Predicting the cumulative risk of death during hospitalization by modeling weekend, weekday and diurnal mortality risks

Abstract

BackgroundCurrent prognostic models factor in patient and disease specific variables but do not consider cumulative risks of hospitalization over time. We developed risk models of the likelihood of death associated with cumulative exposure to hospitalization, based on time-varying risks of hospitalization over any given day, as well as day of the week. Model performance was evaluated alone, and in combination with simple disease-specific models.MethodPatients admitted between 2000 and 2006 from 501 public and private hospitals in NSW, Australia were used for training and 2007 data for evaluation. The impact of hospital care delivered over different days of the week and or times of the day was modeled by separating hospitalization risk into 21 separate time periods (morning, day, night across the days of the week). Three models were developed to predict death up to 7-days post-discharge: 1/a simple background risk model using age, gender; 2/a time-varying risk model for exposure to hospitalization (admission time, days in hospital); 3/disease specific models (Charlson co-morbidity index, DRG). Combining these three generated a full model. Models were evaluated by accuracy, AUC, Akaike and Bayesian information criteria.ResultsThere was a clear diurnal rhythm to hospital mortality in the data set, peaking in the evening, as well as the well-known ‘weekend-effect’ where mortality peaks with weekend admissions. Individual models had modest performance on the test data set (AUC 0.71, 0.79 and 0.79 respectively). The combined model which included time-varying risk however yielded an average AUC of 0.92. This model performed best for stays up to 7-days (93% of admissions), peaking at days 3 to 5 (AUC 0.94).ConclusionsRisks of hospitalization vary not just with the day of the week but also time of the day, and can be used to make predictions about the cumulative risk of death associated with an individual’s hospitalization. Combining disease specific models with such time varying- estimates appears to result in robust predictive performance. Such risk exposure models should find utility both in enhancing standard prognostic models as well as estimating the risk of continuation of hospitalization.

Weekly variation in health-care quality by day and time of admission: a nationwide, registry-based, prospective cohort study of acute stroke care

“…There are however a small number of studies that have considered how care might vary in this way. For example, administrative data has been used to model daily and diurnal patterns in mortality risk as part of a prognostic model for hospital inpatients 23 and identified weekend effects lag into the following week 24 . Diurnal patterns have also been observed in the frequency of obstetric complications.…”

Is it time for consultants to join trainees in working night shifts? Yes

“…Of these, three quarters are admitted through an ED and their chance of dying within 7 days is sevenfold that of a patient admitted directly to a ward . We have shown recently that the risk of dying increases not only for patients admitted on weekends, but also for those admitted in the evenings and at night, when it is over fivefold greater than that for a patient admitted at the start of a weekday. There is some evidence that inadequate service provision underlies this for some conditions (such as acute cardiovascular events) and that disease or biological characteristics (such as having a lymphoma) might be more important in others, but whatever the mechanism or circumstance there would seem to be an overwhelming argument for ED patients to receive prompt and appropriate care, especially at night and on weekends.…”

Risk-adjusted survival for adults following in-hospital cardiac arrest by day of week and time of day: observational cohort study

“…[1][2][3][4][5][6][7][8] The effect exists for a range of diagnoses, including several cardiological conditions. 1 2 4 7 8 Concha et al 4 found that for patients admitted at weekends with cardiac arrest and arrhythmia the majority of excess deaths occurred within the first 24 h after admission, suggesting that the different survival between weekday and weekend admissions is most likely due to variations in care.…”