This research uses wearable data and AI to detect disease earlier by analyzing continuous health signals rather than isolated clinical snapshots. By personalizing models to individual baselines, the system identifies subtle changes linked to conditions like infections, heart issues, and mental health crises, enabling earlier intervention and potentially saving lives.

This research challenges the one-size-fits-all approach to obesity by comparing childhood- and adult-onset cases. Through physiological testing before and after weight loss, it examines differences in inflammation, metabolism, and fitness. Findings aim to support personalised treatments, improving patient outcomes and reducing the broader healthcare burden associated with obesity.

This research uses spatial transcriptomics to map interactions between T cells, cancer cells, and immunosuppressive cells in tumours. Findings suggest cancer suppresses immune responses by surrounding and weakening T cells. The work aims to improve immunotherapy and enable personalised cancer treatment through detailed tumour mapping.

This research develops digital twin systems to personalise robotic exoskeleton movement. By integrating biomechanical modelling with real-time robotic control, it enables adaptive, user-specific walking patterns. The approach aims to improve rehabilitation outcomes by making assistive devices more natural, responsive, and aligned with individual movement needs.

This research engineers immune T cells to better fight ovarian cancer. By modifying them to recognize tumor-specific proteins and resist cancer’s suppressive signals, the project strengthens the body’s natural defenses. The goal is to improve immunotherapy effectiveness, overcome tumor resistance, and increase survival rates for women facing this deadly disease.

This research develops an affordable, rapid genetic testing system to personalize antidepressant treatment. By detecting DNA mutations that affect drug metabolism, the technology helps doctors prescribe the right medication for each patient. The goal is to reduce ineffective treatments and improve mental health care—especially for veterans struggling with PTSD and depression.

This research investigates why blocking an early asthma “alarmin” signal often fails as a treatment. Using mouse models, it reveals that environmental differences—particularly the microbiome—can bypass this signal and still drive asthma. Understanding microbiome health may help predict treatment success and lead to more personalized, effective asthma therapies.

Malnutrition is a major but often overlooked cause of mortality in cancer patients, driven by the side effects of aggressive treatments. This research focuses on personalized nutritional care, combining medical data with patient experiences to improve strength, quality of life, and treatment tolerance—because without nutrition, effective cancer therapy is impossible.

A researcher explains how anatomical differences in the vagus nerve drive inconsistent outcomes in epilepsy treatment. By dissecting and 3D-mapping human vagus nerves, the team reveals major left–right differences, enabling more precise electrode placement. This work promises safer, more effective nerve stimulation therapies for epilepsy and other diseases.

This research shows that genetic risk scores alone are insufficient for predicting chronic disease. By incorporating social and environmental factors using machine learning, disease prediction improves substantially, especially for disadvantaged populations. Integrating genetic and social risk is essential for equitable, effective personalized medicine.