CRO/Sponsor

Clinical Trial Supply Chain

Decentralized Clinical Trials

Early Phase Development

Investigative Sites

Protocol Design

Risk-Based Monitoring

Study Start-Up

Trial Design

Clinical Operations & Strategy

Diversity Action Plans

Industry Initiatives

Recruitment

Analytics

Electronic Data Capture

Metrics & Benchmarks

Real World Evidence

Data Management

CRAACO

Enrollment

Integrated Research

Patient Participation

Institutional Review Board & Ethics Committee

Regulatory

Artificial Intelligence/Machine Learning

eClinical

mHealth

Technology

News

Academy

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

Events

Front & Center

Partner Perspectives

White Papers

Webcasts

Subscribe

Applied Clinical Trials is the thought leader in pharmaceutical drug development operations and clinical trial design, management, and monitoring.

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

DE&I

Topic

1rem

Authors

Following a discussion around summarization in Part 1, Part 2 discusses the method of pure abstraction in light of recent advances in deep learning and AI.

AI/ML Approaches to Assisted Medical Writing—Part 2

Experimenting with different methods using AI.

AI/ML Approaches to Assisted Medical Writing—Part 1

Chatbots can benefit regulatory landscape in light of evolving standards and guidelines.

The Future of Regulatory Intelligence With Conversational AI

eTMF-blockchain technology offers a myriad of application benefits to data quality and integrity while ensuring compliance to ethical standards. 

Future of Clinical Trial Documentation Management: eTMF Integrated with Blockchain 

Video interview with Sepehr Shojaei, VP, Design Solutions, Lightship

Lightship's Approach to Accessible, Representative, and Impactful Clinical Trials

Lightship prioritizes patient accessibility and centricity in clinical trials, ensuring a seamless and positive experience for every participant. Learn more about:

Lightship's mission and core purpose as a company

How Lightship’s mobile nursing teams and home visits enhance study participation and retention

The role of mobile research units in the community and how they enhance participant education, accessibility, and convenience

Sepehr Shojaei, VP of Design Solutions at Lightship, talks about how the company works with pharma and contract research organization (CRO) partners to support clinical trials that are patient-first and accessible.

Latest Conference Coverage

Lightship’s Approach to Accessible, Representative, and Impactful Clinical Trials

Video interview with David MacMurchy, CEO of Lightship

Accelerate Inclusive Enrollment and Delivery with Lightship

Lightship focuses on patient accessibility and centricity in clinical trials, ensuring the patient experience is a positive one. Learn more about:

Lightship's impact on achieving diversity in clinical trials by engaging underrepresented patient populations

How Lightship utilizes hybrid and decentralized trial designs to reduce patient burden

The impact a patient centric model has on clinical trial participation and outcomes

David MacMurchy, Chief Executive Officer at Lightship, offers some insights into the company's mission toward improving equity and diversity in clinical trials. 

In clinical trials, feasibility assessments often hinge on population-level eligibility data. But in the age of digital prescreening and short attention spans, there’s a critical layer we often miss: just because someone qualifies doesn’t mean they’ll participate. The real-world difference between curiosity and motivation is creating a silent bottleneck in patient recruitment, and many feasibility models aren’t equipped to see it coming.

At TrialScreen, we recently analyzed user behavior across more than 1,300 online eligibility screeners from December 2024 to April 2025. The goal was simple: to quantify the conversion cliff between people who 

From interested to engaged: A drop-off worth noticing

Of the 1,324 screener completions, 58.6% of individuals met the preliminary eligibility criteria. But of those eligible, only 41% provided an email address to connect with the research team. Zooming out, just 24.2% of those who completed a screener progressed to a point where real contact could be made.

Let’s call this what it is: a curiosity-motivation gap.

TrialScreen.org is a free digital platform designed to connect patients, families, and healthcare providers with actively recruiting clinical trials around the world. Users can search for trials in their area, complete a plain-language online pre-screener to check if they might be eligible, and if they pass, choose whether to provide their contact details to connect directly with the study team. It’s a low-barrier tool built to bridge awareness and action. But that final step submitting an email address emerges as a major inflection point.

