Sujay Jadhav, CEO of Verana Health, is advancing clinical trial capabilities, data-as-a-service offerings, and data enrichment.
Adoption of clinical trials is at the forefront of drug and medical device development for companies, but they often encounter significant hurdles. The vast majority of trials fail, which can lengthen the development process, incur significant costs, and prevent patients from accessing potentially life-saving treatments. Traditional recruitment methods relied on manual processes, word of mouth, and limited data sources, but the integration of artificial intelligence (AI) and data related to patient health and healthcare delivery from real-world settings A new solution has appeared. Also known as real-world data (RWD).
The role of AI and RWD in clinical trial recruitment
AI has the potential to transform clinical trial recruitment by leveraging RWD to find eligible participants. By leveraging AI, researchers can analyze the vast amounts of data provided by RWD, such as electronic medical record data, claims data, and imaging data, to uncover patterns and insights that are nearly impossible to detect manually. Can be identified. Other potential benefits include:
Optimized patient selection
AI can analyze complex datasets to identify precise patient subgroups that meet specific inclusion criteria. This reduces the diversity and inclusivity of trials, as underserved and rural areas do not have access to the same health infrastructure as areas historically targeted for clinical trials. It could be improved. Ultimately, lack of representation in clinical trials can result in results that do not accurately reflect the broader population, perpetuating health disparities. With AI and RWD, you can discover more patients, ensure trials are conducted with participants who best fit your criteria, and increase the validity and confidence of your results.
Shortened hiring schedule
AI's ability to rapidly process and analyze large datasets allows for rapid identification and pre-screening of potential participants. This significantly shortens adoption timelines, which is critical for companies bringing new treatments to market and improving outcomes for patients in need.
cost reduction
Without adequate patient participation, clinical trials may struggle to meet endpoints, resulting in companies incurring costs to continue trials and losing out on valuable market share. It will be. AI can reduce costs associated with clinical trials by accelerating the recruitment process and optimizing patient selection. This is critical considering that 90% of clinical drug developments fail and the average cost of research and development per product is $1.1 billion.
real case study
As electronic health record (EHR) data collection and analysis becomes more sophisticated, RWD-driven approaches are being used to streamline drug development. My company recently supported a Phase 2 clinical trial for chronic induced corneal pain after laser vision correction surgery (CICP). CICP has a complex patient history and lacks easily searchable diagnosis codes in regular data sources. Traditional recruitment methods have proven insufficient to meet recruitment goals. However, by using AI and selective RWD, researchers were able to identify a large number of previously overlooked sites. It included multispecialty practices with more than 200,000 patients in its network, 12,000 of whom were potential candidates for the trial.
AI and RWD can help in many ways, from uncovering the most promising indications and identifying the right combination of drugs to pursue new assets, to refining trial eligibility criteria and patient demographics to closely track primary endpoints. It is also used at important decision-making points. over time.
Considerations when incorporating AI into clinical trial recruitment
AI applications have a number of important considerations to keep in mind, including biases, illusions, and the fact that they require vast amounts of training data to function accurately. Solving these challenges becomes even more important when using AI in healthcare applications. For example, patient privacy is of paramount importance, but this can be difficult given the sheer volume of data required and the multiple sources that data can be linked to. This is the case when analyzing EHR data linked to claims data to generate RWE. Therefore, it is important to ensure the highest standards of data privacy and security when managing healthcare data.
It is important to also consider human-machine interaction in clinical decision-making. AI models are producing valuable information, but like any AI model, it's important that humans verify the accuracy of what they produce. If the data in question is clinical data, clinical validation is required.
To effectively leverage AI and RWD in clinical trials, stakeholders must be mindful of and manage the complexities of these technologies. By ensuring the highest standards of quality and accuracy are maintained, the healthcare industry can leverage these tools to more efficiently and accurately navigate the complexities of clinical trial recruitment, ultimately faster. We can deliver innovative treatments to our patients at a faster pace and at a lower cost.
Forbes Business Council is the leading growth and networking organization for business owners and leaders. Are you eligible?
