101 results about "Patient record" patented technology

Systems and methods for de-identifying patient data are disclosed herein. In some embodiments, a method for de-identifying patient data includes receiving a patient record including one or more identifiers. The method can include generating a first de-identified record from the patient record using a first de-identification process. The first de-identification process can be configured to produce a first re-identification risk score. The method can further include receiving a request from a data recipient to access the first de-identified record. The method can also include generating a second de-identified record from the first de-identified record by using a second de-identification process. The second de-identification process can be configured to produce a second re-identification risk score lower than the first re-identification risk score.

Systems, methods and interfaces are provided for processing natural language queries. A machine learning-powered search interface may process complex natural language queries across specialized domains. The method may utilize a transformer-based natural language processing model that analyzes user intent by examining both current and historical user inputs. A graph data structure may be used to represent interconnected domains like patient records, insurance claims, and business metrics enables dynamic information retrieval. The system may use an A* search algorithm to navigate domain nodes and identify relevant answers. An abbreviation expansion mechanism resolves technical shorthand by referencing domain-specific mapping databases, ensuring precise interpretation of user queries. The method may identify keywords, traces optimal answer pathways, and adapt by updating graph relationships and abbreviation mappings. By generating contextually rich natural language summaries, the system delivers precise, comprehensive responses through an intuitive search interface.

A system and a method for automatically assisting physicians during patient encounters includes transcribing and diarizing physician-patient interactions, extracting clinical concepts, and combining data with patient history data to provide suggestions to the physicians. A speech and gesture recognition module captures audio from patient-doctor interactions and transcribes the audio into text in real-time. A natural language processing module diarizes the transcribed text to attribute speech. A clinical concept extraction module identifies and extracts clinical concepts from transcription. A clinical recommendation module integrates real-time data with historical patient records and analyzes the combined data set to generate evidence-based suggestions to the physician. A physician's own historical data is validated to generate a unique profile for each physician. Interactions with the physician are analyzed to understand decision-making patterns. The physician's profile is updated and future physician decisions are forecast based on past behavior.

A community electronic medical record provides access to a patient's records. A unity server of the present invention allows a user to enter a query requesting the information that a medical provider needs such as past history, allergies, billing information, and other medical data that may be related to the patient. The unity server queries at least one database, preferably many, to access the patient's records relevant to the provider's query. The unity server retrieves information from multiple sources to provide increased information for treatment of the patient.

Described herein are methods of managing eosinophilic esophagitis (EoE) in a patient, wherein the patient records the number of episodes of dysphagia on a patient report outcome (PRO) questionnaire prior to and during the course of treatment. While on treatment, the number of episodes of dysphagia are reduced, as reported on the PRO questionnaire. In some embodiments, the esophageal eosinophils are counted before or after treatment, or both. In some embodiments, esophageal eosinophils counts are not correlated with a reduction in the episodes of dysphagia.

Systems and methods for de-identifying patient data are disclosed herein. In some embodiments, a method for de-identifying patient data includes receiving a patient record including one or more identifiers. The method can include generating a first de-identified record from the patient record using a first de-identification process. The first de-identification process can be configured to produce a first re-identification risk score. The method can further include receiving a request from a data recipient to access the first de-identified record. The method can also include generating a second de-identified record from the first de-identified record by using a second de-identification process. The second de-identification process can be configured to produce a second re-identification risk score lower than the first re-identification risk score.

Systems and methods for selecting a treatment regimen for a particular patient are provided. The treatment regimen is selected using a first data store including a first plurality of patient records for a first plurality of patients, and a second data store including efficacy rates of a plurality of treatment regimens against a plurality of infections and infection-causing pathogens. The system, or a user of the system, identifies a first infection of the particular patient and a first treatment regimen to be prescribed to treat the first infection. A second plurality of patient records is generated by identifying, in the first plurality of patient records of the first data store, patient records associated with diagnosis or treatment of the first infection. The second plurality of patient records are appended with efficacy rates for the first infection from the second data store. Systems and methods of the present disclosure can use these appended records to generate a dynamic model configured to determine a likelihood estimation that the first treatment regimen is an appropriate treatment regimen to treat the first infection.

