88 results about "Treatment decision making" patented technology

The invention discloses a failure restoration retreatment decision-making method based on dynamic occlusion analysis, and the method comprises the steps: constructing a four-dimensional virtual biomechanical model which comprises a patient anatomical structure and a dynamic function through multi-modal data fusion, and enabling the model to be embedded into a real three-dimensional mandibular movement track of a patient to simulate functional movement, thereby breaking through a static analysis blind area, and achieving the real three-dimensional mandibular movement of the patient. The missed diagnosis rate of dynamic interference is reduced; based on quantitative indexes and thresholds such as occlusal contact displacement, occlusal contact distribution symmetry and adjustment quantity of the maximum tooth tip staggering position and the median relation position, experience judgment of doctors is replaced, objectivity, repeatability and accuracy of failure repair and retreatment decision are improved, and excessive or insufficient adjustment is avoided; the treatment effect rehearsal is realized through virtual presetting, the irreversible operation risk is avoided, and the number of times of re-visit and the trial and error cost of a patient are reduced; and meanwhile, the four-dimensional virtual model can be connected with transition and design and manufacturing of a final restoration, so that the accuracy, safety and efficiency of retreatment of a failed restoration are improved.

The invention discloses an intensive care treatment scheme intelligent decision-making system based on data driving, and relates to the technical field of medical information, and the system comprises a data collection module which is used for obtaining multi-source clinical data of an intensive care unit in real time; and the decision generation module is connected with the data acquisition module and is used for generating a treatment scheme according to the clinical data. According to the intensive care treatment scheme intelligent decision-making system based on data driving, through four-dimensional snapshot construction of a dynamic decision-making chain and medical interpretable evolution relation labeling, continuous logic of an intensive care decision-making is guaranteed, data abnormal driving change and medical logic jump risks are effectively identified, medical errors caused by decision-making faults are reduced, and the decision-making efficiency is improved. The abstract decision-making process is converted into a concrete evidence chain capable of penetrating auditing, and the clinical responsibility traceability and the doctor-patient credibility are improved.

The invention discloses a layering and preference learning-based personalized dynamic treatment strategy generation system for Parkinson's disease, which comprises a dynamic state and preference representation module, a preference-based reward function learning module, a layering treatment strategy generation module and a treatment path simulation and interactive output module, the system learns preferences from doctor-patient interaction and generates layered, dynamic and explainable personalized long-term treatment strategies, so that making of personalized long-term treatment decisions is achieved, and the problems that in an existing Parkinson's disease reinforcement learning scheme, an award function is fixed, and long-term planning ability is lacked are solved.

The invention provides a special disease first-aid full-process auxiliary decision-making method based on multi-modal perception and AI, and relates to the technical field of medical first aid, and the method comprises the steps: obtaining first-aid field multi-modal data, constructing a feature dependence graph, and recognizing the type and symptom features of a special disease; indexing special disease diagnosis and treatment data based on the symptom feature vector, and determining a reference case and a treatment path; the action space is constructed in combination with clinical specifications, the expected income is predicted by applying Monte Carlo search, and the optimal treatment scheme is generated, so that the first-aid special disease recognition accuracy can be improved, the treatment decision time can be shortened, and the first-aid intervention effect can be improved.

The invention provides a dental implant data monitoring analysis method based on deep learning, and the method comprises the steps: collecting the multi-modal structural data of a patient, such as preoperative images, clinical examination and surgical parameters, carrying out the standardized preprocessing, and inputting the data into a deep neural network model with a double-branch structure, thereby achieving the extraction of the implant failure risk score and local causal association strength; on the basis of model output, a dynamic individualized causal map is constructed, key clinical intervention variables serve as regulation and control nodes, anti-fact disturbance simulation is carried out, variable intervention sensitivity is quantified, and a key causal path is analyzed; according to the method, a priority intervention suggestion list and an auxiliary decision report are generated, the causal atlas can be adaptively optimized according to actual follow-up feedback, long-term closed-loop evolution is realized, the accuracy of implant failure risk prediction and the pertinence and operability of an intervention scheme are improved, and clinical individualized treatment decision support is enhanced.

