[A predictive model for affect of atopic dermatitis in infancy by neural network and multiple logistic regression].

OBJECTS

To analyze the predictive accuracy of the predictive model for affect of atopic dermatitis in infancy, from the data of the epidemiological survey, which were conducted for 10,000 of mothers of infants and children in 1993.

SUBJECTS AND METHODS

A total of 4610 replies were received: 2714 from mothers of infants (12 month old) and 1,896 from mothers of children (2 years old). The sensitivity, specificity and predictive accuracy were calculated from probabilistic model by neural network analysis (NNA) and multiple logistic regression analysis (MLA).

RESULTS

Risk factors for probabilistic model by NNA were family history (father, mother, siblings, grand father, grand mother), food restriction, food allergy, age, food restriction of mother, egg introduced time, cow's milk introduced time. The sensitivity, specificity and predictive accuracy of NNA model was 88.6%, 99.5% and 96.4%, respectively and MLA model was 75.1%, 82.6% and 82.3%, respectively.

CONCLUSION

These results suggest that the NNA is a good and useful method for prediction of onset of AD than MLA. Furthermore, It is necessary to investigate the artificial neural networks for diagnosis and/or treatment by physician.