Predicting chemotherapy-induced thrombocytopenia in cancer patients with solid tumors or lymphoma

Chemotherapy-induced thrombocytopenia is a serious complication in chemotherapy-treated patients. Identification of patients at risk for chemotherapy-induced thrombocytopenia could have clinical value in personalized management of patients and optimized administration of prophylactic thrombopoietic agents. The aim of this study was to develop a predictive model for chemotherapy-induced thrombocytopenia (platelet count < 100,000/µl) in cancer patients undergoing chemotherapy.

A total of 14 covariates were prospectively assessed as explanatory variables in a cohort of consecutive patients with solid tumors or lymphoma. A multivariable logistic regression model was developed after univariable analysis. A bootstrapping technique was applied for internal validation.

Data from 305 patients during 1732 chemotherapy cycles were considered for analysis. Forty-eight patients (15.73%) developed chemotherapy-induced thrombocytopenia during their treatment course. The multivariable model exhibited three final predictors for chemotherapy-induced thrombocytopenia, including high ferritin (odds ratio, 4.41; bootstrap P = 0.001), estimated glomerular filtration rate <60 ml/min/1.73 m² (odds ratio, 3.08; bootstrap P = 0.005), and body mass index <23 kg/m² (odds ratio, 2.23; bootstrap P = 0.044). The main characteristics of the model include sensitivity 75%, specificity 65.4%, positive likelihood ratio 2.16, and negative likelihood ratio 0.382. Moreover, the model was well calibrated (Hosmer-Lemeshow P = 0.713) and the area under the receiver operating characteristic curve was 0.735 (95% confidence interval, 0.654-0.816; P < 0.001).

We developed a predictive model for chemotherapy-induced thrombocytopenia based on readily available and easily assessable clinical and laboratory factors. This study may provide a valuable insight to guide optimized treatment of cancer patients. Further studies with larger sample size are warranted.