12 results about "Hospital system" patented technology

An endoscope apparatus includes an endoscope and processing circuitry. The endoscope includes an imaging device disposed at a distal end of an insertion portion and configured to capture endoscopic images when the endoscope is inserted into a human body. The processing circuitry is configured to determine, based on image changes of the endoscopic images, whether each endoscopic image is a non-observation target image or an observation target image, detect a specific region based on image characteristics in endoscopic images determined as the non-observation target images, determine images including the specific region among the non-observation target images as correction target images, determine a directional relationship between a direction of the imaging device and an anatomical orientation of the human body, based on the correction target images, andperform direction standardization processing based on the directional relationship, thereby standardizing orientations of the correction target images based on the anatomical orientation.

This invention discloses an integrated liquid diet supply and digestion monitoring system for gastrointestinal care. The system includes a core control module, a liquid diet supply module, a digestive status monitoring module, a multi-scenario adaptation module, a multi-device collaboration module, and a data management module. By constructing a three-tiered closed-loop system of "early warning-intervention-emergency care" to prevent aspiration, it achieves non-invasive automatic monitoring of gastric residual volume, personalized customization and infusion linkage of liquid diet formulas, linkage between intermittent infusion and oral care, and full-process traceability analysis of abnormal events. It is portable and can interconnect with multiple devices such as smart beds, monitors, and hospital HIS / LIS systems to form a smart medical ecosystem. This invention achieves the integration and intelligentization of liquid diet supply, digestion monitoring, and gastrointestinal care, covering four major scenarios: hospitals, rehabilitation centers, nursing homes, and homes. It significantly improves diagnostic and treatment efficiency and patient comfort, meeting both clinical needs and quality control research requirements.

The application discloses a time axis key node automatic acquisition system for chest pain diagnosis and treatment, relates to the field of information and communication technology of medical data, and comprises a pre-stored interval template containing starting or ending anchor point rules; an event stream carrying chest pain patient identification and source system time stamp derived from one or more medical information systems is acquired in real time; an active interval instance in memory is created and maintained for the chest pain patient; a candidate ending event is inferred; source system time reference drift is identified, and a reliability label is attached to time-consuming data. The application realizes automatic and real-time monitoring of the time consumption of the diagnosis and treatment process. The system not only supports starting and ending anchor point matching, automatically identifies time reference drift and attaches a reliability label, but also guarantees the reliability of time-consuming data in a real complex environment without relying on strict time synchronization of the whole hospital system.

This invention relates to a method and apparatus for cross-application split-screen data processing combined with a virtual digital human. The target user inputs their actions via voice; the virtual digital human converts these actions into text and inserts it into the chat history; external software sends the current page information to the central intent control prompt; the central intent control prompt obtains system prompts based on the current page information and the chat history, identifies the system prompts, and outputs a standard intent; a business prompt receives the standard intent and accesses the chat history; the business prompt generates an intent result and sends it to the virtual digital human; the virtual digital human outputs the intent result; and the business prompt inserts the intent result into the chat history. This achieves data interaction between the virtual human software and external software, thus realizing the technical integration of virtual human software and external software. The self-service registration machine software has already completed interface integration with the hospital's HIS system; the virtual human software only needs to interface with the self-service registration machine software and does not need to repeatedly interface with the hospital's underlying interface.

This invention discloses a drug dictionary intelligent matching method and system based on multi-level intelligent agents, belonging to the field of medical information technology. Addressing the problems of low accuracy, high labor costs, and difficulty in adapting to heterogeneous information of various types of drugs in existing methods, this invention constructs an architecture of embedded representation – semantic retrieval – multi-dimensional LLM judgment – ​​result fusion. Dedicated vector knowledge bases and matching logic are designed for Western medicine / traditional Chinese medicine preparations, granules, and traditional Chinese medicine: Western medicine / traditional Chinese medicine preparations are verified in three dimensions (name, specifications, and manufacturer); granules are verified in two dimensions (name and manufacturer); and traditional Chinese medicine is verified only in the name dimension. Semantic vectors are generated using qianwen3-embedding-8b, and candidate sets are obtained through Milvus retrieval and gte-rerank-v2 ranking. A large language model then performs candidate set optimization and multi-dimensional parallel / serial verification, outputting results including matching identifiers and failure reasons. This achieves semantic-level drug matching, improving accuracy and robustness, and is suitable for automated mapping of drug dictionaries and medical insurance standard dictionaries in hospital HIS systems.

