67 results about "Icu patients" patented technology

The invention discloses an ICU patient abnormity identification method based on video monitoring, and relates to the technical field of video monitoring, and the method comprises the steps: collecting historical data, building a standard set and a habit feature set according to the collected historical data, and generating a prediction set based on the standard set and the habit feature set; collecting real-time data, comparing the real-time data with the standard set, the habit feature set and the prediction set to obtain an abnormal coefficient of the data, calculating a comprehensive danger coefficient according to the abnormal coefficient of the data, and triggering early warning based on the comprehensive danger coefficient; a plurality of disease types of a patient are collected in real time, one disease type is screened out through a two-stage recognition method, the danger degree of the patient is quantified through calculation of a comprehensive danger coefficient, visual decision support is provided for medical staff, and the judgment accuracy is improved through comparative analysis of a standard set, a habit feature set and a prediction set.

The present invention discloses a method for early warning of ICU patient self-extubation behavior based on RGB video monitoring, which belongs to the field of computer vision behavior recognition. It includes constructing an ICU patient self-extubation behavior dataset, obtaining a patient self-extubation early warning classification model based on a neural network and based on optical flow behavior features in an ICU scenario based on the dataset, obtaining a video image texture feature classification result by the patient self-extubation early warning classification model in an ICU scenario based on a neural network, and obtaining a patient self-extubation optical flow behavior feature classification result by the patient self-extubation early warning classification model in an ICU scenario based on optical flow behavior features; the above two classification results are fused and used as input to build a dual-stream ICU scenario patient self-extubation early warning model, thereby realizing ICU patient self-extubation early warning work based on RGB monitoring video. The present invention solves the problem of incomplete feature extraction from a single-stream structure, and has the advantages of high real-time performance, high accuracy, full automation and contactlessness.

The invention discloses a multi-drug-resistant bacterium infection risk assessment method, system and device and a storage medium, and belongs to the technical field of medical data analysis, and the method comprises the steps: collecting a clinical related data set of an ICU patient, and carrying out the preprocessing of the clinical related data set to obtain a to-be-assessed data set; performing feature extraction on the to-be-evaluated data set in combination with a long short-term memory network and a time sequence attention mechanism to obtain a high-risk feature set; inputting the high-risk feature set into a pre-constructed dynamic scoring model, and calculating a corresponding risk score through the dynamic scoring model; and grading the risk score based on a preset grading rule to obtain a current risk level, and outputting a corresponding intervention strategy through a preset intervention decision mechanism based on the current risk level. According to the scheme, the high-risk feature set is extracted by combining the long-short-term memory network with the time sequence attention mechanism, then the risk score is calculated through the dynamic scoring model, the risk level is determined according to the preset grading rule, the intervention strategy is output, and the accuracy of MDRO infection assessment is improved.

The invention discloses an optimization system and method for a cognitive disorder intervention scheme of a post-ICU patient, and belongs to the technical field of medical rehabilitation. The optimization system comprises a multi-dimensional evaluation module, a personalized intervention strategy generation module and a dynamic monitoring and feedback module; the multi-dimensional evaluation module comprises a cognitive function evaluation unit, a physiological parameter monitoring unit and a psychological state evaluation unit; the personalized intervention strategy generation module comprises a non-drug intervention library, a drug intervention decision tree and an environment optimization parameter library. Comprising the following steps: acquiring a dynamic data set through a multi-dimensional evaluation module; when the SpO2lt is detected; the MoCA directional force score is reduced by gt; when the concentration is 30%, generating a combined strategy of oxygen therapy and execution function training; and optimizing the intervention strategy weight based on the reinforcement learning model. The method has the advantages that a multi-dimensional dynamic evaluation system breaks through the limitation of traditional static evaluation; a closed-loop dynamic adjustment mechanism is adopted, so that accurate intervention is realized; a multi-dimensional collaborative intervention system breaks through a single treatment mode; and the decision-making accuracy is high.

The utility model relates to the technical field related to medical care, in particular to a nursing waistband for an ICU (intensive care unit), which comprises a waist support and a positioning mechanism, the positioning mechanism is arranged on one side of the surface of the waist support, and a bunching component is mounted on one side of the surface of the waist support. According to the nursing waistband for the ICU, through the arrangement of the positioning mechanism, when the body position of an ICU patient needs to be restrained, a display screen can be clicked to control the controller, and due to the fact that the four sets of air bags are symmetrically distributed, the appropriate air bags can be selected through the controller to be inflated according to needs, so that the air bags at the corresponding positions are bulged, and the nursing waistband for the ICU is convenient to use. When the air bags on the two sides are inflated, a patient can be restrained in a flat lying position, and when the air bag on the single side is inflated, the patient can be restrained in a side lying position, so that the situation that the patient cannot keep the same position for a long time, and illness rehabilitation is affected is avoided; at the moment, the dustproof cover can be opened for charging through the charging interface.

