[ad_1]
“One of the most difficult parts of my job is recruiting patients to participate in research,” said Nicholas Boris, the chief medical officer of Lawrenceville, New Jersey, a biotechnology company Celsion that develops applications for liver and ovarian cancer and certain Some types of next-generation chemotherapy and immunotherapy drugs for brain tumors. Borys estimates that less than 10% of cancer patients participate in clinical trials. “If we can increase this ratio to 20% or 30%, then we may now have defeated several cancers.”
Clinical trials test new drugs, devices, and procedures to determine whether they are safe and effective before they are approved for general use. But the road from research design to approval is long, tortuous and expensive. Today, researchers are using artificial intelligence and advanced data analysis to speed up this process, reduce costs, and provide effective treatments to people in need faster.They are using an underutilized but rapidly growing resource: patient data from past trials
Establish external control
Clinical trials usually involve at least two groups or “groups”: the test or experimental group receiving investigational treatment, and the control group not receiving treatment. The control group may not receive any treatment, placebo, or current standard of care for the disease being treated, depending on the type of treatment being studied and which treatments are compared with under the study protocol. It’s easy to see the recruitment problem for researchers working on treatments for cancer and other deadly diseases: life-threatening patients now need help. Borys said that although they may be willing to risk new treatments, “the last of them want to be randomly assigned to a control group.” This unwillingness to recruit patients with relatively rare diseases (for example, a specific genetic In combination with breast cancer marked as a feature), the time to recruit enough people may be extended by months or even years. Nine out of 10 global clinical trials—not only for cancer, but also for all types of diseases—cannot recruit enough people within the target time frame. Due to lack of enough participants, some trials completely failed.
What if researchers do not need to recruit a control group at all and can provide experimental treatment for everyone who agrees to participate in the study? Celsion is exploring this approach with New York-based Medidata, which provides management software and electronic data collection for more than half of the world’s clinical trials, serving most major pharmaceutical and medical device companies and academic medical centers. Medidata was acquired by the French software company Dassault Systèmes in 2019, bringing together a huge resource of “big data”: detailed information from more than 23,000 trials and nearly 7 million patients, which can be traced back about 10 years ago.
The idea is to reuse patient data from past trials to create an “external control arm.” The functions of these groups are the same as the traditional control group, but they can be used in situations where the control group is difficult to recruit: for example, extremely rare diseases or imminent life-threatening diseases such as cancer. They can also be effectively used in “one-arm” trials, which makes the control group impractical: for example, to measure the effectiveness of implanted devices or surgical procedures. Perhaps their most valuable immediate use is to conduct rapid preliminary trials to assess whether the treatment is worthy of full clinical trials.
Medidata uses artificial intelligence to explore its database and find patients who have served as controls in past treatment trials for a certain disease to create its proprietary version of the external control arm. Arnaub Chatterjee, Medidata’s senior vice president of Acorn AI products, said: “We can carefully select these historical patients and match the current experimental group with historical trial data.” (Acorn AI is Medidata’s data and analysis department.) Trials and patients Compliance with research goals—so-called endpoints, such as reducing mortality or how long patients stay cancer-free—and other aspects of research design, such as the type of data collected at the start of the study and during the course of the study.
Ruthie Davi, vice president of data science at Acorn AI at Medidata, said that when creating an external control arm, “we will make every effort to simulate an ideal randomized controlled trial.” The first step is to search the database using key eligibility criteria from the research trial. Possible control candidates: For example, the type of cancer, the key characteristics of the disease and the degree of progression, and whether it is the first time the patient is receiving treatment. Davi said this is basically the same process used to select control patients in standard clinical trials-except that data recorded at the start of past trials, rather than current trial data, is used to determine eligibility. “We are looking for historical patients, and if they exist today, they will be eligible to participate in the trial.”
download Full report.
This content was produced by Insights, the custom content division of MIT Technology Review. It was not written by the editors of MIT Technology Review.
[ad_2]
Source link
