Analytics

CRO/Sponsor

Clinical Operations

Clinical Trial Supply Chain

DE&I

Data Management

Early Phase Development

Emerging Technology

Executive Roundtable

Feature Article

Industry Trends

Investigative Sites

Metrics and Benchmarks

Oncology

Online Extras

Patient Participation

Peer-Reviewed Articles

Protocol Design

Real World Evidence

Regulatory

Risk-Based Monitoring

Study Start-Up

Therapeutic Areas

Trial Design

Vendor Strategy & Collaboration

eClinical

mHealth

News

Publications

All Publications

E-Books

Media

Editorial Podcasts

Editorial Videos

Peer Exchange

Practice Academy

Conferences

Conference Coverage

Conference Listing

Columns

All Columns

A Closing Thought

Clinical Trial Insights

View from Brussels

View from Washington

Resources

Advertise

Blogs

Brand Insights

Events

Front & Center

White Papers

Webcasts

Subscribe

Latest solutions, case studies, interviews, practical articles for clinical trials operations, data management, technology, investigative sites and services.

About

Contact Us

Editorial Contacts

Do Not Sell My Personal Information

Privacy Policy

Terms and Conditions

Applied Clinical Trials Online

LinkedIN

Instagram

Facebook

Youtube

Soundcloud

Threads

Spotlight

Topic

1rem

How the inclusion of measures centered on net treatment benefit can drive an effective multifaceted approach. 

Enhancing Empowerment in Patient-Focused Research 

The potential of next-generation platforms in transforming patient recruitment. 

Harnessing Unstructured Data and Hospital Interoperability 

Results from survey of 100 site personnel suggest a disconnect is present between these stakeholders.


5 Strategies for Bridging the Sponsor-Site Tech Divide

Developing a strategic approach for labs that can identify and tackle global health challenges.

Re-imagining the Labs

From design and trial start-up to conduct and analysis, there is enormous potential for applications of artificial intelligence within clinical trials to have a profound impact on human health.

AI Already Starting to Deliver Faster, Safer, More Effective Clinical Trials

In this video interview, Jeff Sidell, PhD, chief technology officer, Advarra, highlights how integration can simplify processes. 

Solving Clinical Technology Challenges with Integration

, Jeff Sidell, PhD, chief technology officer, Advarra, discussed current challenges in clinical research technology. He highlighted the overabundance of systems and emphasized the need for integration to streamline processes and reduce administrative overhead. Sidell also discussed the potential of AI, particularly predictive analytics, to automate repetitive tasks, enhancing efficiency and quality.

A transcript of Sidell’s conversation with 

ACT: How can stakeholders address some of the technology overload industry is currently experiencing?

 One simple answer is integration. I've been in technology for long enough that I've seen when there's an integration play, so we're going integrate all these systems together, and you'll only have to log on once, and you only have to enter data once, and it's a good idea, but there's always a struggle, whose integration are you going to use? It's sort of like, who's going to be the first among equals? I still think it's possible. I think that, Advarra, for example, is in a good position to because we start at the very beginning of a clinical trial, when a protocol document is submitted to the IRB (institutional review board), all the way through to the conduct of the trial at the sites. Just like everybody else, we're going to make a play to be the integration provider. I think we're a little farther along than some of the other solution providers, but it's going to be a horse race.

Videos

In this video interview, Jeff Sidell, PhD, chief technology officer, Advarra, discusses how sites are being burdened by increasingly complex technologies.

Complexities with Managing the Overabundance of Clinical Technology

ACT: What are some current trends and challenges you’re seeing right now with technology in clinical research?

 I think for the most part, it's an overabundance of technology. If you ask somebody who's working in a clinical trial at a site, how many systems they have to touch during the conduct of a clinical trial, it keeps rising over the years. I think it's now up to 20 or so. I mean, 20 separate systems that they've got to go and log into, enter data, or move data from one place to another. Not only are the systems becoming more complicated, the trials themselves are becoming more complicated, so they're going on for longer, the conduct of the trial is much more complex, so you put those two things together, and they're drowning in activities, none of which are actually administering care to a subject. It's all just overhead.

In this video interview, Jimmy Bechtel, vice president, site engagement, SCRS, highlights how sites are bearing the burdens of cost and training with implementing new technologies. 