The invention belongs to the technical field of medical information, and particularly relates to a newly diagnosed HIV infected person antiviral treatment intelligent decision support system which comprises a multi-source data integration module, a medicine knowledge module, an individualized decision support module, an interactive output module, a knowledge optimization module and a safety and privacy protection module. The system replaces doctors to query and integrate patient data across multiple systems, clinical time is saved, key information omission is avoided, comprehensive data support is provided for treatment decisions, experience decisions are converted into systematic analysis and graded risk prompts are generated by means of an individualized decision support module, scheme deviation is effectively reduced, the medication risk is reduced, and the treatment efficiency is improved. The method assists the basic level in improving the treatment normalization, allows doctors to input new experience and new achievements summarized in practice into the system after double-blind auditing, and provides continuously iterative knowledge support for the scientificity of the antiviral treatment decision of the newly diagnosed HIV infected person.

This invention relates to the field of medical imaging systems, specifically disclosing a multimodal developmentally adapted intelligent diagnostic and differentiated treatment decision-making system for pediatric diseases. The system includes a multimodal data acquisition module for children, a developmental deviation quantification module, a physiological adaptive image standardization module, a multimodal physiological feature encoding module, a developmental constraint prediction model construction module, and a longitudinal incremental iteration module. Based on the DDI index and developmental grading, this invention generates spatial transformation and grayscale normalization parameters adapted to the child's developmental state, eliminating anatomical scale differences, refining the registration of key anatomical structures, dynamically adjusting deformation constraints, preserving core developmental and pathological features, avoiding registration artifacts, and establishing a solid foundation for high-precision data.

Embodiments pertain to a method of assessing the cardiometabolic health of a subject by (1) receiving a plurality of parameters of the subject, where the plurality of parameters includes a T2 relaxation time constant of a subject's blood (T2 value) and one or more additional parameters; and (2) feeding the plurality of parameters into an algorithm, where the algorithm correlates the plurality of parameters to the subject's cardiometabolic health. The methods may also include a step of communicating cardiometabolic health risk. The methods may also include a step of implementing a treatment decision. Further embodiments pertain to system for assessing the cardiometabolic health of a subject in accordance with such methods.

The present disclosure encompasses methods for molecularly subtyping formalin-fixed paraffin-embedded tumor samples. The disclosure works particularly well for old and degraded (archival) samples for which standard methods are unfeasible. Further, the methods disclosed allow for the correlation of patient outcome data with the molecular subtype of the tumor and provides a wealth of information which will guide treatment decisions and / or selection of therapeutic agents.

The application provides a cross-institutional referral intelligent routing method and system based on a medical intelligent agent middleware, relates to the technical field of medical informatization, and comprises the following steps: establishing a sign data monitoring window, mapping sign index changes and medication record time sequences, constructing a drug reaction sensitivity curve to calculate a treatment effective coefficient; adopting a dynamic time warping algorithm to match a drug-sign correlation graph, and generating a treatment decision tree; and predicting disease development, identifying the best referral opportunity and target institution based on the treatment effective coefficient and specialty characteristics. The application improves cross-institutional referral efficiency, optimizes medical resource allocation, and enhances patient treatment effect.

The disclosure relates to targeted Chromatin Accessibility and Mutation Sequencing (tCAM-seq) for parallel analysis of genetic and epigenetic analysis of patients with pancreatic adenocarcinoma (PDAC) to 1) determine responsiveness to standard of care chemotherapy, and 2) identify actionable allelic variant mutations that can be used to guide treatment decisions. Prognostic methods and treatment strategies are also provided.

The invention provides a knee osteoarthritis treatment decision-making tree system and device, and relates to the technical field of knee osteoarthritis treatment decision-making trees, and the system comprises a data receiving module, a data processing module and a result generation module. The data receiving module is used for receiving natural language text data and iconography image data of the patient and respectively preprocessing the natural language text data and the iconography image data; the data processing module comprises a text feature unit, an image feature unit and a decision unit; the decision-making unit is used for fusing the text features and the image quantization features to obtain comprehensive features; based on the comprehensive features, through a decision tree model, a treatment scheme for knee osteoarthritis is output; and the result generation module is used for sending out the treatment scheme. According to the scheme, information such as medical records of patients can be automatically analyzed, personalized treatment schemes are given, interference of human factors is reduced, real-time and objective decision support is provided for doctors, and therefore the diagnosis and treatment efficiency and effect are improved.

