Skip to main content
. 2021 Oct 2;10(19):4576. doi: 10.3390/jcm10194576

Table 1.

Identification of the selection of data and methods for machine learning analysis of subjects.

Feature Set Used Lab Feature Extraction Method Feature Counts AUC Accuracy (%)
Laboratory data only Method 1 39 0.7954 73.74
Method 2 39 0.7790 71.53
Method 3 36 0.7226 65.32
Method 1 + 3 75 0.8095 73.83
Method 2 + 3 75 0.7950 72.26
Method 1 + 2 + 3 114 0.8012 73.06
Clinical data only - 30 0.7493 69.79
Laboratory and clinical data Method 1 69 0.8284 76.09
Method 2 69 0.8096 72.68
Method 3 66 0.8100 72.98
Method 1 + 3 105 0.8350 74.85
Method 2 + 3 105 0.8141 73.02
Method 1 + 2 + 3 144 0.8219 74.21

Note: method 1 = average value of each laboratory code during the follow-up period; method 2 = the first value of each laboratory code when T2DM was diagnosed initially; method 3 = the pattern of laboratory code changes (−1, 0, or 1), Abbreviations: AUC = area under the curve.