Department of Surgery, Stanford University, Stanford, California.
Department of Computer Science, Stanford University, Stanford, California.
JAMA Netw Open. 2023 Oct 2;6(10):e2336196. doi: 10.1001/jamanetworkopen.2023.36196.
Quantifying injury severity is integral to trauma care benchmarking, decision-making, and research, yet the most prevalent metric to quantify injury severity-Injury Severity Score (ISS)- is impractical to use in real time.
To develop and validate a practical model that uses a limited number of injury patterns to quantify injury severity in real time through 3 intuitive outcomes.
DESIGN, SETTING, AND PARTICIPANTS: In this cohort study for prediction model development and validation, training, development, and internal validation cohorts comprised 223 545, 74 514, and 74 514 admission encounters, respectively, of adults (age ≥18 years) with a primary diagnosis of traumatic injury hospitalized more than 2 days (2017-2018 National Inpatient Sample). The external validation cohort comprised 3855 adults admitted to a level I trauma center who met criteria for the 2 highest of the institution's 3 trauma activation levels.
Three outcomes were hospital length of stay, probability of discharge disposition to a facility, and probability of inpatient mortality. The prediction performance metric for length of stay was mean absolute error. Prediction performance metrics for discharge disposition and inpatient mortality were average precision, precision, recall, specificity, F1 score, and area under the receiver operating characteristic curve (AUROC). Calibration was evaluated using calibration plots. Shapley addictive explanations analysis and bee swarm plots facilitated model explainability analysis.
The Length of Stay, Disposition, Mortality (LDM) Injury Index (the model) comprised a multitask deep learning model trained, developed, and internally validated on a data set of 372 573 traumatic injury encounters (mean [SD] age = 68.7 [19.3] years, 56.6% female). The model used 176 potential injuries to output 3 interpretable outcomes: the predicted hospital length of stay, probability of discharge to a facility, and probability of inpatient mortality. For the external validation set, the ISS predicted length of stay with mean absolute error was 4.16 (95% CI, 4.13-4.20) days. Compared with the ISS, the model had comparable external validation set discrimination performance (facility discharge AUROC: 0.67 [95% CI, 0.67-0.68] vs 0.65 [95% CI, 0.65-0.66]; recall: 0.59 [95% CI, 0.58-0.61] vs 0.59 [95% CI, 0.58-0.60]; specificity: 0.66 [95% CI, 0.66-0.66] vs 0.62 [95%CI, 0.60-0.63]; mortality AUROC: 0.83 [95% CI, 0.81-0.84] vs 0.82 [95% CI, 0.82-0.82]; recall: 0.74 [95% CI, 0.72-0.77] vs 0.75 [95% CI, 0.75-0.76]; specificity: 0.81 [95% CI, 0.81-0.81] vs 0.76 [95% CI, 0.75-0.77]). The model had excellent calibration for predicting facility discharge disposition, but overestimated inpatient mortality. Explainability analysis found the inputs influencing model predictions matched intuition.
In this cohort study using a limited number of injury patterns, the model quantified injury severity using 3 intuitive outcomes. Further study is required to evaluate the model at scale.
重要性：量化损伤严重程度是创伤护理基准测试、决策和研究的重要组成部分，但最常用的量化损伤严重程度的指标——损伤严重程度评分（ISS）——在实时使用时并不实用。
目的：开发和验证一种实用模型，该模型使用有限数量的损伤模式，通过 3 个直观的结果实时量化损伤严重程度。
设计、环境和参与者：在这项用于预测模型开发和验证的队列研究中，训练、开发和内部验证队列分别包括 223545、74514 和 74514 例成年患者（年龄≥18 岁）的入院记录，这些患者的主要诊断为创伤性损伤，住院时间超过 2 天（2017-2018 年全国住院患者样本）。外部验证队列包括 3855 名入住一级创伤中心的成年人，符合该机构 3 个创伤激活级别中 2 个最高级别的标准。
主要结局和测量：三个结局是住院时间、出院去向设施的概率和住院死亡率。住院时间的预测性能指标是平均绝对误差。出院去向和住院死亡率的预测性能指标是平均精度、精度、召回率、特异性、F1 分数和接收器操作特征曲线下的面积（AUROC）。使用校准图评估校准。Shapley 可加性解释分析和蜜蜂群分析有助于模型可解释性分析。
结果：长度、处置、死亡率（LDM）损伤指数（模型）由一个多任务深度学习模型组成，该模型在一个包含 372573 例创伤性损伤事件的数据集中进行了训练、开发和内部验证（平均[标准差]年龄=68.7[19.3]岁，56.6%为女性）。该模型使用 176 种潜在损伤来输出 3 个可解释的结果：预测的住院时间、出院到设施的概率和住院死亡率。对于外部验证集，ISS 预测的住院时间平均绝对误差为 4.16（95%置信区间，4.13-4.20）天。与 ISS 相比，该模型具有相当的外部验证集区分性能（设施出院 AUROC：0.67[95%置信区间，0.67-0.68]与 0.65[95%置信区间，0.65-0.66]；召回率：0.59[95%置信区间，0.58-0.61]与 0.59[95%置信区间，0.58-0.60]；特异性：0.66[95%置信区间，0.66-0.66]与 0.62[95%置信区间，0.60-0.63]；死亡率 AUROC：0.83[95%置信区间，0.81-0.84]与 0.82[95%置信区间，0.82-0.82]；召回率：0.74[95%置信区间，0.72-0.77]与 0.75[95%置信区间，0.75-0.76]；特异性：0.81[95%置信区间，0.81-0.81]与 0.76[95%置信区间，0.75-0.77]）。该模型在预测设施出院去向方面具有出色的校准性能，但高估了住院死亡率。可解释性分析发现，影响模型预测的输入与直觉相符。
结论和相关性：在这项使用有限数量损伤模式的队列研究中，该模型使用 3 个直观的结果量化了损伤严重程度。需要进一步研究来评估该模型的规模。