These figures matter, not because conversion should be perfect, but because many recruitment strategies still assume that eligibility equals intent. In reality, online engagement reveals a layered psychological process. Patients may be curious enough to explore a trial but not yet motivated to take a step that feels like a commitment.

For clinical trial sponsors, contract research organizations, and feasibility planners, that’s a risk hiding in plain sight.

The psychology of progression: What’s holding people back?

In today’s digital environment, asking for personal information is not a neutral step. For many, submitting contact details represents a shift, from passive information gathering to active participation. That shift carries weight, especially in a healthcare context where trust, privacy, and previous experiences all play a role.

Our data also showed temporal patterns. The most screeners were completed on Wednesdays, aligning with peaks in organic search behavior related to clinical trials. This tells us that engagement interest builds during the workweek, but converting that interest depends heavily on what happens next.

And here lies another overlooked factor: response time.

Customer service literature is clear: response rates drop dramatically when organizations delay outreach beyond 24 hours. Some sources suggest expectations now sit closer to a one-to-four-hour window before interest begins to wane.

In clinical trials, this urgency collides with a common reality: many site coordinators work part-time, juggle multiple roles, and are not resourced to reply within that critical window. This leads to missed connections not because people aren’t interested, but because the system isn’t designed to meet them where they are.

Importantly, automated “thanks for your inquiry” emails don’t solve the problem. The attention clock only stops when a real person responds with meaningful information.

What this means for feasibility and resourcing

If only one in four people who pass an eligibility screener submit their details, then population-level estimates of “eligible patients” may dramatically overstate recruitment potential—unless we account for motivation and follow-up speed.

This is particularly important when designing feasibility projections for rare disease trials or narrowly defined patient cohorts. If a digital campaign attracts 1,000 screener completions, the expected number of engaged leads is not 1,000. It’s more like 240—if your system is responsive. By monitoring behavioral drop-off in real time, we enable recalibration of feasibility strategies mid-campaign, rather than waiting for enrollment delays to surface later.

Recruitment models must factor in behavioral drop-off

—not a binary state of yes/no, but a spectrum that fluctuates with how we engage.

Improving recruitment isn’t just about better algorithms, it’s about better timing and human follow-up. Here are three steps to bridge the curiosity-motivation gap:

Identify peak screener days (e.g., Wednesdays) and prioritize staff availability accordingly. TrialScreen’s data shows that responding quickly on these days can dramatically improve conversion.

Use automation to acknowledge, but not replace, human outreach. Patients know the difference and act accordingly.

Make it clear at every step that patients are in control. Respect for privacy, simple language, and visible transparency about what happens after they share their details all contribute to reducing hesitation.

As clinical trials navigate a digitized future, it’s not enough to identify the right patients. We must also understand what makes them move from curious observers to motivated participants.

In a world competing for attention, success lies not just in finding patients who qualify but in showing up when they’re ready.

Hugo Stephenson, MD, is Co-Founder and Executive Chair of TrialScreen

1. Toister, J. How Quickly Should You Respond to Email? Toister Solutions. April 7, 2020. 

https://www.toistersolutions.com/blog/how-quickly-should-you-respond-to-email

2. Response Time Metrics 2023: Guide & Explanation. Pexly. 

https://pexly.com/blog/customer-care/response-time-metrics-2023-guide-explanation

Clinical trials face a critical challenge: bridging the gap between patient curiosity and motivation to participate, impacting recruitment success.

The Curious vs. the Motivated: Rethinking Feasibility in the Attention Economy

Over the last half a century or so, clinical research has progressively shifted from a somewhat paternalistic focus on physiological or surrogate endpoints such as biomarkers or imaging, toward the inclusion of patient-centered outcomes that explore an individual’s lived experiences of their illness and treatment.

This transition reflects a recognition that traditional clinical metrics, while objective and quantifiable, may not fully represent how patients feel or function in their daily lives. A significant change in a biomarker may not translate to a meaningful change in a patient’s real-world experience.