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.

This invention relates to a method and apparatus for invoking a virtual digital human across application scenarios. The target terminal is configured with a Windows program containing multiple .exe processes. These processes share a single window for integrated display. Each .exe process includes both virtual human software and external software processes, enabling the virtual human software to combine with the external software for cross-application scenario virtual digital human invocation. The target terminal also has a background configuration page for splitting the user interface of the virtual human software and external software. This splitting can be either vertical or horizontal. The target terminal also configures the positional ratio and screen resolution of the virtual human software and external software within the background configuration page. The self-service registration machine software has already integrated with the hospital's HIS system; the virtual human software only needs to interface with the self-service registration machine software and does not require repeated integration with the hospital's underlying interface.

This invention relates to the field of cardiovascular disease risk prediction technology, and particularly to a cardiovascular disease risk prediction method based on multimodal data fusion. The method includes: acquiring four types of multimodal data—genetic data, imaging data, electronic medical record data, and physiological time-series data—based on hospital systems and wearable devices; processing the four types of multimodal data separately using a multimodal feature extraction strategy to obtain medical record semantic feature vectors, time-series feature vectors, genetic feature vectors, and imaging feature vectors; fusing these vectors using a multi-level feature fusion strategy to obtain a multimodal fused feature vector; and inputting the multimodal fused feature vector into a pre-trained cardiovascular disease risk prediction model to output the cardiovascular disease risk prediction result. This invention enables the synergistic utilization of risk information from each modality while preserving its own clinical semantics, improving the effectiveness of integrating multi-source heterogeneous information in long-term cardiovascular disease risk prediction.

This invention discloses a dynamic priority-based intelligent scheduling method for medical queuing and calling, belonging to the field of medical service scheduling technology. It includes connecting to multiple hospital systems, collecting and integrating patient information, medical resources, and queue data; constructing a multi-dimensional dynamic priority rule base for initial patient priority assessment; adjusting priorities in real time to intelligently match patients with medical and clinic resources; publishing calling information across multiple terminals; monitoring queue status and issuing warnings; and statistically analyzing multi-dimensional data to support optimization. This invention balances the urgency and fairness of medical visits through dynamic priority and intelligent scheduling, improving the utilization rate of medical resources. Accurate information push from multiple terminals optimizes the patient experience, and full-process monitoring and data support assist hospitals in refined management, improving the efficiency and quality of outpatient services.

The application relates to the technical field of routing, and provides an automatic routing method, system, electronic device, program product and storage medium. The method comprises the following steps: querying a proxy access medical large model library; registering a hospital retrieval enhancement generation RAG system; signing a query user; based on a query question initiated by the query user, acquiring a matched medical large model and a matched hospital RAG system; routing the query question to the matched medical large model and the matched hospital RAG system to obtain a matched answer to the query question. According to the application, the medical large model and the RAG system that are suitable for the needs of the query user can be accurately matched and selected without manual selection and switching of the user, so that the cost of selection and switching of the user is reduced; on the other hand, the fixed binding relationship between the medical large model and the RAG system is decoupled, so that the combination mode of the two can be flexibly adjusted according to different scenes, and the maximum efficiency of the system can be brought into play.

The present application relates to the technical field of medical data integration, and particularly relates to a medical full-industry data asset integration system and method based on blockchain and AI. The system comprises a data collection layer, a blockchain right confirmation layer, a federal learning analysis layer, a data asset transaction platform and a supply chain traceability optimization module. The data collection layer comprises an edge computing node, the edge computing node is internally provided with a data cleaning engine and a desensitization algorithm, and is used for local cleaning and desensitization processing of hospital HIS system data, medicine RFID data, medicine research and development experiment data and medical image data. The blockchain right confirmation layer constructs a medical data asset account book based on a consortium chain architecture, the asset account book comprises data hash records, contributor identity labels and use authorization logs, and an intelligent contract module is integrated for dynamic permission management. The present application can break the medical data island, and realize cross-field data safe integration and efficient utilization.