The invention provides an ICU patient gastrointestinal complication risk prediction method and system based on time sequence data and a neural network. The method comprises the following steps: collecting time sequence physiological monitoring, static clinical and medical event data with timestamps of a patient, and constructing a dynamic time sequence knowledge graph in real time to represent clinical state evolution; map semantic embedding features are extracted from the map and fused with time sequence dynamic features extracted from the physiological data and static risk features extracted from the static data, and the fusion process is guided by map entity association; historical data and the corresponding atlas are used for training the risk prediction model, and atlas attenuation type label propagation based on atlas association is carried out on training labels according to the atlas structure and the time sequence path during training so as to optimize parameters; and inputting real-time data of a patient to be predicted into the trained model, and outputting a risk prediction result of gastrointestinal complications in a future time window. According to the method, the dynamic knowledge graph and deep learning are fused, and the accuracy and interpretability of risk prediction are improved.

The invention relates to an ICU patient delirium risk early screening system based on AI electrocardiogram analysis. The system comprises a neural signal extraction module, a component mode determination module, a delirium type identification module, a risk trajectory prediction module and a risk alarm generation module, wherein the neural signal extraction module extracts neuromodulation related signal fragments based on an electrocardiogram signal sequence and a preset neuromodulation specificity index; a component mode determination module extracts time sequence features from the fragments and determines an abnormal component distribution mode; the delirium type identification module is used for matching potential delirium types through the feature database; the risk trajectory prediction module predicts a risk trajectory in combination with a long-short-term memory network; a risk alert generation module evaluates a risk level and generates an alert. With the adoption of the system, early and dynamic screening of delirium risks can be realized, the screening accuracy and timeliness are improved through multi-module collaborative analysis, and accurate monitoring support is provided for ICU (Intensive Care Unit) patients.

The invention provides an ICU patient remote ward-round system and method based on VR, and the system achieves the immersive remote presentation of the state of an ICU patient through high-precision data synchronization, multi-mode interaction design and a low-delay rendering architecture, remarkably improves the doctor-patient communication efficiency and the psychological pacifying effect of family members, and improves the patient experience. And a brand-new digital solution is provided for an intensive care scene. A doctor can quickly position the abnormal states of multiple patients through a VR scene (for example, the doctor can check the breathing amplitudes of the patients in 10 wards at the same time), and the ward round efficiency is improved by 300% (the traditional polling ward round needs 15 minutes for each patient, and the VR system only needs 3 minutes). Clinical tests show that after VR is used for visiting, the score of an anxiety scale (GAD-7) of family members of a patient is averagely reduced, and the score is mainly attributed to'real contact feeling 'and vital sign transparency caused by tactile interaction.

This application provides a multi-agent, multimodal collaborative method, device, equipment, and storage medium for diagnosing the condition of patients in the intensive care unit (ICU), belonging to the field of medical artificial intelligence and intelligent analysis technology for intensive care. The method includes: receiving multimodal clinical monitoring data in an ICU setting, including bedside medical images, continuous life time series, and critical care clinical text; identifying and adaptively routing the input data through a modality detection agent, distributing it to corresponding domain expert agents for pathological and physiological feature extraction; constructing a patient-centric graph structure representing the dynamic clinical condition of ICU patients through a knowledge graph agent based on the features output by each domain expert agent, this graph structure integrating structured medical knowledge of entity extraction and relational reasoning; further, inputting the constructed graph structure and original multimodal features into a collaborative agent, generating the final ICU patient condition diagnosis result (such as mortality prediction, ICU long-stay prediction, etc.) and a traceable reasoning path through graph traversal and collaborative reasoning. This application effectively breaks down data silos between different monitoring devices in the intensive care unit environment, dynamically captures cross-modal associations specific to critically ill patients, and significantly improves the accuracy of critical care clinical diagnosis and medical trust.

