Researchers at Florida International University and First Ascent Biomedical have used an artificial intelligence (AI)-powered, functional precision medicine (FPM) platform to identify unique therapeutic treatment options for children with relapsed cancer diagnoses. They published their study, “Feasibility of Functional Precision Medicine for Guiding Treatment of Relapsed or Refractory Pediatric Cancers,” in Nature Medicine.
The study involved 25 initial patients with relapsed solid or blood-based cancers. Each patient underwent drug sensitivity testing (DST) and genomic profiling and 19 who completed this testing received treatment recommendations. The final cohort of patients was split into two groups, with six patients receiving FPM-guided treatments, and eight patients receiving treatments based on physician’s choice (PC).
The authors found that of the six patients to get FPM-guided treatments, “83% (five patients) experienced a greater than 1.3-fold improved progression-free survival compared to their previous therapy.” They also “demonstrated a significant increase in progression-free survival and objective response rate compared to non-guided patients,” wrote the authors.
FPM treatment in action
The process of using FPM includes sampling tumors or blood and growing them to mimic the environment in the body. These samples are exposed to more than 120 FDA-approved drugs individually and in combination. The use of AI in FPM “gets rid of the guesswork and delivers a list of the most effective drugs that the oncologist can work with,” said Tomás R. Guilarte, PhD, dean of Stempel College and a co-author of the study.
Actionable results can be produced in about a week for clinicians to begin treatment. “We have shown the ability to return data rapidly, and that [these] data improved outcomes in patients with guided treatments. Similarly, we foresee the potential of an FPM approach to reduce toxicity and cost,” Diana Azzam, PhD, Florida International University, co-author of the study, and co-founder of First Ascent Biomedical told GEN.
One patient, whose cancer relapsed 14 months after initial treatment, was one of the six patients to receive FPM-guided treatment. After 33 days of treatment, he reached remission, while his prior treatment took 150 days for results. He has been in remission for more than two years following the FPM-guided treatment. “I believe that AI is a critical component of the future of FPM and driving better outcomes for cancer patients,” said Azzam.
Interview with the lead author
IPM interviewed Azzam about her latest publication and the future of cancer research using FPM applications.
The following has been lightly edited for clarity.
IPM: Successful treatment of 5 out of 6 FPM-guided patients is phenomenal. What are the next steps for broadening the scale of treatment options?
Azzam: We have two big next steps for our FPM program. Expanding patient count: Now that we have shown feasibility of returning drug sensitivity testing data in under two weeks, and demonstrated the clinical benefit that FPM data can provide, we need to demonstrate the clinical impact this can have at a large scale, to continue to demonstrate the benefit to patients, doctors, hospitals, and insurance companies. First Ascent is also finalizing plans with an insurance partner to roll out a health economics study driven by FPM.
We have two open clinical trials right now for patients with childhood cancer (NCT05857969) and patients with adult cancer (NCT06024603) to start answering this question, and we are working to start new trials, including a large-scale randomized trial, as soon as possible.
First Ascent is working to expand our capabilities to provide this beyond clinical study. This requires CLIA (Clinical Laboratory Improvement Amendments) certification to allow us to help patients outside of a study. We are working with a partner and are in the process of the CLIA validation, which will enable us to help patients around the country. We expect the lab to be fully CLIA-validated by June 2024. This will enable First Ascent to support our two clinical studies and have a patient capacity of about 500 patients annually. We realize the urgency of those fighting cancer. Our goal is to make our FPM approach accessible to patients as quickly as possible, and we have a commitment from Gannon University to partner with First Ascent in building a CLIA lab with a 15,000-patient capacity expected to start helping patients in mid-2025. First Ascent has two additional labs in the planning stage, as we accelerate to meet this need.
IPM: Can you speak a bit more about First Ascent Biomedical and how AI is impacting this work?
Azzam: I believe that AI is a critical component of the future of FPM and driving better outcomes for cancer patients. Before I co-founded First Ascent, I had the biology expertise, but I needed the AI side of the equation. That’s how my collaboration with Noah Berlow, PhD, co-author on the study, started. We are now both co-founders of First Ascent.
