Genetic algorithm with logistic regression for prediction of progression to Alzheimer's disease

BMC Bioinformatics

Table 6 Variable selection from GA for prediction of conversion from MCI to AD, compared with random selections of features.

# of features	Average AUC (GA selected variable sets)	Average AUC (randomly selected variable sets)
4	0.86	0.67
5	0.85	0.67
6	0.85	0.68
7	0.86	0.69
8	0.86	0.69

The best performance is associated with the feature sets of lengths 7 and 8, that can be classified as good performance (0.9>AUC>0.8). Random selection of features resulted in poor prediction (AUC<0.7).

ISSN: 1471-2105