The utility model belongs to the field of ICU (intensive care unit) patient transfer, particularly relates to an ICU patient transfer device, and aims to solve the problems that although a patient can be transferred during use in the prior art, medical personnel need to hold an infusion bottle during infusion of the patient in the transfer process, inconvenience is caused, a handle on a bed board cannot be stored, and inconvenience is caused. According to the technical scheme, the transfer bed comprises a transfer bed body, the transfer bed body is composed of a bottom plate, two supporting legs, two guardrails and a bed plate, the bottoms of the two supporting legs are fixedly connected with the two sides of the top of the bottom plate, the bottom of the bed plate is fixedly connected with the tops of the two supporting legs, and an infusion bottle is hung on an infusion support through an infusion mechanism. The concave barrel and the infusion support can be fixed through the first fixing mechanism and are convenient to disassemble, the guardrail can be fixed through the second fixing mechanism, and the concave barrel and the infusion support can be integrally stored through the storage mechanism.

This invention discloses a cold stimulation device for the rehabilitation of dysphagia in ICU patients, belonging to the field of dysphagia rehabilitation devices. The invention provides a cold stimulation device for the rehabilitation of dysphagia in ICU patients that enhances the effect of cold stimulation therapy. It includes a horizontal plate and an inclined plate. The horizontal plate is connected to the top of the inclined plate, and the horizontal plate is connected to symmetrically arranged arc frames. A nozzle is connected between the arc frames, and three rows of nozzles are opened at the rear of the nozzle. A cylinder is connected to the side of the nozzle away from the arc frames, and a movable circular plate is slidably connected to the cylinder. By moving the connecting frame forward, the connecting frame drives a threaded rod to rotate, which in turn drives the movable circular plate to move backward, directly spraying the cold stimulation liquid through the nozzles onto the patient's throat. Firstly, the direct contact of the cold stimulation liquid with the throat allows the patient's throat to receive continuous cold stimulation; secondly, the impact force generated by the spray enhances the stimulation of the patient's throat.

The invention relates to the technical field of molecular biomedicine, in particular to a method and system for predicting the outcome of an ICU patient based on bronchoalveolar lavage fluid mNGS flora in combination with machine learning. The mNGS detection technology disclosed by the invention comprises the following steps: extracting nucleic acid in pulmonary alveolar lavage fluid, constructing a library, sequencing on a machine, analyzing flora and constructing a machine learning prediction model. According to the invention, a method for accurately predicting the outcome of the ICU patient can be provided clinically.

The invention discloses an ICU patient closed-loop mode psychological intervention system and method based on physiological signal feedback, and belongs to the technical field of medical monitoring and intervention. The method comprises the following steps: acquiring a multi-modal physiological signal of an ICU patient, and generating a real-time physiological state vector; based on the physiological state vector, activating at least one intervention agent in an intervention agent cluster in parallel to generate an acting force vector; dynamically updating the state of a multi-dimensional intervention potential field according to the acting force vector; based on the state of the multi-dimensional intervention potential field, a multi-sensory intervention stimulus is synthesized and executed in real time. According to the method, the intervention decision-making system which is driven by a large number of agents following simple local rules and emerges from bottom to top is constructed, selection of an intervention scheme is converted into a physical process for seeking dynamic balance in an abstract potential field space, and therefore subtle changes of the physiological state of a patient can be accurately responded in real time; a highly personalized multi-sense organ healing microenvironment is generated, and the transformation from passive treatment to active and predictive intervention is realized.

The invention belongs to the technical field of artificial intelligence and medical health information processing, particularly relates to an ICU critical patient multi-mode risk early warning system based on deep learning, and aims to solve the problems that in intensive care, illness state prediction lags behind, multi-source data fusion is difficult, and single-index early warning precision is low. According to the system, high-frequency physiological signals, clinical observation values, inspection images and unstructured texts are collected through the data sensing layer, cross-modal embedding and comparative learning alignment are carried out through the heterogeneous fusion layer, and a shared semantic space is constructed; the time sequence reasoning layer utilizes an improved space-time diagram neural network to model a dynamic knowledge graph, and causal and time sequence dependence among clinical events is captured; and the risk decision-making layer outputs multi-dimensional risk probabilities of sepsis, respiratory failure and sudden cardiac arrest in parallel. The system supports online incremental learning and individualized time decay modeling, the timeliness, accuracy and interpretability of early warning are improved, and the method is obviously superior to a traditional method in clinical verification.

