The aim of this study was to examine risk factors for and causes of mortality in patients with obstructive sleep apnoea syndrome (OSAS) treated by nasal continuous positive airway pressure (CPAP). Univariate and multivariate analyses of the data on patients registered in the Association Nationale pour le Traitement A Domicile de l'Insuffisance Respiratoire chronique (ANTADIR) Observatory between January 1, 1985 and December 31, 1993 and followed to January 1, 1996. Survival ratios were compared to those of the French population. A case control study compared patients who died with patients of the same age and sex, in the same Regional Association, who were equipped with CPAP at the same time. Five-thousand-six-hundred-and-sixty-nine patients had CPAP treatment. Two-hundred-and-seventy-six had died. One-hundred-and-twenty-four deaths were examined and compared to 123 control subjects. Overall mortality was the same as the general French population. Independent risk factors for death were age, oxygen tension in arterial blood (Pa,O2) and forced expiratory volume in one second (FEV1) (per cent predicted). In the case-control study independent risk factors for death in the past history were cardiac arrhythmia with an odds ratio (OR) of 2.8 (95% confidence interval (CI) 1.1-7.2), respiratory disorders (OR 2.8; CI 1.6-4.9) ischaemic events (OR 2.2; CI 1.2-4.2), neurological and psychiatric disorders (OR 2.4; CI 1.1-5.4). A significant excess of cardiovascular deaths and an excess of deaths from accidents and poisonings was found. In conclusion, patients die on therapy predominantly from cardiovascular causes but many have a past history of cardiovascular conditions. Compliance with treatment may be important for survival. Continuous positive airway pressure is an effective therapy for obstructive sleep apnoea syndrome but older patients with reduced spirometry and hypoxaemia may need more attention paid to these aspects of their condition.