This shift in emphasis to the importance of understanding the patient experience was driven by the FDA’s Guidance for Industry: Patient-Reported Outcome Measures,

 which outlined the use of patient-reported outcomes (PROs) in supporting labeling claims, and the development of standardized outcome measures through initiatives such as the NIH’s Patient-Reported Outcomes Measurement Information System (PROMIS).

In parallel, the International Council for Harmonization’s guidelines began emphasizing the importance of patient input in trial design, and the establishment of the Patient-Centered Outcomes Research Institute in 2010 further institutionalized the importance of patient experience in comparative effectiveness research. Collectively, these efforts have facilitated a reorientation in clinical research toward outcomes that matter most to patients.

Alongside these developments, over the last decade there has been a move away from paper to electronic capture of clinical outcome assessment (COA) data in clinical trials, due to benefits predominately revolving around improved data quality and, arguably, patient preference. These electronic COA (eCOA) systems are widely used across all geographies and phases of clinical research and have become integral to the successful execution of modern clinical trials. Typically deployed via an app on a smartphone provisioned to participants in a trial, or, increasingly, on apps or web browsers on a participant’s own device, there has been much talk in the eCOA industry of the importance of good usability and patient-centered design in order to reduce the burden on participants interacting with these systems in clinical trials.

Outside clinical research, general app and web-design best practices have long prioritized the accessibility and usability of these systems for the widest range of users. The history of web and app accessibility standards, particularly the Web Content Accessibility Guidelines (WCAG), reflects a global effort to ensure that digital content is usable by everyone, including people with disabilities.

Emerging from the broader push for civil rights, WCAG was developed by the World Wide Web Consortium to provide consistent, testable guidelines for accessible web design. Since its first iteration in 1999, WCAG has evolved in response to technological advances and user needs, particularly to support mobile access, impaired vision users, and those with cognitive disabilities. The most recent version, WCAG 2.2 (2023) continues this trajectory by addressing issues such as touch target size and accessible authentication. These standards are now essential for enabling equitable access to information, services, and participation in digital life and often form the basis of legal enforcement of compliance to the same.

This is not the case with eCOA, despite the purported importance of diversity and inclusivity of clinical trial populations. Integrating these practices into eCOA systems presents unique challenges. Ironically, the very same 2009 FDA guidance, which set the scene for the rise of PROs, also contained a statement that also set the scene for decades of repetitive research and conservatism in how PROs were implemented on eCOA systems.

Specifically, FDA stated that “Examples of changes that can alter the way that patients respond to the same set of questions include changing an instrument from paper to electronic format” and went on to suggest additional testing was recommended to demonstrate patients would not rate their experiences differently across different modes of data capture.

This guidance was solidified with the release of the 2009 ISPOR ePRO Good Research Practices Task Force report,3 which described the methods by which one might demonstrate this comparability.

This led to a lingering concern about the comparability of different modes of data capture in clinical research (e.g., paper vs. electronic, or between different modes of electronic data capture such as tablet and smartphone), and a focus on minimizing variability between modes by, for example, limiting to a single item and response option per screen. While this concern is finally fading in light of decades of research showing minimal impact on questionnaire integrity,

arguably the issue has stifled the broad adoption of accessibility standards in ePROM systems due to the variability in presentation they may introduce, for example, allowing patients to set their own font size.

Comparing Web Content Accessibility Guidelines (WCAG 2.2)

 with electronic PROM (ePROM) design best practices

 suggests that, while many of the WCAG guidelines can be applied to ePROM systems today without concerns for questionnaire integrity, tensions remain between the accessibility success criteria and ePROM best practices concerning changing content size and device orientation.

 by Mowlem and O’Donohoe highlighted the key considerations and tensions that arise:

Web/app best practices: Prioritize accessibility and usability for the broadest range of users, including those with disabilities, through principles like scalable text, flexible layouts, device orientation options, and compatibility with assistive technologies.

ePROM best practices: Historically focus on maintaining the measurement integrity of validated questionnaires when moving from paper to electronic formats i.e. a “faithful migration.” The goal has been to minimize changes in layout, wording, and structure to preserve data comparability.

 Allow users to enlarge text and adjust layouts for better readability.

