<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The dynamics of microbial communities are closely related to human health. Deep learning techniques have shown great potential in bioinformatics by demonstrating powerful data analysis capabilities in areas such as microbial data modeling and disease Prediction since recent years. Our paper explores new approaches combining deep learning techniques with microbial data to generate more precise predictive models for early diagnosis and treatment. This study is dedicated to developing a method for modeling microbial data and predicting diseases that incorporates deep learning. Multiple deep learning models combine data from microbial communities to improve prediction accuracy through an integrated learning strategy. Experiments were conducted on two primary disease datasets: Inflammatory Bowel Disease (IBD) and Colorectal Cancer (Colorectal). This research method’s AUC values were 0.897 and 0.876, which is an improvement compared to traditional machine learning methods. A new perspective on the study of disease mechanisms was provided by identifying highly correlated microbial markers through feature selection analysis. This study can effectively enhance the use of microbial data in disease prediction by integrating deep learning models, which provides powerful technical support for future clinical diagnosis and treatment.</p>
</abstract>

The dynamics of microbial communities are closely related to human health. Deep learning techniques have shown great potential in bioinformatics by demonstrating powerful data analysis capabilities in areas such as microbial data modeling and disease Prediction since recent years. Our paper explores new approaches combining deep learning techniques with microbial data to generate more precise predictive models for early diagnosis and treatment. This study is dedicated to developing a method for modeling microbial data and predicting diseases that incorporates deep learning. Multiple deep learning models combine data from microbial communities to improve prediction accuracy through an integrated learning strategy. Experiments were conducted on two primary disease datasets: Inflammatory Bowel Disease (IBD) and Colorectal Cancer (Colorectal). This research method’s AUC values were 0.897 and 0.876, which is an improvement compared to traditional machine learning methods. A new perspective on the study of disease mechanisms was provided by identifying highly correlated microbial markers through feature selection analysis. This study can effectively enhance the use of microbial data in disease prediction by integrating deep learning models, which provides powerful technical support for future clinical diagnosis and treatment.

Research on microbial data modeling and disease prediction by fusion and integration of deep learning

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The dynamics of microbial communities are closely related to human health. Deep learning techniques have shown great potential in bioinformatics by...

Research on microbial data modeling and disease prediction by fusion and integration of deep learning

Data publikacji: 03 maj 2024

Zakres stron: -

Otrzymano: 20 kwi 2024

Przyjęty: 28 kwi 2024

DOI: https://doi.org/10.2478/amns-2024-0884

Słowa kluczowe
Deep learning, Microbial data modeling, Disease prediction, Integrated learning

© 2024 Zidong Wang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on microbial data modeling and disease prediction by fusion and integration of deep learning

Data publikacji: 03 maj 2024

Zakres stron: -

Otrzymano: 20 kwi 2024

Przyjęty: 28 kwi 2024

DOI: https://doi.org/10.2478/amns-2024-0884

Słowa kluczoweDeep learning, Microbial data modeling, Disease prediction, Integrated learning

© 2024 Zidong Wang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Słowa kluczowe
Deep learning, Microbial data modeling, Disease prediction, Integrated learning