32 results about "Pulmonary disease" patented technology

The application discloses a medical data processing method and product based on multi-stage transfer learning and multi-modal data collaborative fusion, relates to the technical field of medical data processing and artificial intelligence, and adopts MedicalNet medical special pre-training weights to initialize a classification model backbone network; a three-stage progressive fine-tuning framework is constructed on the basis, field adaptive coarse classification fine-tuning and target task fine classification are performed, and clinical structured data is introduced in the third stage; after high-dimensional image features are reduced in dimension and low-dimensional clinical features are increased in dimension through an adaptive multi-branch multi-level MLP architecture, mid-term deep fusion is performed, the application can effectively mine the complex relationships such as complementation, correlation and cooperation of multi-modal heterogeneous data, improve the lung disease classification precision and model generalization capability, and significantly inhibit the small sample overfitting phenomenon.

A deep learning system that detects and counts A-lines in lung images obtained with the VSI protocol, allowing untrained personnel to perform scans. By segmenting and counting A-lines, the system distinguishes between healthy lungs and conditions such as pneumonia or edema, without a specialist intervention. The Attention U-Net architecture improves accuracy, and A-line counting provides quantitative data for diagnostics. This approach aims to expand access to diagnostics, specially in resource-limited areas, offering a scalable solution for early detection of lung disease.

This invention relates to catheter and handle assemblies for tissue treatment. More specifically, the invention relates to a catheter assembly having an elongated shaft, an ablation component coupled to one end of the shaft, and a handle coupled to the other end of the shaft. The handle facilitates axial and circumferential positioning of the ablation component via the shaft in an airway, tubing, or blood vessel for tissue treatment. Embodiments include using the handle during treatment of lung diseases such as COPD and asthma to facilitate axial and circumferential positioning of the shaft and ablation component through and independently of the working channel of a bronchoscope.

The invention relates to the technical field of traditional Chinese medicines, in particular to a traditional Chinese medicine composition for treating lung diseases and a preparation method and application thereof. The traditional Chinese medicine composition comprises the following raw materials: codonopsis pilosula, astragalus membranaceus, white mulberry root-bark, oyster, salvia miltiorrhiza, houttuynia cordata, loofah sponge, angelica sinensis, ligusticum wallichii, peach kernel, lumbricus, radix stephaniae tetrandrae, radix peucedani, radix stemonae, spina gleditsiae, radix curcumae and acanthopanax. Based on the'lung-intestinal axis' theory, by tonifying qi and lung, clearing heat and eliminating phlegm, promoting blood circulation and dredging collaterals, relieving cough and asthma and remodeling intestinal flora of a patient, the level of inflammatory factors is reduced, and the risk of acute exacerbation is reduced. Clinical application shows that the traditional Chinese medicine composition can effectively improve the clinical symptoms of patients, reduce the levels of IL-1beta, IL-6 and TNF-alpha and regulate the intestinal flora structure, and has good treatment potential.

The utility model discloses a powder collection device of powder coating powder outlet, which aims to solve the technical problem that the existing laboratory sample printing small capacity high speed mixer lacks a dustproof mechanism in the powder collection process of the powder outlet, and the dust of the powder coating may be inhaled by the human body, which may cause respiratory tract irritation or long-term lung disease. The utility model discloses a high speed mixer, a mixing barrel arranged on the top of the high speed mixer, a lower drive motor group fixedly connected to the center of the bottom surface of the mixing barrel, a hinged barrel cover arranged on the edge of the top of the mixing barrel, a discharge channel fixedly arranged on the edge of the bottom surface of the mixing barrel, a manual discharge door fixedly arranged on the inlet of the discharge channel and a receiving barrel. The discharge channel comprises a discharge port. The discharge port is detachably sleeved with a first dustproof cloth and a second dustproof cloth which are through from top to bottom. The first dustproof cloth is located outside the second dustproof cloth. The first dustproof cloth is circumferentially arrayed with a plurality of deformable metal strips along the vertical direction.

The invention relates to a catheter and handle assembly for treating tissue. More specifically, the present invention relates to catheter assemblies having an elongate shaft, an ablation assembly coupled to one end of the shaft, and a handle coupled to the other end of the shaft. The handle facilitates axial and circumferential positioning of the ablation assembly through the shaft in the airway, conduit or vessel for treatment of tissue. Embodiments include the use of a handle to facilitate axial and circumferential positioning of the shaft and ablation assembly through and independent of the working channel of the bronchoscope during the treatment of pulmonary diseases such as COPD and asthma.