: Changes in visual presentation (such as increased font size or layout shift) may unintentionally influence how individuals interpret questions, potentially affecting response validity.

Enable flexible orientation (portrait or landscape) to suit user preferences and accessibility needs.

Preserving a consistent presentation format across clinical trial participants is prioritized to avoid introducing variation that could impact measurement consistency.

 Personalization and device/browser accessibility tools are encouraged.

Standardization has been preferred to ensure all participants interact with the same layout of the measure, minimizing potential sources of bias.

The electronic data capture field has shown a trend towards flexibility and growing comfort with variability in how patients interact with their study tasks, and the time is ripe for a move towards harmonizing accessibility with validated data capture tools.

The goal is to eventually reach a point where accessibility best practices are ePRO best practices are aligned—making clinical trials more inclusive and representative, especially for people with impairments.

To make clinical trials meaningfully patient-centric and ensure we are making them accessible to all possible patients, not just a subset, it is essential that existing web and app accessibility best practices are integrated into eCOA systems.

While some standards can be adopted today, significant industry inertia remains to be overcome, and there are outstanding questions to address before best practices can be more meaningfully embraced.

However, with the transition away from concerns about comparability, the life sciences industry has demonstrated it can learn and adapt, and with patients’ best interests at heart, we are confident meaningful progress will be made in the coming years.

 is Senior Director, eCOA Product and Science, at Medidata; and 

, PhD, is Chief Scientific Officer at uMotif

Guidance for Industry Patient-Reported Outcome Measures: Use in Medical Product Development to Support Labeling Claims 

2. Cella, D; Yount, S.; Rothrock, N.; et al. The Patient-Reported Outcomes Measurement Information System (PROMIS): Progress of an NIH Roadmap Cooperative Group During its First Two Years. 

https://pubmed.ncbi.nlm.nih.gov/17443116/

3. Coons, S.J.; Gwaltney, C.J.; Hays, R.D.; et al. Recommendations on Evidence Needed to Support Measurement Equivalence Between Electronic and Paper-Based Patient-Reported Outcome (PRO) Measures: ISPOR ePRO Good Research Practices Task Force Report. 

https://pubmed.ncbi.nlm.nih.gov/19900250/

4. O'Donohoe, P.; Reasner, D.S.; Kovacs, S.M.; et al. Updated Recommendations on Evidence Needed to Support Measurement Comparability Among Modes of Data Collection for Patient-Reported Outcome Measures: A Good Practices Report of an ISPOR Task Force. 

https://pubmed.ncbi.nlm.nih.gov/37121630/

5. Web Content Accessibility Guidelines (WCAG) 2.2. W3C. December 12, 2024. 

6. Mowlem, F.D.; Elash, C.A.; Dumais, K.M.; et al. Best Practices for the Electronic Implementation and Migration of Patient-Reported Outcome Measures. 

https://www.valueinhealthjournal.com/article/S1098-3015(23)06153-3/fulltext

7. Mowlem, F.D.; O'Donohoe, P. Accessible Data Collection Methods in Clinical Trials: Do Current Best Practices for the Implementation of Electronic Patient-Reported Outcome Measures (ePROMs) Meet Accessibility Standards? Sciety. 

https://sciety.org/articles/activity/10.21203/rs.3.rs-5741400/v1

Clinical research evolves to prioritize patient-centered outcomes, integrating accessibility standards in electronic data capture for inclusive clinical trials.

Navigating the Intersection of Accessibility and Measurement Integrity in eCOA 

Over the past two years, generative artificial intelligence (AI) has emerged as a top strategic priority in the life sciences industry, driving innovation across drug development and regulatory processes. With generative AI now capable of accelerating clinical documentation, regulatory submissions, and content generation, organizations are faced with the dual challenge of ensuring data and content readiness and managing the broader organizational changes required for successful generative AI implementation.

At the heart of this transformation lies the clinical study report (CSR), a cornerstone document in the drug development process. Generative AI offers the potential to automate the creation of CSRs, reducing manual workload, enhancing accuracy, and speeding up the time-to-market for new therapies. However, for organizations to fully leverage generative AI-driven automation, they must first ensure that their content ecosystems are optimized for this technology. This involves data readiness, content readiness, aligning documentation processes with regulatory requirements, and designing a content ecosystem in which each document serves a unique purpose.

