The move toward more participant-centric clinical research has taken an important step forward.

At the Clinical Pharmacology & Therapeutics journal, the first papers from the RADIAL trial, the flagship study of the Trials@Home project have now been published, offering valuable insights into how clinical research can be effectively brought to participants’ homes.

The project set out to explore the opportunities, benefits, and challenges of moving beyond traditional site-based clinical trials toward decentralised and hybrid approaches, all while maintaining scientific rigor, participant safety, and regulatory compliance.

The Challenge: Rethinking the Traditional Clinical Trial Model

For decades, clinical trials have relied on participants visiting centralised research sites for every step—from screening and consenting to assessments and follow-up.

While this model has proven robust, it presents significant barriers to accessibility, inclusivity, and efficiency. Participants often face long travel times, scheduling constraints, and logistical burdens that can limit enrolment and retention.

As digital health technologies mature, a key question has emerged:
Can clinical trials be conducted safely and effectively from the participant’s home?

Addressing this question requires balancing innovation with regulatory and operational standards—ensuring that new models of research remain reliable, compliant, and participant-friendly.

A Multi-Arm Approach: Traditional, Remote, and Hybrid Designs

To explore this question, the RADIAL trial implemented a unique three-arm design comparing:

• Traditional (site-based) – all study activities conducted at research sites.

• Remote (fully decentralised) – participants completed all study tasks at home.

• Hybrid – a blend of site visits and remote participation.

Each arm was assessed according to key performance indicators related to safety, data quality, participant satisfaction, and operational efficiency.

Our organisation served as the core technology provider for the trial—helping enable remote assessments, data capture, and participant engagement tools across all trial configurations.

Key Findings: Proof of Feasibility and Value

Initial results from the RADIAL trial demonstrate that decentralised and hybrid models can be safe, effective, and participant-friendly, provided that technology and operational workflows are implemented thoughtfully.

Key takeaways include:

• Comparable data quality and safety were achieved across all trial arms, indicating that decentralised models can maintain high standards of integrity and compliance.

• Participant satisfaction was high in the remote and hybrid arms, highlighting the appeal of reduced travel and greater scheduling flexibility.

• Operational efficiency improved in several domains, though logistical and regulatory complexities require continued refinement.

These findings offer concrete evidence that clinical trial activities can indeed be brought to the participant—without compromising scientific or ethical standards.

Collaboration, Curiosity, and Impact

Our involvement in the Trials@Home project was guided by three core principles:

• Collaboration – Working in a consortium of leading pharmaceutical companies, technology providers, and academic partners allowed us to integrate diverse expertise spanning medical, regulatory, and ethical dimensions.

• Curiosity – Challenging traditional models of research delivery was essential to driving innovation and reimagining how clinical trials can operate.

• Impact – Our focus was always on where technology could add the greatest value—supporting, not replacing, the human aspects of clinical research.

Why This Matters

Decentralised and hybrid clinical trial models have the potential to transform how research is conducted globally. By making participation more accessible, inclusive, and flexible, these models can reduce barriers, enhance diversity in clinical research, and speed up the generation of meaningful evidence.

Validated technologies, robust protocols, and strong partnerships are key to scaling these innovations safely and effectively.

Implications and Future Directions

The publication of the RADIAL trial papers marks an important milestone, but the work continues. Future efforts will focus on:

• Optimising remote recruitment and consenting processes to ensure inclusivity and compliance.

• Refining technology solutions to further streamline data capture and monitoring.

• Building regulatory and operational frameworks that support widespread adoption of decentralised approaches.

By learning from the RADIAL experience, sponsors and CROs can design future studies that blend the best of both worlds—maintaining scientific rigor while putting participants at the center.

Conclusion

The RADIAL trial has demonstrated that bringing clinical research to participants’ homes is not only feasible but can enhance the quality, efficiency, and inclusivity of clinical trials.

As we continue to refine these approaches, we move closer to a future where participation in clinical research is more flexible, accessible, and human-centered—no matter where participants live.

We are proud to have contributed to this landmark initiative and look forward to helping our partners apply these learnings to shape the next generation of decentralised clinical trials.