Disclosed embodiments include computer-implemented methods and systems that can efficiently generate highly relevant recommended search terms to clinicians. A hybrid collaborative filtering model recommends search terms for a specific patient to the clinician. The model draws on information from patients' clinical encounters and the searches that were performed during the clinical encounters. To generate recommendations, the model uses search terms which are (1) frequently co-occurring with the ICD codes recorded for the patient and (2) highly relevant to the most recent search terms. One variation of the model uses only the most recent ICD codes assigned to the patient. Another variation uses all ICD codes. Comprehensive experiments of embodiments of the methods and systems have demonstrate high levels of performance.

In some embodiments thereof, the present invention discloses systems and methods for expeditiously designing and fabricating properly-fitted dental prostheses. A customizable arch-shaped apparatus approximating dentition is employed intraorally to register positional and relational characteristics between maxillary and mandibular arches, including the vertical dimension of occlusion. The apparatus is configured to allow accurate interface with oral anatomy via its constituent material(s) being pliable and moldable preferably but not necessarily when heated. Representations of dentition may be integrated on the apparatus to aid proper positioning. Intraoral scan data detailing precise arch dimensions is either referenced from pre-existing patient records or procured through digital oral scanning of the apparatus in situ. The registered positional relationships and acquired scan data are jointly utilized to virtually model and subsequently manufacture bridgework, veneers or dentures; the apparatus allowing dentition to be modeled and fabricated in a singular office visit prior to a final, confirmatory try-in where minor adjustments may ensue.

Disclosed herein are techniques for deidentifying personally identifiable information (Pll). A method includes training a large language model (LLM) on a set of clinical records to generate a clinical analysis; fine tuning the LLM on a set of Pll training data to identify Pll using machine learning-based name entity recognition; receiving from a client device a clinical analysis request and a patient identifier; providing, to the LLM the clinical analysis request and one or more patient records associated with the patient identifier, causing the LLM to generate a clinical analysis, identify one or more Pll instances in the clinical analysis, deidentify at least one of the one or more Pll instances to generate a deidentified clinical analysis; receiving from the LLM a deidentified clinical analysis; and transmitting the deidentified clinical analysis to the client device.

A digital healthcare ecosystem to transform patient care with real-time queue management, including: an appointment and laboratory test booking module configured to allow patients to easily book and schedule doctor consultations and diagnostic tests; a healthcare provider module configured to manage appointments, patient records, billing, internal laboratory and pharmacy integration, and operational analytics, with the healthcare provider module configured to manage dashboard features for physicians, hospital administrators, and laboratory technicians to monitor and update patient status; a real-time queue management module coupled to the healthcare provider module and the appointment and laboratory test booking module, wherein the real-time queue management module is configured to assign a digital token number to patients upon booking once accepted by the healthcare provider module, wherein the real-time queue management module is configured to update the queue position of patients using time-stamped data; a patient interface configured to allow patients to view real-time queue updates, book appointments, and access lab reports using the digital token number; a notification system configured to send notifications to patients and physicians regarding appointment reminders, queue progress, and follow-up instructions; a cloud-based server configured to securely store patient data and enable seamless communication between the patient interface and the healthcare provider module; a display unit configured to show estimated waiting times and notify patients when it is their turn; and a dynamic scheduling module configured to take into account physician availability, patient preferences, and historical data to minimize waiting times and avoid overbooking.

A system and method may monitor a stream of messages from plural different sources of medical records to identify a new or updated record of the medical records, identifying one or more suspect records from a system of record (SOR) database. The one or more suspect records are identified as being potential matches to the new or updated record that is identified. The system and method can determine that the one or more suspect records match the new or updated record, and can obtain a person entity profile related to the new or updated record from a person entity database. The system and method can merge the new or updated record with the one or more suspect records or splitting the new or updated record from the one or more suspect records based on the person entity profile that is obtained.

A method for processing a sparsely populated data source, method for generating a training set for training a model to predict mitral regurgitation from echocardiograph data, and method of predicting heart failure from echocardiograph data including the steps of: retrieving echocardiograph measurement data from a plurality of patient records comprising echocardiography reports; analysing the echocardiograph data to determine unpopulated data fields; populating the unpopulated data fields with imputed echocardiograph data determined by a machine learning model; calculating a probability output from a trained model; analysing echocardiograph measurement data of individual patient records from the echocardiograph data to determine a prediction of the presence of a disease state in the patient on the basis of the calculated probability output; and associating the presence of the disease state to a prediction of heart failure in the patient.

