Joyce Nina R, Lombardi Leah R, Pfeiffer Melissa R, Curry Allison E, Margolis Seth A, Ott Brian R, Zullo Andrew R
Department of Epidemiology, Brown University School of Public Health, 121 South Main St., Box G-121-S2, Providence, RI, 02192, USA.
Center for Gerontology and Health Care Research, Brown University School of Public Health, Providence, RI, USA.
Inj Epidemiol. 2024 Aug 12;11(1):38. doi: 10.1186/s40621-024-00523-3.
Administrative healthcare databases, such as Medicare, are increasingly used to identify groups at risk of a crash. However, they only contain information on crash-related injuries, not all crashes. If the driver characteristics associated with crash and crash-related injury differ, conflating the two may result in ineffective or imprecise policy interventions.
We linked 10 years (2008-2017) of Medicare claims to New Jersey police crash reports to compare the demographics, clinical diagnoses, and prescription drug dispensings for crash-involved drivers ≥ 68 years with a police-reported crash to those with a claim for a crash-related injury. We calculated standardized mean differences to compare characteristics between groups.
Crash-involved drivers with a Medicare claim for an injury were more likely than those with a police-reported crash to be female (62.4% vs. 51.8%, standardized mean difference [SMD] = 0.30), had more clinical diagnoses including Alzheimer's disease and related dementias (13.0% vs. 9.2%, SMD = 0.20) and rheumatoid arthritis/osteoarthritis (69.5% vs 61.4%, SMD = 0.20), and a higher rate of dispensing for opioids (33.8% vs 27.6%, SMD = 0.18) and antiepileptics (12.9% vs 9.6%, SMD = 0.14) prior to the crash. Despite documented inconsistencies in coding practices, findings were robust when restricted to claims indicating the injured party was the driver or was left unspecified.
To identify effective mechanisms for reducing morbidity and mortality from crashes, researchers should consider augmenting administrative datasets with information from police crash reports, and vice versa. When those data are not available, we caution researchers and policymakers against the tendency to conflate crash and crash-related injury when interpreting their findings.
诸如医疗保险等行政医疗保健数据库越来越多地用于识别有撞车风险的群体。然而，它们仅包含与撞车相关伤害的信息，而非所有撞车事故。如果与撞车及撞车相关伤害相关的驾驶员特征有所不同，将两者混为一谈可能会导致无效或不精确的政策干预措施。
我们将10年（2008 - 2017年）的医疗保险理赔记录与新泽西州警方的撞车报告相链接；以比较68岁及以上涉及撞车事故且有警方报告的撞车事故的驾驶员与有与撞车相关伤害理赔记录的驾驶员的人口统计学特征、临床诊断和处方药配药情况。我们计算标准化平均差异以比较组间特征。
有医疗保险伤害理赔记录的涉撞驾驶员比有警方报告撞车事故的驾驶员更可能为女性（62.4%对51.8%，标准化平均差异[SMD]=0.30），有更多临床诊断，包括阿尔茨海默病及相关痴呆症（13.0%对9.2%，SMD = 0.20）和类风湿性关节炎/骨关节炎（69.5%对61.4%，SMD = 0.20），并且在撞车事故发生前，阿片类药物（33.8%对27.6%，SMD = 0.18）和抗癫痫药（12.9%对9.6%，SMD = 0.14）的配药率更高。尽管编码实践中存在记录不一致的情况，但当仅限于表明受伤方为驾驶员或未明确说明的理赔记录时，研究结果仍然可靠。
为了确定降低撞车事故发病率和死亡率的有效机制，研究人员应考虑用警方撞车报告中的信息扩充行政数据集，反之亦然。当无法获取这些数据时，我们提醒研究人员和政策制定者在解释研究结果时不要将撞车事故和与撞车相关的伤害混为一谈。