Clinical Trial Sites and Technology Overload

, Jimmy Bechtel, vice president, site engagement, SCRS, discussed key challenges and initiatives at the site-level. AI's impact on sites is significant, with uncertainty around its implementation. Diversity requirements pose challenges, and technology overload is a major issue due to inconsistent tech stacks and financial burdens on sites. Bechtel also highlighted some initiatives that SCRS is currently working on and gave an overview of the most recent Global Site Solutions Summit.

A transcript of Bechtel’s conversation with

ACT: One thing we hear a lot about is sites experiencing a technology overload recently. Why do you think sites are expressing this?

 Yeah, I think a lot has to do with the sheer amount and variety of technology that sites are being asked to implement on their clinical trials, coupled with the fact that there isn't any sort of standardization or consistency around it. You could have one trial from one organization use one tech stack, and then another trial from the same organization use a completely different tech stack, and that just repeats itself and compounds upon itself for all the different sponsors and CROs that a site is working with, so it's that lack of consistency and lack of interoperability and integration that has a lot to do with the challenges that the sites see. Every time they see a new technology is used in a new or different way, they have to start from scratch with the training and the knowledge and the education and how to use it and educating their patients. There's just a lot of inefficiencies that comes with this pilot-phase that we're in still with a lot of these technologies. I think we're moving in the right direction. It sounds like a lot of sponsors and CROs and professional service providers and these technology companies hear that, the dust is settling, and they're starting to understand which ones they want to use, and they're starting to build in some consistency. By now, a lot of sites have seen a lot of the solutions in one way, shape, or form, so they're starting to realize those things. It's kind of been a rough couple of years that we've tried to work through some of that.

I would also say that the financial aspect of utilizing and implementing these technologies, operationalizing them at the site level is a real challenge for sites, because there's, as you can imagine, when you have to train and implement and, again, operationalize these technologies at the site and patient level, that takes a lot of time and effort and training and coordination into parts of the site that sponsors and CROs probably never even think about. IT, and integrating that when you have a system that might be pulling data or data might be moving over that site's network and its patient data, there's a whole a bunch of cybersecurity, and IT questions that we have. It’s just one example of ways in which the dollars can start to build up in ways that we don't expect, so approaching a clinical trial with a traditional budget doesn't really work in the case of implementing technologies. Sites are seeing themselves bear a lot of these costs because they don't necessarily know either approaching some of these technologies. It's not until we're well into the clinical trial and well into that implementation phase of these technologies that we start to realize and recognize some of those true and real costs, but by then, unfortunately, sponsors and CROs say it's too late to renegotiate the budget, so the sites are stuck bearing those costs as a result of implementing that clinical trial. It’s learning the lesson the hard way, unfortunately, but that's definitely a major part of what we're seeing.

In this video interview, Jimmy Bechtel, vice president, site engagement, SCRS, discusses some challenges and trends he is currently hearing about from sites.

Uncertainty With Artificial Intelligence at the Site-Level 

ACT: What are some current challenges or trends for sites that you’ve been hearing about recently?

 AI (artificial intelligence) is definitely the new hot topic for the sites. It's not necessarily a challenge right now, there's a lot of unknowns, and sites don't want it to become a challenge and things like this tend to become a challenge. They happen at the sponsor, CRO, and service provider levels, and then the sites suffer the ramifications of whatever decisions are made at the industry level, so that that's definitely one that the sites have a big question mark around and there's a lot of discussion, a lot of thirst for information, and how is this being used? How can I use it as a site, etc.?

Then diversity, I think, is also a big challenge at the site level, knowing how to meet the needs. Even farther back from that, what the needs are going to be, what are sponsors and CROs going to be asking of sites with diversity plans and things like that? How can they be prepared to meet those? Should they be presented with some sort of diversity-level requirement—an inclusive-level requirement on their clinical trials?

In this video interview, Jimmy Bechtel, vice president, site engagement, SCRS, discusses challenges and trends he is currently hearing about from sites.

In this video interview with ACT editor Andy, Studna, Silvio Galea, chief data & analytics officer, WCG, highlights the need for relevant, quality data and the challenges with needing to use multiple technologies. 

