Real-World Data Archives -

Real-World Data Strategies and Challenges: Making Data Work for Your External Control Arm Study

External control arms (ECAs) are gaining popularity in comparative effectiveness studies, driven by a growing emphasis on robust evidence across disease areas and regulatory body acceptance. ECAs can provide a control group for single-arm studies, complement a larger portfolio of evidence, and enable research for rare or genetic conditions for which randomized controlled trials may be unethical or infeasible.

At the same time, real-world data (RWD) is becoming an essential foundation for building credible ECAs. RWD offers unique advantages: it reflects real clinical practice, captures diverse patient populations, and can provide data for robust treatment effects.

However, integrating data from multiple sources, such as historical trials, concurrent trials, patient registries, and cross-population datasets, requires careful methodological planning to ensure validity and regulatory acceptance.

To fully harness the value of external control arms, sponsors must ensure selected data is fit-for-purpose, index dates are aligned with trial eligibility, and rigorous statistical methods are applied to ensure comparable patient profiles. Here, we outline these three essential elements.

Choosing the right data source for your external control arm

When building ECAs, different types of external data sources have different strengths.

Historical or concurrent randomized trials

Historical or concurrent randomized trials contain systematically collected data and well-defined endpoints, following a detailed protocol. However, they often have small sample sizes, and evolving standards of care or diagnostic criteria can limit comparability over time.

Electronic health records and insurance claims

Electronic health records and insurance claims contain large, diverse cohorts and broad population coverage. But they frequently lack clinical details such as out-of-hospital care and non-prescription medications.

Patient registries

Patient registries provide systematic, detailed data collection, the potential for linkage and long-term follow up. Yet they can have high missingness and over-represent healthier patients, which could reduce the overlap in characteristics with trial populations.

Selecting the best data sources should be guided by fit-for-purpose assessments. These studies include exploring the availability of key prognostic characteristics and missingness, along with practical considerations such as access and timelines.

Defining appropriate eligibility criteria and index dates

Carefully establishing index dates is critical yet challenging when incorporating an ECA. In a trial population, the index date is clearly defined as when the patient meets eligibility or is randomized. The same eligibility criteria need to be applied to ECA patients using variables in the external data source. The index date should reflect the point at which those criteria are met. Misalignment of the index date leads to specific types of selection bias, including immortal time. This bias occurs when periods during which an outcome could not have occurred are misclassified, potentially creating a false treatment benefit.

Ensuring treatment and control patients are similar

In RCTs, randomization naturally balances prognostic factors between treatment arms. ECAs, by contrast, require explicit identification and adjustment of these variables. Clinical expertise is essential for determining which characteristics matter most. Comparing the distributions of these variables between the treated versus control arm helps to assess similarity. Statistical techniques including propensity-matched controls and inverse treatment of probability weighting can improve comparability and approximate the balance achieved through randomization. Assessing pre- and post-adjustment distribution of baseline characteristics quantifies the success of the method.

Final takeaways

Overall, to fully harness the value of external control arms, three elements are essential:

Selecting fit-for-purpose data
Defining index dates that align with trial eligibility
Applying rigorous statistical methods to ensure comparable patient profiles

When executed thoughtfully, ECAs can meaningfully strengthen evidence generation and expand the possibilities for clinical research.

Interested in learning more?

Join Deepa Jahagirdar and Vartika Savarna for their upcoming webinar, “Driving Credibility in External Control Arms with Real-World Data,” on Thursday, April 9 at 10 am ET.

What a New Study on AI Adoption in US Hospitals May Tell Us About the Future of Real-World Data

Artificial intelligence is becoming increasingly common in US hospitals. Nearly half of hospitals surveyed in 2023–2024 reported using AI-based predictive models — but adoption is not evenly distributed across the country. Some regions and health systems are moving quickly, while others — particularly those in healthcare shortage areas — are adopting more slowly.

These findings come from “The Landscape of AI Implementation in US Hospitals,” led by Yeon-Mi Hwang and colleagues and published in Nature Health in 2026.1 The study analyzes data from more than 3,500 hospitals nationwide and maps where predictive AI tools are being implemented — and where they are not.

At first glance, this may seem like a technology adoption story. In reality, it is also a data story.

As healthcare increasingly relies on real-world data (RWD) for research, regulatory decisions, safety monitoring, and value-based payment models, the way hospitals adopt AI could directly influence the quality and coverage of the data being produced across the United States.

AI adoption signals digital maturity

Hwang and colleagues found that interoperability — the ability of hospital systems to exchange and integrate data — was the strongest predictor of AI adoption. Hospitals with better health information exchange capabilities and fewer data-sharing barriers were much more likely to implement predictive AI tools.

This matters because AI systems require structured, standardized, and well-integrated data to function effectively. When hospitals invest in AI, they often strengthen their documentation practices, data governance, and system integration in the process. Those same improvements elevate the overall quality of clinical data.

In other words, hospitals that are ready for AI are often also ready to produce higher-quality RWD.

Why high-adoption regions may produce richer RWD

Predictive AI systems frequently generate structured outputs such as risk scores, alerts, and time-stamped predictions. These outputs are recorded in electronic health records and become part of the clinical data landscape.

As a result, regions with higher AI adoption may generate data that is more complete, more standardized, and better linked across care settings. Their records may contain clearer severity markers, earlier detection signals, and more consistent documentation of clinical decision points.

This is why high-adoption regions may produce richer RWD. The data is not only documented — it is more granular and more measurable.

Because the study shows that AI adoption clusters geographically, these differences in data richness may also cluster by region.

The geography gap

One of the more striking findings in the study is that hospitals in healthcare shortage areas and medically underserved regions were less likely to adopt predictive AI. These areas often include rural and resource-constrained institutions.

If these hospitals have less advanced digital infrastructure, the data they generate may be more fragmented and less standardized. Over time, this could create meaningful differences in data coverage across the country. Regions with strong AI adoption may produce deeper, more analyzable datasets, while underserved areas may remain underrepresented in national RWD pipelines.

That imbalance could influence which populations are most visible in research and regulatory evidence.

