Seize the opportunity to leverage AI and ML for clinical research
by Analytics Insight
July 12, 2021
Pharmacy professionals believe artificial intelligence (AI) will be the most disruptive technology in industry in 2021. As AI and machine learning (ML) become essential tools to keep pace with the industry, clinical development is an area that can greatly benefit, offering time savings and money while providing better and faster information to inform decision-making. However, for patients, these tools provide improved safety practices that lead to better and safer medications. Here’s how AI / ML can be used to help pharmaceutical companies bring safer drugs to market.
Overcoming Obstacles to the Use of AI in Clinical Research
Today, AI and ML can be used to support clinical research in many ways; including the identification of molecules that have potential for clinical treatments, the search for patient populations that meet specific inclusion or exclusion criteria, as well as the analysis of assays, claim reports and reports. ‘other health data to identify trends in clinical research and treatments that drive faster decisions.
However, to take full advantage of the benefits of AI / ML technology, organizations performing clinical trials must first have access to industry-specific tools, expertise, and data sets to enable them to create tailored algorithms. to their specific needs. Health data, unlike purely digital data extracted from monitoring systems and tools such as IoT or SaaS platforms, is typically unstructured due to the way the data is collected (through doctor visits and unstructured web sources) and must adhere to strict security protocols to ensure patient privacy.
To truly leverage AI and ML for clinical research, data must be collected, studied, combined, and protected to make effective healthcare decisions. When clinical researchers collaborate with partners who have both technical skills and pharmaceutical expertise, they ensure that data is structured and analyzed in such a way as to simultaneously reduce risks and improve the quality of clinical research.
The benefits of AI for clinical research
When it comes to research study design, site identification and patient recruitment, as well as clinical surveillance, AI and machine learning have great potential to make clinical trials faster, more efficient. and, above all, more secure.
The study design sets the stage for a clinical research initiative. The cost, effectiveness and potential success of clinical trials rest entirely on the design and plans of the study. AI and ML tools, along with natural language processing (NLP), can analyze large health data sets to assess and identify primary and secondary endpoints in clinical research design. This ensures that protocols for regulators, payers and patients are well defined before clinical trials begin. Setting parameters such as these optimizes study design by helping to identify ideal search sites and enrollment models. Ultimately, better study design leads to more predictable results, reduced cycle time for protocol development, and a generally more efficient study.
Identifying trial sites and recruiting patients for clinical research is a more difficult task than it might at first appear. Clinical researchers need to identify the area that will provide sufficient access to patients who meet the inclusion and exclusion criteria. As studies focus more on rarer diseases or specific populations, recruiting participants for clinical trials becomes more difficult, increasing the cost, timing and risk of clinical study failure if enough patients cannot be recruited for research. AI and ML tools can help identify sites for clinical research by mapping patient populations and proactively targeting sites with the most potential patients who meet inclusion criteria. This allows fewer research sites to meet recruitment requirements and lower the overall cost of patient recruitment.
Clinical surveillance is a tedious manual process of analyzing the risks of the clinical research site and determining specific actions to be taken to mitigate those risks. Risks in clinical research include recruitment or performance issues, as well as risks to patient safety. AI and ML automate risk assessment in the clinical research environment and provide suggestions based on predictive analytics to better monitor and prevent risks. Automating this assessment removes the risk of manual error and reduces the time spent analyzing clinical research data.
Strategies for using AI for clinical research
During clinical trials, the patient population is limited, as research subjects must meet predefined parameters to be included in the study. On the other hand, unlike post-market research, clinical researchers have vast amounts of information about their patients, including the medications they are taking, their medical history, and their current environment.
Additionally, since the clinical researcher works closely with the patient and is knowledgeable about the drug or product being researched, the researcher is very familiar with all of the potential variables involved in the research. clinical test. Simply put, clinical trials have a lot of information to analyze, but few patients to research with. Because of this disproportionate ratio of patient information, each case in a clinical research setting is extremely important to the future of the study drug.
The massive amount of patient and drug information available to clinical researchers necessitates the use of NLP tools to analyze and process patient documents and charts. NLP may search documents and records for specific terms, phrases, and words that could indicate a problem or risk in the clinical trial. This eliminates the need for manual analysis of clinical trial data, reducing and in some cases eliminating the risk of human error while increasing patient safety. This is particularly useful in long clinical trials, where researchers will need to analyze patient histories and drug results over a long period of time. Many clinical trials have long document trails and questionnaires that can total hundreds of pages of patient data for researchers to analyze.
In a clinical trial, researchers are ultimately trying to determine whether the benefits of a specific treatment outweigh the risks. AI can be particularly useful in clinical trials of high-risk drugs. If a researcher knows that a drug cures or relieves a disease or condition, but also knows that the potential side effects of that drug can have a significant negative impact on the patient, they will want to know how to determine if a patient is likely to present. these negative side effects. NLP can be used to produce word clouds of potential signals of the negative side effects of a drug that patients would experience.
The only way to do this type of analysis manually is to identify these words with the help of human researchers, then analyze patient reports to find those words and group those reports into risk profiles. NLP can automate this entire process and provide information about risk indicators in patients much more efficiently and safely than human researchers ever could.
Integration of AI and ML with clinical research creates competitive results
AI and ML technologies, in particular NLP, hold great promise for supporting and optimizing clinical research. However, this assurance can only be achieved by organizations that have the tools, expertise, and partners to take full advantage of the benefits of AI and ML. AI and ML solutions support the optimization of clinical research by more effectively analyzing research data for risks and enabling faster trial planning and research. Those who do not engage AI and ML for clinical research may find that their competitors are doing so and, therefore, will bring new drugs and products to market faster with higher profits due to research time. reduced and safer practices.
Updesh Dosanjh, Practice Leader, Pharmacovigilance Technological Solutions, IQVIA
As Practice Leader for IQVIA’s Technology Solutions business unit, Updesh Dosanjh is responsible for developing the overall strategy for artificial intelligence and machine learning as it relates to safety and pharmacovigilance. It focuses on adopting these innovative technologies and processes that will help optimize pharmacovigilance activities for better and faster results. Dosanjh has over 25 years of knowledge and experience in the management, development, implementation and operation of processes and systems in the life sciences and other industries. Most recently, Dosanjh was at Foresight and joined IQVIA following an acquisition. During his career, Dosanjh has also worked with WCI, Logistics Consulting Partners, Amersys Systems Limited and FJ Systems. Dosanjh holds a BA in Materials Science from the University of Manchester and an MA in Advanced Manufacturing Systems and Technologies from the University of Liverpool.