Prioritizing Data Quality Amidst Complexity in Clinical Trials

, Silvio Galea, chief data & analytics officer, WCG, discussed the challenges in the clinical trial industry, emphasizing low awareness among both patients and providers. He highlighted operational issues, including the difficulty in identifying and engaging patients, data interoperability, and ensuring data quality. Galea stressed the importance of user experience in electronic data capture tools and the need for industry standards. Prioritizing data collection should focus on safety, efficacy, and efficiency, ensuring data quality, and avoiding workflow disruptions.

A transcript of Galea’s conversation with

ACT: On the clinical operations side, how should stakeholders be prioritizing the data they receive considering how many new solutions and data collecting mediums have entered the market recently?

 Ideally we wouldn't have to prioritize the data we're collecting, because it should all be equally valuable, right? The challenge with that is that it's not coming in as a single stream, tying back to the lack of interoperability and the sheer number of technical solutions that are out there. I keep hearing metrics like 13-15 different technologies that CRC needs to work with to make sure that we're operating in accordance to the protocol. I mean, that's crazy. Do we use 13 different technologies on a particular day? Then you've got to do this across multiple trials. That’s one issue that's leading the need to prioritize data as you rightfully ask, but if we have to do a straight up prioritization of data, it has to be the data hat ties to the key facets of our industry; safety, efficacy, and efficiency. Are we collecting the right data? Is it the data that's needed to meet the goals. Is it being collected safely? Is there adequate quality checks in place to make sure that we're not putting any part of the process at risk and is it being processed in an effective, simple, issue-averse way? [It’s about] making sure that we're not introducing issues into the workflow that is going to put the entire integrity of everything that's happened at risk and we have to go back and redo any parts.

In this video interview with ACT editor Andy, Studna, Silvio Galea, chief data & analytics officer, WCG, highlights the need for relevant, quality data and the challenges with needing to use multiple technologies.

In this video interview with ACT editor Andy, Studna, Silvio Galea, chief data & analytics officer, WCG, touches on the usability of clinical technology.

Harmonizing Data in Clinical Research

ACT: Do you think decentralized data collection tools such as eConsent and electronic patient-reported outcomes (ePROs) increase patient centricity or do they create more burden by adding complexity? Why?

 Yeah, I think that, obviously, the ability of having electronic data capture capabilities is important and beneficial. I do think that there are two hurdles that we need to overcome. The first one is the user experience of these applications, right? I think we as consumers living in a digital world have a particular bar to which we expect to interact with technology, and that bar from a B2C consumer perspective, has to be held in the B2B, or in the medical, or in the record collection, or in eCOA (electronic clinical outcome assessment), ePROs, and others. The expectation is that I'm interacting with it, with an application that Apple's research and the same level of integrity, user experience, speed, and feedback should be there. First of all, these technologies should be at a certain level of usability. Secondly, from the back end, we're collecting this data, we don't have yet an industry standard for how this is all collected. On the healthcare side, with Medicare, about 10 years ago, the government put forth the FHIR (Fast Healthcare Interoperability Resources) standard for how data interoperability should work. That's great from an EHR (electronic health record)-medical record perspective, but we don't necessarily have one in the life sciences space right now that we could all harmonize against, so there's a lot of work being done in the back end to take my format of data, make sure that the semantics equal your format and semantical structure, not just the syntax, but the semantics, and then make sure that I could harmonize it and present it as a unified data set. From the patient's perspective, making sure that it's something I want to use, and it's not a hurdle, and there's no barrier of me entering data in a qualitative fashion, and then on the back end, it's if the data is there, how do we bring it together so that we could measure it quickly and efficiently and not have the data harmonization collection be a white space between the milestones of the clinical life sciences space?

In this video interview with ACT editor Andy Studna, Rich Gliklich, founder of OM1 discusses automating data collection and organizing unstructured data. 

The Potential of AI in Data Collection

ACT: Is there any potential for the use of artificial intelligence (AI) in the data collection space?

I love that question because we literally power our data automation and data collection with AI in multiple ways. It starts with automating data mapping and quality assurance. When we bring data in from a medical record system or a laboratory information management system, we need to bring that into a common data model by leveraging generative AI, we can do that much faster and then verify it. Where we see its greatest benefits today are in collecting and transforming unstructured data, like clinical notes, imaging reports, pathology reports, procedure reports, into structured variables, so capturing MRI lesions or symptoms, those are areas that we're using today at scale. We still have to go and validate it with extractors to demonstrate, at least in a sample, that it's doing the right thing. That's one area. Another area that we find really exciting is the concept of using clinical narratives for generating estimated or surrogate endpoints, so estimated endpoints, or surrogate endpoints, as you know, can speed a trial or make more patients useful in a trial, and we can derive those from the medical record patterns that we see using AI or from an estimation.

