Determining timeframes to death for imminently dying patients: a retrospective cohort study

BackgroundClinicians are frequently asked 'how long' questions at end-of-life by patients and those important to them, yet predicting timeframes to death remains uncertain, even in the last weeks and days of life. Patients and families wish to know so they can ask questions, plan, make decisions, have time to visit and say their goodbyes, and have holistic care needs met. Consequently, this necessitates a more accurate assessment of empirical data to better inform prognostication and reduce uncertainty around time until death. The aims of this study were to determine the timeframes for palliative care patients (a) between becoming comatose and death, and (b) between being totally dependent and bedfast, and then comatose, or death, using Australia-modified Karnofsky Performance Status (AKPS) scores. The secondary aim was to determine if covariates predicted timeframes.MethodThis is a large retrospective cohort study of 2,438 patients, 18 years and over, cared for as hospice inpatients or by community palliative care services, died between January 2017 and December 2021, and who collectively had 49,842 AKPS data points. An Interval-Censored Cox Proportional Hazards regression model was used.ResultsOver 53% (n = 1,306) were comatose (AKPS 10) for longer than one day before death (mean = 2 days, median = 1, SD = 2.0). On average, patients were found to be totally dependent and bedfast (AKPS 20) for 24 days, before progressing to being comatose. A difference in life expectancy was observed at AKPS 20 among people with cancer (mean = 14.4, median = 2, SD = 38.8) and those who did not have cancer (mean = 53.3, median = 5, SD = 157.1).ConclusionResults provide clinicians with validated data to guide communication when answering 'how long' questions at end-of-life. Knowledge of projected time to death can prompt timely conversations while the patient can understand and engage in meaningful conversations. The importance of considering covariates such as location and diagnosis in determining timeframes has been highlighted. Shared decision-making and essential person-centered end-of-life care can be planned.