The invention provides a construction method of a coronary heart disease risk prediction model based on deep learning, and the method comprises the following steps: S1, obtaining examination data of patients recorded in a hospital, and respectively obtaining 12-lead electrocardiogram data of a coronary heart disease patient and a non-coronary heart disease patient in an HL7 format according to a coronary angiography examination result; s2, preprocessing the acquired electrocardiogram data; s3, dividing the preprocessed electrocardiogram data into a training set, a verification set and a test set; constructing a ResNet-LSTM integrated model, inputting features extracted by the ResNet neural network into LSTM for classification, and inputting electrocardiogram data into the model for training and verification by adopting ten-fold cross validation to obtain a trained model and a verification result; s4, optimizing parameters of the trained model based on a verification result; and S5, performing coronary heart disease risk prediction on the optimized integrated model by using test set data. The space and time information of the electrocardiogram can be fully captured, and more accurate coronary heart disease risk prediction is realized.

In a local coil arrangement (5) for use on a patient bed (1) with a magnetic field sensor (6) for measuring the main magnetic field of a magnetic resonance device (16) in order to determine position information of the local coil arrangement (5) by comparison with a main magnetic field map, the following sequence of steps is proposed to check the correct function of the magnetic resonance sensor in a procedure: - Recording of the first measured value (12) of the magnetic field sensor (6) outside the patient recording (2) at the first measuring position of the local coil arrangement (5) at a first lying position (4) of the patient bed (1) and determination of the first position information, - Recording of a second measurement (15) of the magnetic field sensor (6) during or after completion of a movement of the patient bed (1) into the patient receptacle (2) at a second measurement position (13) of the local coil arrangement (5) at a second position (14) of the patient bed (1), which is different from the first measurement position (9) and is located in particular within the patient receptacle. - Determination of at least one reference value that describes the expected main magnetic field at the second measurement position (13), which is determined from the first position information and the displacement distance of the patient bed (1) between the first and the second bed position (4, 14) according to the position determination device (18), and - Determination of error information indicating a potential measurement error by comparing the second measured value (15) with the reference value.

The invention discloses a multi-modal feature fusion prediction method and system for early screening of Alzheimer's disease, and belongs to the technical field of brain disease prediction. The method comprises the following steps: acquiring multi-dimensional data containing cognitive test scores, brain image scanning results and biomarker concentration levels from a patient record database, and performing standardization processing to obtain a multi-dimensional data set in a unified format; key feature vectors are extracted through a dimensionality reduction analysis method to capture the covariant relation between cognitive test scores and brain image changes; when the reduction range of the cognitive test score exceeds a preset threshold value and the brain image displays an atrophy sign, a classification model is constructed through an integrated learning method to preliminarily classify abnormal signals; and fusing the biomarker concentration level to obtain an abnormal signal vector. According to the method, the accuracy and efficiency of early screening of brain diseases such as Alzheimer's disease are remarkably improved through accurate evaluation of key parts of the human brain, such as hippocampus.

A viewing support system in which an information processing terminal on which an electronic patient record is displayed and an electronic patient record management server which acquires information pertaining to a sticky note attached to the electronic patient record are connected by a network, wherein the electronic patient record management server includes: a sticky note management unit which manages sticky note information indicating the position of a sticky note attached to an electronic patient record, and displays a sticky note created at the position of the sticky note specified by the sticky note information such that the sticky note can be viewed by another user different from the user who created the sticky note; and a supplementary patient record generation unit which generates a supplementary patient record summarizing the electronic patient record and the sticky note information on the basis of the electronic patient record and the sticky note information.

To support obtaining a confirmed diagnosis by causing a large language model to additionally learn patient records of a large number of diagnosed cases, causing the additionally trained large language model to propose an efficient test plan for confirming a diagnosis from symptom findings obtained from an undiagnosed patient visiting a hospital, and integrating obtained test results. An electronic health record system using a large language model in combination includes: a "possible diagnosis name, additional symptom, physical finding, and test answering means" that answers at least one of a list of possible diagnosis names and probabilities of the diagnosis names, and a recommended additional symptom, physical finding, and test; and a sequential diagnosis improvement means for repeating a "symptom, physical finding, and test result data provision means" and the "possible diagnosis name, additional symptom, physical finding, and test answering means" until the list of possible diagnosis names and probabilities of the diagnosis names has sufficient accuracy for confirmed diagnosis.

