Yunu Co-Founders Discuss Challenges Within the Current Landscape of Clinical Trials


Jeff Sorenson and Gael Kuhn, Co-founders, Yunu, provide commentary on current obstacles associated with clinical trials and how their company is addressing them.

ACT: Can you elaborate on the specific challenges you see within the current landscape of clinical trial imaging and how Yunu addresses them?

Sorenson: There are fundamental challenges when sponsors, CROs, and imaging CROs are trying to run imaging centric clinical trials. For example, the systems that they're using today are web uploaders that basically sit at the edge of a site and they have no concept of what the patient's schedule is. They may know in their CTMS what the schedule is, but the system that's doing the data transfer doesn't know, and it doesn't have a way to communicate with the folks at the site. So, there's broken email communications requesting for data uploads. There's even confusion that can happen when the patient's scan is or if it’s changed. And then the systems also aren't capable of de identifying the data, very often, in the exact type and requirements for each specific clinical trial. So, you put that all together, and you have a problem where you have data capture, de-identification, and workflow problems. So, what we do is provide an intelligent data capture system that's managing the end-to-end data transfer. It knows when the patient scans are scheduled, it notifies the assigned readers when they need to actually take action on those studies, ensures the upload is correct, facilitates the communication even when things go wrong and there needs to be re-review. That communication can happen in our tool between the study staff and the readers. And we've developed a web uploader that is actually created for each trial, and a software agent that can communicate with their local systems as a light software appliance if they'd like to use that for high volume scenarios. So, the imaging data is de-identified in flight, everyone stays connected, and the efficiencies are profound.

Gael: So, as you understood, the immediate workflow is highly disorganized and disconnected. So, every site involved in a trial is a snowflake and are struggling to be responsive and accurate. Also, imaging CRO are piecing together homemade workflow and provide the technology, managing much more of the work manually. Also, lack a way to apply their innovative data science initiative to their in-flight clinical trial to extract the needed information. So with all of that, what does Yunu do to solve the problem? Yunu provides a full cloud-based user configurable solution that manages all of the trial imaging data, study staff workflow, and measurement, meeting the widest range of requirements. It’s currently used across 4,200 clinical trials with data from over 400 industry sponsors. This opens the door to many AI use cases.

Sorenson: If you think about a huge problem in terms of challenges in clinical trials, with respect to imaging, data loss is sort of a sad consequence of having lots of manual steps and manual workflows. The measurements that are made on the images that represent the numbers, the tumor metrics that are being gathered, those two things are not connected. So, you know, when you're reading in a PACS system, the PACS system doesn't do math, the reporting system is typically receiving those measurements verbally, and a study team is extracting those into other documents. So, you can see how the there's a disconnect between where exactly in the images the measurements were made, and the actual values that represent those measurements. With workflow chaos, the measurements can change and once again, you have a disconnect with your source images, so they're not kept together. That's reducing all of the future value of imaging data and everything that we can learn from it. Then, you know, when that happens, the sponsors are actually having to go find similar data to that which they lost and buy it back, which is very expensive, and then you still have to pay to have it relabeled, to have the measurements actually applied on those images that you've bought. All of that could be avoided. When you have so many stakeholders and so many manual processes, the images themselves, even that source imaging data with all of its value, the actual pictures are being left behind, and it's turning into just values. So, not only is it disconnected, but very often the data is being lost. So, what Yunu does is provide an end-to-end image data management system that's connected to the workflow of all of the stakeholders, and it prospectively preserves all of the imaging data at every step. And so, it delivers huge workflow efficiencies, because you always know where you're at in the process, you always have all of your data and are audit ready. Because of that, in the systematic approach, it allows for faster study starts and also dramatically lower costs.

Related Videos
Related Content
© 2024 MJH Life Sciences

All rights reserved.