Provided are an inhalable pharmaceutical preparation, an apparatus using same, and use thereof in treating pulmonary diseases. The inhalable pharmaceutical preparation comprises a propellant, at least two active pharmaceutical ingredients, a cosolvent, and an anti-aggregation agent, wherein the cosolvent is selected from ethanol and absolute ethanol, and the propellant is tetrafluoropropene.

The present application relates to a method for detecting lung disease by cough sound, which specifically comprises: removing non-cough sound segments from original cough audio to obtain cough audio, and obtaining the start and end time of each single cough segment in the cough audio; generating a logarithmic mel-cepstrum matrix corresponding to each single cough segment according to the start and end time of each single cough segment, and calculating a position encoding matrix corresponding to each single cough segment; obtaining a feature matrix of the cough audio according to the logarithmic mel-cepstrum matrix and the position encoding matrix corresponding to each single cough segment; multiplying the normalized feature matrix of the cough audio by a proportion factor, adding the obtained product to the feature matrix of the cough audio, and inputting the result into a classification network for classification. The present application also relates to a device comprising a cough sound detection unit, an audio signal processing unit, a splicing unit, a normalization unit and a classification network unit. The method and device of the present application can improve the accuracy of the detection result.

The invention provides methods and compositions relating to identification and use of genetic information from the FOXO3A gene that can be used for determining and increasing an individual's likelihood of longevity and of retaining physical and cognitive function during aging, and for determining and decreasing an individual's likelihood of developing a cardiovascular-, metabolic- or age-related disease, including coronary artery (heart) disease, stroke, cancer, chronic pulmonary disease, diabetes, Parkinson's disease and dementia.

The application discloses a medical data processing method and product based on multi-stage transfer learning and multi-modal data collaborative fusion, relates to the technical field of medical data processing and artificial intelligence, and adopts MedicalNet medical special pre-training weights to initialize a classification model backbone network; a three-stage progressive fine-tuning framework is constructed on the basis, field adaptive coarse classification fine-tuning and target task fine classification are performed, and clinical structured data is introduced in the third stage; after high-dimensional image features are reduced in dimension and low-dimensional clinical features are increased in dimension through an adaptive multi-branch multi-level MLP architecture, mid-term deep fusion is performed, the application can effectively mine the complex relationships such as complementation, correlation and cooperation of multi-modal heterogeneous data, improve the lung disease classification precision and model generalization capability, and significantly inhibit the small sample overfitting phenomenon.

DEEP LEARNING-BASED DEVICE FOR EARLY LUNG DISEASE DETECTION

The present application relates to the technical field of traditional Chinese medicine, and particularly relates to a traditional Chinese medicine composition for treating pulmonary diseases and a preparation method and application thereof.The traditional Chinese medicine composition comprises the following raw materials: radix codonopsis, radix astragali, cortex mori, oyster, radix salviae miltiorrhizae, hedyotis diffusae, luffa, angelica sinensis, ligusticum wallichii, persicae semen, earthworm, radix stephaniae tetrandrae, radix peucedani, radices baphlai, kadsurae caudice, radix notoginseng and acanthopanax.The present application is based on the theory of lung-intestine axis, and can improve the clinical symptoms of patients, reduce the levels of IL-1beta, IL-6 and TNF-alpha, regulate the structure of intestinal flora, and has good treatment potential by tonifying qi and tonifying lung, clearing heat and reducing phlegm, promoting blood circulation and dredging collaterals, relieving cough and asthma, and remodeling intestinal flora of patients.

A positive expiratory pressure-generating device for reducing breathlessness in a subject with one or more pulmonary disorders is disclosed. The device is rigid and hollow and can be held in the mouth of the subject. The device has at least one air chamber, at least one opening in the portion of the device that is held in the mouth and at least one additional airflow orifice. The device is configured to increase expiratory resistance and can be supported by the mouth of the subject without the need for additional support by hands, another device or other means.

