Jadwal Sholat

Memuat jadwal sholatโ€ฆ

Ilmu Komputer & AI editorial

Open AccessOA2024

Advances in AI and Machine Learning for Predictive Medicine

This review explores how deep learning, particularly convolutional neural networks (CNNs), revolutionizes predictive modeling in omics by converting tabular data into image-like representations via methods like DeepInsight. It highlights enhanced predictive power and transfer learning benefits, while addressing challenges in interpretability, data heterogeneity, and size.
Alok Sharma; Artem Lysenko; Shang-Ru Jia; K. Boroevich; T. Tsunodaยท Journal of Human Geneticsยท 2024ยท DOI 10.1038/s10038-024-01231-y

The core problem

The field of omics, driven by advances in high-throughput sequencing, faces a data explosion. This abundance of data offers unprecedented opportunities for predictive modeling in precision medicine, but also presents formidable challenges in data analysis and interpretation. Traditional machine learning (ML) techniques have been partly successful in generating predictive models for omics analysis but exhibit limitations in handling potential relationships within the data for more accurate prediction. This review explores a revolutionary shift in predictive modeling through the application of deep learning (DL), specifically convolutional neural networks (CNNs).

Innovation

The authors review the application of deep learning, particularly CNNs, to omics data. A key methodological innovation is the use of transformation methods such as DeepInsight, which convert omics data with independent variables in tabular (table-like, including vector) form into image-like representations. This enables CNNs to capture latent features effectively. The review discusses how this approach not only enhances predictive power but also leverages transfer learning, reducing computational time and improving performance.
Introduction
The field of omics, driven by advances in high-throughput sequencing, faces a data explosion. This abundance of data offers unprecedented opportunities for predictive modeling in precision medicine, but also presents formidable challenges in data analysis and interpretation. Traditional machine learning (ML) techniques have been partly successful in generating predictive models for omics analysis but exhibit limitations in handling potential relationships within the data for more accurate prediction. This review explores a revolutionary shift in predictive modeling through the application of deep learning (DL), specifically convolutional neural networks (CNNs).

Why it matters

The authors illuminate the complexities of using CNNs in omics data analysis and chart a course for future research to unlock the full predictive potential of CNNs in omics data analysis and related fields. Addressing these challenges requires a multidisciplinary approach, involving collaborations between ML experts, bioinformatics researchers, biologists, and medical doctors. The review emphasizes that while CNNs offer significant advantages, careful consideration of interpretability, data heterogeneity, and data size is essential for successful implementation in precision medicine.

Who should read this

Pembaca Research Digest dan praktisi rumpun ini.

Opening member contentโ€ฆ