Logistic Regression Model in a Machine Learning Application to Predict Elderly Kidney Transplant Recipients with Worse Renal Function One Year after Kidney Transplant: Elderly KTbot
Table 4
Analysis of composite outcomes for postkidney transplant proteinuria >0.3 g/24 h among younger and elderly risk patients.
Covariables
<60 years (n = 100)
≥60 years (n = 18)
OR
95% CI
n (%)
n (%)
Proteinuria
3.913
1.310–11.689
No
70 (75.3%)
07 (43.8%)
0.017
Yes
23 (24.7%)
09 (56.3%)
Total
93 (100%)
16 (100%)
Prekidney transplant urine protein + DM pre-KT
20.68
3.576–119.627
No
91 (97.8%)
11 (68.8%)
0.001
Yes
02 (2.2%)
05 (31.3%)
Total
93 (100%)
16 (100%)
Postkidney transplant urine protein + NODAT
0.819
0.094–7.144
No
86 (92.5%)
15 (93.8%)
1.000
Yes
07 (7.5%)
01 (06.3%)
Total
93 (100%)
16 (100%)
Urine protein + mTOR inhibitor
1.111
0.283–4.353
No
77 (82.8%)
13 (81.3%)
1.000
Yes
16 (17.2%)
03 (18.8%)
Total
93 (100%)
16 (100%)
Urine protein + mTOR inhibitor + corticosteroid
1.111
0.283–4.353
No
77 (82.8%)
13 (81.3%)
1.000
Yes
16 (17.2%)
03 (18.8%)
Total
93 (100%)
16 (100%)
Urine protein + mTOR inhibitor + corticosteroid + calcineurin inhibitor
1.111
0.283–4.353
No
77 (82.8%)
13 (81.3%)
1.000
Yes
16 (17.2%)
03 (18.8%)
Total
93 (100%)
16 (100%)
OR: odds ratio; CI: confidence interval; KT: kidney transplant; DM: diabetes mellitus; NODAT: new-onset diabetes after transplant; and mTOR: mammalian target of rapamycin. mTOR inhibitor was everolimus or sirolimus. Calcineurin inhibitor was cyclosporine or tacrolimus. Corticosteroid was prednisone. Chi-square test.
