system providing end-to-end health prevention, screening, diagnosis, treatment optimization, and longitudinal digital-twin-based monitoring. The platform introduces a closed-loop clinical architecture that continuously analyzes heterogeneous patient data including radiology, pathology, genomics, laboratory findings, longitudinal clinical records, wearable streams, and environmental exposures. A multimodal transformer (MT-X) generates a unified patient-specific representation, enabling high-precision diagnostic and prognostic inference. A novel Autonomous Screening Interval Generator (ASIG) dynamically determines individualized screening schedules based on calibrated risk models and temporal disease-evolution forecasting. A Digital Twin Engine (DTE) simulates tumor progression, metastasis probability, toxicity trajectories, and therapy response. An Adaptive Therapy Optimization Engine (ATOE), based on reinforcement learning, identifies optimal treatment strategies tailored to patient biology and system-level constraints. The invention is industrially applicable to hospitals, centers, national screening programs, tele-networks, and Al-enabled health systems. The integrated nature of the invention, the closed-loop framework, and the combination of digital-twin simulation with intelligent screening and therapy design constitute a substantial improvement beyond conventional medical Al solutions.

Presented herein are systems and methods for automated analysis of patient data. More particularly, in certain embodiments, the invention relates to systems and methods for predicting the context of a particular phrase (e.g. the name of a diagnosis / condition) in a clinical record of a patient using a reportability classifier. In another aspect, the invention relates to systems and methods for automatically identifying a potential care gap and / or adverse health trend for a patient from clinical data.

The invention discloses a prescription identification matching method for methotrexate administration, particularly relates to the field of intelligent prescriptions and medical informatics, and is used for solving the problem that in the prior art, a methotrexate administration scheme mainly depends on doctor experience adjustment and is difficult to carry out individualized matching by comprehensively utilizing historical case data. A disease activity manifold trajectory is constructed by extracting historical clinical records in electronic medical records of a target patient, a delay accumulation rule of disease state change after administration is analyzed in combination with prescription records to obtain drug effect attenuation state parameters, patient attenuation subtypes are identified on the basis, and causal relationship analysis is performed to obtain a causal contribution weight vector; and searching similar patient groups from a historical case library, generating a candidate intervention track set containing success probability distribution, and finally generating a methotrexate administration scheme recommendation list according to success probability sorting, thereby providing a more reasonable methotrexate administration scheme with reference value for a target patient.

The invention provides a heart disease case classification prediction system based on a cascading generalization method, and belongs to the technical field of precision medical heart disease case classification prediction, and the system comprises a data obtaining module which is configured to obtain heart disease patient clinical record data published by a website and UCI acknowledged heart disease data, and merge the data as a data set; the data pre-processing module is configured to pre-process the data in the data set to obtain pre-processed data; the model building module based on the cascading generalization method is configured to train a plurality of models by utilizing the preprocessed data, select the model with the best performance as a meta-learning model of the cascading generalization method based on a training result, and perform cascading generalization training on other models in the plurality of models to obtain a final trained model; and the heart disease case classification prediction module is configured to analyze to-be-predicted data by using the trained final model and output a heart disease case classification prediction result.

The application discloses an emergency trauma wound area intelligent measurement and recording system based on deep learning, relates to the field of computer vision, synchronously acquires a two-dimensional image sequence, a six-axis attitude vector and a time stamp, extracts a mask by using a segmentation network, and constructs a local curved surface geometric model in combination with prior parameters; a non-homogeneous weight compensation matrix is generated by calculating the included angle distribution of a space vector and an optical axis vector; target wound physical surface areas are acquired by performing pixel-by-pixel weighted integration on mask pixels based on the matrix, and the shrinkage caused by projection is compensated. According to the weight matrix gradient, confidence is evaluated, and dynamic acquisition guidance or structured data encapsulation is realized. The application effectively corrects non-homogeneous curved surface projection distortion, and improves measurement accuracy and the reliability of clinical records.

