Complexities in Data Management

In part 1 of this video interview, Diane Lacroix, vice president, clinical data management, eClinical Solutions discusses the current landscape of data collection in clinical trials and the growing complexity of protocols.

ACT: What are some of the biggest challenges you are currently seeing with data management in clinical trials?

Lacroix: Since I’ve been in industry for over 20 years, the complexity of protocols which we continually hear; you talk to people in industry—we’re going from one indication, one study drug, to multiple indications, multiple study drugs. The majority of the trials that we’re seeing at eClinical are platform trials, basket trials, and all of these master protocols and adaptive trials that are extremely complex. In addition to that, we’re seeing a lot of different data types and data sources that we’ve never seen before, and they’re just continuing to grow. Coming from historical trials where we had EDC (electronic data capture); it’s a very site-centric data collection. We still see EDC, but we’re seeing a lot of other data acquisition tools that are adding complexity to that diversity of data sources and data types. The volume as well; the volume of data is very large. We’re processing extremely large data sets and managing all of those data flows and for data managers, it’s very different. We’re trying to coordinate, manage, and work with multiple stakeholders across study teams, so people often don’t think about that part of it in that not only are the protocols getting more complex, but it introduces new players, new stakeholders, more decision-makers at the table that we have to coordinate and manage. Of course, with all of this, there’s continual pressure to do it faster. We want data insight sooner—in that reduction in cycle time and cost and risk reduction—that pressure is just continuing to grow in the face of all of this complexity.

Watch the video.

Addressing Data Management Challenges With Automation

In part 2 of this video interview, Diane Lacroix, vice president, clinical data management, eClinical Solutions highlights how artificial intelligence can help industry keep pace with the increasing complexity of data.

ACT: How can data management challenges be addressed? Specifically, is there any opportunity to address them with artificial intelligence (AI)?

Lacroix: There is a lot of opportunity across the life cycle to assist with this and it’s interesting because historically it was always: we want to throw people at some of these problems. I think it’s important to mention that people are not always the answer. Specifically in data management, there’s a shortage of resources. There’s a shortage of resources with the appropriate skill sets to manage the complexity, so we really do need to look at innovative processes and technologies to assist with managing this complexity; AI is one of those. When we’re talking about all of the data and the high volume of data coming in, and specifically these adaptive trial designs, AI can help us with processing those large volumes of data to be able to automate and we need to build in automation for ingestion of these continual data flows, and utilize artificial intelligence to help us interrogate that data to be able to gain those insights, specifically around these adaptive trials, because of the ongoing decision making that happens throughout the course of these trials.

Utilizing automation is what we do at eClinical Solutions, as far as automating all those data sources into a clinical data management platform, elluminate, where the tool and the technology helps us to not only ingest, but to standardize and harmonize that data in a way that unifies that data so that we can look at that data more holistically and cohesively for that decision making for these adaptive trials. The data cleaning part of it is specifically for data management, it’s a big area that this can help with. As these large volumes of data continue to grow, we can’t continue to throw edit checks at it or line listings at it. We need to use more smart and innovative tools to be able to process and interrogate that data.

Watch the video.

Benefits of Using AI in Data Management

In part 3 of this video interview, Diane Lacroix, vice president, clinical data management, eClinical Solutions touches on some of the greatest benefits she has seen with the integration of artificial intelligence into data management.

ACT: What are the greatest benefits to utilizing artificial intelligence (AI) in data management?

Lacroix: Coming from a data management background, there’s of course, across the trial lifecycle, lots of opportunities where AI can be applied. We hear a lot about patient recruitment. We hear about predicting the appropriate patients, the appropriate patients that will achieve the outcomes we’re looking for. We hear about drug discovery and accelerating drug discovery and more patient-centric approaches, but where my experience lies is more in the data management area, and for us, for my group specifically, that is the biggest area that we’ve been focused on, and where we started at eClinical is that as a data organization, we had access to the data, so that made sense for us to start with clinical data review. As data managers, we are largely responsible for processing that data—reviewing, data cleaning, coding—to ensure the data is of the of the highest quality for analysis. Traditional data review models don’t lend themselves to managing and processing these high volumes of data sources. In traditional approaches, data managers would have to sift through rows and rows and thousands and thousands of data points with a lot of overhead for manual programming, QC, and execution of edit checks. This is just not going to scale. It doesn’t scale with what we’re seeing today, so we really do need to look at more innovative approaches to be able to manage the complexity, and it’s just extremely inefficient.

Using AI and ML (machine learning) for data cleaning and interrogation is no longer an option and I think data management teams that aren’t traveling towards the use of AI and ML are going to be left behind, and are going to find themselves in a difficult position. We have so much more to manage as data managers that we need to look at the areas where AI can assist us and reduce that manual effort and burden and allow us to focus again on what’s critical. So, being able to utilize artificial intelligence for our data cleaning and data processing in our experience, and what we’re using at eClinical is it truly reduces the overall effort of looking at large volumes of data, stripping away what is not important, what the model deems as acceptable, and allowing us to focus only on what’s absolutely critical and anomalous. This really does reduce the time and effort. It allows us also to identify risks sooner in the process. When I think about looking at lab data, vitals data—these data sets that continually tend to be your largest, voluminous data sets, and trying to surface things that are concerning or trends, risks, shifts without intelligence is near impossible, or if it’s achievable, it takes a lot of individuals looking at it and a lot of time and effort to get there. The other piece that AI is assisting us with is manual reviews. They are very subjective, and the human is making all of the decisions as to what is deemed in general. We have rules around risk and safety risks and concerns, but there’s a human and that’s making a lot of the judgment calls, and people think differently. There’s inconsistency, so AI is really adding that consistency, reducing that kind of human subjectiveness, but yet still allowing the human to stay in the loop as the decision maker to determine what action needs to be taken.

