Diagnosis method of auxiliary diagnosis model based on disease binary classifier
A binary classifier and auxiliary diagnosis technology, applied in the medical field, can solve problems such as uncertain number of class labels, difficult to distinguish diseases, and ambiguous relationship between class labels
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0034] Six respiratory diseases were selected as examples: pulmonary fungal infection, pneumoconiosis, pulmonary granuloma, radiation pneumonitis, bronchial tuberculosis, and chronic sinusitis.
[0035] Model training:
[0036] For patients with the six respiratory diseases mentioned above (lung fungal infection, pneumoconiosis, pulmonary granuloma, radiation pneumonitis, bronchial tuberculosis, chronic sinusitis), the characteristics of present illness history, physical examination, and imaging description were combined as its general description. Here we take the training of a binary classifier for pulmonary granuloma as an example. First, all patients diagnosed with "pulmonary granuloma" are used as positive samples, and negative samples are all patients with the other five diseases, and then the next step is screened.
[0037] First, BERT is used to generate representations of these samples, and then GMM is used to cluster these samples. Here, the range of the number of ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap