876 results about "Early detection" patented technology

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

The invention relates to the technical field of production debugging control, and discloses a production debugging control method and system for a plastic container. The method comprises the following steps: arranging a plurality of different sensors in plastic container blow molding equipment, and simultaneously collecting blow molding process parameter data; performing wavelet threshold denoising and anomaly identification on the blow molding process parameter data to obtain a process parameter anomaly identification result; establishing a transfer function matrix between the process parameters and quality indexes according to the process parameter anomaly identification result, and obtaining a target process parameter set through multi-target optimization; and inputting the target process parameter set into a double-integral enhanced recurrent neural network for parameter regulation and control calculation to obtain a process parameter adjustment amount. According to the method, early detection and accurate positioning of process abnormity in the blow molding process are realized, the quality fluctuation risk and the defective product rate are greatly reduced, and the technical problem that different response characteristic parameters are difficult to coordinate is solved.

The invention discloses a multi-modal cognitive impairment evaluation system based on a multi-dimensional cognitive function hypergraph. The multi-modal cognitive impairment evaluation system comprises a multi-modal signal acquisition system, a cognitive function evaluation normal form design, a universal feature extraction framework of each modal and online hypergraph learning based on a multi-dimensional cognitive function. The system constructs a dimensionality evaluation normal form containing the cognitive function based on multi-modal physiological and behavior signals, so that comprehensive evaluation of the cognitive function of the elderly is realized. Firstly, physiological and behavior responses of a user under different tasks and situations are recorded and analyzed in real time by fusing multi-mode signals such as electroencephalogram, electrocardio, voice and facial expressions. And then, mining fusion representation among the multi-modal signals, generating unified feature representation, introducing an online hypergraph of clinical knowledge, capturing a complex multi-modal data relationship, and providing an analysis result containing cognitive function evaluation. Finally, in combination with the technical means, the system can realize early detection of cognitive impairment.

The invention discloses a GIS-based urban underground pipe network monitoring and early warning platform, and relates to the technical field of underground pipe network early warning. A data acquisition module is used for acquiring a pressure fluctuation signal in a pipeline, fluid flow data, a pipe wall vibration spectrum and surrounding soil moisture content change data in real time to form a multi-source time sequence data set; the feature extraction module is used for performing wavelet packet decomposition on the pressure signals, extracting high-frequency-band micro pressure pulsation features, processing vibration data by adopting empirical mode decomposition, and separating a normal operation mode and an abnormal disturbance component of a pipeline, so that the early detection capability of micro leakage is remarkably improved, the false alarm rate is reduced, and meanwhile, high-precision positioning is realized; reliable technical guarantee is provided for safe operation of the underground pipe network, and resource waste and safety accidents caused by tiny leakage are effectively avoided.

This document generally describes methods and systems for generating digital reconstructions of tissue from humans or other species. The method can, for example, include receiving, at a computing system, image data of a tissue sample, where one or more sections of the tissue sample are stained with hematoxylin and eosin (H&E), registering the image data to generate registered image data, identifying tissue subtypes based on application of a machine learning model to the registered image data, annotating the identified tissue subtypes to generate annotated image data, and determining a digital volume of the tissue sample in three dimensional (3D) space based on the annotated image data. The disclosed technology can provide for single-cell analysis and other analysis of tissue samples, such as early detection of cancer in human tissue samples.

The subject matter described herein includes methods, systems, and computer readable media for early detection of a neurodevelopmental or psychiatric disorder using scalable computational behavioral phenotyping. According to one method for early detection of a neurodevelopmental or psychiatric disorder using scalable computational behavioral phenotyping includes obtaining user related information, wherein the user related information includes metrics derived from a user interacting with one or more applications executing on at least one user device; generating, using the user related information and a machine learning based model, a user assessment report including a prediction value indicating a likelihood that the user has a neurodevelopmental or psychiatric (neurodevelopmental / psychiatric) disorder and a prediction confidence value computed using relative contributions of the metrics to the prediction value generated using the machine learning based model; and providing the user assessment report to a display or a data store.

