Table 2 GFR estimated by decision tree model and traditional equations based on BSA for test set (Mean (P25–P75)).

From: Construct a classification decision tree model to select the optimal equation for estimating glomerular filtration rate and estimate it more accurately

Equationa

Test set (n = 156)

Cockcroft gault

64.6 (30.7–85.9)

MDRD

59.9 (25.42–84.78)

Abbreviated MDRD

23.4 (9.9–33.69)

Chinese modification MDRD

72.0 (30.6–101.9)

Chinese modification abbreviated MDRD

30.6 (12.9–43.9)

CKD-EPI(Cr)

23.9 (9.3–33.4)

CKD-EPI(CysC)

24.2 (13.2–28.8)

CKD-EPI(Cr-CysC)

22.7 (10.7–29.9)

Asian modified CKD-EPI(Cr)

25.2 (9.8–35.3)

BIS-2

27.6 (15.8–34.2)

MacIsaac

31.3 (19.3–38.7)

Ruijin

28.2 (14.6–38.2)

Xiangya

38.8 (27.1–49.0)

Decision tree classifier

25.3 (13.6–32.1)

sGFRb

26.6 (15.1–34.6)

  1. aAll GFR estimation equations were converted to a uniform unit, mL/min per 1.73 m2.
  2. bsGFR: GFR was measured by 99mTc-DTPA, and the GFR was converted to 1.73 m2 standard body surface area based on the patient's body surface area.
Back to article page