Clinical Trials Bot Matches Patients to Studies

Microsoft is working with pharma companies and software partners to develop products.

 As part of a Microsoft healthcare bot initiative designed to help software company partners create automatic chat rooms for triaging patients, answering questions about insurance benefits and other activities, Microsoft has developed a chat bot that helps link patients to appropriate clinical trials.


The Clinical Trials Bot was created as part of a hackathon project at Microsoft's lab in Israel. First, a patient or doctor searches for studies related to a particular disease. The program then asks a series of text questions to find out more information and eventually provides a list of links to trials that best match the needs of the patient. The program can also be used by pharma companies to identify possible trial participants, which is currently a real challenge in the industry.


The bot uses machine reading to catalog all of the selection criteria for different clinical trials, which can be as many as 20–30 for each trial. This data is then used to develop appropriate multiple-choice questions that will enable the program to match the patient with suitable trials, and each user response helps to further refine the list of available trials.


Microsoft is talking to pharma companies that may use the bot for finding trial participants and to potential software company partners that might develop the technology into a formal tool for patients.


Nice Insight

Nice Insight, established in 2010, is the research division of That’s Nice, A Science Agency, providing data and analysis from proprietary annual surveys, custom primary qualitative and quantitative research as well as extensive secondary research. Current annual surveys include The Nice Insight Contract Development & Manufacturing (CDMO/CMO), Survey The Nice Insight Contract Research - Preclinical and Clinical (CRO) Survey, The Nice Insight Pharmaceutical Equipment Survey, and The Nice Insight Pharmaceutical Excipients Survey.