AI changes the shape of the data

AI adoption does not simply improve data capture — it can also shape how care is delivered and recorded. Predictive systems may trigger alerts, influence documentation patterns, and alter clinical workflows. These changes become embedded in patient records.

As a result, RWD from high-adoption environments may reflect AI-influenced care pathways, while RWD from lower-adoption settings reflects more traditional workflows. Differences in adoption may therefore create differences not only in data volume, but also in data structure and interpretation.

Why this matters for real-world evidence

Real-world data increasingly underpins post-market surveillance, comparative effectiveness research, regulatory decision-making, and value-based care arrangements. If richer, more granular data clusters in digitally advanced regions, then the evidence generated from national datasets may disproportionately reflect those environments.

This is not necessarily intentional. It is a structural consequence of uneven infrastructure development. But without attention to digital equity, disparities in AI adoption could gradually translate into disparities in evidence generation.

The bottom line

The nationwide analysis by Yeon-Mi Hwang and colleagues offers one of the clearest early views of how AI is spreading across US hospitals. Because AI adoption is closely tied to interoperability, digital maturity, and institutional capacity, it likely influences how real-world data is captured, structured, and represented.

High-adoption regions may produce richer RWD — data that is more complete, more granular, and better connected across care settings. At the same time, uneven adoption raises important questions about representativeness and equity in national datasets.

Understanding how AI adoption is expanding — and where it remains limited — may become a key factor in strengthening the US data ecosystem. If increasing AI adoption leads to more complete and structured RWD, it could significantly enhance the power and reliability of real-world evidence. But ensuring that this digital maturity is broadly distributed will be essential. Otherwise, the strength of future RWE may reflect infrastructure patterns as much as clinical reality.

As AI becomes more embedded in healthcare, how and where it is implemented may quietly shape not only care delivery — but the evidence base that guides it.

External Control Arms in Drug Development: Methodological and Regulatory Considerations

Drug development is growing more complex, with compressed timelines and increasingly high expectations from regulators, payers, and health systems. In this setting, external control arms (ECAs) leveraging real‑world data (RWD) are emerging as a pragmatic approach to support clinical development and downstream commercial decision‑making.

Randomized controlled trials (RCTs) remain the gold standard for evidence generation. However, in many modern development programs, traditional randomized designs are not feasible or may raise ethical concerns. Sponsors increasingly encounter situations in which:

Patient recruitment is slow, limited, or not achievable
Randomization is ethically challenging
Development costs escalate rapidly
Competitive dynamics demand accelerated evidence generation
Patient populations are small or rapidly progressing
There is a high unmet medical need

These challenges are particularly acute in oncology, rare diseases, post‑approval expansion studies, and advanced or cell‑based therapies.

What is an external control arm?

An external control arm replaces or supplements a traditional control group by leveraging data from patients treated outside the clinical trial. These patients are drawn from routine clinical practice and reflect outcomes under standard‑of‑care treatment in real‑world settings.

External controls are typically constructed using real‑world data sources such as:

Electronic health records (EHRs)
Administrative and insurance claims
Disease and treatment registries

Unlike trial data, real‑world data reflect patterns of diagnosis, treatment, and follow‑up in everyday clinical care. The foundation of a well‑designed external control study is the use of fit‑for‑purpose data that are sufficiently complete, clinically relevant, and reliable to support robust and defensible analyses.

Strategic value of external control arms

When thoughtfully designed and appropriately governed, ECAs can provide meaningful strategic benefits, including:

Shortened development timelines
Improved feasibility of clinical studies
Evidence generation in small or rare populations
Stronger value narratives for payers and health technology assessment bodies
Support for lifecycle management and label expansion strategies

Methodological considerations and risks to manage

The credibility and acceptability of an external control arm depend heavily on methodological rigor.

Key considerations include the following:

1. Study design

External control studies should be designed to closely mirror the clinical trial, including:

Alignment of inclusion and exclusion criteria
Clear definition of index date and baseline
Comparable follow‑up periods and outcome assessment windows
Consistent treatment context and line of therapy

Pre-specification of the estimand and statistical analysis plan is critical to avoid post‑hoc decision‑making.

2. Patient selection and alignment

Ensuring comparability between trial participants and real‑world patients is one of the most critical aspects of ECA design. Sponsors should:

Use transparent, reproducible cohort selection algorithms
Apply consistent definitions for key demographic and clinical variables
Assess overlap and positivity between trial and external populations
Explicitly evaluate differences in baseline characteristics

Sensitivity analyses should be conducted to quantify the impact of residual differences where appropriate.

3. Handling confounding and bias

Because external control arms lack randomization, confounding must be actively addressed. Common analytical approaches include:

Propensity score methods (matching, weighting, stratification)
Multivariable outcome regression
Doubly robust methods that combine weighting and modeling

Method selection should be driven by study objectives, data characteristics, sample size, and variable completeness and not for analytical convenience.

4. Data quality and missingness

Real‑world data are inherently heterogeneous and incomplete. Methodological plans should address:

Data provenance, completeness, and validation
Handling of missing or partially observed variables
Measurement variability across providers, systems, or data sources
Differences in assessment timing and frequency

Imputation strategies and key assumptions should be explicitly documented and tested through sensitivity analyses.

5. Outcome definition and assessment

Endpoints derived from RWD must be clinically meaningful and aligned as closely as possible with trial definitions. Considerations include:

Use of validated real‑world endpoint definitions
Clear attribution and timing of outcomes
Consistency with regulatory‑recognized measures of clinical benefit
Avoidance of surrogate endpoints unless scientifically justified

Outcome misclassification remains a key risk and should be explicitly evaluated.

6. Sensitivity and robustness analyses

Regulators expect evidence that findings are robust under alternative assumptions. Analyses may include:

Variation in matching or weighting specifications
Alternative cohort definitions or look‑back periods
Use of negative control outcomes or exposures
Quantitative bias analyses where feasible

The objective is to demonstrate that conclusions are not driven by a single design or modeling decision.

