About
Asthma is a common and complex disease with substantial heritability. It has been shown that asthma is associated with clinical variables and genetics, but their association to asthma is still not sufficiently characterized. Currently, there is no gold standard for diagnosis of asthma because of its heterogeneity and complexity. Thus, an accurate asthma prediction model is on demand. With the growth of big data in the biomedical community, researchers are able to use a large sample size and large scale of variables to predict disease status with higher accuracy. Thus, in this study, we propose to use deep learning to train a prediction model for asthma diagnosis by using the UK Biobank samples. Our final prediction model will be freely accessible to the research community. This can help asthma to be diagnosed more accurately. We expect that this study takes around 15 months.
2 Returns
Return ID | App ID | Description | Archive Date |
3582 | 43252 | Glycated Hemoglobin A1c, Lung Function, and Hospitalizations Among Adults with Asthma | 22 Jun 2021 |
3653 | 43252 | Serum free testosterone and asthma, asthma hospitalisations and lung function in British adults | 15 Jul 2021 |
2 Publications
Pub ID | Title | Author(s) | Year | Journal |
3583 | Glycated Hemoglobin A1c, Lung Function, and Hospitalizations Among Adults with Asthma | Yang G et al. | 2020 | J Allergy Clin Immunol Pract |
3654 | Serum free testosterone and asthma, asthma hospitalisations and lung function in British adults | Han YY et al. | 2020 | Thorax |