The invention provides a cross-institution referral intelligent routing method and system based on medical agent middleware, and relates to the technical field of medical informationization, and the method comprises the steps: building a physical sign data monitoring window, carrying out the time sequence mapping of physical sign index changes and medication records, constructing a drug response sensitivity curve, and calculating a treatment effective coefficient; adopting a dynamic time warping algorithm to match the medicine-physical sign association map, and generating a treatment decision tree; disease progression is predicted based on the effective treatment coefficients and specialized specialities, and the optimal referral opportunity and target mechanism are identified. According to the invention, the cross-mechanism referral efficiency is improved, the medical resource configuration is optimized, and the patient treatment effect is enhanced.

The application provides a disease-specific emergency whole-process auxiliary decision-making method based on multi-modal perception and AI, relates to the technical field of medical emergency, and comprises the following steps: acquiring multi-modal data of an emergency scene, constructing a feature dependency graph, and identifying disease types and symptom characteristics; indexing disease diagnosis and treatment data based on a symptom characteristic vector, determining reference cases and treatment paths; combining clinical norms to construct an action space, applying Monte Carlo search to predict expected returns, and generating an optimal treatment plan, which can improve the accuracy of emergency disease identification, shorten the treatment decision-making time, and improve the emergency intervention effect.

A method of detecting disease through analysis of hair images can indicate specific diseases is an intriguing topic intersecting dermatology, diagnostic medicine, and technology. By obtaining a hair from the body and analyzing images for fungus as an indicator of various health conditions. Disclosed herein is a methods relating to the classification of hair samples which can be used to identify and to diagnose conditions or to support treatment-related decisions.

The invention discloses a method and a system for rapidly drawing up an Angler class II malocclusion treatment scheme, and belongs to the field of orthodontics, and the method comprises the following steps: obtaining head shadow measurement data and model measurement data, and distributing a unique variable code for each data; calculating tooth extraction gap values corresponding to all upper and lower jaw tooth extraction combinations based on the obtained tooth crown widths; based on the data after the unique variable code is allocated and the tooth extraction gap value, establishing constraint conditions for the key parameters; all tooth extraction combinations of the upper jaw and the lower jaw are calculated one by one, Z treatment scheme candidate combinations meeting the constraint conditions are screened, and corresponding parameter calculation results are output. According to the method, a more accurate treatment scheme can be provided, the uncertainty of decision making can be effectively reduced in clinical practice, a clinician is helped to judge whether key treatment decisions such as tooth extraction and anchorage selection are needed or not through quantitative analysis, therefore, making of clinical decisions is assisted, and scientificity and accuracy of treatment planning are improved.

Devices, systems, and methods for monitoring of heart failure patient fluid volume with improved accuracy and reduced lag time to identify changes in volume status using one or more of passive, implantable sensors and non-invasive receiving equipment that measure the temporal variation in IVC area as a means to remotely assess and manage heart failure disease status and support self-management optionally employing a new, normalized index of heart failure (HF) congestion. The new normalized HF congestion index further contributes to improved speed and accuracy of heart failure diagnostic and treatment decisions and thus can help to improve patient outcomes and reduce hospitalization occurrences and costs.

The invention belongs to the technical field of intelligent medical treatment and clinical decision, and particularly relates to an idiopathic membranous nephropathy prognosis prediction method and system based on deep learning and a cross-modal attention mechanism. In order to realize accurate prognosis evaluation of IMN, depth features of a kidney tissue pathological image are automatically extracted through a deep learning technology and are innovatively and deeply fused with clinical data of a patient, and finally a high-precision and explainable intelligent prediction model is constructed to guide clinical early intervention and individualized treatment decision.

Embodiments of the present disclosure pertain to methods of assessing glioma in a subject by (1) receiving a plurality of measured biomarker levels of the subject; and (2) assessing glioma in the subject based on the measured biomarker levels by at least correlating differentially expressed levels of the measured biomarkers to at least one of (a) diagnosis of glioma, (b) progression of glioma, (c) treatment outcome, and / or (d) tumor burden. The methods of the present disclosure also include a step of (3) making a treatment decision based on the assessment. Additional embodiments of the present disclosure pertain to systems for assessing glioma in a subject.

