AWS Partner Network (APN) Blog

Successful Decentralized Clinical Trials: A True Possibility with AWS in the Post-Pandemic Era

By Dr. Niket Gupta, Chief Strategist, Healthcare & Life Sciences – SourceFuse

Connect with SourceFuse-1

For decades, the focus of improving clinical trial outcomes has been on reducing time and cost. Historically, the challenge has been that not many patients join clinical trials—due to the burden, time, and effort to travel to clinical sites.

According to a Roots Analysis study, 80% of clinical trials fail to meet their patient recruitment targets. Around 30% of patients drop out of the trials on average, and approximately 36% have reported a protocol deviation. The pandemic increased these challenges and ignited the need for digitization as well as decentralization of the clinical trial lifecycle.

Decentralized clinical trials (DCTs) put the patient at the center of the trial experience and incorporate digital technologies like artificial intelligence (AI) and machine learning (ML) models to address the challenges associated with traditional clinical trials.

DCTs can reshape workflows across the clinical lifecycle—from trial design and patient recruitment to evidence generation. Benefits include a significant decrease in time and cost of the clinical studies, while at the same time improving patient engagement and experience during the clinical trials.

In this post, we will explore key challenges addressed by DCTs and how SourceFuse is leveraging Amazon Web Services (AWS) to build the right solutions for its clients to transform clinical research.

SourceFuse is an AWS Advanced Tier Services Partner and AWS Marketplace Seller with the Healthcare Consulting Competency. It is transforming the way today’s most successful companies develop breakthrough roadmaps leveraging cloud-based technologies.

Speed and Diversity of Patient Recruitment in Clinical Trials

Patient recruitment remains one of the largest obstacles in drug development. Broad marketing campaigns through avenues like social media have proven expensive and largely ineffective since it’s nearly impossible to identify participants that meet clinical criteria at the right time and in the right place.

For rare diseases specifically, it’s difficult to meet minimum patient enrolment targets within specified timeframes.

The diversity of trial participants is also a challenge that has generated a significant effort in the industry. Currently, trials do not adequately represent the population with respect to gender, race, or ethnicity.

Nature published a study in 2018 showing that while African Americans comprise 14% of the U.S. population, they only make up 2% of clinical trial participants. In a more recent study examining clinical trial diversity (BR J Clin Pharm, 2022) this trend continues, reporting that Black Americans make up only 1.8%.

This lack of diversity in clinical trials can result in:

  • Reduced drug efficacy for people with certain demographics.
  • Smaller market for new and innovative drugs.
  • Poor health outcomes for certain populations.
  • Lower revenues for pharmaceutical companies.


Figure 1 – Statistics of Black Americans in clinical trials.

The combination of AI/ML and DCTs is the key to overcoming this challenge. Together, they can advance the identification, enrolment, and participation of underrepresented groups by removing barriers such as selection bias, geography, transportation, and more.

In addition to ensuring diversity of participants, AI can better identify candidates who are most likely to respond to the intervention and even project which patients are less likely to drop out.

Machine learning applied to clinical data maintained in electronic health records (EHRs) can identify regions and individuals with higher pre-recruitment probability for screening success in case of time-sensitive clinical studies such as Covid-19 and Alzheimer’s disease.

SourceFuse is working with a digital healthcare startup which is focused on more racial equitable participation in clinical trials to build a solution which can address these issues. The pilot program is based on colorectal cancer clinical trials and aims to leverage AI/ML and AWS services to create a solution which will not only help address the gender diversity challenge but also find the right candidates at the right time.

Patient Engagement, Retention, and Experience During the Trial

Decentralized clinical trials focus on patient engagement to encourage patients to join and stay in the clinical trials. The shift to cloud-first and cloud-native architectures allows for global scaling and interoperability. This enables direct data capture from patients remotely through mobile devices and other innovative ways such as Amazon Alexa.

DCTs also use behavioral insights and nudges to improve patient retention and protocol compliance by helping patients modify their behaviours.


Figure 2 – AWS serverless platform creating an effective patient engagement.

Using AWS services, SourceFuse developed a breakthrough solution for a global pharmaceutical company to enable patient engagement.

The platform can seamlessly connect the patient, caregivers, doctors, nurses, and all other clinical stakeholders involved in the treatment journey while maintaining the highest level of security. It enforces regulatory compliance such as HIPAA and grants 100% data privacy as a part of public health information (PHI) standards.

SourceFuse developed a native iOS and Android application and a web app supportive of all modern browsers, connecting patients with doctors from the comfort of their homes. The application is a highly-secure, care-driven platform enabling the “right time-right patient-right medication” plan of action.

The application can be used by patients and/or caregivers when the patient is not equipped to use it themselves.


Figure 3 – Reference architecture of the SourceFuse platform.

Enhancing Data Quality in Evidence Generation

Decentralized clinical trials require digital avenues to evaluate the effects of an intervention. This requires interpretation of physiologic data to detect side effects and monitor patient safety. Therefore, DCTs collect more data that require efficient and accurate analysis and management.

It’s widely known that machine learning-generated biomarkers from preclinical datasets are crucial to drug discovery. It requires ingestion, transformation, and loading of the vast amounts of structured and unstructured clinical data from fragmented sources into a data lake. Data can be ingested from smartphone sensors, surveys, devices, lab data, and more. From there, descriptive and predictive analytics on this data to find biomarkers and actionable insights is enabled.

This end-to-end task requires a unique solution, a centralized repository that allows storing all of the structured and unstructured data in a standard format, such as FHIR R4, at any scale. Such a solution should also be able to analyze this data using various tools and technologies, which is where Amazon HealthLake comes in.

This AWS HIPAA-eligible service enables healthcare and life sciences organizations to securely store, transform, query, and analyze health data in minutes. Amazon HealthLake’s enhanced capability of AI/ML models, data visualizations, and analytics packages delivers specialized ML models to extract meaningful insights, identify trends, and make predictions at scale.


Figure 4 – Conceptual architecture using Amazon HealthLake.


Clinical trials can be decentralized and digitized in true sense and successfully executed using AWS Cloud infrastructure and services to overcome the challenges associated with traditional ways of doing clinical trials.

Benefits of this approach include:

  • Achieve patient recruitment goals and targets in clinical trials in terms of timelines and patient diversity.
  • Improve patient engagement, retention, and experience during the trial.
  • Enhancing data quality in evidence generation; for example, target validation, trial design, and patient identification.

Learn more about how SourceFuse is leveraging AWS to build the right solutions for its clients to transform clinical research. You can also learn more about SourceFuse in AWS Marketplace.

The content and opinions in this blog are those of the third-party author and AWS is not responsible for the content or accuracy of this post.


SourceFuse – AWS Partner Spotlight

SourceFuse is an AWS Advanced Tier Services Partner with the Healthcare Consulting Competency that is transforming the way today’s most successful companies develop breakthrough roadmaps leveraging cloud-based technologies.

Contact SourceFuse | Partner Overview | AWS Marketplace