We'll take a clinical note, and we will use patients where or visits where a measurement has been recorded, and those where it hasn't been recorded, and the system will actually read the clinical note, it's almost magical, and estimate an endpoint from that. We validate many of those and I was using some examples from lupus, the SLEDAI as an example, because it's used in clinical trials, but it's only used in like 5% of practice in the clinical world; 5% of encounters, so it's incredibly valuable to be able to do that. Those are some of the areas where we see value and data collection.

In an interview with Nico Saraceno at DPHARM 2024, Munther Baara, VP strategy and innovation, EDETEK touches on the features an effective AI/ML model can provide and how they benefit data management in trials.

DPHARM 2024: Developing AI/ML Models for Clinical Trials

ACT: You have an upcoming session on “Transforming Clinical Trials: From Reactive to Predictive.” What are some of the main points that will be discussed during the session?

 I'll be talking about the metaphor of travelers. Back in the days—it depends how old you are—you might remember when people used to travel, they'll have a map with them. There'll be a passenger next to them with the highlighter trying to map their route, and if they miss an exit, it will probably take them another hour to come back and then we progressed to the MapQuest, where we printed the map, and then we end up with the GPS, and then we end up with a smartphone, and then became a gamification with ways and now we're getting into the predictive analytics to basically predict how you get to do your next day and probably telling you what you should be doing, etc. I see this like in our clinical trials, there's some companies that are still using the paper, navigating with the highlighter, there's people at the GPS, and once a new study with different endpoints, it becomes harder and harder for them, basically, to navigate and be able to see the big picture.

What I'm going to talk about is very simple concept. We call it the four Cs—connect, collect, conform, and consume. What we've done, we’ve built this whole architecture to allow you to connect to the different data providers at the site level or at the study level, so that gives you the ultimate flexibility. You could use different ADC vendors, central labs, ePRO, new digital endpoints, genomics, data, etc., it doesn't matter. The idea behind it is those data providers will immediately be basically pushing data into what we call our digital data pipeline. Then, once the data starts flowing in, you'll see the data coming in and then conforming to the standard of your liking, whether it's for submission or for data review, and then provide you the final piece, which is what we call the consume piece. That's what's so powerful, because now you have to think about it like, you come to a building, you expect light, electricity, and water, right? You don't think about it. Once we do these hooks into the building, into your clinical trial, into our digital data pipeline, things start flowing, and now you're seeing everything in one place, one version of the truth. There are no delays because typically study managers tell me my study was great—green for six, nine months, the first DMC data monitoring committee meeting, I need to do the cleanup or interim analysis—that's when things start basically going south. It went immediately from yellow to red, and I see I have the wrong patients in the study, etc. We solve this problem from day one. That's the key. Study starts. Data starts flowing in. You're seeing whether you are enrolling the right patients into the study or not.

ACT: From a technological standpoint, what’s required for the development of more accurate AI/ML models?

 That's a good question. I struggle a lot of the time when people talk about AI and machine learning, and I feel like they have not done the foundational pieces that's needed in place. Of course, you need AI and modeling and machine learning, but you’ve got to think about: you need to be able to curate the data, aggregate the data, and you need to make sure the data is validated with high quality, so not only curate, but cleansing of the data. The 4 Cs concept that I described does exactly that because we bring data in real time, we basically run all these validation checks, and we have what we call flexible validation rules that you can do through and point and click. Zero programming involved. It eliminates SAS coding, et cetera, especially when you cross data across different data providers. I can look, for example, like somebody says in the exposure data, we adjusted the treatment, and then I look in adverse events, there is no reason for adjustment, et cetera. I can basically cross reference a lot of data. I can cross reference lab collection with the actual lab results, the ePRO data, with how the patient reported safety versus SAE, so I can do that all in coding and then we can apply algorithms as well to monitor the quality of the data. As the data comes in, you immediately point out where there's weak points or what needs to be addressed and tackled, and you’re cleaning the data as you go. That gives you the foundation to have excellent AI and machine learning, basically models in place in order to respond to this. Without it, your model is going to be weak. You're going to be missing a lot of pieces, and not only that—which I forgot to talk about—is the metadata about the data. In order for machine learning and AI to increase the accuracy of it, you need to have the data about the data and that's what our platform has. We can take raw data, transform it to any target data, like from the EDC collection to the CDISC SDTM format that's ready for submission for the regulatory agencies, so that together is needed in order to be able really to get into the next level.