7. Transparency and documentation

Methodological transparency is essential for regulatory and payer review. Best practices include:

Prespecifying analysis plans and decision rules
Fully documenting data sources, algorithms, and assumptions
Providing traceability from raw data to final outcomes
Enabling reproducibility of key analyses

Regulatory outlook and expectations

Regulatory agencies and health technology assessment bodies, including the U.S. Food and Drug Administration (FDA), the European Medicines Agency (EMA), and the Canadian Agency for Drugs and Technologies in Health (CADTH) have recognized the potential role of external control arms under conditions of methodological rigor and transparency.

Regulatory agencies have not lowered evidentiary standards. Rather, they have:

Provided greater clarity on scenarios in which external control arms may be acceptable
More explicitly articulated methodological expectations
Encouraged early and proactive dialogue with sponsors

Successful regulatory submissions that incorporate ECAs typically:

Provide a clear scientific and ethical rationale for why randomization is not feasible or appropriate
Use high‑quality, fit‑for‑purpose real‑world data sources
Transparently define patient selection criteria and demonstrate alignment with the trial population
Show that findings are robust, reproducible, and minimally biased

Early engagement with regulators remains critical to aligning expectations and maximizing the likelihood of success.

Join Anupama Vasudevan and James Matcham on February 3 at 10 a.m. ET for an open office hours on “Evidence Generation with External Control Arms”:

Breaking Barriers in Rare Disease Research with Generative AI and Synthetic Data

In healthcare innovation, one of the most pressing challenges lies in rare disease research. There are approximately 7,000 rare diseases affecting over 300 million people worldwide. With only a handful of patients dispersed globally, gathering sufficient data to power robust clinical studies or predictive models is a monumental hurdle. However, a solution is emerging at the intersection of generative AI and real-world data (RWD) — a novel approach with the potential to reshape possibilities and unlock insights to address unmet medical needs in rare diseases.

The rare disease data dilemma

In the U.S., rare diseases are defined as conditions affecting fewer than 200,000 people. Despite their low individual prevalence, rare diseases collectively impose a significant burden on both patients and healthcare systems.

Research and development in rare diseases often face a vicious cycle: low prevalence leads to data scarcity. Traditional clinical trials are often infeasible and/or statistically underpowered due to the limited pool of participants.

Meanwhile, RWD sources such as electronic health records (EHRs), insurance claims, registries, and patient-reported outcomes offer valuable, albeit messy and fragmented, glimpses into the patient journey. Yet even RWD struggles to paint a complete picture in rare diseases. This is where generative AI steps in.

Enter generative AI: Making data where there is none

Generative AI — especially models like Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and, more recently, large foundation models — has a transformative ability: it can learn patterns from limited datasets and generate synthetic yet realistic datasets.

How it works

Learning from RWD: Even small datasets from rare disease patients can be used to train and fine-tune generative models. These models identify patterns, distributions, and time-dependent relationships present in the data.
Synthesizing patients: Once trained, the model can create new, synthetic patient records that preserve the statistical properties and characteristics of the original data. These “digital patients” simulate disease progression, treatment responses, and comorbidities.
Validating realism: Synthetic data must be validated to ensure it reflects the real-world data it was trained on. Techniques like distributional comparison, propensity scoring, and expert validation are used to ensure accuracy and utility.

Why synthetic data matters for rare diseases

Synthetic data can enhance rare disease clinical research in many ways, including:

1. Augmenting small cohorts

Synthetic data can boost sample sizes for rare disease studies, enabling:

Simulation of clinical trials
Development of more robust predictive models
Generation of synthetic control arms where traditional controls are ethically or logistically impractical

2. Enhancing privacy

In rare diseases, patient re-identification is an increased risk due to unique phenotypes or genetic markers. Synthetic data protects patient privacy, while at the same time preserves the utility of the data.

3. Facilitating global collaboration

As synthetic data is deidentified, it facilitates data sharing among researchers, institutions and borders, minimizing regulatory hurdles and fostering cross-collaborative discovery.

4. Accelerating drug development

Pharma and biotech companies can use synthetic data to:

Test drug targeting strategies
Model long-term outcomes
Conduct in silico trials in the earliest stages of development

Challenges and considerations

While promising, this approach is not without its challenges:

Bias amplification: Synthetic data reflects the biases of its training data. If the RWD is incomplete or skewed, so will the synthetic outputs be. Strategies to handle bias are essential.
Regulatory acceptance: Regulatory bodies are still evaluating how to incorporate synthetic data into approval pathways.
Validation standards: There is a need for consistent benchmarks and best practices for validating synthetic data — both in terms of privacy and utility, as well as broader generative AI applications in healthcare.

Looking ahead

The marriage of generative AI and RWD opens new doors for rare disease research. With the ability to synthesize patient data that preserves real-world complexity, we can begin to break free from the constraints of scarcity — generating insights, hypotheses, and interventions that were once out of reach.

As we move forward, interdisciplinary collaboration among clinicians, data scientists, regulatory bodies, and patient advocacy groups will be key to harnessing this potential ethically and effectively.

Interested in learning more?

Download our complimentary ebook, Rare Disease Clinical Trials: Design Strategies and Regulatory Considerations:

External Control Arms: A Powerful Tool for Oncology and Rare Disease Research

In clinical research, the randomized controlled trial (RCT) has been considered the gold standard. Yet in many areas — especially in oncology and rare diseases — running an RCT with a balanced control arm is not always possible. Patients, physicians, and regulators often face a difficult reality: how do we evaluate promising new therapies when traditional designs aren’t feasible?

This is where external control arms (ECAs) come into play. By carefully drawing on existing data sources and applying rigorous methodology, ECAs can help provide the context and comparative evidence needed to make better decisions.

Here, we will explore why ECAs are particularly valuable in oncology and rare diseases, how they support decision-making and study design, what data sources they can rely on, and which statistical methods are essential to reduce bias. We will also introduce the concept of quantitative bias analysis and conclude with why experienced statisticians are key to the success of this methodology.

Why external control arms matter in oncology and rare diseases

Oncology and rare disease research share several challenges that make traditional RCTs difficult:

Small patient populations: In rare diseases, the number of eligible patients is often extremely limited. Asking half of them to enroll in a control arm may make recruitment impossible.
High unmet need: In oncology, patients and families are eager for new options. Many consider it unacceptable to randomize patients to placebo or outdated standards of care.
Ethical constraints: For life-threatening conditions, denying patients access to an experimental therapy can be ethically challenging.
Rapidly changing standards of care: In oncology, new treatments are approved frequently. A control arm that was relevant when a trial began may become outdated by the time results are available.

