Alexander Schubert develops machine learning methods to expand access to life-saving cardiovascular interventions. His work centers on deep learning applied to electrocardiogram waveforms and large-scale clinical data, with the goal of identifying patients who stand to benefit from cardiovascular treatments but are missed by current diagnostic tools. His research spans three streams aimed at the decision-makers who shape cardiovascular outcomes. For physicians and health systems, he builds clinical risk models that identify risk not captured by established clinical markers, with current work on sudden cardiac death. For patients in low-resource settings, he develops AI for handheld ECG devices, including ongoing validation of a screening tool for silent myocardial infarction in rural India. For drug developers, he builds models for cardiac safety liability assessment, with a focus on hERG channel inhibition. Alexander is a PhD student in Computational Precision Health at UC Berkeley and a fellow at the Eric and Wendy Schmidt Center at the Broad Institute of MIT and Harvard. Before academia, he was a senior consultant at McKinsey & Company, advising pharma and healthcare clients on analytics-driven strategies. When he is not thinking about medical AI, you can usually find him on the walls of the nearest climbing gym.