The search for reliable, accessible biomarkers for early detection of cognitive decline has taken an important step forward.

At AAIC 2025, our team presented data demonstrating that speech and language patterns can serve as valid digital biomarkers for Mild Cognitive Impairment (MCI) and Alzheimer’s disease (AD) across multiple languages. This is a critical advancement for global clinical research, helping ensure that early detection and monitoring tools are inclusive and effective for diverse populations.

The Challenge: Moving Beyond English-Only Research

While researchers have long recognized that neurodegenerative diseases affect speech and language, most studies have historically focused on English-speaking populations. As clinical trials expand globally, there is a pressing need for digital endpoints that work reliably across different languages.

A key question emerged: Do speech markers for MCI and AD hold true across different languages and linguistic structures? Addressing this question could significantly enhance the inclusivity and applicability of digital cognitive assessments.

A Multilingual Approach

To explore this, we analySed baseline data from 242 patients with MCI and AD across four languages: Danish, Dutch, German, and Spanish. Each participant completed a standardised picture description task in their native language, and we analysed their speech using the Winterlight speech processing pipeline.

We focused on five key speech features previously linked to MCI and AD:

1. Number of picture objects described

2. Number of nouns used

3. Speech rate

4. Pronoun-to-noun ratio

5. Average word length

We also created a composite score combining these measures and examined how all features related to the Mini Mental State Examination (MMSE), a widely used cognitive assessment tool.

Key Findings: Consistency Across Languages

Our results provide encouraging evidence for the cross-linguistic validity of speech biomarkers:

• Consistent patterns across languages: The relationships among speech features showed generally consistent directions across all four languages, with German showing the strongest correlations.

• Strong correlations with cognitive function: Both the composite score and object content unit score were significantly correlated with MMSE scores across all languages. Composite score correlations ranged from –0.26 to –0.47, while object content unit correlations ranged from 0.27 to 0.42.

• Enhanced sensitivity through combined measures: The composite score and object content unit score were more sensitive to cognitive decline than individual speech features alone, suggesting that a holistic approach to speech analysis is most effective.

Why This Matters

Validated digital endpoints that work across languages can enable more inclusive and diverse clinical trials, potentially accelerating the development of new treatments for neurodegenerative diseases.

Speech-based assessments offer several advantages:

• Non-invasive and accessible

• Provide objective, quantifiable data

• Complement clinician assessments and patient-reported outcomes

These tools could transform how cognitive health is monitored, making early detection of MCI and AD possible for people regardless of the language they speak.

Implications and Future Research

These results provide objective evidence that executive function deficits can be captured through the speech of individuals with depression. By detecting these changes through brief, low-burden, scalable assessments, speech markers offer a valuable tool for assessing both depression and cognitive dysfunction in a flexible, high-frequency manner. This helps to shine a light on aspects of cognition and behaviour that are affected but often missed by routine clinical assessments.

The next crucial steps involve a longitudinal follow-up to build on these findings with repeated testing. This research will test whether voice assessments can track changes in depressive symptoms following treatment.

Conclusion

The cross-linguistic validity of speech and language digital biomarkers represents a meaningful step toward more inclusive and accessible approaches to detecting and monitoring cognitive decline. By continuing to refine these tools and expand their use across diverse populations, we move closer to a future where early intervention for neurodegenerative diseases is available to all.

This year’s Clinical Trials on Alzheimer’s Disease (CTAD) conference brings together global leaders advancing research and innovation in Alzheimer’s and dementia treatment. We’re proud to be part of this important event connecting academia, industry, and regulatory experts to drive meaningful progress in clinical development.

As pioneers in digital health and cognitive assessment technologies, Cambridge Cognition is committed to supporting advancements in the measurement of cognitive function, improving trial efficiency, and enhancing the understanding of brain health in neurodegenerative diseases.

CTAD offers an exciting opportunity to share perspectives, explore emerging research, and engage with the international Alzheimer’s community. We look forward to connecting with researchers, clinicians, and partners who share our mission to accelerate innovation in neuroscience.