In such contexts, single-arm studies (where all patients receive the experimental therapy) are common. But single-arm results alone are not sufficient. Without a comparator, how do we know if the observed survival or response rate truly reflects an advance? ECAs provide the missing context.

Even when a trial includes a control arm, unbalanced designs — such as smaller control groups or cross-over to experimental treatment — can limit the ability to make clean comparisons. External controls can augment these designs, helping to stabilize estimates and provide reassurance that results are robust.

Supporting internal and regulatory decision-making

ECAs serve multiple purposes:

Internal decision-making:
- Companies developing new therapies must decide whether to advance to the next trial phase, expand into new indications, or pursue partnerships.
- ECAs help answer questions like: Is the observed benefit large enough compared to historical data? Do safety signals look acceptable in context?
Regulatory decision-making:
- Regulatory agencies such as FDA and EMA increasingly accept ECAs as part of submissions, especially in rare diseases and oncology.
- While not a replacement for RCTs, ECAs can strengthen the evidence package and demonstrate comparative effectiveness in situations where randomization is not feasible.
Helping the medical community:
- Physicians, payers, and patients need to interpret trial results. An overall survival rate of 18 months in a single-arm study may sound promising, but how does it compare to similar patients receiving standard of care?
- ECAs help put numbers into perspective, allowing the community to better understand the true value of a new therapy.

Designing better studies with ECAs

External controls are not only a tool for analyzing results — they can also improve study design.

Feasibility assessments: By examining real-world data or prior trial results, sponsors can estimate expected event rates, patient characteristics, and recruitment timelines. This reduces the risk of under- or over-powered studies.
Endpoint selection: Understanding how endpoints behave in historical or real-world settings helps refine choices for the trial, ensuring relevance to both regulators and clinicians.
Eligibility criteria: RWD and earlier trial data can reveal which inclusion/exclusion criteria are overly restrictive. Adjusting them can broaden access while maintaining scientific rigor.
Sample size planning: By leveraging ECAs, trialists may reduce the number of patients required for an internal control arm, easing recruitment in small populations.

In other words, ECAs can shape trials from the start, rather than being seen only as a “rescue” option after the fact.

Sources of external control data

An ECA is only as good as the data it relies on. Broadly, there are three main sources:

Other clinical trials:
- Prior trials of standard of care treatments can serve as external comparators.
- Individual patient-level data (IPD) is preferred, but often only summary data is available.
- These data are typically high quality but may not perfectly match the new study population.
Published studies:
- Systematic reviews and meta-analyses of the literature can provide comparator data.
- Useful when IPD is unavailable but limited by reporting standards and heterogeneity across studies.
Real-world data (RWD):
- Sources include electronic health records, registries, and insurance claims databases.
- These capture routine clinical practice, reflecting the diversity of real patients.
- However, RWD often suffers from missing data, variable quality, and lack of standardized endpoints.

Each source has strengths and weaknesses. Often, the best approach is to triangulate across multiple sources, ensuring that conclusions do not rest on a single dataset.

The value of earlier clinical trials

Earlier-phase trials (Phase I and II) can be particularly valuable in constructing ECAs. These studies often include control arms, detailed eligibility criteria, and well-captured endpoints.

For rare diseases and oncology, earlier trials may be the only available benchmark. By carefully aligning populations and endpoints, statisticians can extract maximum value from these datasets.

The challenge, of course, is ensuring comparability. Patient populations may differ in prognostic factors, supportive care practices may evolve, and definitions of endpoints may shift over time.

This is where advanced statistical methods become essential.

Reducing bias with propensity scoring

One of the key criticisms of ECAs is the risk of bias. Without randomization, patients receiving the experimental therapy may differ systematically from those in the external control.

Propensity score methods are a powerful way to reduce this bias. The idea is simple:

For each patient, estimate the probability (the “propensity”) of receiving the experimental treatment based on baseline characteristics.
Match or weight patients in the external control group so that their distribution of covariates mirrors that of the trial patients.

This approach creates a “pseudo-randomized” comparison, balancing measured variables. While it cannot eliminate unmeasured confounding, it greatly improves fairness in comparisons.

Quantitative bias analysis: Addressing the unmeasured

Even with careful propensity scoring, unmeasured confounding remains a concern. Clinical researchers often ask: What if there are factors we didn’t account for?

This is where quantitative bias analysis (QBA) enters. QBA does not eliminate bias but helps us understand its potential impact.

For example:

Analysts can model how strong an unmeasured confounder would need to be to explain away the observed treatment effect.
Sensitivity analyses can simulate scenarios with different assumptions about unmeasured variables.

By explicitly quantifying uncertainty, QBA provides transparency. Regulators and clinicians gain confidence that conclusions are robust — or at least, that limitations are clearly understood.

The need for experienced statisticians

Constructing an ECA is not a “plug-and-play” exercise. It requires expertise across multiple domains:

Data curation: Selecting fit-for-purpose datasets, cleaning and harmonizing variables, and aligning endpoints.
Study design: Defining eligibility, follow-up time, and analysis plans that minimize bias.
Statistical methodology: Applying techniques like propensity scoring, inverse probability weighting, Bayesian borrowing, and QBA.
Regulatory communication: Explaining assumptions, limitations, and sensitivity analyses in language that regulators and clinicians can understand.

In short, ECAs demand both technical skill and strategic judgment. Partnering with experienced statisticians ensures that external controls provide credible, decision-grade evidence rather than misleading comparisons.

Final takeaways

External control arms are rapidly becoming an indispensable tool in modern clinical research — especially in oncology and rare diseases, where traditional RCTs often fall short.

They offer:

Context for single-arm studies and unbalanced designs.
Support for both internal and regulatory decisions.
Guidance in study design and feasibility planning.

By leveraging diverse data sources — from earlier trials to real-world evidence — and applying rigorous methods such as propensity scoring and quantitative bias analysis, ECAs can bring clarity and credibility to difficult development programs.

