Racial Disparities are Present in the Timing of Radiographic Assessment and Surgical Treatment of Hip Fractures.

BACKGROUND: Hip fractures are associated with 1-year mortality rates as high as 19% to 33%. Nonwhite patients have higher mortality and lower mobility rates at 6 months postoperatively than white patients. Studies have extensively documented racial disparities in hip fracture outcomes, but few have directly assessed racial disparities in the timing of hip fracture care. QUESTIONS/PURPOSES: Our purpose was to assess racial disparities in the care provided to patients with hip fractures. We asked, (1) do racial disparities exist in radiographic timing, surgical timing, length of hospital stay, and 30-day hospital readmission rates? (2) Does the hospital type modify the association between race and the outcomes of interest? METHODS: We retrospectively reviewed the records of 1535 patients aged 60 years or older who were admitted to the emergency department and treated surgically for a hip fracture at one of five hospitals (three community hospitals and two tertiary hospitals) in our health system from 2015 to 2017. Multivariable generalized linear models were used to assess associations between race and the outcomes of interest. RESULTS: After adjusting for patient characteristics, we found that black patients had a longer mean time to radiographic evaluation (4.2 hours; 95% confidence interval, -0.6 to 9.0 versus 1.2 hours; 95% CI, 0.1-2.3; p = 0.01) and surgical fixation (41 hours; 95% CI, 34-48 versus 34 hours 95% CI, 32-35; p < 0.05) than white patients did. Hospital type only modified the association between race and surgical timing. In community hospitals, black patients experienced a 51% (95% CI, 17%-95%; p < 0.01) longer time to surgery than white patients did; however, there were no differences in surgical timing between black and white patients in tertiary hospitals. No race-based differences were observed in the length of hospital stay and 30-day hospital readmission rates. CONCLUSIONS: After adjusting for patient characteristics, we found that black patients experienced longer wait times to radiographic evaluation and surgical fixation than white patients. Hospitals should consider evaluating racial disparities in the timing of hip fracture care in their health systems. Raising awareness of these disparities and implementing unconscious bias training for healthcare providers may help mitigate these disparities and improve the timing of care for patients who are at a greater risk of delay. LEVEL OF EVIDENCE: Level III, therapeutic study.

Machine-Learning-Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index.

STUDY OBJECTIVE: Standards for emergency department (ED) triage in the United States rely heavily on subjective assessment and are limited in their ability to risk-stratify patients. This study seeks to evaluate an electronic triage system (e-triage) based on machine learning that predicts likelihood of acute outcomes enabling improved patient differentiation. METHODS: A multisite, retrospective, cross-sectional study of 172,726 ED visits from urban and community EDs was conducted. E-triage is composed of a random forest model applied to triage data (vital signs, chief complaint, and active medical history) that predicts the need for critical care, an emergency procedure, and inpatient hospitalization in parallel and translates risk to triage level designations. Predicted outcomes and secondary outcomes of elevated troponin and lactate levels were evaluated and compared with the Emergency Severity Index (ESI). RESULTS: E-triage predictions had an area under the curve ranging from 0.73 to 0.92 and demonstrated equivalent or improved identification of clinical patient outcomes compared with ESI at both EDs. E-triage provided rationale for risk-based differentiation of the more than 65% of ED visits triaged to ESI level 3. Matching the ESI patient distribution for comparisons, e-triage identified more than 10% (14,326 patients) of ESI level 3 patients requiring up triage who had substantially increased risk of critical care or emergency procedure (1.7% ESI level 3 versus 6.2% up triaged) and hospitalization (18.9% versus 45.4%) across EDs. CONCLUSION: E-triage more accurately classifies ESI level 3 patients and highlights opportunities to use predictive analytics to support triage decisionmaking. Further prospective validation is needed.