The present invention is concerned with the automated updating of a digital patient record with actual vital signs data values for the patient, thereby obviating the need for a healthcare professional attending to the patient to manually input such data values into the digital patient record. To this end, the present application provides several computer-implemented methods for capturing such vital signs data values in digital form, e.g. a photographic image or screen capture[BA1], and automatically extracting the vital signs data values captured in such a digital image therefrom, e.g. using OCR algorithms. Also provided are computer program products for implementing such methods and electronic devices configured to implement such methods.

Systems, methods, and computer-readable media are provided for patient case and care complexity characterization, and detecting matches of an individual patient's record with collections of other patients' records, based on serial, longitudinal patterns, for facilitating efficient health services utilization, implementing programs to reduce complexity, preventive medicine, and risk management in health care. In an embodiment, time series are formed by electronically representing information pertaining to successive longitudinal episodes of health services utilization and the circumstances in which the episodes were incurred; calculating time-series K-nearest-neighbor clusters and distances for each combination; determining the cluster to which a given candidate patient complexity record is nearest, and prescribing one or more interventions specific to hazards that are characteristic of trajectories that are members of that cluster, or that are deemed to be relevant to mitigating those hazards, thereby preventing the adverse outcomes and subsequent excess utilization that are prevalent in that cluster.

Described is a system for receiving a disease specific treatment algorithm corresponding to a disease of a patient from a first Electronic Health Record (EHR) system, processing data corresponding to the disease specific treatment algorithm using a Large Language Model (LLM), receiving one or more CQL models from the LLM based on the processing of the data corresponding to the disease specific treatment algorithm, receiving an update to a patient record of the patient from the first EHR system, based on the update to the patient record and the one or more CQL models, triggering a Clinical Decision Support (CDS) hook to generate an alert, and causing transmission of the alert for a medical practitioner associated with the first EHR system.

A system and method of property collection management and architecture that can organize patient data while maintaining context is presented. The present disclosure provides for a database system implementing a ‘Property Collection’ as a collection of ‘property name’ and ‘property value’ pairs, which are used to describe a ‘data entity.’ Further, the present disclosure can provide for historical access to data to track data changes. The present disclosure solves the technological problem of accessing data having differing data for the same person. The immutable electronic health record data storage system solves the aforementioned technological problem by providing a blockchain, transaction blockchain API, serialization module, and a deserialization module, among others that can format, process, and store data in a Global Patient Record (GPR).

To provide a photographing support device capable of efficiently collecting photographs of an affected part while suppressing a load on a doctor.SOLUTION: The medical image processing apparatus includes a registration unit that registers a disease name of an imaging target, an acquisition unit that acquires medical information of a patient recorded in an electronic medical record, a determination unit that determines whether the disease name of the patient acquired by the acquisition unit matches the disease name of the imaging target registered by the registration unit, and a notification unit that performs notification for prompting a user to image an affected part in a case where the determination unit determines that the disease name of the patient matches the disease name of the imaging target.SELECTED DRAWING: Figure 2

Systems and methods herein provide for access control to information in electronic patient records. One method includes receiving a request from an entity for access to one or more of a plurality of electronic patient records, the records having been machine learned to identify patient information in the electronic patient records including personally identifiable information and protected health information. The method also includes determining a level of access of the entity, retrieving, from a database, the one or more electronic patient records requested by the entity, applying a rule to the retrieved one or more electronic patient records based on the determined level of access of the entity to mask, encrypt, show, etc. one or more elements in the one or more electronic patient records. In response to applying the rule to the retrieved one or more electronic patient records, the electronic patient records are transferred to the entity.

