A computational phenomapping approach to personalize the cardiometabolic benefits of novel glucagon-like peptide-1 receptor and glucose-dependent insulinotropic polypeptide agonists in patients with type 2 diabetes mellitus

According to the World Health Organization (WHO), more than 1 billion people worldwide are living with obesity, which increases the risk of serious health problems like heart disease, type 2 diabetes (where blood sugar levels are too high), and certain cancers. Obesity happens when excess body fat accumulates to the point where it affects health, often due to a combination of genetic, lifestyle, and environmental factors.

A new group of medications, called glucagon-like peptide-1 (GLP-1) receptor and glucose-dependent insulinotropic polypeptide (GIP) agonists, have been developed to help with weight loss. These drugs work by mimicking natural hormones that regulate appetite and digestion, helping people feel full longer and reducing food intake. Research has shown that these medications can also improve heart health and reduce obesity-related complications.

A series of clinical trials have demonstrated the effectiveness and safety of tirzepatide, a medication that activates both the GIP and GLP-1 receptors. These studies have shown that tirzepatide leads to significant and lasting weight loss in people with obesity, often more than other available treatments. However, the overall health benefits for heart-related outcomes may vary between individuals and are being formally evaluated, in dedicated outcome studies, with one clinical trial so far, SURPASS-4, showing potential benefit. This highlights the need for further studies of the effects of Tirzepatide on heart health.

Since people with obesity have different health profiles and risk factors, it is important to understand which individuals will benefit the most from these treatments. Personalized approaches to obesity management—considering factors like metabolism and other health conditions—can help ensure that each person receives the safest and most effective treatment for their needs.

We hereby propose a study with the aim to provide personalized estimates of treatment efficacy and safety for GLP-1/GIP agonists. Our approach is based on our machine learning method, called 'computational trial phenomapping', that has been previously employed across a range of cardiometabolic trials and has detected varying treatment effects, including among patients with type 2 diabetes treated with newer antihyperglycemic therapies (glucose-lowering medication), such as sodium-glucose cotransporter-2 (SGLT2) inhibitors, a class of drugs that lower blood sugar levels by preventing the kidneys from reabsorbing sugar that is created by the body.