OBJECTIVE: To investigate whether hospital mortality of patients was associated with the day of the week or time of admission to intensive care units (ICUs). DESIGN: Cohort study. SETTING: One hundred two adult, general (mixed medical/surgical) ICUs in England, Wales and Northern Ireland. PATIENTS AND PARTICIPANTS: A total of 56,250 admissions from 1995 to 2000 that fit the inclusion criteria for calculation of the APACHE II probability of hospital mortality. INTERVENTIONS: None. MEASUREMENTS AND RESULTS: Crude and case mix adjusted hospital mortality were examined by day of the week and time of day of admission to ICU. Patients admitted on Saturday and Sunday had higher crude hospital mortality compared with admissions on Wednesday [Saturday crude odds ratio (OR) 1.41, 95% CI 1.32-1.52; Sunday OR 1.56, 1.45-1.68]. The association was still significant after adjustment using the UK APACHE II model (Saturday OR 1.16, 1.1.07-1.26; Sunday OR 1.24, 1.14-1.35) but not after adjustment using individual components of the APACHE II model (Saturday OR 1.03, 0.95-1.12; Sunday OR 1.09, 1.00-1.19). Night admissions were also associated with higher mortality compared with day both before and after adjustment for case mix using the UK APACHE II model (crude OR 1.43, 1.37-1.51; adjusted OR 1.16, 1.10-1.23) but not after adjustment using components of the APACHE II model (OR 1.02, 95% CI 0.96-1.09). CONCLUSIONS: After appropriate adjustment for case mix, day of the week and time of day of admission of patients to ICU were not associated with significant differences in hospital mortality.