Systems, methods and interfaces are provided for processing natural language queries. A machine learning-powered search interface may process complex natural language queries across specialized domains. The method may utilize a transformer-based natural language processing model that analyzes user intent by examining both current and historical user inputs. A graph data structure may be used to represent interconnected domains like patient records, insurance claims, and business metrics enables dynamic information retrieval. The system may use an A* search algorithm to navigate domain nodes and identify relevant answers. An abbreviation expansion mechanism resolves technical shorthand by referencing domain-specific mapping databases, ensuring precise interpretation of user queries. The method may identify keywords, traces optimal answer pathways, and adapt by updating graph relationships and abbreviation mappings. By generating contextually rich natural language summaries, the system delivers precise, comprehensive responses through an intuitive search interface.

The invention provides a document classification method and device based on a large model, an intelligent agent and electronic equipment, and relates to the technical field of artificial intelligence, in particular to the technical fields of natural language processing, large models and the like. The method can be applied to scenes of enterprise internal document management based on artificial intelligence, patient record management of medical institutions, news classification, social media topic classification, spam filtering, medical literature classification, legal document classification and the like. According to the specific implementation scheme, an input document is obtained; determining the document type of the input document, wherein the document type is divided into a streaming document and a format document; generating corresponding target prompt word information according to the document type; document classification is conducted on the input document based on the target prompt word information through the multi-modal large model, the category of the input document is obtained, and the category of the input document refers to the semantic category of the input document. The prediction performance of the document classification system can be improved, and the prediction time can be shortened.

The present invention relates to a computer implemented method for data cleansing. In the method, a data pre-processing module of a first computing instance (3) obtains an at least two-dimensional un-shuffled data structure (10). The data structure (10) comprises healthcare patient data. The data structure (10) comprises data on a plurality of patient records. Each patient record comprises one or more fields wherein each field has a field type and wherein the patient records have a pre-shuffled order. The data pre-processing module of the first computing device shuffles fields of a first field type by moving fields having the first field types from one patient record to another patient record. Fields with the first field type have a post-shuffled order after the shuffling thereby creating a shuffled data structure(lO). A communications module transmits (5) the shuffled data structure (10) comprising the healthcare patient data over a communications network (7) from the first computing instance to a second computing instance.

The computer-implemented system includes a computer having a processor and memory with executable instructions that run a platform for creating and displaying medical information. The system may receive medical data relating to a patient in FHIR / LPR format, including patient records and vital statistics. The system may perform temporal analysis and feature extraction on the medical data. Using an artificial intelligence model trained on historical patient data, the system may analyze the data to generate a knowledge graph by identifying nodes, determining relationships using semantic analysis and natural language processing, generating edges, and applying graph database algorithms. The system may create a visual output including a health snapshot with generated prose ranked using page rank algorithms, an interactive body map identifying health issues, and an enhanced timeline format health history with drill-down capabilities.

A system and method for electronic health record permissioning and monetization that can grant or deny access to patient data and pay one or more entities for access to the data is presented. The present disclosure provides for a system configured to provide a patient the ability to: ‘grant,’‘deny,’‘update,’ and ‘revoke’ the permission to read data for a specific entity, and specific properties within that entity, from their personal data records (e.g., an electronic health record, a Global Patient Record (GPR), pharmaceutical records, demographic records, financial records, criminal records, or other suitable personal information). A Data-Read-Permission request can be a ‘Property Collection’ (PC) containing specific properties that describe the read permission rights and an amount the Data-Client is willing to offer for the Data-Read-Permission rights. This PC can be written as part of a blockchain transaction (TX1), which can be issued by the Data-Client.

In some embodiments thereof, the present invention discloses a reusable smart syringe for radically enhanced liquid medication delivery through integrated digital measurement, dosage guidance and tracking technology. In some aspects thereof, an optical scanner reads embedded prescription codes on medicine labels to automatically recognize and set required dispensed volumes. Precision fluid amount sensing and electronic control circuitry coupled to a digital display panel enables exact fluid volume measurement and user verification improving upon imprecise analog techniques. Dosage volumes are also digitally limited as per scanned prescription codes to prevent under / overfills. An ergonomic thumb-press facilitates smooth one-handed operation alongside recyclable, detachable nozzle tips reducing medical plastic waste. All dispensed events are logged electronically interfacing with patient records for intelligent medication compliance improvement. The inventive integration of digital enhancements including computer vision, electronics, data connectivity and ergonomic engineering within legacy syringes establishes the next generation of safe, effective smart medication delivery advancing patient outcomes.