Table 5.

Feature engineering methods used in the asthma studies included in this review.

Method		Values, n (%)a
Univariate feature transformation
	Logarithmic transformation	21 (33)
	Box-Cox transformation	1 (2)
	Method not explained	1 (2)
Feature selection
	Factor analysisb	8 (13)
	Principal component analysisb	5 (8)
	Avoid collinearity	3 (5)
	Avoid multicollinearity	3 (5)
	Supervised learning methods	2 (3)
	Multiple correspondence analysis	1 (2)
Feature transformation
	Principal component analysis	4 (6)
	Factor analysis	1 (2)
	Multiple correspondence analysis	1 (2)

^aAs a percentage of all 63 studies.

^bThese are not typically methods of feature selection but have been used in these studies.