The invention discloses a PCB surface defect detection method and system, an electronic device and a medium, and relates to the technical field of defect detection, the connection condition caused by excessive tin soldering of a tin bridge or adjacent welding spots can be automatically identified by judging the connection state between the welding spots, an overall detection instruction is triggered, early detection is facilitated, connectivity defects are avoided, and the detection efficiency is improved. And the welding spot connection reliability is improved. The image is divided into a plurality of image blocks, the texture difference data of each image block is obtained, the texture abnormal state of the surface of the PCB can be finely analyzed by calculating the texture deviation coefficient, the subtle texture change in different areas can be identified by the block analysis method, and surface defects such as scratches and bubbles on the surface of the PCB can be accurately detected. And in combination with the texture deviation coefficient and the geometric features of the welding spots, unified normalization fitting is performed on the defect features to generate the defect recognition index, so that the defect features of different types can be captured, and the robustness and accuracy of the model can be improved.

The invention discloses an aircraft intelligent maintenance and diagnosis system, and relates to the technical field of aircraft maintenance and diagnosis, and the system comprises a data collection module which is used for collecting various data in the actual operation of an aircraft. According to the invention, a digital twin model construction module is utilized to accurately simulate the operation state and fault condition of the aircraft, early discovery and accurate diagnosis of potential faults are realized, the pertinence and effectiveness of maintenance are improved, immersive fault experience and maintenance guidance are provided for maintenance personnel through fusion of VR / AR technologies, and the maintenance efficiency is improved. The maintenance accuracy and efficiency are improved, pre-diagnosis and maintenance scheme verification are carried out on the digital twin model, unnecessary disassembly and detection work is avoided, the maintenance time and labor cost are reduced, potential safety hazards can be eliminated in time through accurate fault diagnosis and an effective maintenance scheme, the flight safety of an aircraft is improved, and the safety of the aircraft is improved. And the maintenance scheme is comprehensively evaluated and optimized, so that the performance and the structural integrity of the maintained aircraft are ensured.

The present invention relates to the fields of child health monitoring and artificial intelligence technology, and provides a child scoliosis monitoring and early warning system. Existing methods rely on static inspections, and it is difficult to capture abnormal dynamic changes of the spine in real time. The present invention acquires multimodal data through posture sensors, acceleration sensors, and image acquisition devices, combines convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) to perform deep feature extraction, and uses hidden Markov models (HMMs) to identify children's behavioral contexts and dynamically adjust the early warning threshold. The system uses a Q-learning algorithm to generate personalized health intervention strategies, and uses differential privacy and homomorphic encryption technologies to ensure data security. Finally, the system generates a three-level health warning signal to immediately remind children to adjust their postures and notify guardians. The present invention realizes real-time monitoring and personalized intervention of spinal health, provides an efficient and safe health management solution, and promotes the early detection and correction of scoliosis.

The invention relates to the technical field of wind power generation, in particular to a blade icing diagnosis method and device, an intelligent deicing system and a storage medium. According to the invention, blade icing diagnosis is carried out by adopting multi-modal data, the early detection accuracy of blade icing is improved, the false alarm rate of single sensor detection is reduced, and accurate diagnosis of blade icing is realized. When the multi-modal data is processed, a dynamic alignment algorithm is adopted, the limitation that traditional data alignment only depends on timestamps is broken through, meteorological data is introduced to serve as an alignment constraint condition, and the problem that physical relevance of the multi-modal data is missing is solved. And meanwhile, a hybrid expert architecture is adopted to process the multi-modal data, so that effective fusion and high-robustness diagnosis of the multi-modal data are realized.

An exemplary system and method are disclosed that is configured to detect cognitive impairment (e.g., early cognitive impairment) or assess cognitive function by analyzing, via machine learning and artificial intelligence analysis, behavioral metadata collected from a smart app during the course when a subject is using a cognitive test instrument for cognitive tests that incorporate motor activity (e.g., drawing or writing). The machine learning and artificial intelligence analysis can execute features associated with the test taker's metadata (e.g., time spent on task or questions, changing answers, referring back to the previous question), drawing qualities (e.g., line straightness, completeness), among others.