I’m probably going on too much about data management, but this is where we’re experiencing the most benefit and the most benefit for our customers, and that we’re able to identify those risks and trends much sooner in the process. We’re able to allocate resources differently because we’re not having to have so many individuals executing on these data reviews and really allow us to work much more efficiently for our customers.

Watch the video.

Considerations for Integrating Artificial Intelligence

In part 4 of this video interview, Diane Lacroix, vice president, clinical data management, eClinical Solutions discusses what industry stakeholders should be keeping top of mind when integrating AI into their workflows.

ACT: What should industry stakeholders be keeping top of mind when implementing artificial intelligence (AI) into their workflows?

Lacroix: When we started thinking, or when I was brought into the initiatives at eClinical to start thinking about artificial intelligence and where we want to apply it; immediately you start thinking, I want to do it everywhere, right? I think it’s critically important to focus on where are your inefficiencies and redundancies, and where can you automate repetitive tasks that aren’t adding value. The thinking is if there are things that can be done, and again, I’m thinking about data management, if there are things that can be done with rules that are successful, there’s no need to necessarily innovate and automate everything—focus on the areas that truly are redundant, time and effort, and resource intensive and aren’t adding value.

I would say, for organizations that are thinking about implementing, think about starting small. Think about what outcomes you’re trying to achieve and set a roadmap of what are your objectives and what are you expecting that innovation to accomplish? The other is ensuring that you have high quality data to be able to introduce artificial intelligence into your organization. I think there’s the need to have a clinical data management platform with data that you can use to train models and to build out your AI workflows is really important and I think that oftentimes, as organizations are engaging on this journey, they aren’t necessarily thinking also about the investment in artificial intelligence. It’s not a magic bullet. It takes time to build out these models. It takes time to refine these models and interestingly, our industry survey at the end of last year was respondents expected within 12 months to be able to see significant benefits from introducing AI and ML, yet the majority of them hadn’t even started on their AI/ML journey.

I think being realistic about, again, what you’re trying to achieve, and putting some realistic timelines around what is acceptable, having the investment from the organization into those initiatives, and then consider the people in the process as well. As I said, AI is a technology. It has infinite potential to impact the life sciences so significantly, but yet, it’s not going to solve all the world’s problems alone. You need to think about the individuals that are going to be using the tool in the processes around the artificial intelligence and machine learning, so that individuals are truly optimizing the technology and you’re achieving the business outcomes that you want to achieve. I think people often forget about the processes and the people when they’re talking about implementing AI into their workflows, because it does and it will significantly change how people are functioning in their roles and in their day-to-day.

Watch the video.

Future Use of Artificial Intelligence in Clinical Trials

In the fifth and final part of this video interview, Diane Lacroix, vice president, clinical data management, eClinical Solutions looks to the future and touches on what the use of AI in clinical trials could like in five years.

ACT: Looking forward, where do you see the use of artificial intelligence (AI) in clinical trials in five years?

Lacroix: We’re going to continue to see more, of course, growth in in this area, as far as the use of artificial intelligence and machine learning and I think we’re also going to start to see more evidence around where is the best place to put our focus with artificial intelligence. We’re hearing a lot of people in industry talk about their use of it. We’re hearing there’s organizations that are planning on how they’re going to use it, but we have yet to see real, tangible kind of outcomes of where to put our focus as an industry, and what is going to garner us the most benefits, as far as reaping the benefits of where those models. We know we see it, like I said, in patient recruitment, we know we see it in some of the outcomes and predictions for the right patient populations, and starting to see it with this drug discovery, but I think for clinical trials and life sciences teams, I think we’re still exploring where we’re going to see the most benefit.

If I had to, again, think about where we’re going to be in five years; we’re going to see more smarter tools and advanced analytics. I think as data managers and as life sciences teams, we’re going to continue to be involved, and need to have supervision over these models, we’ll continue to be humans in the loop in the use of these models. I think we’re going to start to see, and what I hope that we’re going to start to see, especially for those of us that are looking at data all day long, is to be able to have more intelligence that can help us to string together the patient experience and the patient journey throughout the life cycle. We do still tend to look at data in aggregate and data overall, but to really start to be able to have the intelligence put together these patient stories, to help us—medical monitors, clinicians—see and identify those patterns in the patients. We’ll start to see more ability to have more patient-centric trials, as well as patient-centric treatments that are more personalized in the long run, and we can start to personalize the treatment for our patients more. That’s my hope, is that we’ll have better tools to be able to develop those more personalized medicines.

Watch the video.