Objectives: We aimed to assess the effectiveness and nephrotoxicity of polymyxin B in critically ill patients with nosocomial pneumonia and to evaluate the utility of its therapeutic drug monitoring (TDM). Methods: We retrospectively analyzed patients who received polymyxin B treatment for >= 48 h since the establishment of polymyxin B TDM in a 26-bed tertiary referral intensive care unit. Univariate and multivariate analyses were conducted to assess the variables associated with polymyxin B effectiveness and nephrotoxicity. Results: A total of 62 patients were enrolled. Most (56.5%) of the patients performed TDM, 54.3% of them reached the therapeutic target of area under curve across 24 h at steady state (AUC(ss,24h)) of 50-100 mg h L-1, and 10 patients had an AUC(ss,24h) value of <50 mg h L-1. Thirty-six (58.1) and 31 (50.0%) patients had favorable clinical and microbiological responses, respectively. Reaching the therapeutic target of AUC(ss,24h) (odds ratio [OR] = 13.15, p = 0.015), a favorable microbiological response (OR = 40.80, p = 0.00), and complicated with septic shock (OR = 0.12, p = 0.021) were independently associated with favorable clinical outcomes of polymyxin B treatment. The incidence of acute kidney injury (AKI) was 45.2%. A lower creatinine clearance (OR = 0.96, p = 0.008) and concomitant treatment with loop diuretics (OR = 5.93, p = 0.046) were predictive of nephrotoxicity. Conclusion: Our findings show that TDM of polymyxin B is a valuable intervention, and the achievement of its optimal pharmacodynamic target can improve treatment outcome. Renal insufficiency and concomitant treatment with loop diuretics were found to be associated with the risk of nephrotoxicity.