1 Background: For many elderly patients, a "disproportionate" amount of health care resources and expenditures is spent during the last year of life, despite the discomfort and reduced quality of life associated with many aggressive medical approaches. However, few prognostic tools have focused on predicting all-cause one-year mortality among elderly patients at a statewide level, an issue that has implications for improving quality of life while distributing scarce resource fairly. Objective: Using data from a statewide elderly population (≥65 years old), we sought to validate prospectively an algorithm to identify patients at risk for dying in the future one year, for the purpose of minimizing decision uncertainty, improving quality of life, and reducing futile treatment. Methods: Analysis was performed using electronic medical records (EMRs) from the Health Information Exchange (HIE) in the state of Maine, which covered records of nearly 95% of the statewide population. The model was developed from 125,896 patients aged at least 65 years who were discharged from any care facility in the HIE network from September 5, 2013 to September 4, 2015. Validation was conducted using 153,199 patients with same inclusion and exclusion criteria from September 5, 2014 to September 4, 2016. Patients were stratified into risk groups. The association between all-cause one-year mortality and risk factors was screened by chi-squared test and manually reviewed by two clinicians. We calculated risk scores for individual patients using a gradient tree based boost algorithm, which measured the probability of mortality within the next 1 year based on the preceding one-year clinical profile. A total of 99 independent risk factors (n=99) for mortality were identified (reported as odds ratios; 95%CIs). Different tumor sites were recognized as driving risk factors, such as ovary (14.42; 2.24-53.04), colon (14.07; 10.08-19.08), stomach (13.64; 3.26-86.57), and bronchus/lung (12.38; 2.91-36.04). Disparities were also found in patients' social determinants like respiratory hazard index (1.24; 0.92-1.40), and unemployment rate (1.18; 0.98-1.24). Among high-risk patients who expired in our dataset, cerebrovascular accident, amputation, and type 1 diabetes were the top 3 diseases in terms of average cost in the last year of life. Conclusions: With statewide EMRs datasets, our study prospectively validated an accurate one-year risk prediction model and stratification for the elderly population (≥65 years old) at risk of mortality. It should be a valuable adjunct for helping patients to make better quality-of-life choices, and alerting care givers to target high-risk elderly for appropriate care and discussions, thus cutting back on futile treatment.
Results