Background: Tangshen Formula (TSF) is a traditional Chinese medicine for the treatment of diabetic kidney disease (DKD). Liver-type fatty acid binding protein (L-FABP) is expressed in various tissues, including the kidney, where it is known as urinary L-FABP. Other studies demonstrated that urinary L-FABP may be a useful biomarker for monitoring DKD. This post-hoc analysis and cross-sectional study evaluated the changes in urinary L-FABP in DKD patients treated with TSF and conventional medicine. Methods: Post-hoc analysis was conducted on a multicenter, randomized, double-blind, placebo-controlled trial. A total of 180 participants with DKD including 98 with microalbuminuria and 82 with macroalbuminuria were enrolled in the original study. In addition to conventional treatment, 122 participants were randomly assigned to receive TSF and 58 to receive placebo. After 24-weeks of treatment, the intention-to-treat population in microalbuminuria stage was 56 in the TSF group and 25 in the placebo group, and in the macroalbuminuria stage 42 and 19, respectively. The primary outcome in the original trial was urinary protein level. In the current study, urinary and plasma L-FABP levels were measured in 30 microalbuminuria patients (15 in the TSF group and 15 in the placebo group) and 30 macroalbuminuria patients (15 in the TSF group and 15 in the placebo group). In addition, another 30 patients with normoalbuminuria (urinary albumin excretion rate (UAER) < 20 mu g/min) were recruited for the cross-sectional study. Results: (1) In microalbuminuria patients, UAER in the TSF group displayed a significant decrease after 24 weeks of treatment (P = 0.045). Levels of urinary L-FABP in the TSF group were markedly lower than in the placebo group after 12 and 24 weeks (P = 0.004 and P = 0.047, respectively). (2) In macroalbuminuria patients, 24-h urinary protein levels decreased significantly compared with baseline in the TSF group at week 12 (P = 0.042) and week 24 (P = 0.041). The TSF group showed a significant decrease in urinary L-FABP after 12 and 24 weeks (P = 0.036 and P = 0.046, respectively). (3) Levels of urinary L-FABP increased markedly, correlating with severity of DKD. L-FABP in patients with normoalbuminuria, microalbuminuria, and macroalbuminuria were 5.9 (5.2, 7.8) mu g/ml, 11.4 (6.8, 13.4) mu g/ml and 18.5 (10.9, 23.4) mu g/ml, respectively (P = 0.000). Conclusions: TSF combined with conventional therapy appeared to be effective in reducing urinary protein and urinary L-FABP. Urinary L-FABP levels appear to be associated with the severity of DKD.