From gating to computational flow cytometry: Exploiting artificial intelligence for MRD diagnostics.

Area of Science:

• Hematology
• Computational Biology
• Artificial Intelligence

Background:

• Flow cytometry is crucial for diagnosing hematological malignancies.
• Assessing minimal residual disease (MRD) is vital for treatment monitoring in chronic lymphocytic leukemia (CLL).
• Traditional MRD assessment methods can be complex and time-consuming.

Purpose of the Study:

• To evaluate an emerging machine learning approach for MRD assessment in CLL.
• To determine the feasibility and robustness of AI-driven computational flow cytometry for MRD detection.
• To explore the potential of AI in advancing diagnostics for hematological malignancies.

Main Methods:

• Utilized a machine learning algorithm for computational flow cytometry analysis.
• Applied the AI approach to assess phenotypic MRD in chronic lymphocytic leukaemia patient samples.
• Compared AI-based results with established methods for MRD detection.

Main Results:

• The AI-driven computational analysis demonstrated accurate assessment of MRD in CLL patients.
• The method proved to be a robust and feasible tool for advanced diagnostics.
• AI-based flow cytometry offers a promising alternative for MRD evaluation.

Conclusions:

• AI-based computational flow cytometry is a powerful tool for MRD assessment in CLL.
• This approach represents a significant advancement in the diagnostics of hematological malignancies.
• The era of AI in flow cytometry diagnostics for hematology has begun.