The invention discloses a three-dimensional positron emission tomography data image classification method based on multi-stage progressive feature extraction, and is applied to the technical field of Alzheimer's disease auxiliary diagnosis. The auxiliary diagnosis method comprises the following steps: acquiring and preprocessing PET image data of an Alzheimer's disease patient; improving the reliability of the data set by using data enhancement; performing long-range dynamic modeling on the three-dimensional voxel sequence through a stacked Lmamba block; global context semantic adaptive fusion is realized through a layer-by-layer cross-scale channel attention fusion module (CSACF), and a channel spatial perception module (CSPM) is constructed to optimize spatial feature fusion; an inverted bottleneck module is mixed with long-distance space and position information to enhance the capturing capability of the model on detail features; and finally, predicting the disease category probability through global average pooling, full connection and softmax functions. According to the method, the precision of AD early diagnosis and MCI conversion risk prediction can be greatly improved, the defects of a medical image diagnosis method of a convolutional neural network (CNN) and Transform in long-range dependence on modeling and calculation complexity are overcome, and the method has good application prospects and is suitable for AD early detection and MCI conversion risk assessment.

The invention relates to a system for early detection and risk prediction of schizophrenia. The system comprises a feature extraction module which performs parallel processing on a multi-mode original signal; the fusion prediction module fuses the voice feature signal, the behavior feature signal and the clinical feature signal through a cross-modal attention weighting mechanism to generate a fusion feature vector, and outputs an initial risk prediction signal through a machine learning classifier based on the vector; the dynamic updating module receives an incremental characteristic signal triggered by newly added collected data of a user, generates an updating risk prediction signal through incremental learning, and feeds back the updating risk prediction signal to the fusion prediction module to optimize the weight of a classifier; and the visual output module converts the updated risk prediction signal into a dynamic risk trajectory diagram and an interpretable feature contribution thermodynamic diagram. The system for early detection and risk prediction of schizophrenia can solve the problems that early screening of schizophrenia lags behind and dynamic risk assessment is missing.

The invention discloses a power transformation equipment working condition detection system and method based on self-adaption, and relates to the field of power equipment state monitoring. The method comprises the following steps: collecting multi-source monitoring data of power transformation equipment and carrying out standardization processing to generate standard time sequence data; dividing a time window based on working conditions, extracting characteristic parameters, and constructing a characteristic track; establishing and updating an adaptive reference library containing standard reference points and health tolerance boundaries under different working conditions based on historical health data; comparing the real-time characteristic track with a standard reference point and a health tolerance boundary of a corresponding working condition in a self-adaptive reference library, calculating a deviation degree and generating an operation health index; and determining a dynamic early warning threshold value according to the historical operation health index data, and judging the state of the equipment by comparing the real-time operation health index with the dynamic early warning threshold value and a preset rigid alarm threshold value. And early discovery of weak degradation of the internal coordination relation of the power transformation equipment is realized by constructing a comparison mechanism of a self-adaptive health benchmark and a feature trajectory.

The invention discloses an older child infantile autism evaluation system based on multi-modal data analysis. The older child infantile autism evaluation system comprises a multi-modal signal acquisition module and a multi-modal feature extraction and fusion module. The multi-modal signal acquisition module is used for acquiring physiological signals, behavior signals and scale data; and the multi-modal feature extraction and fusion module is used for extracting and fusing the features of the modal signals, generating unified feature representation, and providing an analysis result including autism evaluation in combination with scale data so as to realize the autism evaluation of the older children. According to the invention, early detection of older children can be realized.

The invention belongs to the technical field of magnetic nanoparticle imaging, particularly relates to an MPI magnetic particle imaging method and system for early detection of an AD patient, and aims to complete MPI time sequence imaging by using a diffusion model and solve the problem that the feature dimension of an input signal in the diffusion model is not matched with the resolution of an expected generated image. The method comprises the following steps: constructing a generative network model, and performing staged training; mPI time sequence one-dimensional signals are collected, and image reconstruction is carried out based on the generative network model to obtain MPI time sequence images; carrying out registration and dividing a brain region; and constructing a functional connection diagram and a functional connection matrix by using the RV coefficient, and drawing the brain network. According to the method, by constructing the Seq-VAE / Regression / Sig-LDM step-by-step network and performing staged training, free input of a signal sequence of a fixed feature dimension is realized, the image sequence reconstruction effect is improved, a default mode network is drawn based on the reconstructed image sequence, and accurate data is provided for subsequent application.

