DIA Japan 2019

Syneos Health Lunch Seminar

A Machine Learning-Assisted Tool for Assessing Burden on Patients Participating in Clinical Trials
Clare Grace, VP, Site & Patient Access, Syneos Health
Nov 11
12:45 – 1:30pm
Seminar room 605, 6th floor

Clare Grace will describe a new tool developed with machine learning that highlights the most stressful aspects of a proposed study for patients and provides sponsors with valuable data related to recruitment and retention risks. Receiving this information prior to the onset of a trial allows sponsors to either adapt their protocol or adequately mitigate the potential risks, which leads to happier patients and more predictable study conduct.

Syneos Health’s PatientPulse™ provides burden estimates for three components of clinical trials; procedures, visits and studies. In addition to the burden that results from the procedures themselves, PatientPulse takes into account 11 other factors that influence the study burden score, including procedure duration. By collating these estimates over the course of individual visits and the trial as a whole, Patient Pulse estimates the amount of time patients will have to spend at clinical sites, and permits the comparison of a protocol against others to understand if a particular protocol would be more or less intense than the average protocol in the same indication.

Data will be shared to show impact of the assessment and how the use of a tool such as this can streamline protocols and support increased enrollment and retention in clinical studies.