As clinical trials have become more decentralized, there has been an increased focus on the need for more patient-centric drug development. This focus has led to a variety of eClinical applications. Electronic patient-reported outcomes (ePRO) and other electronic clinical outcome assessment (eCOA) approaches can transform trials to make them more pragmatic, patient-centric and efficient. Such approaches can accelerate data access through electronic health records and assist trial managers in making reliable data-driven decisions and mitigating risks.
ePRO methods in clinical trials may not be new, but the pandemic has boosted deployment. As the acceptance and proliferation of digital devices and wearables by regulators, clinicians and patients have grown, it has fueled more opportunities for remote monitoring.
Currently, one of our partners is running 17 COVID-19 studies in ePRO. They are conducting these studies in more than 38 countries with up to 400 participating sites and patient counts in the tens of thousands. Another partner is conducting 15 worldwide COVID-19 studies in ePRO, a clear indication that the market is confident in more patient-centric alternatives to the traditional trial model.
ePRO and other eCOA data have taken a higher priority in assuring accurate patient experiences are collected. But, to ensure accuracy, data must go through a process of validation measures to be used as a primary endpoint in drug development and trial evaluations.
Technology advances enable finely tuned outcomes
With the continuous mutations of SARS-CoV-2, drug developers are challenged to quickly determine the efficacy of current vaccines against the emerging strains. Therefore, the focus is on improved visibility and oversight of data collection, faster trial implementation, and real-time data sharing.
It is now possible to gather ePRO data via an app that can gather records — even photos and videos.
Wearable devices bring another opportunity to expand patient engagement. As wearables are an example of bring-your-own-device (BYOD) technology, there is not yet a clear path as to sponsors’ preferred methods, i.e., BYOD versus the provisioning of a device. Factors may include cost implications and privacy/security concerns.
Data science teams can develop dashboards, visualizations and analyses to enable effective safety and trial risk management. Such items alleviate some of the concerns with BYOD, such as participants turning off or changing notification settings, which lead to missing data points. Tools such as dashboards can reassure sponsors that sites can track compliance and potentially improve outcomes by telephone or text reminders to solicit engagement.
Some sponsors have adopted partially decentralized or hybrid eCOA approaches that require patient visits to a central site for major assessments but also include home visits by trained nurses. While limiting the number of visits to a central site, there is assurance that patients are complying with protocols and are comfortable using the digital device.
A major upside to monitoring in hybrid or remote trials is the opportunity to engage wider global patient participation, ensuring the trials are representative of a larger and more diverse population.
AI/ML strategies help ensure data integrity and regulatory acceptance
Clinical data management (CDM) teams have a crucial role in a successful clinical trial to ensure the production of quality, accurate and comprehensive clinical data to meet safety and efficacy standards to pass regulatory review. Modern data science tools and technologies support data validation and reporting, proving effective in identifying data inaccuracies. One of these tools is artificial intelligence (AI) and related visualizations that deliver insights, drive efficiencies and add substantial value to the clinical trial process. The CDM approach considers five essential data elements: data volume, variety, velocity, veracity and value. Data science techniques support CDM in these areas via the exploration, application and development of different technologies and approaches.
AI and machine learning (ML) inspire real data-driven decisions. For the trial sponsor, the application of AI/ML techniques uses historical data easily factored into data moving forward. For example, algorithms can help identify profiles, like gender, race, ethnicity of participants in the trial and then use existing data to engage the patient to follow correct procedures. ePRO also provides a huge bank of data, which can help with current and future participant behavior.
AI can also identify issues where automation could benefit the data cleaning process and, with a rules-based approach, identify potential data quality issues. AI can auto-detect potential hot-spots of data inconsistencies and potential anomalies. A rule-based approach can be applied to these hot spots to highlight potential data anomalies, creating efficiencies in the overall data cleaning process.
The pandemic has accelerated their adoption of AI/ML technologies. In event prediction, for example, a trial manager can look into a company’s historical clinical trial data and provide data guidance when perhaps writing new protocols. For instance, dosages may need to be increased/reduced for trials in different geographic areas or age groups. At an organizational level, it is possible to advise the sponsor based on a virtual trial conducted with historical data. At the patient level, these techniques can predict adverse events causality.
Cost benefits are real
Embracing new technologies requires investments, but the pros outweigh the cons. Various factors can impact the cost of a trial, i.e., data reconciliation errors, mistakes in data input or quality, or regulatory actions that can create hold-ups. Many of these issues can be mitigated with advanced technologies.
Technology continues to evolve in support of data gathering
It makes sense for sponsors to continue embracing and investing in existing and new technologies that bring cost-saving potential and an opportunity for wider patient engagement.
In sum, the future is bright for ePRO data collection, and it may have taken a pandemic to bring new ways to ensure its ongoing success.
The future is already here — sort of!
How much further can we go? In many respects, having the ability to BYOD has already been a huge step into the future. No training is required to use your own device. There are cost-savings for sponsors, efficient roll-out for trials, and so forth. The main barrier to ensuring quality collection of the data, however, has been patient engagement. But emerging solutions provide patients with in-gaming techniques and rewards to ensure the feedback loop is continuously closed.
But, what if the patient did not have to engage? Is there a way to collect data on the go? Or is there a way for machines to learn from a patient’s behavior patterns and ensure reminders appear to notify patients when they are most likely to engage?
The future of ePRO in clinical trials is looking toward ways to bring together vast amounts of digital data sources and use advanced computing power to identify patterns in the data, including patient behaviors. These ML algorithms and AI will play a significant role in modernizing the way information is gathered and processed as well as how trials and patient engagement will be conducted.
Now and in the future, AI and ML technologies represent a huge potential across the pharma industry. There have been several exciting applications, and we expect these will increase to enable speedier drug development and get the right treatments to the right patients faster. As AI and ML technologies become more sophisticated, they will support the use of continually growing volumes of usable data to provide earlier evidence-based decision-making in clinical trials.
Sachin Bharadia is an account manager for the CRO PHASTAR. He has more than 20 years’ experience in the pharmaceutical and CRO industry, and extensive experience of master data management, data lifecycle and effective use of research data through biometrics and management and oversight of vendor relationships.
Filed Under: clinical trials, Drug Discovery