The invention discloses a shielding self-adaptive delirium monitoring system and method for an ICU (Intensive Care Unit) patient, and relates to the technical field of visual processing, and the method comprises the following steps: collecting continuous video streams and clinical metadata in a delirium monitoring process of the ICU patient; extracting a regional feature vector of the patient from the continuous video stream, wherein the region comprises a face region and a limb region; coding the clinical metadata into semantic vectors; performing interaction enhancement on the regional feature vector and the semantic vector to obtain a fusion feature vector; and outputting a delirium stage identification result according to the fusion feature vector. According to the invention, by constructing the occlusion perception adaptive fusion mechanism and dynamically adjusting the fusion weight of the multi-region features, stable monitoring in a complex ICU environment is realized, the delirium risk can be early warned, a key window is provided for clinical early intervention, and the problem that the face of a patient is seriously occluded by medical equipment, so that the face of the patient is affected is solved. The visual monitoring method is poor in robustness, and continuous and effective monitoring cannot be realized.

A wearable wireless temperature monitoring device includes a micromachined thermocouple probe fabricated on a Silicon-On-Insulator (SOI) substrate, including an electrically insulated housing and a microneedle probe. A doped silicon (Si)Zchrome (Cr)Zgold (Au) junction on the microneedle probe provides a Seebeck coefficient of approximately 447 μV / °C. The device further includes a wireless data communication transceiver positioned in the housing for continuous real-time temperature monitoring. The microneedle has a diameter of less than 100 microns and a submicron sharp tip for minimally invasive temperature measurements.

The invention relates to the technical field of medical information, and particularly discloses a method for identifying the death risk and safety index range of an ICU patient, and the method comprises the steps: obtaining vital sign data and blood gas analysis index data of the patient after entering the ICU; clustering results of the vital sign data are fused through consensus clustering fused with prognosis difference degree constraints, and patient subtypes are obtained; selecting a high-risk subtype; performing causal risk weighted two-factor interactive algorithm analysis on the high-risk subtype blood gas analysis index data to obtain a safety range of blood gas indexes; the blood gas index of the target patient after entering the ICU is obtained in real time, and the death risk of the target patient is judged. According to the invention, the typing stability is improved through ensemble learning, and the typing result is ensured to have clear clinical prognosis difference through prognosis constraint; and through a causal inference framework, hybrid bias is controlled, death risks are identified, and a key clinical index danger range is accurately defined for high-risk subtype patients.

1. Name of the designed product: patient gown (ICU). 2. Use of the designed product: the designed product is used for patient gown for ICU patients. 3. Design points of the designed product: in shape. 4. Picture or photo that best indicates the design points: perspective view. 5. The designed product is a thin product, omitting the left view; the designed product is a thin product, omitting the right view; the designed product is a thin product, omitting the top view; the designed product is a thin product, omitting the bottom view.

The invention relates to the technical field of medical instruments, and discloses an adjustable old ICU patient restraint nursing suite which comprises a bed body, a bed sheet is arranged on the upper side of the bed body, a restraint frame is arranged above the bed sheet, and a plurality of restraint air bags are sequentially fixed to the inner wall of the restraint frame from top to bottom; a plurality of pressure sensors are arranged on the side, away from the bed body, of the restraint air bag, first electric push rods are arranged on the two sides of the bed body correspondingly, the output ends of the two first electric push rods are rotationally connected to the two sides of the restraint frame correspondingly, and a controller is arranged on one side of one first electric push rod; and the controller is electrically connected with the pressure sensor. Through the first electric push rod, the restraint frame, the controller and the pressure sensor, the pressure between the restraint air bag and the patient is maintained in a proper range, and therefore the problem that under the condition that the elderly patient suffers from severe pain, the body turns around and moves, and the pain of the patient is increased due to interference of the four limbs and the restraint device is solved.

A method of improving glycemic control is provided. The method includes stimulating a cutaneous distribution of a subject's vagus nerve within the subject's ear with a nerve stimulating signal. The method also includes monitoring the subject's blood glucose. The method further includes administering insulin infusions to the subject.

The utility model relates to the field of medical instruments, and discloses a saliva receiving container for a neurosurgery ICU patient, which comprises a cover nozzle, the cover nozzle is worn on the head of the patient through an elastic rope, a monitoring component and an adjusting component are arranged on the elastic rope in series, the monitoring component comprises a monitoring tube shell, and a piston is sleeved in the monitoring tube shell. A spring is arranged between the piston and the shell cover, a sensor is arranged in the monitoring tube shell, the adjusting assembly comprises an adjusting tube shell, a rope winding shaft is installed in the adjusting tube shell, a coil spring is arranged at the installation position, an inserting shaft is arranged in the small-diameter section of the rope winding shaft in a sleeved mode, and at the beginning, the spline section of the inserting shaft is in spline connection with the small-diameter section. The end of the smooth section of the inserting shaft extends out of the adjusting pipe shell and is provided with a button, the inserting shaft and the adjusting pipe shell form sliding connection, the monitoring pipe shell and the adjusting pipe shell are connected through a second rope, the piston and the cover nozzle are connected through a first rope, a third rope is wound on the rope winding shaft, and the tail end of the third rope extends out of the monitoring pipe shell and is connected with the cover nozzle.

