Neural networks and artificial intelligence in thoracic surgery.

ABSTRACT

The human brain has billions of neurons and connections that cannot be emulated by computers. This structure could explain the anatomical basis of typically human psychological activities like intuition or artistic creation. On the other hand, the computer-organized way of "reasoning" binary problems through systematic comparison of a large number of data-as AIM does--is impossible to be emulated by humans. At the same time, AIM, through the use of different methods like ANN or DM systems, is able to give individualized answers to otherwise probabilistic population problems. Hence, that is the reason for its application in the assessment of surgical risk in lung resection candidates. With regard to AIM methodology, many issues could be addressed and argued, especially on the data collection because of the retrospective nature of the data on which the available contributions from the literature are based. In the larger studies, patients from different centers treated by different surgical teams were included. Both circumstances could have caused heterogeneity of the study groups, which, in turn, can lead to less-reliable conclusions. Even if limited, our experience became an appealing one because AIM seems to be a potentially useful complementary tool to the nonreplaceable clinical judgment.