Classification Algorithm to Distinguish Between Type 1 and Type 2 Myocardial Infarction in Administrative Claims Data.
Classification Algorithm to Distinguish Between Type 1 and Type 2 Myocardial Infarction in Administrative Claims Data.
复制标题
行政索赔数据中区分 1 型和 2 型心肌梗塞的分类算法。
DOI：
10.1161/circoutcomes.123.009986
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Hsu,John
中科院分区：
文献类型：
--
作者：
Wasfy,JasonH;Price,Mary;Normand,Sharon-LiseT;JanuzziJr,JamesL;McCarthy,CianP;Hsu,John
背景 2 型心肌梗死 (T2MI) 和 1 型心肌梗死 (T1MI) 在人口统计学、合并症、治疗和临床结果方面有所不同。可靠的质量和结果评估取决于区分行政索赔数据中的 T1MI 和 T2MI 的能力。因此，我们的目的是开发一种分类算法来区分可应用于索赔数据的 T1MI 和 T2MI。方法使用新英格兰大型医疗保健系统中 Medicare 责任护理组织合同受益人的数据，我们检查了 2018 年至 2021 年间 MI 诊断代码的分布以及出院诊断受益人的护理和编码模式国际疾病分类，T2MI 第十次修订代码，与 T1MI 相比。然后，我们评估了每次住院治疗 T2MI 与 T1MI 的概率，并检查了 2017 年引入 T2MI 代码之前的护理情况。结果应用纳入和排除标准后，仍有 7759 例因心肌梗塞住院（46.5% T1MI 和 53.5% T2MI；平均年龄，79±10.3 岁；47% 女性）。在分类算法中，女性性别（比值比，1.26 [95% CI，1.11–1.44]）、黑人种族相对于白人种族（比值比，2.48 [95% CI，1.76–3.48]）以及诊断为 COVID-19（比值比，1.74 [95% CI，1.11–2.71]）或高血压急症（比值比，1.46 [95% CI，1.00-2.14]）与 T2MI 住院几率高于 T1MI 相关。当应用于测试样本时，完整模型的 C 统计量为 0.83。分类的 T2MI 和观察到的 T2MI 的比较表明，在 T2MI 代码之前和之后都可能存在严重错误分类。 结论 简单的分类算法似乎能够区分引入 T2MI 代码之前和之后的 T1MI 和 T2MI 住院情况。这可以促进对急性心肌梗死的质量和结果进行更准确的纵向评估。
BACKGROUNDType 2 myocardial infarction (T2MI) and type 1 myocardial infarction (T1MI) differ with respect to demographics, comorbidities, treatments, and clinical outcomes. Reliable quality and outcomes assessment depends on the ability to distinguish between T1MI and T2MI in administrative claims data. As such, we aimed to develop a classification algorithm to distinguish between T1MI and T2MI that could be applied to claims data.METHODSUsing data for beneficiaries in a Medicare accountable care organization contract in a large health care system in New England, we examined the distribution of MI diagnosis codes between 2018 to 2021 and the patterns of care and coding for beneficiaries with a hospital discharge diagnosisInternational Classification of Diseases,Tenth Revisioncode for T2MI, compared with those for T1MI. We then assessed the probability that each hospitalization was for a T2MI versus T1MI and examined care occurring in 2017 before the introduction of the T2MI code.RESULTSAfter application of inclusion and exclusion criteria, 7759 hospitalizations for myocardial infarction remained (46.5% T1MI and 53.5% T2MI; mean age, 79±10.3 years; 47% female). In the classification algorithm, female gender (odds ratio, 1.26 [95% CI, 1.11–1.44]), Black race relative to White race (odds ratio, 2.48 [95% CI, 1.76–3.48]), and diagnoses of COVID-19 (odds ratio, 1.74 [95% CI, 1.11–2.71]) or hypertensive emergency (odds ratio, 1.46 [95% CI, 1.00–2.14]) were associated with higher odds of the hospitalization being for T2MI versus T1MI. When applied to the testing sample, the C-statistic of the full model was 0.83. Comparison of classified T2MI and observed T2MI suggest the possibility of substantial misclassification both before and after the T2MI code.CONCLUSIONSA simple classification algorithm appears to be able to differentiate between hospitalizations for T1MI and T2MI before and after the T2MI code was introduced. This could facilitate more accurate longitudinal assessments of acute myocardial infarction quality and outcomes.