Parkinsonian gait is one of several motor symptoms that are the hallmarks of Parkinson’s disease, including slowness of movement and tremors. Motor symptoms in Parkinson’s disease come from a lack of control over movements and difficulty initiating muscle movements. Gait disturbances can be detected throughout the progression of the disease: reduced amplitude of arm swing, reduced smoothness of locomotion, low speed, reduced stride length, shuffling steps, etc. However, gait can be difficult to assess and quantify through the usual clinical evaluation and in addition patient performance is associated with huge variability due to daily fluctuation. Hence, gait parameters as assessed objectively by a digital tool have a huge potential as biomarkers in relation to diagnosis/differentiation, tracking of disease progression, clinical trial outcome, etc., and therefore can support both researchers and clinicians in their decision making.

The FeetMe devices provide a platform for digital gait measurement the application of which can be adapted to the scope. The smart insoles can collect data ranging from fully controlled settings using standard gait tests to completely remote real life home monitoring, in an objective, quantifiable way, overcoming the limitations of the currently available technologies.

Gait`N`Park is a clinical study that was initiated in collaboration between Lundbeck, Lille University Hospital and FeetMe with the objective to assess “Markers of Disease Progression and Gait Within the Parkinsonian Population”. The study design and the first insight into the preliminary results reflect the flexible use of the technology and serve as a great example of the advantages of real world gait monitoring in a research setting.

Jonas Wiedemann, Specialist Biostatistician, Lundbeck
Alexis Mathieu, Co-founder and Senior Advisor, FeetMe

In this case study, we show how the Roche Parkinson's Disease Digital Biomarker Application identified a persistent reduction in bradykinesia progression when comparing the early-start prasinezumab group compared with the delayed-start group. The case study illustrates how digital biomarker approaches can be used to detect treatment effects.

Thomas Kustermann, Biomarker and Experimental Medicine Leader, Biomarkers and Translational Technologies Neuroscience and Rare Diseases (NRD), Roche Pharma Research and Early Development
Marzia Antonella Scelsi, Senior Statistical Scientist, Roche Pharma Development Data Science

Digital endpoints hold promise as more sensitive and less burdensome efficacy endpoints to improve drug development in neuroscience. We will present Novartis’ strategy to advance and de-risk the inclusion of digital endpoints in clinical trials. We will focus on our non-interventional methodology study carried out in early Alzheimer’s disease. Specifically, we will discuss how we introduced a mild cognitive challenge model to evaluate the sensitivity to change of 10 novel digital technologies.

Jennifer Sorinas Nerin, Postdoctoral Fellow, Novartis Institutes for BioMedical Research

• Where does the industry stand currently?
• How impactful are Digital Biomarkers in the meanwhile for the pharmaceutical industry?
• Digital Biomarker development in times of a pandemic. Challenge or catalyst?
• Key insights when transforming clinically relevant symptoms into digitally measurable biomarkers
• Progress and evolution of pre-competitive collaborations

Thibaud Guymard, General Manager, Digital Measurement Solutions, Biogen Digital Health
Florian Lipsmeier, Group Leader, Digital Biomarkers Data Analysis, pRED Data & Analytics, Roche
Jelena Curcic, Sr. Data Scientist, Biomarker Development, Digital Endpoint Analytics, Novartis
Dan Karlin, Chief Medical Officer, MindMed

Led by: Christian Gossens, Global Area Head, Digital Biomarkers, pRED Data & Analytics, Roche

Clinical trials for Alzheimer’s Disease (AD) have shifted focus to earlier phases of the disease and
therefore recruit from a more general population with little-to-no symptoms of dementia.
Screening for these studies is long, costly, and often experiences a high screen-fail rate due to a
lack of adequate pre-screeners to verify AD pathology. This recruitment problem is accompanied
by high costs and timely expansion of AD clinical trials. Thus, recruitment is a major limiting factor
to drug development for AD.