Techniques for an autonomous edit process for medical claims are disclosed. An electronic claim associated with a patient encounter is retrieved, along with a flag indicative of the claim being erroneous, and an error report identifying an error condition within the claim. A plurality of heterogeneous electronic medical records associated with the patient encounter is retrieved, the plurality including structured billing codes, structured data, semi-structured data, and / or free-text clinical notes. A feature-extraction engine transforms the plurality of heterogeneous electronic medical records into a unified machine-readable representation including semantic embeddings, which are processed by a trained machine learning (ML) model, to generate a mapping between the error condition and one or more spans within the unified representation. The ML model identifies documentary evidence within the one or more spans that satisfies a model-learned evidentiary relevance condition, and generates one or more machine-formatted corrective actions to resolve the error condition.

A Patient Data Directory System (PDDS) provides metadata that identifies a patient's clinical record at a plurality of clinical sites. This metadata includes patient-encrypted access information that is required for accessing these clinical records. The patient maintains access control by selectively providing the decrypted access information to clinicians upon request. To assure that the clinician is able to access these records when the patient is incapacitated, the patient creates an emergency-access key that enables the encrypted access information to be decrypted and / or re-encrypted, and is recoverable based on two secrets. The patient provides the first secret to a delegate, and the second secret to the PDDS. When emergency access is required, the delegate and the PDDS engage in a Secure Multiparty Computation (SMC) that enables recovery of the emergency-access key without revealing the first secret to the PDDS or the second secret to the delegate.

The invention relates to the technical field of diagnostics, and discloses a pulmonary tuberculosis multi-modal fusion diagnosis system, which comprises a data acquisition module, a multi-modal fusion module, an intelligent diagnosis module, an early warning output module and a system management module, uniform format conversion, coding and space-time registration are carried out on multi-source heterogeneous data from image equipment, a laboratory system and clinical records by formulating standardization and alignment rules of multi-modal data, and it is guaranteed that diagnosis information of different sources and different time sequences has a consistent structure and a comparable reference before fusion; and meanwhile, deep features of each modal are deeply integrated through a feature extraction and fusion mechanism, so that feature contradiction and noise interference caused by different data standards and information dislocation can be eliminated, the consistency and reliability of a multi-modal fusion diagnosis information basis are ensured, and diagnosis errors caused by original data quality defects are reduced.

The invention discloses a multi-mode heart failure early screening system based on a large model, and the system comprises a data collection and processing module which is used for collecting forms, clinical record texts and electrocardiosignals, related to heart failure, of a patient; the abstract generation module is used for extracting text abstracts from clinical record texts by using a large model and introducing heart failure knowledge constraints; the multi-modal feature extraction module is used for extracting pathological index change features, semantic features and electrocardio waveform change features from tables, clinical record texts and electrocardio signals; the multi-modal feature measurement module is used for obtaining a weight coefficient of each modal based on the multi-modal data; the multi-modal feature alignment module maps the weighted modal features to a shared representation space through a learnable projection layer, and realizes feature fusion through a bidirectional cross attention mechanism and an adversarial learning strategy; and the heart failure early screening module is used for obtaining a heart failure disease early screening prediction result and a risk probability through feature fusion. The heart failure prediction accuracy can be improved.

The invention discloses a traditional Chinese medicine prescription intelligent recommendation method based on a double-layer medical knowledge alignment network, and the method comprises the steps: collecting clinical diagnosis and treatment records, and associating the clinical diagnosis and treatment records with a traditional Chinese medicine prescription issued by a doctor to form a data pair; a heterogeneous knowledge graph is constructed; a double-layer alignment network recommendation model is constructed, and an in-modal alignment module can deeply understand an input clinical record text and generate a context representation related to a task; the cross-modal alignment module integrates structured traditional Chinese medicine knowledge into patient representation to realize knowledge enhancement; the fusion prediction module intelligently fuses the information of the intra-modal alignment module and the cross-modal alignment module, and generates a final prediction result; designing a loss function, and formulating a training strategy. According to the method, deep semantic information of clinical texts and heterogeneous knowledge in the field of traditional Chinese medicine are systematically fused, and the accuracy and rationality of prescription recommendation are remarkably improved.

