Monitoring asthma control in allergic children by soft computing of lung function and exhaled nitric oxide

BACKGROUND: Asthma control is emphasized by new guidelines but it remains poor in many children. Evaluation of control relies on subjective patient recall, and may be over-estimated by health care professionals. OBJECTIVES: To assess the value of spirometry and exhaled nitric oxide (FeNO) measurements, used alone or in combination, in models developed by a machine learning approach, in the objective classification of asthma control according to GINA guidelines, and to test the model in a second group of asthmatics. METHODS: 53 children with persistent atopic asthma underwent 2-6 evaluations of asthma control, including spirometry and FeNO. Soft computing evaluation was performed by means of Artificial Neural Networks, and Principal Component Analysis. The model was then tested in a cross-sectional study in a further 77 allergic asthmatic children RESULTS: The machine learning method was not able to distinguish different levels of control using either spirometry or FeNO values alone. However, their use in combination modelled by soft computing was able to discriminate levels of asthma control. In particular the model is able to recognize all uncontrolled asthmatic children and correctly identifies 99.0% totally controlled children. In the cross-sectional study the model prospectively identified correctly all the uncontrolled children and 79.6% of the controlled children. CONCLUSIONS: Soft computing analysis of spirometry and FeNO allows objective categorisation of asthma control status.