Beyond EDC: Wearable integrations

This is the fourth in a series of articles exploring the evolving EDC landscape and the pressing challenges shaping the industry’s evolution.

In our previous article, Beyond EDC: Enhancing Clinical Trials through CTMS Integrations, we discussed how integrating a CTMS with an EDC software can streamline clinical trial processes, and highlighted how Viedoc is pioneering this approach through advanced data pipelines.  

In this article, we once again consult Majd Mirza, Viedoc’s Chief Innovation Officer, and Binish Peter, Technical Fellow at Viedoc, to explore how Viedoc is leveraging wearable integrations. They will take us through a recent proof-of-concept study involving a smartwatch integration and its implications for clinical trials. 

It’s time to think beyond EDC.

​​Setting the scene​ 

Automatic data capture through wearables is transforming clinical trials by making participation easier for patients. This passive, real-time method of data collection eliminates manual input and reduces errors, while also providing continuous insights throughout the study. 

Traditionally, study data was integrated at specific time points or at the very end of a trial. Wearables, however, enable a shift to continuous data streams, and offer several key benefits:  

1. Real-time feedback boosts patient involvement  

Passive data collection ensures that patients can contribute data effortlessly, improving participation while negating input errors. This seamless experience encourages long-term engagement. 

2. Personalized monitoring allows tailored interventions 

Both patients and investigators can access immediate feedback and daily summaries, often presented in easy-to-interpret graphs. This enables rapid adjustments to treatment or study plans based on real-time data.  

3. AI-driven insights enable early detection of adverse events 

Wearable data streams can be analyzed using AI models to detect potential health issues early. This allows quicker interventions, enhancing patient safety and trial outcomes. 

Despite these advantages, wearable integrations in clinical trials remain underutilized. The sheer volume of data wearables generate is challenging to manage and traditional EDC systems were not designed to process or make use of such large-scale data streams. 

To extract actionable insights, the raw data must be aggregated, transformed, and summarized in ways that are relevant to the study, while revealing trends or patterns.  

Integrating the Viedoc way

At Viedoc, we recently conducted a proof-of-concept case study using a medically-certified smartwatch equipped with a SIM card and global data roaming. This device tracks steps and heart rate, with data sent directly to our system without intermediaries. 

The goal was to process the raw data streams, received every two minutes, into meaningful insights. We achieved this by aggregating and transforming the data into formats suitable for analysis and visualization, which could then be presented to investigators.  

Data transformation process 

Data collected throughout the day was aggregated, converted from JSON to CSV, and used to generate visualizations such as heart rate versus time graphs.  

The processed data, including graphs and summary statistics were then pushed into Viedoc EDC. This process was powered by Viedoc’s clinical data platform and data pipelines, which pull data from various sources (extract), standardize it (transform), and load it into the destination system for analysis (load).  

Binish explains further, “In this case, the data was pushed from the device to our system, which triggered the aggregation and transformation process. Since we received data every two minutes, we consolidated it into hourly and daily summaries, transformed it into CSV files, and generated insights and visualizations before pushing the results into the Viedoc EDC.” 

Storing and reprocessing data

All raw, aggregated, and transformed data is stored in Viedoc’s data lake. This ensures that the original data is always accessible for reanalysis, enabling the application of new algorithms or models to extract additional insights as technology advances. 

Majd reflects on the smartwatch case study, “This approach can be extended to support any wearable, digital health technology, or medical device that generates large volumes of data requiring aggregation and transformation before analysis. It’s a scalable, customizable solution tailored to meet the needs of any study.”  

Devices such as Apple watch, Samsung Galaxy watch, Withings devices, and Oura rings are just a few examples of wearable consumer devices that could be integrated using the same framework.  

Looking ahead: advanced data solutions and integrations 

Look out for the fifth and final article in this series, where we’ll focus on generating custom reports, custom data transformations, and integration with other data repositories. But in the meantime, why not explore our EDC software and learn more about how we can help streamline your trials.