Currently systems for Length of Stay (LoS) and clinical interventions for patients work independent of each other. However, they are highly interdependent decisions for overall medical predictions for patients. Embodiments disclosed provide a method and system for transformer-based Neural Network (NN) for jointly predicting LoS and critical interventions for patients admitted to medical facilities. A joint NN model, comprising Bidirectional Encoder Representations from Transformers (BERT) model as one of the layers, processes first day clinical notes, available in an unstructured data format, and a plurality of medical attributes of the patient available in a structured data. Further, the joint NN model jointly predicts s (a) the LoS of the patient into one of the classes comprising LONG and SHORT and (b) a Type of Intervention (ToI) for the patient into one among a plurality of classes with each class of the ToI comprising a list of critical clinical interventions.

A hospital examination test name alignment method based on community discovery, a patient's disease diagnosis, operation and examination test in a clinical record are constituted into a graph structure, and then a community discovery algorithm is used to cluster the graph structure into different communities, the edges in the community are closely connected and the edges between different communities are sparse, the internal of a community all belong to disease diagnosis, operation or examination test which are closely related to each other, so when the examination test name alignment is performed, the alignment object is only searched from the community where the examination test is located, thereby reducing the deviation of the examination test name alignment.

The present disclosure generally relates to methods and user interfaces for viewing and managing signed clinical records. In some embodiments, methods and user interfaces for adding a signed clinical record to a computer system are described. In some embodiments, methods and user interfaces for displaying signed clinical records with unsigned clinical records, wherein signed clinical records include a visual indication that they are signed, are described. In some embodiments, methods and user interfaces for adding signed and / or unsigned clinical records related to vision are described.

The invention relates to the technical field of medicine information, and discloses a system and a method for accurately selecting tacrolimus treatment dosage of a myasthenia gravis patient. The method comprises the following steps: acquiring multi-cycle administration records and corresponding blood concentration of a patient to form an initial sequence; establishing a theoretical contribution degree matrix through lagging compensation, and reversely decomposing a pure single administration concentration curve; matching the curve with an individual pharmacokinetic template, and identifying an abnormal metabolic segment; and associating the same-period clinical records to generate clinical metabolism association pairs, establishing a mapping relation between concentration fluctuation and clinical symptoms, and classifying abnormal drug effect modes. According to the method, the independent metabolism trajectory of single administration can be analyzed from the mixed monitoring data, and the drug metabolism dynamics and the clinical effect are accurately associated, so that a technical basis is provided for realizing prospective individualized accurate administration.

The present disclosure relates to a method and device for generating clinical record data for recording medical treatment. The method includes receiving medical data in which medical treatment, performed in advance, is recorded; recording information, included in the medical data, in a layer corresponding to an item related to the medical data from among a plurality of layers classified according to a plurality of items; and generating a clinical report based on the plurality of layers.

Presented herein are methods and systems for generating a synchronous clinical record that is reflective of contemporaneous activity pertaining to at least one of operation or management of a medical device. One or more contemporaneous clinical activities of a clinical session are monitored to generate a contemporaneous activity log. An artificial intelligence (AI) model is applied to process the contemporaneous activity log. Based on the processing, the AI model generates a synchronous clinical record that is reflective of the one or more contemporaneous clinical activities.

The application discloses a kind of cerebral vascular patient personalized health management methods combined with medical information, specifically related to chronic disease management and medical information processing field, for solving the problems of experience judgment in the process of existing cerebral vascular patient stage health management, lack of continuous quantitative characterization and insufficient personalized intervention strategy;By fusing clinical records, scale scores and voice behavior data, auxiliary sound confusion matrix and language layer loss features are constructed, and health state change evolution vector is formed on the unified time axis, combined with historical follow-up samples to establish a health state recognition model, to realize the objective determination of the recovery stage;Further based on the historical sample matched with the current stage, extract intervention configuration parameters, generate personalized health management plan, dynamically match intervention strategy and patient recovery process, so as to improve the continuity, pertinence and implementation effect of cerebral vascular patient stage health management.