Background: Clinical research associates (CRAs) monitor the progress of a trial, verify the data collected, and ensure that the trial is carried out and reported in accordance with the trial protocol, standard operating procedures, and relevant laws and regulations. In response to monitoring challenges during the COVID-19 pandemic, Peking University Cancer Hospital launched a remote monitoring system and established a monitoring model, combining on-site and remote monitoring of clinical trials. Considering the increasing digitization of clinical trials, it is important to determine the optimal monitoring model for the general benefit of centers conducting clinical trials worldwide. Objective: We sought to summarize our practical experience of a hybrid model of remote and on-site monitoring of clinical trials and provide guidance for clinical trial monitoring management. Methods: We evaluated 201 trials conducted by our hospital that used on-site monitoring alone or a hybrid monitoring model, of which 91 trials used on-site monitoring alone (arm A) and 110 used a hybrid model of remote and on-site monitoring (arm B). We reviewed trial monitoring reports from June 20, 2021, to June 20, 2022, and used a customized questionnaire to collect and compare the following information: monitoring cost of trials in the 2 models as a sum of the CRAs' transportation (eg, taxi fare and air fare), accommodation, and meal costs; differences in monitoring frequency; the number of monitored documents; and monitoring duration. Results: From June 20, 2021, to June 20, 2022, a total of 320 CRAs representing 201 sponsors used the remote monitoring system for source data review and the verification of data from 3299 patients in 320 trials. Arm A trials were monitored 728 times and arm B trials were monitored 849 times. The hybrid model in arm B had 52.9% (449/849) remote visits and 48.1% (409/849) on-site visits. The number of patients' visits that could be reviewed in the hybrid monitoring model increased by 34% (4.70/13.80; P=.004) compared with that in the traditional model, whereas the duration of monitoring decreased by 13.8% (3.96/28.61; P=.03) and the total cost of monitoring decreased by 46.2% (CNY yen 188.74/408.80; P<.001). These differences were shown by nonparametric testing to be statistically significant (P<.05). Conclusions: The hybrid monitoring model can ensure timely detection of monitoring issues, improve monitoring efficiency, and reduce the cost of clinical trials and should therefore be applied more broadly in future clinical studies.