Latest Conference Coverage

Jim Murphy, CEO of Greenphire discusses the role of artificial intelligence, using trusted data, and simplifying protocols

The Potential of AI in Budgeting and Forecasting

ACT: Is there any potential for the use of artificial intelligence (AI) in budgeting and forecasting? If so, how?

 Everybody's asking themselves what are the boundaries and what's the timeline for AI to touch their universe? I would say maybe as a starting point, the entire process of budgeting and forecasting is based on data patterns, structured data patterns that are applied through tools to extrapolate outcomes. That analytic use of data, it's not AI, obviously, but it is really thoughtful use of structured data, and I think about the idea of a ChatGPT or some sort of accessible AI tool that's using an open internet-based approach, you're not really going to be able to do a ton in terms of budgeting-type activity for clinical trials, because where those solutions do their best work is where there's just a ton of information out on the internet or in a closed system, where maybe the algorithm can be a little bit more targeted towards trusted data, but there really aren't places where that much trusted data exists to drive budgeting and nuance is tough for AI, and really nuance is that therapeutic area and geography basis, there's regulatory considerations that have to be in, so I think the short answer is, certainly there is a role, but I think good data analytics is really what is still the emerging need, which ultimately is just now being addressed. Fair market value has been around for some time, and is constantly getting better as we apply more real-time information into that equation and algorithm, patient-neutral spend and travel-related spend that's never existed. We're creating that now and really taking this amazing amount of insight and putting into hands of people.

I do think there are some interesting areas, though, that are adjacent to the budgeting process that there is some benefit that I can imagine more immediately from AI. Protocol simplification is absolutely a quest, make it easier for greater inclusion/exclusion criteria and enrollment and whatnot. I think there's broader health system data across different countries that's more accessible that might be used to do some of that chore of trying to figure out where things can be bent and flexed to simplify where possible, and then synthetic treatment arms, that's another angle off similar real-life, real-world data that maybe it's analytic, maybe it's an artificial intelligence opportunity, I'm not sure, it's sort of right there at the at the edge of the two. That would be my best insight for the most immediate-term in the budgeting and forecasting process, as well as maybe some adjacent areas.

In the final part of this video interview, Jim Murphy, CEO of Greenphire discusses the role of artificial intelligence, using trusted data, and simplifying protocols. 

Melissa Easy, VP commercial, digital products & solutions, IQVIA shares what excites her most about the future of clinical technology. 

The Future of Clinical Technology

ACT: What are some potential advancements in clinical technology that you are looking forward to in the future?

 I did mention before One Home for Sites, and I am personally very excited about that, because I have the chance to work across the industry. I am currently working with many other vendors that people would consider competitors, we are working with sites, we are working with many sponsors, and it is about a very positive what can we do together? We are really focused on making the sites’ lives easier. To me, I am a very collaborative person, and I love that people are bought into this, and that we are really focusing on bringing everyone together. To me, that is certainly exciting personally, but I also get very excited about how we are as an industry getting better at reducing burden on sites, so there's a lot of focus on payments and how fast you can pay a site. I think that's brilliant, because of their cash flow. I think about our patients—everything we're doing is about their safety and how we increase it. To me, that is super exciting as a person, but even how we are starting to deploy AI (artificial intelligence) and LLMs (large language models) in a way that optimizes every part of a clinical trial, because we, clearly, all in this industry, want to be able to run studies faster, but safely, so that we are getting things to patients much faster. I, even just as a human—and I think that many people would think this too—I also start to then think about how this helps us with just general diagnosis of people's health. Clearly, a lot of this starts in clinical trials, but how we can move to a more proactive and less reactive kind of way of dealing with people's health, like accurate diagnostics and risk predictions, etc. For me, that actually is one of the driving things. I got very excited there.

In the fifth and final part of this video interview, Melissa Easy, VP commercial, digital products & solutions, IQVIA shares what excites her most about the future of clinical technology. 

Emerging Technology

Latest News