But the value of ECAs depends on how well they are planned and implemented. Done poorly, they risk misleading decisions. Done well, they empower researchers, regulators, and clinicians to make better choices for patients.

As the field evolves, one thing is clear: the expertise of skilled statisticians is the cornerstone of successful ECAs.

Interested in learning more?

Join Alexander Schacht, Steven Ting, and Vahe Asvatourian for their upcoming webinar, “Beyond the Standard Clinical Trial in Early Development: When and Why to Consider External Controls” on Thursday, October 16 at 10 a.m. ET:

Breathing Easier: How Wearables Are Revolutionizing Patient-Reported Outcomes in Respiratory Disease

The rise of wearable technology is transforming how clinicians track chronic respiratory diseases like asthma and COPD (chronic obstructive pulmonary disease). Traditionally, managing these conditions has relied heavily on intermittent clinic visits and subjective symptom reports. But what if we could continuously monitor how patients breathe, move, and feel — right from their homes?

Enter wearables: smart devices that collect real-time physiological and behavioral data. These devices typically work in tandem with smartphone apps that prompt patients to complete patient-reported outcome (PRO) measures — allowing for integrated, real-time tracking of a full range of patient-relevant outcomes. When combined, these tools offer a powerful new lens for respiratory health.

Why PROs matter in respiratory disease

PROs are essential for understanding the true impact of respiratory disease on daily life. PRO measures like the Asthma Control Test (ACT), COPD Assessment Test (CAT), and modified Medical Research Council (mMRC) Dyspnea Scale help patients communicate their symptoms and limitations. Yet, these snapshots — typically completed during in-clinic visits — often miss the nuances of fluctuating symptoms and the effects of lifestyle or environment.

This is where wearables shine: they offer objective, continuous, real-world data that can complement traditional PROs — typically administered in-clinic on paper or electronically — by adding daily context and physiological insight to self-reported symptoms. By enabling patients to complete PRO measures remotely, often via smartphone apps, paired with real-time wearable data, we gain a fuller, more continuous picture of their health and functioning.

What wearables can measure

Modern wearables can track a range of data relevant to respiratory care, including:

Physical activity (steps, walking time, exertion)
Heart rate and heart rate variability
Respiratory rate and breathing patterns
Sleep quality and disruptions
Environmental exposures (via linked apps or sensors)

While wearables provide continuous physiological data, PROs are typically captured via separate smartphone apps or digital platforms, where patients log symptoms, functioning, or side effects on a scheduled or event-triggered basis.

When patients report increased fatigue or shortness of breath, wearables can confirm whether activity levels dropped, sleep was disrupted, or physiologic stress markers changed — giving clinicians a fuller picture of disease impact and progression.

Applications in COPD and asthma

One of the most promising areas for wearables in respiratory care is pulmonary rehabilitation (PR). PR is a cornerstone therapy for COPD and increasingly recommended for severe asthma. However, adherence and engagement outside clinical settings can be challenging.

Wearables like Fitbit or Garmin devices are being used in PR programs to:

Monitor daily activity levels
Set and track exercise goals
Deliver motivational feedback
Correlate physical activity trends with PROs such as dyspnea and fatigue

Recent studies suggest that integrating wearables into PR not only boosts patient motivation but also correlates with improved self-reported symptoms and quality of life.

Another area of growth is early detection of exacerbations. New wearable patches and multi-sensor systems can detect subtle changes in respiratory rate, coughing, or oxygen saturation — sometimes days before a patient would seek help. When combined with self-reported symptoms like increased breathlessness or wheezing, these alerts could trigger early intervention and reduce hospitalizations.

Case in point: A digital lifeline for COPD patients

In one pilot program, COPD patients were equipped with a wearable sensor that tracked activity, respiratory patterns, and heart rate. They also submitted weekly symptom reports via an app. When wearable data indicated decreased activity and rising respiratory rate, and the patient-reported worsening breathlessness, clinicians were alerted and could intervene early — often adjusting treatment or scheduling a check-in before an exacerbation worsened.

This “digital safety net” approach is gaining traction as a way to personalize care and improve outcomes, especially in vulnerable or remote populations.

Challenges to widespread use

Despite their promise, wearables in respiratory care face several hurdles:

Data integration: Many devices still don’t seamlessly connect with electronic health records (EHRs).
Clinical validation: While feasibility is proven, more large-scale trials are needed to show that wearable-enhanced PRO monitoring improves long-term outcomes.
Implementation: Providers may require training in how to teach their patients to utilize wearables and the associated smartphone apps that collect PRO data, meaning that time spent on these activities should be considered billable.
Equity and access: Not all patients have smartphones, internet access, or feel comfortable using digital devices — particularly older adults, those in underserved or rural communities, and individuals facing technological or connectivity barriers.
Privacy and regulation: Health data from consumer-grade devices must be handled securely, and many wearables are not yet classified as medical devices.

The road ahead

With increasing support from healthcare systems, regulators, and tech companies, the future looks bright for wearable-assisted respiratory care. Remote patient monitoring is now reimbursable in countries like the U.S., and smart integration with PRO tools is making these technologies more usable and impactful.

As clinicians and researchers continue to validate these tools, we can expect wearables — and the PRO data they pair with — to become a routine part of respiratory disease management. Smartphone apps are now central to this ecosystem, not just for data capture but for delivering care.

Trustworthy AI in Action: Predicting Stroke Risk Transparently with Claims-Based Machine Learning

In recent years, deep learning and large neural networks have garnered most of the attention in the machine learning (ML) community. Their ability to model complex, high-dimensional data is indeed impressive. But in healthcare — where decisions can have serious consequences and interpretability is paramount — simpler, transparent models like logistic regression still have an important role to play.

Not every problem requires a black box. When it comes to predicting disease risk using structured data, such as insurance claims, traditional models can offer accuracy and insight.

Claims databases: An untapped resource for disease risk prediction

Claims databases are an increasingly valuable source of real-world data (RWD). Unlike clinical trial data, which is highly controlled but limited in scale and scope, administrative claims datasets cover millions of lives over multiple years, reflecting real patient behavior and care patterns.