The invention discloses a preparation method of Au (at) Au (at) Ag / Pt / M NPs and application of the Au (at) Au (at) Ag / Pt / M NPs in klebsiella pneumoniae detection, and belongs to the technical field of analysis and detection. The invention particularly relates to development of a signal probe and combination and assembly of the signal probe and lateral flow immunochromatography (LFIA) for klebsiella pneumoniae detection. Au (at) Au (at) Ag / Pt / MNPs is a multi-element noble metal nanoparticle with plasma resonance property, peroxidase-like activity and light stability, shows strong detection potential in three modes of colorimetric (CM), catalytic colorimetric (CL) and surface enhanced Raman scattering (SERS), and is loaded into LFIA to construct a multi-mode LFIA (CM / CL / SERS-LFIA). The kit is expected to be used for direct multimode detection of klebsiella pneumoniae in clinical sputum samples, and a new early detection strategy is provided for respiratory tract infection diseases such as klebsiella pneumoniae.

The invention relates to the technical field of medical clinical auxiliary diagnosis, in particular to an orthopedic postoperative complication early detection and early warning system based on data analysis, which comprises a multi-modal sign synchronous acquisition module, a sign dynamic difference quantification module, a complication feature association module, a grading early warning decision module and a dissection calibration visualization module. Wherein the multi-modal sign synchronous acquisition module is used for acquiring postoperative data of a patient; calculating a difference quantization parameter; the complication characteristic association module is used for identifying associated risk characteristics of the osteofascia ventricular syndrome, the deep venous thrombosis and the fat embolism; and the grading early warning decision module is used for generating a three-level early warning instruction based on the associated risk characteristics. According to the system and the method, through a multi-modal sign synchronous acquisition, difference quantification and grading early warning linkage mechanism, accurate recognition, risk grade division and visual intervention guidance of postoperative complications are realized, and the continuity of postoperative monitoring and the timeliness of early warning are improved.

The invention discloses a basin-type insulator internal defect detection system and method based on pulse infrared thermal waves, and relates to the technical field of nondestructive testing and computer vision, and the basin-type insulator internal defect detection system comprises a pulse infrared thermal wave excitation module, an infrared thermal imaging module and a data processing module; the pulse infrared thermal wave excitation module is used for enabling the surface of the insulator to generate thermal response in a pulse infrared thermal wave excitation mode; the infrared thermal imaging module captures the temperature change of the surface of the insulator in real time and performs early detection; and the data processing module is used for data preprocessing, feature extraction and defect detection. According to the method for detecting the internal defect of the basin-type insulator based on the pulse infrared thermal wave, the pulse infrared thermal wave excitation and the high-precision infrared thermal imaging technology are combined, so that the bubble defect in the insulator is efficiently detected. The pulse infrared thermal wave technology generates instantaneous temperature change on the surface of the insulator, so that the bubble defect is more obvious, and the detection sensitivity and speed are improved.

The invention provides a scoliosis screening method and system, and relates to the technical field of medical artificial intelligence, human body image data on a low-light detection garment worn by a patient is collected, the human body image data is preprocessed and sent to an SSD module, the SSD module is used for predicting the position of a low-light light source, and a scoliosis detection result is obtained. The key point detection module is used for detecting human body scoliosis, high-precision detection frame information in the detection result is used as a basis, a human body posture result predicted by the key point detection module is restrained and corrected, then human body scoliosis grading is performed, a human body scoliosis detection result is displayed and fed back to a patient, high-precision detection of scoliosis is achieved, and the system has the advantages of high efficiency, non-invasiveness and light weight; the scoliosis early detection rate and grading intervention precision can be remarkably improved, and the problems that traditional medical diagnosis is low in efficiency, large in radiation risk, insufficient in precision and difficult to operate on embedded equipment with limited resources are solved.

