A data-driven approach to decode metabolic dysfunction-associated steatotic liver disease

Area of Science:

• Hepatology
• Artificial Intelligence
• Precision Medicine

Background:

• Metabolic dysfunction-associated steatotic liver disease (MASLD) is the most prevalent cause of chronic liver disease globally, impacting approximately one-third of the population.
• MASLD presents a significant public health challenge due to its variable clinical progression and outcomes, posing a challenge for precision medicine.
• The heterogeneity of MASLD necessitates advanced analytical approaches for effective patient stratification and treatment development.

Purpose of the Study:

• To review the diverse applications of artificial intelligence (AI) and machine learning (ML) in the field of MASLD.
• To explore how AI/ML can enhance patient stratification, biomarker discovery, and therapeutic target identification in MASLD.
• To highlight the role of multimodal data sources and large-scale databases, exemplified by SteatoSITE, in advancing MASLD research.

Main Methods:

• Review of current literature on AI and ML applications in MASLD.
• Analysis of AI/ML use in electronic health records, digital pathology, and medical imaging for MASLD.
• Examination of data commons and consortia leveraging multimodal data for MASLD research.

Main Results:

• AI and ML are increasingly utilized for quantitative and automated analysis in MASLD.
• These technologies show promise in improving patient stratification and identifying novel biomarkers and therapeutic targets.
• Multimodal data integration and large-scale databases are crucial for accelerating research breakthroughs.

Conclusions:

• AI and ML offer powerful tools to address the complexities of MASLD.
• Enhanced data analysis through AI/ML can lead to personalized medicine approaches for MASLD patients.
• The development of data commons like SteatoSITE is vital for overcoming technical challenges and fostering collaborative MASLD research.