A retrospective study of 620 patients evaluated for suspected pulmonary hypertension at a specialist referral centre in Sheffield, England, found that artificial intelligence can extract prognostic signals from routine chest CT scans never intended to assess the heart. Two validated deep learning models measured the volumes of cardiac chambers, great vessels and coronary artery calcifications on routine non-gated, non-contrast CT, and the automated measurements predicted who would die during follow-up even after accounting for age, sex, the subtype of pulmonary hypertension and an established clinical risk score. Published in European Radiology Cardiovascular and Thoracic, the work suggests scans already in hospital archives could yield additional prognostic biomarkers without extra radiation. Patients came from the ASPIRE registry and had undergone right heart catheterisation and CT imaging within one month of assessment; the final cohort was enrolled between 2006 and 2020, with a mean age of 64 years, 62% female participants and 80% self-reporting as white British. Most of the cohort, 76%, had pulmonary hypertension. During follow-up, 388 patients died, 63% of the cohort. Coronary calcifications were common: 45% of patients had calcification in the right coronary artery, 67% in the mainstem and left anterior descending artery, and 35% in the left circumflex artery.