Clinlabomics: leveraging clinical laboratory data by data mining strategies.

Area of Science:

• Medical Informatics
• Artificial Intelligence in Medicine
• Clinical Laboratory Science

Background:

• Big data and AI are transforming medical diagnosis and decision-making.
• AI applications are widespread in medicine, including radiology, pathology, and cardiology.
• Clinical laboratories generate vast amounts of daily testing data, offering potential for AI integration.

Purpose of the Study:

• To address the lack of a defined concept for integrating clinical laboratory data with AI.
• To propose "clinical laboratory omics" (Clinlabomics) as a new framework.
• To review the current applications of AI with clinical laboratory data in medicine.

Main Methods:

• High-throughput methods to extract feature data from various biological samples (blood, body fluids, etc.).
• Utilizing data statistics and machine learning algorithms to analyze extracted clinical laboratory data.
• Reviewing existing literature on the application of AI with clinical laboratory data.

Main Results:

• The proposed Clinlabomics framework enables extraction and analysis of extensive feature data from clinical laboratory tests.
• AI combined with clinical laboratory data can reveal previously undiscovered information for medical applications.
• Existing applications demonstrate the potential of AI in enhancing clinical laboratory diagnostics.

Conclusions:

• Clinlabomics offers a novel approach to leverage clinical laboratory data using AI for enhanced medical insights.
• This integration has the potential to assist numerous medical fields, improving diagnosis and treatment.
• Further multi-center validation is necessary to confirm the broad applicability and reliability of Clinlabomics.