From whiteboard to the world.

Our risk-prediction models were stuck in an older system, difficult to use day to day. RECAI Labs rebuilt them in a current language, redesigned the interface, and deployed them for our team to test. They paired solid engineering with a real understanding of how we work clinically, turning something we’d struggled to operationalize into a tool we can put in front of patients.

We worked with RECAI Labs co-founder on applying machine learning to early detection of Alzheimer’s disease. He led the analysis across a range of machine-learning and deep-learning models, bringing real rigour to a genuinely hard task. They engaged closely with the scientific questions rather than treating it as a black-box exercise, and were a thoughtful, reliable collaborator throughout.

I worked with RECAI’s co-founder on research exploring how longitudinal patient data could inform medication dosing in Parkinson’s disease. What stood out was his commitment to understanding the clinical challenge—the balance between symptom control and treatment side effects—and choosing an analytical approach that reflected it.

He brought scientific rigour and transparency to the work, clearly communicating the assumptions, limitations, and clinical relevance of the findings. He asked thoughtful questions, kept me involved as the results developed, and made my clinical input an integral part of the analysis.

RECAI’s co-founder combines technical expertise with the care and judgement needed for meaningful collaboration in healthcare. These are qualities I value in a research partner and would look for in a team like RECAI Labs. I would gladly work with him again.