Join us as we celebrate progress, collaboration, and the pursuit of better outcomes for patients worldwide. See you at CTAD 2025!

This year’s Digital Implementation Summit brings together global leaders driving the transformation of clinical development from trial design to real-world deployment and we’re proud to be part of the conversation.

We’ll be presenting on “Digital Biomarkers: Voice and Digital Assessments,” exploring how multimodal digital measures can deliver more sensitive, scalable insights into patient function and treatment effects. From early-phase experimental medicine to late-stage validation, voice and cognitive assessments are redefining how we evaluate safety, efficacy, and patient experience.

It’s an exciting opportunity to share our perspective and engage with researchers, technologists, and regulatory experts who are shaping the next generation of digital health innovation.

Join us as we discuss how advances in digital biomarkers are enabling richer endpoints, more inclusive trials, and a deeper understanding of how patients live and respond beyond the clinic.

The development of new therapies for Central Nervous System (CNS) disorders, particularly Major Depressive Disorder (MDD), is fundamentally challenged by the subjectivity and limitations of current assessment tools.

Traditional measures, which often rely on patient self-reports or clinician ratings, frequently fail to capture the subtle but impactful cognitive and affective changes that characterize the illness. This incomplete picture hinders effective intervention and accurate treatment measurement.

To address this critical gap, Micaela Wiseman, PhD Candidate, and Dr. Jennifer Rabin, along with a team from the University of Toronto/Sunnybrook Research Institute, evaluated how objective voice-based assessments can provide a more robust, scalable, and low-burden method for assessing depression in clinical research. By utilizing Cambridge Cognition’s Winterlight app on participants’ own devices, this study aimed to remotely and objectively quantify aspects of depression that traditional, subjective assessments are currently missing.

We dive into the methodology and core findings of their research, “Speech Analysis as an Objective Measure for Cognitive and Affective Symptoms in Treatment Resistant Depression”, which was presented at the Society of Biological Psychiatry earlier this year. This work reveals how objective speech analysis may complement clinical assessments and enhance data quality in mental health research.

The Strategic Challenge: Moving Beyond Subjectivity

The field of psychiatry lacks objective biomarkers, relying heavily on subjective self-report and clinician assessments like the Hamilton Depression Rating Scale. These conventional methods are inherently limited by subjectivity, potentially failing to capture the full picture of depression symptoms and functional impairment, especially cognitive difficulties.

The primary objective of this study was to evaluate if automated speech assessment could serve as an objective, more scalable, and low-burden tool to bridge this gap, and to assess aspects of depression that traditional subjective measures might miss, particularly when using a remote protocol.

The Methodology

The study employed a rigorous approach to measure both subjective and objective data in 66 patients with treatment-resistant Major Depressive Disorder (MDD) and 54 non-depressed control participants:

1. Remote Speech Recordings
   Collected on participants’ own devices using the Winterlight app. Participants completed a brief journaling task (“please tell me how you are feeling today”).
2. Objective Cognition Assessment
   An in-clinic eye-tracking anti-saccade task was used to measure executive function.
3. Standard Clinical Assessment
   Clinician-administered assessments of symptoms, specifically the Hamilton Depression Rating Scale (HAMD-17).

Distinguishing MDD and Highlighting Cognition

The study established that patients with MDD have differences in speech patterns compared to non-depressed controls. This suggests that objective voice analysis can detect signs of depression.

Key features that significantly differed in the MDD group included:

• Linguistic Changes
  Patients used more negative words, words with higher emotional intensity, and words denoting a lower sense of agency.
• Acoustic/Speech Changes
  Patients, on average, spoke with a lower mean pitch, slower speech rate, and longer pauses compared to controls.

While most speech features did not correlate with depression severity scores on the HAMD-17, a number of them correlated with an objective measure of executive function (anti-saccade reaction time). This included speech rate, pause duration, use of negative words, and sense of agency words.

This demonstrates that speech assessments may be able to uniquely detect difficulties in executive function that standard, subjective clinical assessments may be missing.