Trial efficiencies may be realized with the introduction of light-weight, cost-effective and scalable
biomarkers used as a pre-screening step during recruitment. Beyond traditional “wet” biomarkers
measuring biological processes (e.g. based on cerebrospinal fluid daws), behavioral signs such as
impaired cognition is an easy-to-observe hallmark of AD and present throughout all phases of the
disease trajectory including the early stage of Mild Cognitive Impairment (MCI). Speech biomarkers
that detect cognition are especially promising because they provide a reliable, valid, and objective
endpoint for early AD and, moreover, allow for an automatic, non-invasive assessment, making
them a scalable and low-burden tool which is optimal for screening scenarios in a broad
population.

We will present on how the speech biomarker for cognition of ki:elements (ki:e SB-C) is
implemented into Jansen’s Phase II study “Autonomy” through an automated telephone call, how it
is used in parallel to traditional outreach and questionnaires, and how it is used to select patients
that are likely to fit inclusion criteria.

Steve Ruhmel, Associate Director, Janssen Clinical Innovation
Nicklas Linz, CEO, ki: elements

This presentation will review potential advantages to the consideration of a range of validity evidence, driven by explicit context(s) of use and the relative value of construct validity evidence. Potential advantages of digital measures and the validation evidence that might demonstrate these will be considered. Keeping the end in mind from the outset of development may help to guide the successful generation of validity evidence. A unitary model of validation in which several types of evidence contribute to an evaluation of validity for a given context of use may be more valuable than taking the view that there are discrete types of validity, each with binary outcomes.

Chris Edgar, Chief Scientific Officer, Cogstate

High frequency data collection with digital health technologies poses unique opportunities but also challenges for clinical trials. We discuss lessons learned from trials across Roche, covering themes including Missing Data, Drop Outs, and Data Equivalence.

Jonas Dorn, Digital Biomarker Technology Lead, Roche
Timothy Kilchenmann, Digital Biomarker Scientist, Roche

COVID-19 pandemic has further accelerated the adoption of digital health technology in clinical trials enabling over 220 digitally augmented trials in 2021 alone. Researchers and trialists can reach a larger diverse target population and frequently assess their health by collecting individualized real-world data actively and passively. Such a scalable remote observational model helps investigators develop a better and holistic understanding of people’s day-to-day experiences of living with a health condition that ultimately will help improve our understanding of individualized health-related behavior and related outcomes.

However, several real-world challenges related to the quantity and quality of real-world data collected from the target population have surfaced. These include but are not limited to equitable recruitment and long-term retention of the target population. In this talk, I will summarize the ongoing learnings related to real-world data collection from three large-scale multinational studies that have enrolled over 20,000 participants (from young and healthy kids to patients with severe depression). Specifically, I will focus on two key topics:

1. Potential biases may impact the collection of health-related data using active and passive data streams, such as participants' socio-demographics, willingness/concerns, varying participation incentives, disease severity, and technical limitations across iOS and Android ecosystems.

2. Varying quality of sensor-based data collected from smartphones and wearables and its impact on developing robust digital endpoints. I will demonstrate digital signal processing-based data quality metrics to help assess the completeness, correctness, and consistency within and across participants and devices. For example, real-world factors such as device issues (e.g., hardware, software, network) and user-related (e.g., unintended or non-compliant device usage, non-wear).

Abhishek Pratap, Group Head AI & Digital Health, Centre for Addiction and Mental Health (CAMH), Toronto

Key takeaways from the recent FDA DHT Draft guidance and more

Christine Guo, Chief Scientific Officer, ActiGraph

• Next steps for the digital biomarker community
• Discussion of partnerships, regulatory progress
• The pursuit of passive patient monitoring & improved protocol adherence

Tracey Robertson, Head of Patient & Site Engagement Capability Management, Boehringer Ingelheim
Alexander Mion, Head of Clinical Trials Department, Swissmedic
Rinol Alaj, Senior Director, Head of Clinical Outcomes Assessment & Patient Innovation, Regeneron

Moderated by Lada Leyens, Global Regulatory Lead, Clinical Trial Innovation & Digital Health, Roche