Technologies that accelerate and improve Clinical Trials
Artificial intelligence (AI) technology, combined with big data, hold the potential to solve many key clinical trial challenges.
Late phase research, technology solutions and access to RWD are at the forefront of creating efficiencies in all stages of study design and implementation.
New technologies are enhancing the efficiency and scope of clinical trials through:
mHealth device technology has evolved to the point where it is now possible to collect a vast array of physiological data, sleep and activity data, and use advanced analytics to monitor patients in their own home outside of the hospital environment. However the penetration and use of wearables and devices in the pharmaceutical industry is still limited.
In this article, jointly authored by ICON and Intel, we discuss industry concerns about implementation of this technology in a clinical trial. These concerns focus on a number of key areas: Patient Acceptance, Device Suitability, Data Complexity and Insight Generation, Operationalisation, Privacy and Security Issues, and Regulatory Acceptance.
Webinar: Nov 8th - Best Practices for Implementing a Successful Digital Trial
Disruptive innovation is evolving and presenting real solutions but in order to adapt to the emergence of this innovation, companies will need to be more agile and open to learning and dealing with the impact. The barriers of disruptive innovation are forcing pharmaceutical companies and their partners to reshape how they look at everything they do across the entire spectrum of drug development.
Report: Read the views of three Senior Pharma Executives on how their organisations are approaching innovation.
In our industry survey and whitepaper, 'Improving Pharma R&D Efficiency' when asked what technologies would have the most impact improving clinical trial efficiency, the top answer from survey respondents was leveraging big data and AI at 36 percent.
Indeed Big Data and AI technologies are complimentary as AI can help to synthesize and analyse ever-expanding data. AI-enabled measures include data integration, data management and interpretation.
They make possible innovations that are fundamental for transforming clinical trials, such as seamlessly combining phase I and II of clinical trials, developing novel patient-centered endpoints, and collecting and analysing real-world data.
Late phase research is undergoing rapid transformation due to the impact of healthcare digitalisation and access to Real World Data
With the right technology infrastructure and support, sponsors can more completely leverage RWE across the enterprise for maximum value.
RWD such as sleep quality and quantity have clinical relevance in Alzheimer's disease. Review the use of wearables in Alzheimer’s disease to provide objective measures of sleep and activity patterns that are not subject to patient recall bias.
RWD-powered, post-marketing studies require fewer resources and EHRs are an efficient data source to support observational studies. Real World Data from Electronic Health Records can enhance your late phase research studies while decreasing study costs.
Cybersecurity vulnerabilities can emerge in any medical device that is or can be connected to another electronic device and/or network, resulting in potential harm to patients or financial loss for providers, posing major challenges for medical device manufacturers.
Checklist: View the cybersecurity checklist to see how well you're prepared.
Wearable devices and sensors offer great potential in the collection of richer data and insights to enhance our understanding of the effects of treatment. However, implementing wearables and sensors brings new challenges to clinical trial conduct, data management and interpretation.
BYOD promises greater patient-centricity by enabling patients to conduct assessments using the convenience and familiarity of their own hardware devices.
Blockchain technology allows for complete transparency of data, which has immense potential within clinical trials. Blockchain ledgers allow for user confidentiality, so patient privacy can be protected during exchange of data between parties - patient data is the most notable item of transactional nature between networks such as healthcare institutions, patients, and regulators.
Accurately projecting outcomes for diverse patient populations – from the wealth of genomic, phenotypic and outcomes data available through genome sequencing and electronic health records – holds the potential to transform the effectiveness and efficiency of drug and medical device development.
Quantum computing may enable statisticians to quickly explore, understand and interpret these enormous multivariate and often poorly structured data.
ICON is actively exploring this new field of quantum computing, and in spring 2017 co-sponsored a quantum computing workshop.