These databases include information on diagnoses, procedures, prescriptions, and demographics — elements that, while lacking granular clinical detail, can still reveal important patterns in disease progression and risk. The scale of these datasets allows for robust statistical modeling, even for rare outcomes.

The case for explainable machine learning in claims-based risk prediction

When working with claims data, models like logistic regression, Lasso, or Ridge regression are not just sufficient — they are often ideal. These models:

Produce coefficients that quantify the relationship between features and outcomes.
Allow for transparent understanding of why a prediction was made.
Are easier to validate and communicate to clinicians, payers, and regulators.

In contrast, deep learning models often deliver slightly higher accuracy at the cost of interpretability — a trade-off that may not be acceptable in regulated healthcare environments.

A real-world example: Predicting stroke risk with claims data

In a recent study, Cytel used data from over 2.5 million insured individuals to predict the risk of stroke hospitalization. Using only claims-based features such as age, medication use, comorbidities (e.g., diabetes, hypertension), and health service utilization, we compared the performance of several models, including:

Logistic Regression
Regularized linear models (Lasso and Ridge)
XGBoost (a state-of-the-art ML algorithm)

The results? All models achieved similar predictive performance, with area under the ROC curve (AUC) values around 0.81. Logistic regression — simple, explainable, and well-established — performed on par with XGBoost, demonstrating that advanced complexity wasn’t necessary to achieve meaningful predictive power.

Transparency enables trust and action

What sets models like logistic regression apart is their explainability. Stakeholders can see precisely how risk factors like atrial fibrillation, hypercholesterolemia, or age contribute to predicted stroke risk. This level of clarity is essential not only for clinicians making decisions, but also for data governance, compliance, and patient communication.

In a time when “black box” AI models are under increasing scrutiny, explainable models offer a pragmatic path forward — especially when paired with large-scale real-world datasets like claims data.

Keep it simple, keep it transparent

Healthcare doesn’t just need powerful algorithms — it needs trustworthy ones. As our study shows, standard machine learning models remain highly relevant, especially when applied to well-structured real-world data. Claims databases, in particular, offer a rich foundation for developing these models and making preventive healthcare smarter, earlier, and more accessible.

Leveraging Mobile and Wearable Technology for Outcomes Research in Depression

As mobile and wearable technologies become increasingly integrated into daily life, their applications have expanded far beyond convenience and lifestyle. In the field of outcomes research — particularly within mental health — these technologies are opening new frontiers for understanding and monitoring clinical endpoints. A notable case is depression, where continuous digital monitoring can provide rich insights into both the course of illness and treatment impact.

This post draws on our findings from a recent systematic review and poster presentation to examine how mobile and wearable tools are currently deployed in depression monitoring and how this aligns with broader outcomes research goals.

Digital monitoring as a tool for mental health outcomes

Over the past five to six years, depression has seen a marked rise across youth and adult populations globally, underscoring the need for scalable and effective monitoring strategies. In parallel, smartphones and wearables have become ubiquitous, capable of capturing passive, longitudinal health data. These digital tools offer unprecedented potential for outcomes research by providing real-time behavioral and physiological markers relevant to depression.

To map the current landscape, we conducted a comprehensive literature review focused on how smartphones and wearables are used to monitor depression in research contexts. This synthesis aimed to highlight prevailing methods, feature usage, and the extent to which demographic variability is accounted for — critical considerations in health outcomes analysis.

Key findings from the literature

We reviewed 140 studies and identified 22 that met our inclusion criteria. The following themes emerged:

Study characteristics

Recency: Most studies were published in 2024, reflecting the field’s rapid acceleration.
Geography: The U.S. and Pakistan emerged as leading contributors.
Sample Size: Studies included an average of 465 participants, suggesting moderately powered observational designs.

Demographic reporting

Gender and age: Captured in 20 of the 22 studies.
Ethnicity: Reported in just 9 studies.
Education and marital status: Only 4 studies reported these variables — yet both are key social determinants of health and influence depression outcomes.

Monitoring technologies and features

Smartphones were used in 20 of the 22 studies, highlighting their dominance.
Key features monitored included:
- Mood tracking: 20 studies
- Movement (accelerometer data): 10 studies
- Heart Rate Variability (HRV): 5 studies
- Word usage tracking: 4 studies
- Sleep patterns: 2 studies

Clinical assessment tools

Self-reported clinical scales were commonly used as outcome anchors:

PHQ-9 (Patient Health Questionnaire-9): 6 studies
GAD-7 (Generalized Anxiety Disorder-7): 7 studies

(See our original poster for a visual breakdown of these features and tools.)

Implications for outcomes research

From an outcomes research perspective, these technologies offer compelling advantages:

Continuous and passive monitoring: Enables longitudinal capture of clinically relevant endpoints like mood, behavior, and sleep — reducing bias from intermittent self-reporting.
Scalability and reach: Mobile-based data collection can extend to underserved and geographically dispersed populations, improving study generalizability.
Early signal detection: Passive data streams can flag deterioration or improvement earlier than clinical visits alone, offering potential for timely interventions.

However, a consistent limitation observed in the literature is the underreporting of demographic variables — especially education and marital status. This omission constrains subgroup analysis and limits insights into how different populations experience depression and respond to interventions. In outcomes research, such data are essential for contextualizing and stratifying results across socioeconomic or cultural dimensions.

The path forward

As wearable and mobile sensors become more refined, their integration into real-world data frameworks will likely become standard practice in outcomes research. But to truly capitalize on this potential, researchers must enhance demographic reporting and examine interactions between digital phenotypes and traditional health indicators across diverse populations.

These tools not only offer more granular tracking of mental health status — they also help researchers and health systems better understand the dynamics of treatment effectiveness, burden of illness, and quality of life over time.

Interested in learning more?

This blog summarizes findings from the poster presentation, “Exploring Mobile and Wearable Technology for Early Depression Detection and Monitoring,” presented by Lyuboslav Ivanov and Manuel Cossio at Cytel and Universitat de Barcelona.