The invention discloses a diabetic foot early-stage detection method combining infrared and visible light imaging, and relates to the technical field of diabetic foot medical imaging diagnos.The diabetic foot early-stage detection method comprises the steps that multi-mode image collection and standardization processing are conducted, infrared images and visible light images are synchronously collected, and standardization processing such as size normalization is conducted; image registration and space alignment are carried out, marking points are set based on foot anatomical features, and feature extraction, mismatching point elimination and transformation matrix calculation are carried out; extracting and screening multi-dimensional features, extracting temperature and structural features, and screening by using a Relief-F algorithm; feature lesion recognition and classification are fused, and lesion probability is output through a double-branch convolutional neural network; carrying out detection result verification and feedback optimization, and comparing a clinical diagnosis optimization model; and generating a detection report and storing data, and generating a report containing the fused image. The early lesion detection precision is improved through multi-modal fusion, individual and environment differences are adjusted and adapted in a personalized mode, and reliable technical support is provided for clinic.

The invention provides a cardiovascular trend prediction method and system based on time sequence medical health data, and relates to the technical field of medical health data analysis. The method comprises the following steps: collecting time sequence medical health data of a patient through a multi-source sensor, wherein the time sequence medical health data comprises dynamic physiological indexes such as heart rate, blood pressure and oxyhemoglobin saturation; performing time calibration and feature extraction on the acquired multi-source data; constructing a time sequence feature model based on the time sequence features, and fusing the time sequence feature model with the static information of the patient to generate a comprehensive feature vector; using a deep learning model to train historical data, and learning a dynamic change rule of cardiovascular health indexes; predicting the change trend of the cardiovascular health indexes in real time, and evaluating the risk level of cardiovascular diseases; the model parameters are optimized through online learning, the prediction precision is improved, the change trend of cardiovascular health indexes can be predicted in real time, and support is provided for early discovery and personalized medical treatment of cardiovascular diseases.

The invention provides a tumor real-time tracking and benign and malignant detection method based on a mammary gland ultrasonic video, and the method comprises the steps: collecting the mammary gland ultrasonic video in real time, and inputting the mammary gland ultrasonic video into an UltraNet basic detector to generate a detection result of each frame of ultrasonic image; calculating a similarity probability matrix Si, j to reflect the similarity between the ith target and the jth target; performing cascade matching on the target based on the similarity probability matrix Si, j to form a target track pipeline Ti; and carrying out confidence coefficient updating and bounding box position updating on the detection result in each target track pipeline Ti, and finally outputting a breast lesion detection result of each frame of ultrasonic image. The tumor real-time tracking and benign and malignant detection method based on the breast ultrasonic video has the advantages of high calculation efficiency, high precision and strong robustness, can assist a doctor in accurately positioning a focus and performing diagnosis, and is beneficial to early discovery of breast diseases.

The method for determining the myocardial fibrosis evaluation model comprises the following steps: acquiring an ultrasonic image of a target rabbit in an echocardiography; performing feature extraction on the ultrasonic image by using a plurality of preset feature extraction models to form a plurality of feature sets; performing representative feature screening on each feature set by using a plurality of preset feature screening models to form a plurality of feature representative sets; performing feature classification on each feature representative set by using various preset classifiers to form a plurality of classification results; and determining a myocardial fibrosis evaluation model according to the classification result corresponding to each feature set. The problem that in the prior art, no auxiliary diagnosis technology for myocardial fibrosis of living organisms through ultrasonic image analysis exists is solved, robust evaluation on the severity of myocardial fibrosis of people is promoted, and early detection and longitudinal monitoring become possible.

The invention discloses a radionuclide labeled molecular probe for detecting collagen structure denaturation and a preparation method and application thereof, and relates to the technical field of biology. The structural general formula of the radionuclide labeled molecular probe disclosed by the invention is as follows: K (chelating agent-nuclide)-K-Linker-CHP, wherein K (chelating agent-nuclide) is a lysine residue labeled by a side chain amino coupling chelating agent and a radionuclide; the Linker is a connection joint; cHP is a collagen hybrid peptide with a polypeptide sequence of (GfO) n or (GPO) n. The probe has excellent definition and signal-to-noise ratio, not only can detect pancreatic ductal adenocarcinoma in a pancreatic cancer model, but also can sensitively detect precancerous lesions (such as pancreatic intraepithelial neoplasia lesions) of the pancreatic ductal adenocarcinoma and pulmonary fibrosis lesions in a bleomycin pulmonary fibrosis model. And the kit has important significance on early detection of pancreatic duct adenocarcinoma and reflection of dynamic change of ECM remodeling.

