Mayo Clinic and Phenomix study uses AI to predict GLP-1 side effects and advance personalised obesity treatment
Key Takeaways:
- A new study shows Phenomix Sciences’ machine learning algorithm can predict which individuals are more likely to experience nausea from GLP-1 agonist therapies, allowing for more tailored treatment.
- Participants with a high genetic risk score (GRS) were over twice as likely to develop nausea when treated with liraglutide, a common GLP-1 medication, compared with those with a low GRS (68% vs 30%).
- The findings highlight the potential for precision medicine to improve both patient outcomes and clinical trial efficiency, paving the way for more effective, personalised obesity care.
Detailed Findings from Digestive Disease Week 2025
Phenomix Sciences, a leader in precision obesity medicine and the first commercial biotechnology company of its kind, has unveiled new research in partnership with Mayo Clinic scientists that could reshape the future of obesity treatment. Presented at Digestive Disease Week (DDW) 2025, the study demonstrates how Phenomix’s proprietary machine learning algorithms can predict which individuals are more likely to experience side effects—particularly nausea—when undergoing GLP-1 receptor agonist therapy.
The study was led by Dr Andres Acosta, a globally recognised expert in obesity research and co-founder of Phenomix, and was presented by Dr Thomas Fredrick. Their research represents a pivotal step towards personalised obesity treatment and smarter clinical trial design.
Machine Learning Unlocks Predictive Insights
Titled “A Genetic Risk Score Associated with Nausea Resulting from GLP-1 Agonist Treatment: A Post-Hoc Analysis of a Randomised Controlled Trial of Liraglutide,” the study analysed genetic data from 110 participants enrolled in a previous trial. Researchers used a Genetic Risk Score (GRS) powered by machine learning to examine the relationship between individual genetic markers and adverse effects, focusing on nausea—a common and sometimes treatment-limiting side effect of GLP-1 therapies.
The results were striking. Individuals with a high GRS were more than twice as likely to experience nausea from liraglutide, a widely used GLP-1 receptor agonist, compared to those with a low GRS (68% versus 30%).
Nausea affects approximately 40% of people prescribed GLP-1 medications, and up to 6.4% may discontinue treatment as a result. By identifying likely adverse reactions before treatment begins, clinicians can minimise unnecessary hospital visits, reduce healthcare costs, and better align treatment plans to individual tolerability.
Implications for Personalised Care and Drug Development
“These findings represent a meaningful advancement in how we approach obesity treatment at an individual level,” stated Dr Acosta. “By identifying which patients are more likely to experience side effects before starting therapy, we can improve tolerability, support long-term adherence, and better match the right treatment to the right patient. This is a critical step toward delivering on the promise of truly personalised obesity care.”
Dr Fredrick added, “Our team’s research builds on previous findings by showing we can now predict not just who will benefit from GLP-1s, but who is more likely to struggle with side effects. That allows for more balanced, individualised treatment planning. It is an important advancement in the clinical application of precision obesity medicine.”
Phenomix’s MyPhenome® test, a simple saliva swab introduced previously at DDW 2024, identifies biological contributors to obesity, enabling physicians to personalise treatment strategies. Last year’s research demonstrated that MyPhenome could identify likely responders to semaglutide. This new study refines that approach by predicting who might encounter tolerability challenges, further enhancing the precision of obesity care.
A Boost for Clinical Trials and Beyond
Mark Bagnall, CEO of Phenomix Sciences, highlighted the broader implications: “This study underscores the power of predictive tools like MyPhenome to transform how we approach obesity treatment—not just in the clinic, but in the drug development pipeline. By identifying patients at risk for side effects before treatment begins, we can match the right patient to the right therapy, increase real-world adherence, and dramatically improve clinical trial efficiency through smarter patient selection. Our strategic partnership with Mayo Clinic, and its dedicated research team including Drs Acosta and Fredrick, have been critical in validating this precision medicine approach.”
The study was one of 17 presented by Mayo Clinic researchers at DDW 2025, with eight studies integrating Phenomix’s machine learning algorithms. Collectively, this research underscores the increasing importance of precision medicine in tackling obesity and accelerating drug development.
Collaborators and Acknowledgements
The study was co-authored by a multidisciplinary team: Dr Thomas Fredrick; Dr Jessica Atieh; Dr Daniel B. Maselli; Dr Diego Anazco; Dr Lizeth Cifuentes; Dr Maria A. Espinosa; Dr Jose Villamarin; Deborah Eckert BSN; Dr Serban Ciotlos; Dr Timothy O’Connor; Dr Michael Camilleri; and Dr Andres Acosta.
For further details about Phenomix Sciences and its research, please visit phenomixsciences.com. A full list of studies presented at DDW 2025 can be accessed here.
About Phenomix Sciences
Phenomix Sciences is a pioneering precision obesity biotechnology company focused on transforming obesity care by putting individuals at the centre of therapeutic innovation. Through advanced genetic testing, sophisticated analytics, and exclusive technology licensed from Mayo Clinic, Phenomix delivers personalised insights that empower physicians to optimise obesity treatments. These insights also assist pharmaceutical and medical device companies in refining trials, identifying high-responder groups, and accelerating the development of more targeted therapies. Backed by Health2047, the innovation arm of the American Medical Association, Phenomix is committed to shaping a more personalised and impactful future for obesity treatment.