As highlighted in the discussion of the Nature Medicine manuscript, we anticipate the development of a future collaborative workflow that incorporates artificial intelligence and machine learning technologies into FPM.
First Ascent’s AI approach addresses two critical challenges in personalized cancer medicine.
First, what can a patient’s overall response to different drugs tell us about combination therapies that could be effective. Drug combinations are incredibly important in cancer care, and personalizing combinations has the potential to unlock new options for patients in need.
Second, First Ascent’s AI identifies new relationships between response to different cancer drugs and the underlying genomic (DNA and RNA) characteristics of the patient. This insight is critical in better matching patients to current drugs, and developing the next generation of cancer drugs.
First Ascent is also a co-investigator on the NIH-funded R01-equivalent clinical trial.
IPM: The current clinical trial enrolled patients who were in relapse. Do you envision this, or a similar process, to be used for future patients at the beginning of their treatment journey at the onset of diagnosis?
Azzam: FPM and AI represent the future of personalized cancer treatments, and that this approach should move earlier in a patient’s treatment journey. However, we recognize the need for additional clinical validation. Ultimately, compelling clinical data will drive acceptance and bring FPM and AI to patients earlier, similar to how genomics is becoming available to patients in earlier stages of treatment.
We have shown the ability to return data rapidly, and that this data improved outcomes in patients with guided treatments. Similarly, we foresee the potential of an FPM approach to reduce toxicity and cost.
We envision the combination of drug sensitivity testing, genomic tumor profiling, and AI analysis as the cornerstone of the future of personalized cancer care.
IPM: Other studies have explored FPM utility in some adult cancers. How does your study, which exclusively studies children with cancer, change the feasibility or potential of FPM?
Azzam: Unfortunately, childhood cancer patients are dramatically underserved compared to adult cancer patients. They often have fewer clinical trials and treatment options available.
Our study strengthens the position of FPM because we provided treatment options that improved outcomes in both solid and blood cancers.
Most importantly, our study enrolled patients with ALL cancer types, meaning solid cancers and blood cancers. Previous adult FPM studies have demonstrated clinical benefit in blood cancers, which represent ~10% of cancer diagnoses.
IPM: What challenges do you expect for patients, clinicians, labs, and other stakeholders?
Azzam: The big challenge ahead is education and availability.
The reason the Nature Medicine manuscript is so important is it is a strong signal and peer-reviewed validation of the power and potential of an FPM approach. Clinicians worry about efficacy, safety, and toxicity. The benefit of this FPM approach, testing 100s of FDA-approved drugs, is these are drugs the clinicians are familiar with, just being recommended based on drug sensitivity testing plus genomics data, being used in an off-label way. When they see what drugs work and the underlying mechanism why they work they have confidence in treating based on the data.
Our published study and the current open studies provide the blueprint to drive education and acceptance of this new approach to personalized cancer care.
IPM: How accessible is this treatment for the broader community and those in underrepresented and underfunded communities?
Azzam: Our NIH-funded trial is specifically supported by the National Institutes of Minority Health and Health Disparities (NIMHD) to make FPM accessible to underrepresented and underfunded communities. Additionally, because an FPM can match patients with the treatment options available at their clinic or hospital, it can be far easier for patients to really access treatments that can work for them in their own community. Our mission is to make this available for every cancer patient, including those in underrepresented and underfunded communities.
IPM: It seems that FPM can be utilized for other diseases than cancer. Do you envision that in the future this technique can be applied realistically to a broad range of illnesses for individualized medicine?
Azzam: Drug sensitivity testing is routinely used to find the most effective antibiotic to kill infectious microorganisms like bacteria or fungi. However, one limitation of drug sensitivity testing is the need for something to test against. With cancer and microorganisms, the “opponent” is obvious. With other non-malignant or non-infectious diseases, like heart disease, the “opponent” may be harder to test against in real time. However, if this can be approached in other diseases, drug sensitivity testing, and genomic profiling could be a promising path toward more personalized treatments.
