Machine learning and goal direct perfusion

To the Editor:

The author reported no conflicts of interest.

The Journal policy requires editors and reviewers to disclose conflicts of interest and to decline handling or reviewing manuscripts for which they may have a conflict of interest. The editors and reviewers of this article have no conflicts of interest.

Metabolism management plays an essential role during cardiopulmonary bypass (CPB). There are different metabolic-management devices integrated to heart–lung machines; the most commonly used and accepted metabolic target is indexed oxygen delivery (280 mL/min/m²) and cardiac index (2.4 L/min/m²), which can be managed independently or according to other metabolic parameters.¹ During CPB, the realization of goal-directed perfusion involves the integration of different parameters that have a direct and indirect linear correlation.² We reported our experience in a graphical presentation of the central pictures with the interactions of the metabolic parameters on a case series of 500 CPBs. The blue color code shows a positive correlation and the red code a negative correlation between the related parameters. Machine learning has experienced a revolutionary decade, with advances across many disciplines. There has been enormous interest in applying machine learning and artificial intelligence to health care and, in particular, to cardiovascular perfusion and cardiac surgery. During CPB, the fluids in the goal-directed perfusion have an effect in increasing the flow rate and venous return but have a negative effect on the oxygen delivery, predisposing to the consumption of blood products.³ We think that integrating these graphs across multiple numbers will help in the future to understand the cause-and-effect relationships on various rehabilitation programs.