Department of Emergency Medicine, Washington University in St Louis, St Louis, MO 63110, United States.
Institute for Public Health, Washington University in St Louis, St Louis, MO 63110, United States.
J Am Med Inform Assoc. 2024 Oct 1;31(10):2165-2172. doi: 10.1093/jamia/ocae173.
To improve firearm injury encounter classification (new vs follow-up) using machine learning (ML) and compare our ML model to other common approaches.
This retrospective study used data from the St Louis region-wide hospital-based violence intervention program data repository (2010-2020). We randomly selected 500 patients with a firearm injury diagnosis for inclusion, with 808 total firearm injury encounters split (70/30) for training and testing. We trained a least absolute shrinkage and selection operator (LASSO) regression model with the following predictors: admission type, time between firearm injury visits, number of prior firearm injury emergency department (ED) visits, encounter type (ED or other), and diagnostic codes. Our gold standard for new firearm injury encounter classification was manual chart review. We then used our test data to compare the performance of our ML model to other commonly used approaches (proxy measures of ED visits and time between firearm injury encounters, and diagnostic code encounter type designation [initial vs subsequent or sequela]). Performance metrics included area under the curve (AUC), sensitivity, and specificity with 95% confidence intervals (CIs).
The ML model had excellent discrimination (0.92, 0.88-0.96) with high sensitivity (0.95, 0.90-0.98) and specificity (0.89, 0.81-0.95). AUC was significantly higher than time-based outcomes, sensitivity was slightly (but not significantly) lower than other approaches, and specificity was higher than all other methods.
ML successfully delineated new firearm injury encounters, outperforming other approaches in ruling out encounters for follow-up.
ML can be used to identify new firearm injury encounters and may be particularly useful in studies assessing re-injuries.
利用机器学习（ML）改进枪支伤害事件的分类（新发 vs 随访），并比较我们的 ML 模型与其他常见方法。
这项回顾性研究使用了圣路易斯地区基于医院的暴力干预计划数据存储库（2010-2020 年）的数据。我们随机选择了 500 名有枪支伤害诊断的患者，总共 808 例枪支伤害事件被分为（70/30）进行训练和测试。我们使用以下预测因素训练了一个最小绝对收缩和选择算子（LASSO）回归模型：入院类型、枪支伤害就诊之间的时间、之前的枪支伤害急诊就诊次数、就诊类型（急诊或其他）和诊断代码。我们新发枪支伤害事件分类的金标准是手动图表审查。然后，我们使用测试数据将我们的 ML 模型与其他常用方法（急诊就诊次数和枪支伤害就诊之间时间的代理测量值，以及诊断代码就诊类型指定[初次 vs 后续或后遗症]）进行比较。性能指标包括曲线下面积（AUC）、敏感性和特异性，置信区间（CI）为 95%。
ML 模型具有出色的区分度（0.92，0.88-0.96），具有高敏感性（0.95，0.90-0.98）和特异性（0.89，0.81-0.95）。AUC 明显高于基于时间的结果，敏感性略低于（但无统计学意义）其他方法，特异性高于所有其他方法。
ML 成功地区分了新发枪支伤害事件，在排除随访事件方面优于其他方法。
ML 可用于识别新发枪支伤害事件，在评估再伤害的研究中可能特别有用。
