Identifying Age-Specific Risk Factors for Poor Outcomes After Trauma With Machine Learning
Heather R Kregel1, Gabrielle E Hatton1, John A Harvin2
1Division of Acute Care Surgery, Department of Surgery, McGovern Medical School at UTHealth, Houston, Texas; Center for Surgical Trials and Evidence-Based Practice, McGovern Medical School at UTHealth, Houston, Texas; Center for Translational Injury, McGovern Medical School at UTHealth, Houston, Texas.
Insights
Risk factors for poor outcomes after trauma differ by age. Age-specific models can improve care for older trauma patients by identifying unique risk factors and improving hospital benchmarking.
Area of Science:
- Trauma Surgery
- Geriatric Medicine
- Data Science in Healthcare
Background:
- Current trauma risk stratification models are not age-specific.
- This can lead to suboptimal care and inaccurate quality benchmarking for older adults.
- Age-dependent risk factors for trauma outcomes are hypothesized.
Purpose of the Study:
- To assess if risk factors for poor outcomes after trauma are age-dependent.
- To determine if the relative importance of risk factors varies by age.
Main Methods:
- A cohort study of severely injured adult trauma patients (2014-2018) using trauma registry data.
- Random forest algorithms were used to predict poor outcomes (death or complication) in all, younger, and older (≥55 years) patient cohorts.
- Mean Decrease in Accuracy (MDA) was calculated to assess variable importance and significant differences between age cohorts.
Main Results:
- Older patients (25%) had higher poor outcome rates (33%) compared to younger patients (12%).
- Head injury was the top predictor across all cohorts; age was key in the full cohort after head injury.
- Risk factor importance varied by age: surgery for younger, Glasgow Coma Scale for older patients.
Conclusions:
- Supervised machine learning revealed age-specific differences in trauma risk factors and their associations with poor outcomes.
- Age-specific models can enhance hospital benchmarking and identify quality improvement targets for older trauma patients.
Introduction:
Risk stratification for poor outcomes is not currently age-specific. Risk stratification of older patients based on observational cohorts primarily composed of young patients may result in suboptimal clinical care and inaccurate quality benchmarking. We assessed two hypotheses. First, we hypothesized that risk factors for poor outcomes after trauma are age-dependent and, second, that the relative importance of various risk factors are also age-dependent.
Methods:
A cohort study of severely injured adult trauma patients admitted to the intensive care unit 2014-2018 was performed using trauma registry data. Random forest algorithms predicting poor outcomes (death or complication) were built and validated using three cohorts: (1) patients of all ages, (2) younger patients, and (3) older patients. Older patients were defined as aged 55 y or more to maintain consistency with prior trauma literature. Complications assessed included acute renal failure, acute respiratory distress syndrome, cardiac arrest, unplanned intubation, unplanned intensive care unit admission, and unplanned return to the operating room, as defined by the trauma quality improvement program. Mean decrease in model accuracy (MDA), if each variable was removed and scaled to a Z-score, was calculated. MDA change ≥4 standard deviations between age cohorts was considered significant.
Results:
Of 5489 patients, 25% were older. Poor outcomes occurred in 12% of younger and 33% of older patients. Head injury was the most important predictor of poor outcome in all cohorts. In the full cohort, age was the most important predictor of poor outcomes after head injury. Within age cohorts, the most important predictors of poor outcomes, after head injury, were surgery requirement in younger patients and arrival Glasgow Coma Scale in older patients. Compared to younger patients, head injury and arrival Glasgow Coma Scale had the greatest increase in importance for older patients, while systolic blood pressure had the greatest decrease in importance.
Conclusions:
Supervised machine learning identified differences in risk factors and their relative associations with poor outcomes based on age. Age-specific models may improve hospital benchmarking and identify quality improvement targets for older trauma patients.