Innovations in Clinical Trial Design for CNS Disorders

Clinical research in central nervous system (CNS) diseases has long been fraught with challenges. High failure rates, complex pathophysiology, variability in disease progression, strong placebo effects, and difficulties in recruitment and outcome measurement have made CNS disorders one of the riskiest areas for drug development. However, recent innovations in trial design — coupled with advances in digital health and statistical modelling — are transforming how we conduct clinical research in diseases like Huntington’s disease (HD), Alzheimer’s disease (AD), and multiple sclerosis (MS). This blog explores three recent trials that exemplify these innovations and proposes statistical advancements to strengthen their impact.

Adaptive designs in Huntington’s disease: The PIVOT-HD trial

Traditional fixed designs often struggle to efficiently explore dose-response relationships or adapt to emerging data. Adaptive trial designs offer a dynamic solution, particularly valuable in neurodegenerative diseases like Huntington’s disease, where treatment response and disease progression can vary widely.

Case study: PIVOT-HD trial (NCT05358717)

The PIVOT-HD trial, led by PTC Therapeutics, is a Phase II adaptive study evaluating the safety, pharmacodynamics, and early signs of efficacy of PTC518, a novel small-molecule HTT-lowering therapy. PTC518 modulates mRNA splicing to reduce levels of the mutant huntingtin protein, a key driver of HD pathology.

What sets this trial apart is its seamless adaptive design. The trial is structured to adjust dosing and the randomization ratios based on interim pharmacodynamic and safety readouts. By incorporating planned decision-making, PIVOT-HD minimizes exposure to ineffective doses and accelerates identification of promising therapeutic windows.

Digital biomarkers and remote monitoring in Alzheimer’s disease: The DETECT-AD trial

Cognitive decline in AD is insidious and can be difficult to quantify with infrequent clinic visits and subjective tests. Digital health technologies are revolutionizing outcome assessment through continuous, objective, and sensitive data collection.

Case study: DETECT-AD (Digital Evaluations and Technologies Enabling Clinical Translation in Alzheimer’s Disease)

The DETECT-AD initiative, part of a broader effort supported by the NIH and multiple research institutions, is employing wearables, mobile apps, and speech analysis to detect early signs of Alzheimer’s disease in at-risk populations.

In the DETECT-AD observational study, participants use smartphone apps and passive sensors to monitor activities like walking, typing speed, and even voice characteristics. These digital biomarkers are being correlated with traditional cognitive assessments and brain imaging data to predict cognitive decline before clinical symptoms emerge.

Platform trials in multiple sclerosis: The OCTOPUS trial

In diseases like MS, where multiple mechanisms may underlie relapses and progression, traditional “one drug, one trial” designs are increasingly inefficient. Platform trials offer a more flexible and scalable solution.

Case study: The OCTOPUS trial (UK MS Society)

The OCTOPUS (Optimal Clinical Trials Platform for Progressive MS) trial is the world’s first multi-arm, multi-stage platform trial in progressive MS. Spearheaded by the UK MS Society, this innovative study aims to test multiple repurposed therapies simultaneously, using a shared control group and adaptive design principles.

OCTOPUS promises faster answers with fewer patients and more efficient use of resources, particularly crucial in progressive MS where effective treatments are lacking.

Statistical challenges and opportunities

Despite these advances, several statistical hurdles remain. Novel designs require equally innovative statistical approaches to preserve validity and ensure robust interpretation.

Broader adoption of Bayesian statistical frameworks

Bayesian approaches allow the integration of prior knowledge (e.g., historical control data or early biomarkers) and offer probabilistic interpretations of trial results. In adaptive and platform trials, Bayesian methods facilitate:

Interim analyses with posterior probabilities guiding adaptations.
Dynamic borrowing from concurrent or historical control arms.
Greater flexibility in endpoint modelling across heterogeneous subgroups.

For example, the GBM AGILE platform trial in glioblastoma (a CNS tumor) successfully uses Bayesian methods to adapt enrollment and determine early stopping rules. A similar framework could benefit complex CNS conditions like MS or AD, where responses are highly individualized.

Incorporating real-world evidence (RWE) in trial planning and analysis

As clinical trials increasingly occur alongside large electronic health record (EHR) systems, real-world data (RWD) can inform trial design and enhance external validity. Specifically:

RWD can help refine eligibility criteria to better represent actual patient populations.
Real-world comparators can augment underpowered control groups or offer external validation.
Longitudinal RWE provides insight into long-term treatment effects beyond trial duration.

In Alzheimer’s disease, initiatives like the AHEAD 3-45 study are already incorporating observational cohorts and RWE in trial simulation and endpoint modelling.

The next generation of neuroscience trials

The future of CNS clinical trials is increasingly adaptive, digital, and data driven. Innovative designs like PIVOT-HD, DETECT-AD, and OCTOPUS illustrate the power of new methodologies to make trials more efficient, sensitive, and patient-centric. However, to fully realize their potential, we must integrate robust statistical techniques such as Bayesian modelling and real-world data frameworks. These tools will help overcome inherent complexities in CNS research and bring transformative treatments closer to patients in need.

As we look ahead, collaboration between statisticians, clinicians, regulators, and technology developers will be essential in shaping the next generation of neuroscience trials — where precision, agility, and real-world relevance are no longer luxuries, but necessities.

Interested in learning more?

Register now to watch James Matcham’s on-demand webinar, “Clinical Trial Design Innovation in CNS Disorders.” This webinar features a review of regulatory guidelines and showcase recent successful trials in Alzheimer’s disease and other neurological disorders.

From Toplines to Triumph: Visualizing the Pathways to Regulatory Approval

Achieving positive topline results in a clinical trial marks a critical milestone in the drug development process, yet it is far from the end of the submission journey. Instead, it signals the start of a complex, fast-paced effort to prepare for regulatory submission and navigate the FDA’s multi-stage review. The final “regulatory defense” stage demands rigorous collaboration, meticulous planning, and adaptability to meet the expectations of regulatory agencies.

Here we discuss the key stages in the post-topline journey, exploring key milestones, unexpected challenges, and best practices for ensuring a strong submission and a smooth path to approval.

1. The Preparation: Post-topline readiness and strategic planning

The preparation phase begins immediately after topline results are available. During this critical window — often lasting several months — cross-functional teams shift their focus to assembling the final submission package. Statisticians and programmers play a central role here, finalizing the tables, listings, and figures (TLFs) that will populate the Clinical Study Report (CSR) and preparing submission-ready datasets following CDISC standards, including ADaM, SDTM, and associated documentation.