The invention provides an intelligent collection and analysis system and method for emergency patient data, and relates to the technical field of intelligent analysis of the emergency patient data. The data analysis module is used for receiving the emergency patient data set transmitted by the multi-dimensional acquisition module; the data integration module is used for being responsible for integrating all the medical archives stored in the database; the independent coding library generation unit is used for integrating the data set based on the data integration module; according to the system, a received data set is analyzed by applying a machine learning algorithm and a medical knowledge rule, and a standard information data set is generated, so that the situation that a large amount of manpower and time need to be consumed for data conversion, cleaning and matching is reduced, the data processing cost is increased, and data errors and omission are likely to occur; the probability of data consistency and manageability is influenced, and the probability that the timeliness of treatment decision is influenced due to the fact that a doctor is difficult to quickly acquire required patient information in an emergency is reduced.

The invention provides an infertility patient pregnancy prediction method based on active learning and an integrated model, and the method comprises the following steps: carrying out the preprocessing of collected data, including classification variable coding, standardization processing and multi-dimensional abnormal value detection; generating a few categories of synthetic samples through an SMOTE technology, and optimizing data distribution in combination with a Tomek Links method; training a pregnancy prediction model based on machine learning models such as a random forest and XGBoost; the prediction results of the multiple basic models are fused through the Blending technology; based on an uncertainty sampling strategy, selecting samples for labeling and carrying out mixed training; and the pregnancy success prediction probability and credibility are output by inputting patient data. According to the method, the prediction accuracy and stability of the model can be improved, the robustness of the model to noise data and boundary samples is improved, the generalization ability of the model on new data is improved to a certain extent, doctors and patients can obtain more accurate treatment decision support, and the success rate and efficiency of IVF-ET treatment are improved.

This invention relates to the field of biomarkers. Specifically, this invention provides the application of trypsin-like enzymes in the preparation of products for assessing the prognosis of interventional treatment for acute ST-segment elevation myocardial infarction (STEMI). Furthermore, this invention provides a predictive model capable of assessing the prognosis of interventional treatment for STEMI. The model includes trypsin-like enzyme expression levels, the traditional TIMI risk scoring system, and patient clinical information. It exhibits extremely high predictive accuracy in determining whether MACE will occur after interventional treatment for STEMI, and can be effectively used clinically to identify high-risk groups for poor prognosis in STEMI patients at an early stage, providing strong support for patient treatment decisions and prognostic management.

The invention relates to the field of electrical stimulation, and provides a closed-loop control self-adaptive pain electrical stimulation system and method. The closed-loop control self-adaptive pain electrical stimulation system comprises a signal acquisition module; the signal processing module is used for extracting electroencephalogram features and pulse wave features; the pain recognition module is used for splicing the electroencephalogram features and the pulse wave features to form feature vectors, and then determining a current pain coefficient by using a mapping relation model of the feature vectors and pain coefficients; the electrical stimulation parameter adjusting module is used for obtaining an initial electrical stimulation parameter through the controller according to the difference between the preset target pain coefficient and the current pain coefficient, correcting the initial electrical stimulation parameter according to the correction coefficient to obtain a corrected electrical stimulation parameter, and sending the corrected electrical stimulation parameter to the controller; on the basis of the current electrical stimulation parameters, electroencephalogram signals and pulse wave signals of the individuals are collected again to determine corresponding pain coefficients, and the electrical stimulation parameters are iteratively adjusted until preset iteration stopping conditions are met. The system can assist doctors in making personalized pain treatment decisions.

The invention discloses a regional medicine management system, and aims to optimize medicine inventory management, use monitoring and distribution processes and ensure timeliness and safety of medicine supply. The system covers a plurality of modules of inventory acquisition and management, use condition acquisition, predicted use, distribution management and coordination and the like, predicts a drug consumption trend through an intelligent algorithm, and realizes accurate replenishment and efficient distribution. Meanwhile, a medicine locking and auditing mechanism is arranged in the system, and reasonable distribution of the shortage medicine is guaranteed. In addition, the system further comprises a disease treatment knowledge graph module, an intelligent treatment scheme recommendation module and the like, and scientific treatment decision support is provided for doctors. The system also has macroscopic distribution and disease development trend analysis functions to deal with emergencies such as sudden epidemic situations and ensure efficient allocation of drug resources. On the whole, the system significantly improves the efficiency and level of regional drug management through an informatization means.