Standardizing data formats is critical to ensuring accuracy, comparability, and regulatory compliance and is also the foundation for automation.

Except for patient-level datasets formatted in standardized Study Data Tabulation Model (SDTM) and Analysis Data Model (AdaM), summary-level data standards needed for CSRs vary across studies and therapeutic areas, both within companies and between companies. 

Guidelines to provide standardized clinical data

 have been available for several years now, but efforts to implement them remain ongoing. Managing different study designs and data structures requires additional steps when implementing generative AI and putting it into production.

The best practice for an organization is to assess upcoming portfolios and identify early adopting users and studies. In turn, this will help identify past studies that best represent future projects. Another option is to work on anonymized data and documents representing the future state or standards of their business.

Generative AI can now quickly draft some pharmaceutical regulatory documents. However, pharmaceutical companies will not realize the full benefits of using generative AI to automate medical regulatory document development unless they define and simplify the content ecosystem and remove extraneous effort.

Sponsors want to use generative AI to save resources, accelerate timelines, improve reviewers' experience, and enhance quality. However, these same groups often add a large volume of unnecessary information to regulatory documents, especially CSRs, leading to multiple manual reviews, revisions, and the risk of contradiction across related documents.

Therefore, sponsors need to focus on content and process readiness to realize the potential of generative AI.

This article will focus on content readiness exemplified by the CSR.

CSRs are comprehensive technical documents that present the results of individual clinical trials. They typically include a detailed account of the study's design, methodology, and outcomes, which can be conveyed through text, tables, figures, and listings. These elements work together to provide a clear and concise summary of the findings.

CSRs form the backbone of the clinical documentation required for marketing authorization applications, and regulatory reviewers rely heavily on them to evaluate the safety and efficacy of new drugs. However, CSRs are not standalone documents. They are part of a broader ecosystem of documentation that supports drug development and regulatory review. Notably, regulatory reviewers ordinarily assess the risk-benefit of new drugs and indications not based on individual CSR results but rather on the totality of data submitted with marketing authorization applications.

Regulatory guidance for CSRs is antiquated and does not account for what modern regulatory reviewers need to keep pace with medical advances. Regulatory agencies demand objective, unbiased data for a thorough assessment of the safety and efficacy of new medical products. Subjective descriptions can introduce bias and hinder informed decision-making, necessitating the removal of subjective elements to ensure regulatory compliance and evaluation.

TransCelerate modernized CSR writing with a new template that streamlines the preparation and review process in a structured format aligned with regulatory reviewers' requirements. The new template also incorporates feedback from industry experts, regulatory bodies, and other stakeholders. The template avoids redundancy by referring to appendices for detailed information about study design, operational details, and so on.

Despite introducing TransCelerate’s CSR template and technological advances, the time required to produce CSRs has not changed over the last decade. In 2013, the time required to produce a CSR from receipt of final tables, figures, and listings (TFLs) to document approval was between 8 to 15 weeks. A recent survey conducted with 5 global pharmaceutical companies showed the range to be between 6 and 15 weeks.

Define the scope of the document content before automating

Authoring teams often add large volumes of unnecessary information to regulatory documents, especially CSRs, leading to multiple manual reviews, revisions, and the risk of contradiction across related documents. Generative AI produces content based on how it is trained. If trained to write the way authoring teams currently operate, it will. Automating content generation without first changing the way content is written will only accelerate the process of generating masses of content that authoring teams will then pick over for weeks or months. Authoring teams may save time producing their first draft, but those time savings will remain modest.

The first step in automating a document is defining a clear scope, the writing style, and the content detail level that aligns with regulatory guideline compliance. This forms the base from which you work on an automated solution.

To maximize the return on investment in generative AI, authoring teams must first optimize their content. Content optimization involves three primary tasks:

Objective versus subjective content in CSRs

Unlocking the full potential of artificial intelligence requires these stakeholders to ensure their data are accessible and secure. 

Dr. Ashish Indani

Articles

Latest Updated Articles