The invention provides an ICU patient multi-dimensional vital sign real-time monitoring and data early warning system. The system is applied to a monitoring system integrating vital signs, an environment sensor and a clinical operation recorder. The system firstly calculates a real-time standard deviation and a mean value of vital sign data, and generates a dynamic weight through an exponential decay function; standardizing the environmental parameters and performing weighted summation to obtain environmental influence factors; meanwhile, the clinical operation data is subjected to weighted processing, and a logarithmic function is applied to generate contribution terms. And inputting the vital sign data after dynamic weight adjustment, the environmental factors and the operation contribution items into a mode recognition engine, and dynamically optimizing harmonic coefficients by the engine according to a mode recognition result, calculating a comprehensive risk index and generating an early warning. According to the method, through multi-source data fusion and dynamic weight adjustment, accurate risk assessment is realized, the false alarm rate is reduced, and the early warning real-time performance is improved.

The utility model provides a kind of anti-pressure sore bedpan device for ICU patient, including support, the accommodating groove recessed in the support, and be equipped in the accommodating groove two-way drive assembly and cushioning component, the cushioning component includes the support platform connected with the two-way drive assembly, the bedpan placement slot recessed in the support platform, and detachably equipped in the bedpan placement slot bedpan, the bedpan includes rigid body part, and be equipped on the rigid body part elastic part, the bionic curved surface for adhering human body hip is formed on the elastic part.The anti-pressure sore bedpan device for ICU patient in the utility model, the pressure of sacrococcygeal part and ischial tuberosity is dispersed by the elastic part on bedpan, and the unilateral pressure concentration of hip when long-term bedridden patient is in toilet is reduced by two-way drive assembly, to avoid pressure sore.

The invention discloses a critical patient brain function assessment method and system based on electroencephalogram analysis. The method comprises the steps that 1, EEG signals are collected; 2, a data buffering and windowing step; 3, a sub-window data preprocessing step; 4, a brain function prediction step; and 5, a data visualization and alarm step. The evaluation system comprises an EEG signal acquisition device, an EEG signal acquisition module, a data processing module, a brain function prediction module and a visualization module. The critical patient brain function assessment method and system based on electroencephalogram analysis have the advantages that subtle changes of the consciousness state can be captured in time clinically, and objective, continuous and real-time prediction of the brain function state of an ICU patient is achieved.

The invention discloses an ICU patient intelligent wearable rehabilitation training device with a surface myoelectricity feedback function, and relates to the technical field of rehabilitation training. A connecting assembly is arranged at one end of the body assembly, a driving assembly is arranged on one side of the connecting assembly, a massage assembly is arranged on the other side of the connecting assembly, a mounting assembly is arranged on the side face of the body assembly, collecting assemblies are arranged at the two ends of the mounting assembly, and a processing assembly is arranged on the side face of the mounting assembly. Training information is fed back to a patient through the motion state and the function level of muscles of the patient, so that operation of a stepping motor is controlled, personalized training intensity and time are formulated, a front end frame and a rear end frame drive thighs and shanks to conduct inclined rehabilitation training respectively, meanwhile, a rubber massage head massages the muscles around leg joints, and the rehabilitation training effect is achieved. Therefore, the rehabilitation training device can be worn, the rehabilitation training accuracy is guaranteed, the rehabilitation effect of the patient is improved, and the physical condition of the patient is better adapted.

The invention discloses a real-time disease deterioration prediction system based on multi-modal data, and belongs to the technical field of auxiliary medical treatment based on deep learning. Based on a bidirectional encoder characterization model, a Transform model and a text generation model, the ICU model can be accessed to a monitor, an electronic medical record system and the like to obtain multi-modal data, including real-time high-frequency physiological signals, clinical text records, image reports and the like, and the condition deterioration probability of ICU patients in multiple different time periods in the future is predicted; and an interpretable report is generated to prompt a doctor of a basis for model evaluation. According to the invention, complex multi-modal medical data can be processed, disease change of the ICU patient can be detected in real time, early discovery, early intervention and early treatment can be realized, and the method has great potential in optimizing medical resource distribution, improving working efficiency of medical staff and reducing death rate of the ICU patient. In addition, the method is high in generalization ability, and a special system can be developed for specific departments and specific diseases, so that the prediction accuracy and the result credibility are improved.