The invention relates to the field of all-weather safety monitoring in the chemical industry, and discloses an all-weather chemical plant monitoring method, which comprises the following steps: dynamically acquiring quantum state measurement data of environmental parameters through a quantum dot array, capturing parameters such as temperature, pressure and gas concentration in real time by the quantum dot array through a tunneling effect, the sensing principle is based on the displacement effect of the quantum limited energy level; mapping the measurement data to a five-dimensional AdS spatio-temporal manifold and calculating an Einstein tensor; based on the Einstein tensor, solving topology invariant and curvature evolution of the space-time manifold; generating an algebraic decision instruction according to the topology invariant; and the encrypted control signal is fed back to the execution mechanism through the topology photon link. Through dynamic coupling of the quantum dot array and the five-dimensional AdS space-time manifold, cross-scale correlation monitoring of quantum state fluctuation and macroscopic deformation is achieved, the recognition blind area of a traditional method for micro-nano defects is broken through, and the early detection rate of pipeline microcracks is increased by two orders of magnitude.

The invention provides a teenager depression auxiliary diagnosis model training method and system based on multi-modal data, and relates to the technical field of mental health. According to the method, firstly, a VR intelligent interaction scene is constructed, and physiological data of juvenile depression and physiological data of a normal contrast subject in the VR intelligent interaction scene are synchronously collected; data preprocessing and feature extraction are conducted on the electroencephalogram data, the heart rate variability data and the eye movement data, a single-mode depression recognition model is obtained through classifier training, and then a multi-mode depression recognition model and a cross-mode depression recognition model are obtained. The teenager depression auxiliary diagnosis model obtained through machine learning is helpful for early discovery and timely treatment of teenager depression.

The invention relates to the technical field of power equipment fault detection, in particular to a fault detection method for a ring main unit, and aims to solve the problems that in the prior art, the ring main unit of an urban power distribution network and an industrial park faces complex working condition challenges for a long time, and the challenges include severe load fluctuation, electromagnetic interference superposition and multi-node collaborative abnormity. According to the method, the problem of multi-node collaborative anomaly detection under complex working conditions is effectively solved, and the risk of misjudgment caused by electromagnetic interference and load fluctuation is reduced. The position of an abnormal terminal is accurately positioned, the fault cause is judged, and operation and maintenance resource waste caused by blind inspection in a traditional method is avoided. Through the synergistic effect of multi-modal data fusion and topology learning, the early slight anomaly detection rate is remarkably improved, and progressive faults are prevented from developing into equipment damage accidents.

The present disclosure, in some aspects, provides one or more biomarkers (e.g., plasma biomarkers or circulating biomarkers) for Facioscapulohumeral muscular dystrophy (FSHD). In some embodiments, a biomarker (e.g., plasma biomarkers or circulating biomarkers) described herein is regulated by DUX4. Methods (e.g., non-invasive methods) of using the biomarkers, e.g., for detection (e.g., early detection) and monitoring patient as well as treatment efficacy are also provided. The present disclosure, in other aspects, provides one or more biomarkers (e.g., transcriptome biomarkers) for Facioscapulohumeral muscular dystrophy (FSHD). In some embodiments, a biomarker (e.g., transcriptome biomarkers) described herein is regulated by DUX4. Methods of using the biomarkers, e.g., for detection (e.g., early detection) and monitoring patient as well as treatment efficacy are also provided.

The invention relates to the technical field of medical treatment, and discloses a patient cognitive impairment recognition method and system and electronic device.The method comprises the steps that patient original data are obtained, and the patient original data comprise clinical biochemical data, image data and cognitive behavior data; preprocessing the original data of the patient to obtain preprocessed data; feature extraction is conducted on the preprocessed data, key features are obtained, and the key features comprise clinical biochemical features, image features and cognitive behavior features; fusing the clinical biochemical features, the image features and the cognitive behavior features to obtain fused features; and determining a cognitive impairment recognition result based on the fusion features and the cognitive impairment recognition function. According to the embodiment of the invention, the early detection rate of cognitive impairment of the pituitary adenoma patient is improved, missed diagnosis and misdiagnosis are reduced, and the early warning cognitive risk when obvious clinical symptoms do not appear in cognitive impairment recognition of the pituitary adenoma patient is reduced.