Machine Learning Approaches Based on Multiscale Data in Diagnosis, Treatment and Prognosis of Diseases
1Nanjing Drum Tower Hospital, Nanjing, China
2Nanjing Medical University, Changzhou, China
3Nanjing Medical University First Affiliated Hospital, Nanjing, China
4Shanghai Jiaotong University Renji Hospital, Shanghai, China
5David Geffen School of Medicine at UCLA, Los Angeles, USA
6Veer Bahadur Singh Purvanchal University, Jaunpur, India
Machine Learning Approaches Based on Multiscale Data in Diagnosis, Treatment and Prognosis of Diseases
Description
Recently, machine learning has gathered attention in medical research, especially when different technologies have supplied an abundance of data. The complicated data sets are based on image technologies including x-ray, ultrasound, CT, MRI, PET-CT, immunohistochemistry, dermoscopy, and molecular assays such as single-cell sequencing, high throughput DNA/RNA sequencing, TCR-seq, ATAC-seq, and so on.
With sophisticated algorithms applied to large-scale, heterogeneous data sets, we may uncover valuable patterns that even experienced individuals would hardly identify. It is an enormous challenge to dig for useful information from the massive data. Although machine learning has played a transformative role in the diagnosis, treatment, and prognosis of many diseases, significant challenges remain unresolved. More high-quality datasets that are expansive and multi-center are needed to ensure the robust evaluation of machine learning models and new algorithms are expected to enhance the performance of the computational approaches.
This Special Issue focuses on exploring multi-scale datasets with computational approaches, aiming to shed light on the underlying biomedical phenomena. The Special Issue intends to help improve diagnostics, facilitate precision treatment and predict disease prognosis through clinical imaging and molecular tests. We welcome original research and review articles.
Potential topics include but are not limited to the following:
- Machine learning-based methods for the establishment of noninvasive diagnosis of diseases
- Machine learning-based methods for predicting the prognosis of diseases
- Machine learning-based methods for guiding personalized medical treatments
- Machine learning-based methods for guiding post-treatment management
- Computational approaches to analyze clinical images for image biomarkers
- Computational approaches to reveal the molecular mechanisms of diseases
- Comparisons of different computational approaches for the same purpose in medicine
- Application of computational approaches or machine learning-based methods in multi-omics analysis of diseases
- Application of computational approaches or machine learning-based methods in drug sensitivity
- Application of computational approaches or machine learning-based methods in immunotherapy response rate