Advances in Artificial Intelligence

Research Article

Predicting Asthma Outcome Using Partial Least Square Regression and Artificial Neural Networks

Table 1

Prognostic factors.


Category	Prognostic factors

Demographic	Age, sex, ethnicity^#, height, weight, waist’s perimeter, residence^#
Wheezing episodes	Until 3rd year, between 3rd–5th year, until 5th year
Symptoms	Wheezing, cough, allergic rhinitis, runny nose, congestion, eczema, food allergy, pharmaceutical allergy, allergic conjunctivitis, dyspnea, seasonal symptoms^#
Parental history	Asthma*
House conditions	Number of family members, pets*, type of heating^#
Pharmaceutical therapy	Bronchodilators, corticosteroids inhaled, corticosteroids per os, antileukotriene, antihistamine
Breathing tests	FEV₁%, FEF_25/75%
Tests	IgE U/ML
Allergens	D. pteronyssinus^#, D. farinae^#, olive^#, pellitory^#, graminaceae^#, pine^#, cypress^#, cat^#, dog^#, alternaria^#
Neonatal period	Pregnancy duration, breastfeeding duration^#, smoking during pregnancy*
Asthma	Diagnosis of asthma, treatment

The encoding is binary: yes (1) or no (0).
^#The encoding is shown in Table 2.
All other factors are numerical.