Navigating the Challenges of Novel Biomarkers

During the study, there were two primary challenges inherent in novel biomarker adoption:

1. Limited Correlation with Traditional Scores
   Initial analysis showed that most speech features, despite showing strong group differences, did not correlate with HAMD-17 scores. This required the team to investigate if the speech features related to other aspects of depression not covered by the HAM-D, leading to the critical finding linking them to executive function.
2. Feature Selection
   Due to the high volume of measures available from a single speech assessment, it was a challenge on selecting which speech features to focus on. This was addressed by utilizing a select set of speech measures based on existing hypotheses and previous literature.

Implications and Future Research

These results provide objective evidence that executive function deficits can be captured through the speech of individuals with depression. By detecting these changes through brief, low-burden, scalable assessments, speech markers offer a valuable tool for assessing both depression and cognitive dysfunction in a flexible, high-frequency manner. This helps to shine a light on aspects of cognition and behaviour that are affected but often missed by routine clinical assessments.

The next crucial steps involve a longitudinal follow-up to build on these findings with repeated testing. This research will test whether voice assessments can track changes in depressive symptoms following treatment.

The Role of Objective Cognitive Assessment Tools in Clinical Research for CNS Disorders

The findings underscore the importance of objective cognitive assessment tools in mental health assessment and research. Cognitive models suggest that cognitive processes may mediate mood symptoms in depression, yet cognitive assessments are not routinely conducted in the clinic. The integration of highly scalable, objective digital tools allows researchers to capture these vital cognitive components that are often missed, which may be transformational for MDD research and improving care.

Solutions such as Cambridge Cognition’s Winterlight technology enable remote, app-based assessment capabilities, which can offer significant advantages for clinical trials:

• Scalability and Flexibility
  The app allows patients to download and complete assessments on their own time, making testing lower burden and more scalable than in-clinic assessments.
• Data Monitoring
  The system enables research teams to monitor assessments and patient progress on the back end, which is crucial for study management.
• Sensitivity to Symptoms
  These highly sensitive cognitive assessment tools have specificity to certain cognitive domains, providing novel insights into symptoms.

Speak with our specialists to learn how integrating scalable digital and voice cognitive assessments can provide high-quality, objective biomarker data for your CNS clinical research.

This years Clinical Trial Innovation Summit brings together global leaders driving the future of clinical research and we’re proud to be part of the conversation.

We’ll be presenting on “The Importance of Cognitive Assessment in Drug Development,” exploring how innovative cognitive tools are transforming safety and efficacy evaluation across both CNS and non-CNS indications. From early-phase dose selection to long-term outcomes, sensitive computerised assessments and speech biomarkers are providing powerful new insights into drug effects.

It’s a fantastic opportunity to exchange ideas, share our perspective, and collaborate with researchers, industry leaders, and regulatory experts shaping the next generation of clinical trials.

Join us as we highlight how advances in cognitive assessment are opening new possibilities for pharmacodynamic insights, real-world data collection, and smarter trial design.

This year’s program features world-class discussions on precision psychiatry, psychedelic therapies, and lessons from global clinical trials—and we’re proud to be contributing to the conversation.

We’ll be presenting our posters during the dedicated poster session, sharing our latest research and insights with leaders from academia, industry, and regulatory bodies. It’s a fantastic opportunity to exchange ideas, get feedback, and collaborate with experts shaping the future of mental health and neuroscience innovation.

Get ready to explore how our latest findings are pushing the boundaries of what’s possible in early detection, reliable assessment, and effective trial design for neurodegenerative diseases.

Speech as a digital biomarker in clinical research

Changes in how we speak—how quickly we talk, how often we pause, and the words we choose—can be early signs of cognitive decline. People with mild cognitive impairment (MCI) or dementia due to Alzheimer’s disease (AD) often show subtle shifts in their speech patterns, such as slower speech, longer pauses, and changes in pronoun or noun use.^1,2,3

Researchers have been looking for ways to measure these changes in natural, everyday-like situations. One promising approach is the picture description task—a short, low-burden activity where participants describe what they see in an image. The task can be done remotely, captures naturalistic speech, and is well-suited for repeated testing over time.