The invention discloses an ICU (intensive care unit) medicine intelligent blending and information management system, which relates to the technical field of intelligent medical treatment and comprises a data acquisition module, a data integration module, a dose calibration module, a consumption analysis module and an inventory management module. Multi-modal physiological sign data of an ICU patient are collected in real time through the data collection module and preprocessed into standardized physiological sign data, the data integration module is connected with the electronic medical record system to extract clinical basic data and basic sign baseline data, and a unified diagnosis and treatment data set is formed through correlation and integration. The dosage calibration module calculates the adjusted individualized medication dosage and generates an individualized medication instruction on the basis of the unified diagnosis and treatment data set in combination with clinical medication specifications and physical sign fluctuation-dosage adjustment rules, so that the medication dosage is accurately matched with the individual characteristics of the patient and real-time illness state changes, medicine allocation better meets the diagnosis and treatment requirements of the ICU patient, and the diagnosis and treatment efficiency of the ICU patient is improved. And the limitation of a fixed dose scheme is avoided.

The application discloses an ICU patient risk early warning monitoring method and system based on time series data analysis, relates to the technical field of medical information processing and artificial intelligence, and takes synchronously collected electroencephalogram time series signals and electrocardiogram time series signals as original inputs, extracts an autonomic nervous regulation signal from the electrocardiogram signals through heart rate variability analysis, carries out individualized multi-scale decomposition on the electroencephalogram signals and the heart rate variability signals by using adaptive wavelet packet decomposition, separates out a nervous frequency band component and an autonomic nervous frequency band component, extracts the instantaneous phase of each frequency band component by using Hilbert transformation, calculates a cross-frequency band phase locking index to quantize the brain-heart cross-system phase synchronization strength, continuously generates brain-heart coupling features along a time axis sliding window, compares the brain-heart coupling features with an established personalized baseline reference mode, identifies a coupling mode collapse sequence feature, generates an early warning signal when the feature is identified, and realizes early warning of delirium risk of ICU patients.

The utility model discloses a bedside table for nursing an ICU (Intensive Care Unit) patient, which can properly or pre-classify and store various articles according to the illness state and the treatment and nursing requirements of the patient, is convenient for medical personnel to quickly find and take for use when needed, and can flexibly expand and store an operation platform and space according to the treatment and nursing operation requirements. According to the technical scheme, the storage cabinet is characterized by comprising a cabinet body, drawers, a hanging frame, a storage seat and a combination plate, the storage seat is located at the position, close to the edge, of the upper portion of the cabinet body, a plurality of storage grooves in different shapes are formed in the storage seat, and the storage grooves are adaptively arranged corresponding to existing medicine bottles, medicine bags and medical tools in shape; the hanging frame is movably arranged on the side wall of the cabinet body, the hanging frame can be stored or stretched outwards for a certain distance from the cabinet body through an adjusting assembly, the combined plate is arranged in the cabinet body in a drawing mode, and the combined plate can be expanded and positioned at a bedrail of a sickbed.

The utility model belongs to the technical field of medical hospital gowns, and particularly relates to an ICU (intensive care unit) hospital gown which comprises two pieces of front chest sewing cloth which are symmetrically arranged, one sides of the two pieces of front chest sewing cloth are sewn with back repairing sewing cloth, and the edges of the back repairing sewing cloth and the front chest sewing cloth are fixedly sewn with sleeves. A back protection cloth is arranged on the rear side of the rear repair sewing cloth, the two sides of the top edge of the back protection cloth are sewn to the outer side of the rear repair sewing cloth, and extending fixing belts are fixedly sewn to the two sides of the back protection cloth. The back protection cloth is turned backwards to the back area of the patient, so that the back of the patient is protected when the patient sits, the risk that the back of the patient gets cold when the patient sits can be reduced, meanwhile, the back protection cloth is turned backwards to be arranged on the back of the patient in a sleeving mode after the patient sits up, and the back of the patient is protected. And the hospital gown which originally covers the outside of the body of the patient can be prevented from sliding down when the patient sits up.