Comparison of the predictive power of the 2005 and 2010 Caprini risk assessment models for deep vein thrombosis in Chinese orthopedic patients at admission: A prospective cohort study.

Introduction: Several DVT risk assessment tools have been developed and validated to stratify the patients. The 2005 and 2010 Caprini risk assessment models (RAMs) proved reliable in detecting deep vein thrombosis (DVT) and are widely used worldwide. Although the 2010 version was recently modified, the 2005 version is still more exact and popular in the surgical population. This study aimed to compare the predictive power of the 2005 and 2010 Caprini RAMs in Chinese orthopedic patients at admission and describe the incidence of DVT during hospitalization.

Study Design: This prospective cohort study involved 2733 patients from the Arthritis Clinic and Research Center, Orthopedics and Traumatology Department, Orthopedic Oncology Department, and Spinal Surgery Department of Peking University People's Hospital from September 2018 to January 2019. The DVT risk scores and levels were determined for all patients using the 2005 and 2010 Caprini RAMs at admission. The sensitivity and specificity of the two tools were calculated. The patients were divided into the screened and unscreened groups according to whether or not a Doppler ultrasound (DUS) was performed. Depending upon the DUS results, the patients were divided into the DVT and non-DVT groups. The receiver operation characteristic (ROC) curve and the area under the curve (AUC) were evaluated to compare the predictive power.

Results: Eighty-four patients had DVT in the four orthopedic departments, and the incidence of DVT was 3.1 %-17.2 %. The scores between the 2005 and 2010 Caprini RAMs differed (P < 0.001) among orthopedic patients at admission. Among DVT patients, the highest-risk patients accounted for 63.5 % and 52.9 % based on the 2005 and 2010 Caprini RAMs, respectively. The AUCs of the 2005 and 1020 Caprini RAMs were 0.669 ± 0.030 and 0.648 ± 0.032, respectively. There were no significant differences between the two ROC curves (P = 0.164).

Conclusion: The 2005 and 2010 Caprini RAMs showed a similar predictive power in detecting DVT, but neither met the high sensitivity criteria for screening DVT in orthopedic patients. The incidence of DVT in orthopedic patients was relatively high during hospitalization.