DEFEAT-AD collaboration

Researchers at Amsterdam UMC led the DEFEAT-AD study to collect high-frequency speech assessments remotely in a sample of 50 cognitively unimpaired individuals. Participants completed a 5-day “burst” of testing using a tablet and the Winterlight Assessment app including two picture description tasks per day for five consecutive days. In the repeating condition, the same picture was shown every day. In the alternating condition, a different picture was shown each day. After a 2–3 week break, participants repeated the same 5-day burst with identical stimuli.

How reliable are speech measures?

In order for speech measures to be able to be used in higher frequency testing, we need to determine their reliability and susceptibility to practice or learning effects when these tasks are completed repeatedly over several days.

We found that most of our selected speech measures had acceptable test-retest reliability over the five days of testing, and it didn’t matter much if the same or different picture was shown. Some measures, including total words produced and number of objects described, showed some evidence of practice/learning effects, with increasing scores over the first few days.

These results show that picture description tasks can be a reliable way to track speech changes over time in a high-frequency, remote testing setup. Alternating pictures or including a practice phase before data collection may help reduce learning effects. Because picture description tasks are ecologically valid, easy to administer, and low burden, they are promising tools for long-term monitoring of cognitive health—especially in remote or decentralized clinical trials.

Our latest research explores an exciting dataset with the AI–Mind Project, who have given us the opportunity to test the associations of our cognitive assessments alongside classic paper-and-pencil tests to levels of Tau-pathology blood biomarker test (BBM) p-Tau₂₁₇.

The AI-Mind Project

Among many types of data, the AI-Mind project has collected samples of p-Tau₂₁₇ from hundreds of patients that have been clinically diagnosed as having mild cognitive impairment (MCI), either having referred themselves or having had a carer or relative put them in touch with a clinic.

Mild Cognitive Impairment (MCI) and Plasma p-Tau₂₁₇

MCI is often a precursor to AD, with an annual progression rate to AD dementia of between 14% and 18% (e.g. see Tifratene et al. 2015). For that reason, establishing among those with MCI their likely disease trajectory can be very helpful when it comes to screening for inclusion in trials.

Elevated levels of blood plasma p-Tau₂₁₇ can indicate the presence of Alzheimer’s disease (AD) pathology while being relatively non-invasive and inexpensive to assay. This makes it invaluable in AD research and drug development, and in future it may become a routine blood test.

While p-Tau₂₁₇ alone can be an important signpost of underlying pathology, such physiological measures are only part of the story. The primary impacts of AD are cognitive ones, so it is important to understand the relationship between cognitive capabilities and physiological markers.

Cambridge Cognition Alongside Traditional Measures in MCI

The recent poster we presented at the 2025 Alzheimer’s Association International Conference, “Sensitivity of Cognitive Outcome Measures to Plasma p-tau₂₁₇ in Mild Cognitive Impairment in the AI-Mind study”, explores how a variety of our CANTAB test measures relate to p-Tau₂₁₇ levels, while putting them in the context of pencil and paper neuropsychological measures obtained in one-on-one interviews.

The analysis shows that our digital tasks have at least comparable sensitivity to p-Tau₂₁₇ as classical tasks. Whereas classical tasks must be obtained in person by a highly qualified expert neuropsychologist, our tasks are automatically delivered and scored, and are suited to remote testing.

The Alzheimer’s Association International Conference (AAIC) is just around the corner, and we’re incredibly excited to share some of the latest research our team has been working on. This year at AAIC 2025, we are proud to showcase the latest scientific insights derived from our invaluable partnerships and innovative studies. Our contributions provide critical evidence that could help shape the future of CNS drug development, particularly in the vital fields of Alzheimer’s disease and dementia.

Our presentations delve into key areas, from validating digital speech and language assessments across diverse linguistic backgrounds to exploring the sensitivity of cognitive measures to novel biomarkers. We’re also addressing the crucial psychometric considerations for remote voice assessments and developing new speech-based biomarkers for tracking disease progression.

Get ready to explore how our latest findings are pushing the boundaries of what’s possible in early detection, reliable assessment, and effective trial design for neurodegenerative diseases.