The utility model relates to the technical field of cooling fans, in particular to an active oxygen water spray cooling fan which comprises a shell with an opening in the side face and a water spray outlet fixedly installed at the opening and further comprises a water spray pipeline connected with an inlet of the water spray outlet, and the water spray pipeline comprises a water pump, a water flow pipeline, a BDD active oxygen generator, an atomization device and a spray head which are sequentially connected. A light plasma generator is arranged between the nozzle outlet and the water mist outlet, and the light plasma generation direction of the light plasma generator is aligned with the outlet of the water mist outlet. According to the active oxygen water spray cooling fan, the bdd active oxygen generator is arranged in the water conveying pipeline, used for generating water mist, of a conventional cooling fan, water is prepared into active oxygen water in the pipeline, then the active oxygen water is sent to the atomization spray head to be sprayed out, biological pollution in water is reduced through the water mist formed through active oxygen water sterilization, and the water mist is sprayed out. Lung diseases caused by the fact that workers in a service area inhale untreated water mist are reduced.

This invention discloses a medicinal and edible homologous composition and its application in the preparation of drugs or foods for improving chronic lung diseases, belonging to the field of pharmaceutical technology. The medicinal and edible homologous composition of this invention uses donkey-hide gelatin and astragalus as the principal ingredient, apricot kernel and burdock seed as the assistant ingredient, loquat leaf as the adjuvant ingredient, and platycodon and licorice as the auxiliary and guiding ingredients. Through the use of volatile oil extraction and re-addition techniques, as well as the separate "melting" of donkey-hide gelatin, the heat-sensitive volatile oil components in the raw medicinal materials are preserved, and a networked regulatory mode of "synthesis promotion-degradation inhibition-signal enhancement" is constructed, achieving deep activation of the cAMP pathway. The medicinal and edible homologous composition has pharmacological activities that improve lung function and inhibit airway inflammation. The activity is significantly superior to that of donkey-hide gelatin, roflumilast, and hormones used alone; the medicinal and edible homologous composition exhibits excellent synergistic effects in the treatment of COPD and asthma, and has improving and therapeutic effects on chronic lung diseases induced by inflammation, bronchoconstriction, and mucus secretion, and can delay the progression of COPD and asthma, providing a new approach and direction for the preparation of drugs or foods that improve chronic lung diseases; this invention can provide core technical support for the secondary development of traditional Chinese medicine compound prescriptions and the creation of new drugs, thereby effectively promoting the modernization of traditional Chinese medicine.

The present invention relates to compounds of formula I as prostaglandin E2 receptor 4 (EP4) agonists for use in methods of treatment of gastrointestinal and pulmonary diseases or disorders. The present disclosure provides exemplary compounds and pharmacological data.

This invention discloses a traditional Chinese medicine composition containing donkey-hide gelatin and its application in the preparation of drugs or foods for the prevention and / or treatment of chronic lung diseases, belonging to the field of traditional Chinese medicine technology. This invention provides a traditional Chinese medicine composition containing donkey-hide gelatin, which is a compound formula containing donkey-hide gelatin. Donkey-hide gelatin is the principal ingredient, burdock seed and clam shell are the assistant ingredients, apricot kernel is the adjuvant ingredient, and glutinous rice and prepared licorice root are the guiding ingredients. Through this combination, a multi-target synergistic regulatory mechanism is achieved. By synergistically inhibiting the PI3K / Akt signaling pathway through multiple targets and pathways, it significantly reduces airway inflammation, airway hyperresponsiveness, and serum IgE levels in the model. The traditional Chinese medicine composition provided by this invention has a simple and easy preparation process, employing a combined technique of water extraction and volatile oil extraction to maximize the retention of active ingredients. The traditional Chinese medicine composition provided by this invention solves the problems of single target or unclear mechanism in existing technologies, and has broad application prospects in the use of traditional Chinese medicine compositions containing donkey-hide gelatin in the prevention and / or treatment of chronic lung diseases.

In the diagnosis process, a clinician makes full use of multi-modal information such as chief complaint, medical images and laboratory test results. A deep learning model used for auxiliary diagnosis does not meet the requirement. In some aspects, a transformer-based representation learning model may be used as a clinical diagnostic aid for processing multi-modal inputs in a unified manner. The model does not learn modal-specific features, but uses an embedded layer to convert an image, an unstructured text and a structured text into visual lexical elements and text lexical elements. And using bi-directional blocks with intra-modal and inter-modal attention to learn an overall representation of radiographs, unstructured chief complaints and medical records, structured clinical information, such as laboratory test results and patient demographic information. The performance of the unified model in the aspect of lung disease recognition exceeds that of an only image model and that of a non-unified multi-modal diagnosis model (respectively improved by 12% and 9%), and the performance of the unified model in the aspect of COVID-19 patient adverse clinical outcome prediction exceeds that of the only image model and that of the non-unified multi-modal diagnosis model (respectively improved by 29% and 7%). A unified multi-mode transformer-based model is fully utilized, so that a patient triage process can be simplified, and a clinical decision-making process is promoted.