In parallel, a pre-BLA or pre-NDA meeting with the FDA is typically scheduled to align on expectations, identify potential concerns, and set the foundation for a smoother review process. This phase is not just about document generation; it’s about establishing a strategy, anticipating regulatory scrutiny, and ensuring the submission is both complete and compelling. The quality of the groundwork laid here often dictates the ease — or difficulty — of the phases that follow.

2. The Submission: Crossing the threshold to regulatory review

Once the submission is filed, the process transitions into a more structured phase governed by the FDA’s review protocols. The agency begins with a 60-day filing review to assess whether the BLA or NDA is complete and acceptable for full review. If so, the sponsor receives a Day 74 Letter, which provides early feedback, flags any immediate concerns, and confirms the Prescription Drug User Fee Act (PDUFA) date — typically 10 months post-filing for standard reviews or 6 months for priority reviews. Although this phase may seem procedural, its significance is high. A clean, well-organized submission can streamline the review process, limit questions, and reduce the risk of delays. This is also the point where rolling submissions, if applicable under Fast Track designation, can offer a tactical advantage by accelerating document delivery and potentially shortening review timelines.

For statistical and programming teams, this is not a time to sit back and relax — it’s an opportunity to ensure internal alignment and anticipate questions the FDA may raise based on known data complexities. Strong documentation and traceability within datasets and outputs are essential at this point, helping to support any needed follow-up. Proactive communication and readiness during this phase help lay the groundwork for the more intensive regulatory engagement that follows.

3. The Regulatory Defense: Responding, clarifying, and defending your data

The regulatory defense phase is where the bulk of agency interaction occurs — and where flexibility and responsiveness become essential. During this time, the FDA may issue multiple information requests (IRs), asking for clarification on statistical methodology, specific data points, or safety and efficacy outcomes. Mid-cycle communications, typically occurring around months 4–5 for standard reviews, offer a formal opportunity to assess the review’s progress and surface any significant concerns.

In some cases, the agency may convene an Advisory Committee (AdCom) meeting to gather expert input, particularly when there are outstanding safety questions or complex benefit-risk considerations. Throughout this phase, the ability to quickly respond to ad hoc requests, provide high-quality data outputs, and maintain close collaboration across functions is critical. It’s a high-stakes stage where well-prepared teams can help preserve timelines and ensure the submission stays on track.

4. The Unexpected: Adapting to setbacks and charting a new course

In some cases, the regulatory journey doesn’t lead directly to approval. If the FDA identifies significant deficiencies in the initial submission — whether related to clinical data, statistical interpretation, manufacturing, or safety — it may issue a Complete Response Letter (CRL). This marks a temporary halt in the process, requiring the sponsor to address the concerns before resubmission. Depending on the scope of the deficiencies, the resubmission may fall under Class I (minor issues, reviewed in 2 months) or Class II (major issues, reviewed in 6 months).

For statisticians and programmers, this could mean conducting additional analyses, integrating new data, or adjusting the structure and presentation of the submission package. While a CRL can be a setback, it’s also an opportunity to recalibrate, seek additional guidance from the FDA, and improve the likelihood of approval in the next cycle. The key is to approach this phase with transparency, strategic thinking, and a readiness to adapt and respond.

Final takeaways

The path from topline results to regulatory approval is rarely linear. Timelines can range from as little as 12 months in expedited reviews to over 30 months in cases involving major deficiencies and resubmissions. Success in this post-unblinding phase hinges on proactive planning, adaptable resourcing, and the ability to respond quickly and thoroughly to regulatory needs. Equally important is collaboration across functions — clinical, regulatory, biostatistics, programming, and operations must work closely and cohesively to anticipate challenges, align timelines, and respond efficiently to agency requests. Whether following a standard or accelerated route, the shared priority is a comprehensive, high-quality submission that stands up to regulatory scrutiny — and ultimately supports timely access to new therapies for patients.

Interested in learning more?

Watch Jasperlynn Kao and Florence Le Maulf’s recent webinar, “From Toplines to Triumph: Visualizing the Pathways to Regulatory Approval”:

Older Posts

Discovery

Phase I-III Clinical Trials

Commercialization

Real-World Evidence Solutions

Clinical Trial Design

Trial Delivery

Advanced Analytics

Specialty Areas

Strategic Consulting

Beyond Functional Service Provider

Project-Based Analytical Solutions

Trial Design Software

Trial Implementation and Decision Support Software

LiveSLR® Software for Systematic Literature Reviews

Our Solutions

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

Quick Links

About Us

Quick Links

Insights

Quick Links

Careers

Quick Links

Choosing the right data source for your external control arm

Defining appropriate eligibility criteria and index dates

Ensuring treatment and control patients are similar

Final takeaways

Interested in learning more?

AI adoption signals digital maturity

Why high-adoption regions may produce richer RWD

The geography gap

AI changes the shape of the data

Why this matters for real-world evidence

The bottom line

What is an external control arm?

Strategic value of external control arms

Methodological considerations and risks to manage

Regulatory outlook and expectations

The rare disease data dilemma

Enter generative AI: Making data where there is none

How it works

Why synthetic data matters for rare diseases

1. Augmenting small cohorts

2. Enhancing privacy

3. Facilitating global collaboration

4. Accelerating drug development

Challenges and considerations

Looking ahead

Interested in learning more?

Why external control arms matter in oncology and rare diseases

Supporting internal and regulatory decision-making

Designing better studies with ECAs

Sources of external control data

The value of earlier clinical trials

Reducing bias with propensity scoring

Quantitative bias analysis: Addressing the unmeasured

The need for experienced statisticians

Final takeaways

Interested in learning more?

Why PROs matter in respiratory disease

What wearables can measure

Applications in COPD and asthma

Case in point: A digital lifeline for COPD patients

Challenges to widespread use

The road ahead

Claims databases: An untapped resource for disease risk prediction

The case for explainable machine learning in claims-based risk prediction

A real-world example: Predicting stroke risk with claims data