The invention provides a therapeutic response model for acute myelogenous leukemia (AML) accompanied with myelodysplastic syndrome related genetic abnormality (MRGA) and application thereof, a survival risk scoring model and application thereof, and the survival risk scoring model is constructed based on the lifetime, cytogenetics abnormality, gene mutation and clinical factors of a patient. Patients are divided into a low-risk group, a medium-risk group and a high-risk group through the model, the AUC value of the patients reaches 0.789-0.831 in the period of 1-3 years, and the clinical practicability of the model in the aspect of making AML treatment decisions based on myeloid associated dysplasia (MRGA) is proved through remarkable survival differences among different risk groups. In addition, a combined scoring system for the treatment response and lifetime of the MRGA AML patient is further developed, and a new technical support is provided for clinical decision-making of the MRGA AML.

The application provides a palate midline suture maturity prediction method based on deep learning, obtains a plurality of head lateral film image samples, respectively labels palate midline suture maturity information, and obtains a head lateral film image dataset; a palate midline suture maturity prediction model is constructed, the palate midline suture maturity prediction model comprises an image preprocessing module, a feature extraction module, a hybrid multi-scale attention convolutional neural network and a feature fusion module; the head lateral film image dataset is used to train the palate midline suture maturity prediction model, and a trained palate midline suture maturity prediction model is obtained; after a head lateral film image to be predicted is input into the trained palate midline suture maturity prediction model, a palate midline suture maturity prediction result is obtained; the application can reduce subjective differences of artificial interpretation, can improve the accuracy, consistency and reliability of bone age prediction, can realize non-invasive, objective and efficient palate midline suture maturity prediction, and provides a scientific basis for clinical expansion arch treatment decision-making.

The invention belongs to the technical field of intelligent medical treatment, and discloses a gastric cancer far-end metastasis prediction method and system based on multiple examinations, and the method comprises the steps: firstly obtaining imaging, endoscope and blood examination data of the same patient; mapping each check original feature to a predefined unified semantic concept set, and converting the check original features into a unified dimension semantic embedding vector through a modal encoder adapted to a data type; then, a cross-modal semantic alignment module is constructed, and the same-semantic different-source vector distance is shortened based on comparative learning; semantic conflicts are detected, credibility weights of all sources are dynamically distributed, and same-semantic multi-source vectors are weighted and fused according to the weights to obtain fused feature vectors; and finally inputting a downstream prediction model to output a transfer prediction result. The method solves the problem of semantic conflict of multi-modal examination data, improves the prediction accuracy and stability, and provides a reliable basis for clinical treatment decision of gastric cancer.

A method and system for tracking movement includes performing person detection (204) in frames from multiple video streams to identify detected images. Visual and location information from the detected images is combined (206) to generate scores for pairs of detected images across the multiple video streams and across frames of each video stream. A pairwise detection graph is generated (210) using the detected images as nodes and the scores as weighted edges. Movements of individuals are tracked (212) based on a constrained answer set programming problem determined based on matching scores and logical assumptions. Actions corresponding to the tracked movements are performed (606). Tracking patient movements in a healthcare facility can be used to inform treatment decisions by medical professionals.

The present application relates to a kind of insomnia patient rTMS curative effect prediction method based on electroencephalogram microstate, comprising: step 1: obtaining data set, wherein the data set includes the baseline electroencephalogram microstate index of multiple insomnia patients and corresponding rTMS treatment effect category label;Step 2: establish curative effect prediction model, utilize data set to train curative effect prediction model;Step 3: according to the curative effect prediction model of training completion, the treatment effect of rTMS of insomnia patient to be predicted is predicted.The insomnia patient rTMS curative effect prediction method based on electroencephalogram microstate proposed in the present application, by carrying out rTMS treatment insomnia experiment to construct data set, further establish reliable curative effect prediction model, utilize the curative effect prediction model can accurately predict the treatment effect of rTMS to individual, can provide individualized treatment decision information and reasonable medical advice for insomnia patient.