Provided is a liposomal sustained-release composition for use in treatment of pulmonary disease. The liposomal sustained release composition comprises a liposome that includes a polyethylene glycol (PEG)-modified lipid and encapsulates a tyrosine kinase inhibitor. Tyrosine kinase inhibitor is stably entrapped in the liposome, and the resulting liposomal drug formulation can be aerosolized or nebulized for administration via inhalation. This aerosolized liposomal drug formulation yields consistent pharmacokinetic and pharmacodynamic profiles while achieving desired efficacy and safety.

The invention provides a factor combination for improving the anti-pulmonary fibrosis capability of mesenchymal stem cells and reducing the risk of pulmonary thrombosis and application of the factor combination, and relates to the technical field of biology. The factor composition comprises (I) interferon gamma, wherein the acting concentration of the interferon gamma is 0.5-5ng / mL; and (II) an interleukin 4 and / or a tumor necrosis factor alpha, the action concentration of the interleukin 4 being 1-20 ng / mL, and the action concentration of the tumor necrosis factor alpha being 1-25 ng / mL. The mesenchymal stem cells treated by the factor combination not only can improve the anti-pulmonary fibrosis ability of the mesenchymal stem cells, but also can regulate the expression of CD142 in the mesenchymal stem cells and reduce the risk of pulmonary thrombosis of the mesenchymal stem cells, does not promote the occurrence of inflammations, is beneficial to improving the treatment effect and prognosis of patients with lung diseases, and has a wide application prospect. And a new thought is provided for clinical application of MSC in lung diseases.

The present invention relates to a pharmaceutical composition for the prevention or treatment of chronic pulmonary disease comprising exosomes derived from stem cells treated with thrombin as an active ingredient, a pharmaceutical preparation containing the same, and a method for preparing the same. The exosome-based therapeutic agent according to the present invention has the following advantages: it is a cell-free preparation, thus having a low risk of oncogenicity, and there is no problem of graft rejection; there is no concern of capillary obstruction when administered systemically; since it is an isolated material rather than a cell, the agent can be developed in the form of a finished product, reducing production costs; and an excellent therapeutic effect on chronic pulmonary disease is obtained with a low concentration of exosomes by treatment with thrombin.

This disclosure relates to the treatment of interleukin (IL-33)-mediated diseases, including pulmonary diseases. In particular, this disclosure relates to IL-33-binding proteins, including anti-IL-33 antibodies, and their uses in the treatment of IL-33-mediated diseases.

Modulators of extracellular signal-regulated kinase, pharmaceutical compositions thereof, and uses of the compound and pharmaceutical compositions thereof for treating cancer and pulmonary diseases are disclosed.

During the diagnostic process, clinicians leverage multimodal information, such as the chief complaint, medical images, and laboratory-test results. Deep-learning models for aiding diagnosis have yet to meet this requirement. In some aspects, a transformer-based representation-learning model can be used as a clinical-diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model uses embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and bidirectional blocks with intramodal and intermodal attention to learn holistic representations of radiographs, the unstructured chief complaint and clinical history, structured clinical information such as laboratory-test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary disease (by 12%and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29%and 7%, respectively). Leveraging unified multimodal transformer-based models may help streamline the triaging of patients and facilitate the clinical decision process.

To provide a new therapeutic strategy for dealing with fundamental genetic / molecular defects of hereditary pulmonary disease patients.SOLUTION: Provided are recombinant nucleic acids comprising one or more polynucleotides encoding a polypeptide (e.g., an inhaled therapeutic polypeptide, such as a human alpha-1-antitrypsin polypeptide); viruses comprising the recombinant nucleic acids; compositions and formulations comprising the recombinant nucleic acids and / or viruses; methods of use thereof (e.g., to deliver a polypeptide to one or more cells of the respiratory tract and / or for the treatment of a disease affecting the lungs, such as alpha-1-antitrypsin deficiency); and articles of manufacture or kits thereof.SELECTED DRAWING: Figure 3