ChiCTR is a non-profit organization provides the services of register for China’s clinical trials information, it is available in both Chinese and English language. In this study we downloaded clinical trials registration files and extracted the eligibility criteria (EC) text from the sections of “inclusion criteria” and “exclusion criteria” in each trial. There are four types of EC text, including Chinese inclusion criteria (CIC), English inclusion criteria (EIC), Chinese exclusion criteria (CEC), and English exclusion criteria (EEC). An example of eligibility criteria text of Chinese clinical trials showed in Table Table11.

An example of eligibility criteria sentences of Chinese clinical trials registered in ChiCTR

Registration number: ChiCTR1800016069

The EC text is organized as a paragraph with multiple EC sentences. We segmented criteria sentences by the symbol of line break, and excluded the trials in which the number of CIC sentences are not match to the number of EIC sentences, and the number of CEC sentences are not match to the number of EEC sentences. After that, there are 75,754 EC sentence in both Chinese and English remained, and then we filtered the wrong translation and meaningless sentences. Finally we randomly selected 19,185 CEC sentences and EEC sentences in the unsupervised hierarchical clustering section for criteria categories induction, and 38,341 CEC sentences in supervised criteria classification section for the classification capacity validation.

Note: The content above has been extracted from a research article, so it may not display correctly.

Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.

We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.