Cardiovascular disease remains the leading causeof death globally, with hypertension and diabetesas two key risk factors. These conditions are fre-quently underdiagnosed because current diagnos-tic methods often require in-clinic or invasiveprocedures, which delay detection until symp-toms arise - often too late for optimal intervention.In this work, we focus on photoplethysmogra-phy (PPG), a non-invasive signal that can be pas-sively collected using widely available consumerdevices such as smartwatches and smartphones.This makes PPG particularly well-suited for re-mote, continuous health monitoring. We leveragefoundation models (PaPaGeI and TabPFN) to ex-tract features from single-heartbeat PPG signalsto detect hypertension and diabetes. Using datafrom 215,000 subjects in the UK Biobank, wedemonstrate that these models significantly out-perform current state-of-the-art approaches forPPG-based disease detection.