A novel indirect method for deriving reference intervals through iterative data cleaning guided by self-organizing maps of multi-test patterns (SOM-clean)

Key Points

• This method enhances the accuracy of reference intervals derived from laboratory data, improving clinical decision-making.
• Using novel self-organizing maps, reference intervals were estimated with greater precision than traditional methods.
• SOM-clean utilizes a multivariate approach to data cleaning, ensuring robust results across various tests.
• The implications support better understanding and implementation of reference intervals in clinical settings.

Abstract